Income Data for Policy Analysis: A Comparative Assessment of Eight Surveys. Important Differences

12/23/2008

Besides obvious differences in purpose, sample size, response rates, number of income items and interview frequency, there are many important differences among the surveys that affect the quality and utility of their income data for policy analysis. The immense quantity of information in the tables about the design, definitions, fieldwork, content and processing of each survey is not easily summarized. As a guide to users, some survey features which are unique or not well publicized, yet have significant impact on the potential utility of a survey’s income data for policy analysis, are noted here.

ACS Universe. While most of the surveys are described as covering the resident civilian non-institutional population, that is not precisely the case for any of them. The largest difference is for ACS, which was designed to replace the decennial census long form and uses decennial census definitions, including “current residence” rather than “usual residence”.

  • Until 2006, ACS excluded all residents of group quarters, whether institutional or non-institutional, including over two million students in college and university dormitories, but included all active duty military not living in group quarters such as barracks
  • Current ACS data for 2006 and beyond covers the U.S. resident population whether active duty military or not, and in 2006 has 4.1 million persons in institutional group quarters, including 2.1 million persons in adult correctional facilities and 1.8 million in nursing homes and skilled nursing facilities
  • ACS data for 2006 also include 3.9 million persons in non-institutional group quarters that include active duty military, mostly in barracks, and 2.3 million students residing in college and university dormitories and treated as unrelated individuals

Universe for Other Surveys. The other survey universes also differ from the resident civilian non-institutional population, although not usually as much as ACS.

  • CPS and SIPP both include active duty military living with one or more related civilians age 15 or over, on or off base
  • MEPS and NHIS both include civilians living with active duty military on or off base, and the income of the active duty person, but give that individual a zero person weight
  • MEPS and NHIS both exclude unrelated minors age 15 or over, who are included and have income data in SIPP, CPS and ACS
  • SIPP, HRS and PSID include persons who later join sample households, and they are assigned both person weights and household weights for the months during which they live with sample persons; MEPS piggybacks on the NHIS sample, sampling from successful NHIS interviews, and persons who later join MEPS families are not assigned person weights for cross-section analysis unless they were out of scope for the NHIS
  • MCBS includes all Medicare enrollees including those in institutional as well as non-institutional group quarters, and also includes Puerto Rico
  • HRS includes all sample persons including those in institutional as well as non-institutional group quarters and those living in other countries, but in the RAND-HRS files there are no person weights for those in nursing homes
  • HRS includes all persons and their income who are current or former spouses or partners of sample persons, but gives those under age 51 a zero person weight
  • PSID currently includes some persons living in other countries as well as military and institutionalized persons under some circumstances, but excludes most students living in college housing

Students. There is a broad range in treatment of college students, as noted above for ACS, revolving around the treatment of college dormitories and their residents. 

  • NHIS, like ACS, treats college and university housing as group quarters and those in student housing in the interview month become single individuals
  • SIPP, CPS and MEPS include students in the parental family and CPS does not interview in dormitories at all
  • HRS and PSID treat students away from home as “institutionalized” – HRS always excludes them and PSID usually excludes them

ACS Reference Period. Unlike the other seven surveys, ACS income data do not cover the same time period for everyone on the file. ACS gets income for the 12 months prior to the interview, and for a given calendar year the ACS income data are a combination of 12 different 12-month time periods, depending on the month of data collection. Published data and on-line tables based on internal files have been adjusted to the same real dollars using the CPI-U through 2005, and the CPI-U-RS for 2006 and later years.

Timing of Family and Poverty Measures.The surveys differ in the how family composition is measured and how poverty status is calculated. MCBS does not get family information and thus has no poverty measures. Five of the surveys use full-year income for family composition as of a fixed date to calculate poverty measures. PSID takes a different approach that is not definitionally equivalent to official poverty statistics.

  • Family composition is measured December 31 of the income year in MEPS, the month after the income year for ACS, usually March after the income year for CPS, and ranges from January to December after the income year for NHIS, and all use a full year’s income for each person in the family as of that date
  • PSID contains part-year income for part-year family members and a family poverty threshold based on month-by-month family composition to calculate a contemporaneous poverty status for the PSID family
  • SIPP monthly data allow analysts to select the timing used in poverty measures and allows both full-year fixed-date and contemporaneous measures

Family Definition and Poverty. Official poverty statistics incorporate the family definition of the official source of such statistics, the CPS. A different family definition changes who is included or excluded from the family, which affects not only family size but who contributes to family income, and so can change the family’s poverty status.

  • NHIS and MEPS define a family to include unmarried partners of either sex and children or other relatives of the partner, and foster relationships. Partnerships of any duration are treated as marriage.
  • NHIS uses only the broader family definition; MEPS uses both definitions.
  • HRS defines a family in the same way but restricts income data to the age-eligible sample person and spouse or partner. Although the age-eligible sample person and spouse or partner are referred to as a household, they may be members of a larger CPS family and not contain the CPS family householder.
  • PSID defines a family to include unmarried partners but only of the opposite sex, as well as children or other relatives of the partner, foster relationships, and any unrelated persons who are identified as part of the family (which may include same-sex partners). Partnerships of at least one year's duration are treated as marriage.

Identifying Families. Various of the surveys also have limitations in how families are identified.

  • ACS has no information on relationships among persons not related to the household reference person, so that no unrelated subfamilies can be identified
  • SIPP and CPS identify only parental or marital relationships among persons not related to the household reference person, so that only husband-wife and parent-child unrelated subfamilies can be identified, not other related subfamilies, e.g., siblings
  • MEPS identifies members and the reference person of CPS-defined families, but not their relationship to the CPS family reference person; however, while relationships are coded only relative to the MEPS family reference person, there are virtually no cases where the relationship between a CPS family member and the CPS family reference person cannot be discerned
  • Some MEPS families have members not on the public use file—these are designated as families of “undefined size” and close to half have no reference person on the public use file
  • PSID retains separate family status for persons—usually grown children or aging parents—previously living on their own but currently living with a related family

Income by Source by Person. Most of the surveys, like the CPS, have public use files with dollar amounts of income from different sources for a specific time period for each person above some age. Income for each person is the sum of income by source, and family income is the sum of income by person. There are some exceptions.

  • NHIS provides only brackets and not dollar income amounts on public use files. The highest family income bracket was set in 1997 at $75,000 or more and included 28 percent of persons on the file for 2003 (the 2007 redesign of NHIS raised this bracket to $100,000 or more).
  • NHIS internal (non-identifier) files containing dollar amounts are never available for off-site use.
  • NHIS has no income data by person, although there are earnings amounts for each person age 18 or over.
  • NHIS has total income only for the NHIS family, and complex modeling is required to create income for a CPS family to calculate poverty rates equivalent to official poverty statistics. Creating income estimates for policy purposes for other filing units—such as parent(s) and own children under age 22—would be even more difficult.
  • PSID contains total family income and income data by source excluding Social Security for the family head and his spouse or partner (family heads are the male in a couple), but not income by person or by source for other family members, and summary recodes combine the income of the head and spouse (excluding Social Security). Social Security is available as one total amount for the family.
  • MCBS income amounts for married sample persons include the income of the spouse, although the sample is enrollee-based and spouses also enrolled in Medicare are separately represented in the sample.
  • ACS income data on public use files (which are samples from the full internal file for a year) do not contain the month of data collection nor a month-specific inflation adjustment. The price adjustment variable on the file is an average of the 12 monthly adjustment factors, and under-adjusts early months and over-adjusts later months.
  • ACS income amounts on public use files have been rounded (after top-coding). Income amounts from $10 to $1,000 are rounded to the nearest $10, amounts from $1,000 to $50,000 are rounded to the nearest $100, and amounts above $50,000 are rounded to the nearest $1,000.

Income Definition. Official poverty statistics incorporate the income definition of the official source of such statistics, the CPS. A different income definition can change family income and so can change whether the family is counted as poor. Small differences may affect few persons, but large differences or ones affecting many persons in an important demographic group can alter results. There are some significant differences.

  • MEPS income questions use Internal Revenue Service definitions, since the questions reference specific lines on the personal income tax return. Some of these definitions differ significantly from CPS definitions, e.g. taxable wages exclude tax-deferred contributions to retirement accounts (such as 401(k)s, traditional IRAs, 403(b)s and the Federal Thrift Plan) or to Health Savings Accounts; self-employment income refers only to sole proprietorships and farms—other self-employment income from partnerships or S corporations is included with other Schedule E income from rents, royalties and estates; and interest and dividends exclude payments from tax exempt municipals.
  • SIPP, MEPS and HRS include non-periodic (lump-sum) withdrawals from tax-deferred retirement accounts (such as 401(k)s, traditional IRAs, 403(b)s and the Federal Thrift Plan) and (except for MEPS) from tax-advantaged Roth IRAs, which are increasingly important sources of income for the elderly. These sources are likely to substantially replace pension income based on a defined benefit plan in the long term, but are not included in CPS money income.
  • HRS rental income is gross rent before deduction of expenses such as mortgage or tax payments. HRS income for 2003 excludes several CPS income sources including alimony, child support, income from trust funds and royalties and financial assistance from family or friends; however, HRS income exclusions have varied from year to year.
  • RAND’s total income variables for HRS include Food Stamps, although the RAND poverty status variable has been calculated based on income excluding Food Stamps.

Internal Consistency. Most of the surveys, like the CPS, do edits or consistency checks between important variables such as whether a person worked and has earned income, or whether a person receives income from a given source and has an income amount for that source. Most surveys also ensure that total money income for each person equals the sum of income by source for the person, and that total family income equals the sum of incomes for persons in the family. There are some exceptions.

  • NHIS does not address consistency of family earnings (the sum of earnings for persons in the family) and family income to ensure that family income is at least as large as family earnings, even when earnings and income are imputed
  • NHIS does not edit or impute work activity or earnings amounts against reported receipt of wage and salary income or self-employment income for the same time period
  • MEPS does not edit or impute reported wage and salary or self-employment income for the year against work activity reported for the same time period
  • MEPS does not edit or impute work activity against reported wage and salary or self-employment income for the same time period
  • MEPS does not edit or impute type of earned income (wages and salaries vs. self-employment) against data on work activity

The MEPS practices reflect an explicit decision to preserve independent information collected in different sections of the survey instrument (and, to a large extent, at different times of the year), even when discrepancies exist.

Weighting. All surveys calculate weights in stages, starting with person,4 family or household weights based on selection probabilities adjusted for non-response. The resulting first-stage weights are then post-stratified to Census Bureau, CPS, or Medicare enrollment-based control totals by age, race/ethnicity, and (except for PSID) sex of the person, family head, or family reference person. Some surveys use additional demographic information such as type of household, state or county of residence, or Census region and MSA/non-MSA status. Some surveys include a family equalization process to ensure that husbands and wives or partners have the same weights within overall control totals. After person or family weights are calculated, in most of the surveys the family or household weight is set equal to the person weight of the reference person or another family member. One survey uses additional and unique control totals.

  • MEPS post-stratifies persons on the public use file to match CPS poverty rates by age, sex, race/ethnicity, Census region and MSA/non-MSA status for CPS-type families (as of December 31 of the year), thus ensuring that the MEPS public use file yields the same poverty rates by demographic groups as the CPS
  • MEPS also post-stratifies families on the public use file to match CPS counts of families by family size and family type (couple, male head no spouse present, female head no spouse present)

PSID constructs family weights based on selection probabilities adjusted for non-response and attrition, post-stratifies the resulting family weights to CPS-based control totals,5 and then sets person weights equal to the family weight.

  • PSID control totals use CPS counts of primary families and primary individuals by family sizes 1, 2 or 3 or more; they exclude CPS unrelated subfamilies and secondary individuals, and make no adjustments for different treatment in PSID and CPS of unmarried partners and their relatives, students, active duty military, persons living in other countries, some related subfamilies and some institutionalized persons

Other Differences. It should be noted that, in addition to the differences listed above, there are a myriad of other differences among the surveys in almost every aspect in every domain described in the tables. These differences in details may also affect outcomes of policy analysis.

TABLE II.1A. BACKGROUND AND OVERVIEW
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Purpose Specifically designed to provide information on income, populations at risk, and needs and utilization of government programs, for public policy formulation

Provides within-year patterns of income and program participation and a broad range of data relevant to health, retirement and income security programs

Design and field methods intended to maximize accuracy of income and program participation data for lower income populations and those whose income varies within the year

Primary source of detailed information on income and work experience in the United States

Source of official income and poverty estimates, and most widely used estimates of the uninsured

Underlying monthly survey (CPS-1) is the source of official labor force, unemployment and wage rate estimates

Widely used for policy analysis and legislative cost estimates, and as basis for major micro-simulation models such as TRIM

Design Summary Longitudinal panel survey collecting 2½ to 4 years of detailed monthly income and other data through interviews at 4 month intervals (8 to 12 interviews) for all persons in initial sample households and persons added through household formation or change, with most recent panels started in 2001, 2004 and 2008 Annual cross-section household survey at a fixed point in time collecting detailed prior calendar year income and employment data and current demographic and labor force data
File Summary Multiple public use files contain person-month data from full panel Public use file contains household, family and person data
History Based on the Income Survey Development Program, a joint effort of HEW/ASPE, HEW/SSA and Census from 1977 to 1981

First panel fielded in October, 1983

Has been redesigned, expanded and contracted as budget varied

Presently being re-engineered to be implemented in 2011 or 2012

Income questions first asked in April, 1948

Supplement expanded and redesigned many times

Non-cash benefits added in 1980; health insurance questions changed significantly in 1988 and revised in 1995 and 2001

Sample expanded in 2001 to improve State estimates of children in low-income families without health insurance

Responsibilities Survey and questionnaire design: Census Bureau

Field work conducted by Census Bureau

All processing done at Census Bureau

Survey and questionnaire design: Census Bureau

Field work conducted by Census Bureau

All processing done at Census Bureau

 

TABLE II.1B. BACKGROUND AND OVERVIEW
  2002 American Community Survey 2002 Medical Expenditure Panel Survey Household Component
Purpose Small area demographic, income and poverty data, with emphasis on demographics and local area data

As of 2010 will replace the Decennial Census Long Form, the traditional source of small area demographic and income data

Detailed information on health conditions, use of medical services, cost and source of payments in the United States
Design Summary Monthly cross-section household survey collecting prior 12 months income (rolling reference period) and current demographics continuously during the year (rolling sample)

Income in internal files and published data has month-by-month inflation adjustments to calendar year price levels

Unlike other surveys, participation is mandatory not voluntary

Longitudinal panel survey collecting 2 years of event-level health care services and cost information through interviews at 6 month intervals (5 interviews), and prior calendar year income information once per year, for all persons in initial sample households and persons added through household formation or change, with new panel starting every year
File Summary Public use file contains person-level data but data collection month and reference period timing are suppressed, income is rounded, and income has no inflation adjustment

File is geographically oriented based on Decennial Long Form files

Cross-section public use files contain person-wave data for a calendar year from two overlapping annual panels

Public use file includes same-year income information collected in subsequent year

History After pretests, data collection began in 36 counties in 1999 and National sample of 800,000 households in 2000

Full implementation with annual sample of 3 million households covering all counties and county-equivalents began in 2005

Expanded to include non-household population (institutionalized and group quarters) in 2006

Based on National Center for Health Services Research (NCHSR) 1977 National Medical Care Expenditure Surveys and 1987 National Medical Expenditure Survey

First panel fielded in 1996

Responsibilities Survey and questionnaire design: Census Bureau

Field work conducted by Census Bureau

All processing done at Census Bureau

Survey and questionnaire design: Agency for Healthcare Research and Quality (AHRQ)

Field work conducted by Westat under contract with AHRQ

Processing done at AHRQ, Westat, and some years Social and Scientific Systems (SSS)

TABLE II.1C. BACKGROUND AND OVERVIEW
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Purpose Primary source of information on health conditions, access to care and use of medical services in the United States

Widely used for policy analysis

Completion of cost and utilization data for persons ever enrolled in Medicare during each calendar year by linking administrative and Medicare A and B claims data to survey-reported events to add information on non-covered medical services

Event-level information on diagnoses, services, providers, charges, payments, and sources of payment

Design Summary Annual cross-section household survey collecting prior month and year health information, current demographics, and prior calendar year family income continuously during the year (rolling sample) Longitudinal panel enrollee survey collecting 3 years of event-level utilization and other data through interviews at 4 month intervals over 4 years (12 interviews) to supplement Medicare claims data merged with administrative records, with new panel started annually and prior year total income questions in summer and fall
File Summary Public use file contains household, family and person data

Public use file income information limited to $5,000- and $10,000-wide brackets

Files with actual income amounts may not be taken off-site and are available only if research plan approved and daily access fees paid

No public use files - data available if research plan approved and files purchased

Multiple limited access files contain person, service and event data for enrollees ever-on during calendar year including information collected in subsequent years, merged, unduplicated and validated with administrative records and complete Medicare bill files

History Initially fielded in 1957

Redesigned at 10-year intervals

1997 redesign removed person-level income amounts

First panel fielded in 1991

In 1993 redesigned to have 4-year limit on participation and annual new panels adding new enrollees, replacing participants expected to be lost or rotated out and maintaining age stratification

Responsibilities Survey and questionnaire design: National Center for Health Statistics (NCHS)

Field work conducted by Census Bureau under interagency agreement with NCHS

Processing done at Census Bureau and at NCHS

Survey and questionnaire design: Center for Medicare and Medicaid Services (CMS)

Field work conducted by Westat under contract with CMS

Processing done by Westat and CMS

TABLE II.1D. BACKGROUND AND OVERVIEW
  2004 Health and Retirement Study 2003 Panel Study of Income Dynamics
Purpose Longitudinal data on economic circumstances, health and social support of older population including retirement decisions, income, assets, health, family affiliations and support structure as persons age, including institutional care and final illness Longitudinal data on complete family life cycles including family formation and dissolution, changes in employment, income, wealth, housing, fertility and use of transfers, and intergenerational transfer of behavior such as welfare use
Design Summary Longitudinal cohort survey collecting demographic, financial and health information until death through interviews every two years with sampled persons age 51 or over (rises to 55 or over between cohort additions) and their current and former spouses or partners Longitudinal cohort survey collecting demographic, behavioral and financial information until death through interviews every two years with initial sampled families and their descendants including those added through household formation or change
File Summary Public use files available from two sources

HRS: Multiple public use files for each year (37 excluding decedent exit interviews and imputation files) on age-eligible sample, current and former spouses or partners, family, and helpers, from multiple respondents -- longitudinal tracking files allow links across years

RAND: One person-based flat file for each year after cross-section and longitudinal edits and clean-up, with a broad range of new variables having consistent names and content across years

Public use files contain family data with person information for head and current spouse or partner and limited data on other family members

Public use longitudinal files track family relationships over almost 40 years and contain cross-year variables such as gender

History Cohort born 1931-1941 (age 51 to 61) initially fielded in 1992

Cohort born 1923 or earlier (age 70 or more) initially fielded in 1993

Cohorts combined and 2 cohorts added in 1998 to expand sample to persons born 1947 or earlier (age 51 or over) in 1998

New cohorts added every 6 years, starting in 2004 with persons born1948-1953 (age 51 to 56 at time of addition)

Initial cohort of sample families fielded in 1968 and interviewed annually through 1997 then every two years from 1999 forward

Redesigned and supplemented with a sample of recent immigrant families in 1997

Responsibilities Survey and questionnaire design: Institute for Social Research (ISR), University of Michigan, under a grant from the National Institute on Aging (NIA)

Field work conducted by Survey Research Center (SRC), ISR

All processing done at SRC and ISR

RAND work funded by Social Security Administration

Survey and questionnaire design: Institute for Social Research (ISR), University of Michigan, under multiple and varied sponsorship over the years

Field work conducted by Survey Research Center (SRC), ISR

All processing done at SRC and ISR

TABLE II.2A. SURVEY AND SAMPLE DESIGN
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Sample Frame Housing units including housing units on military bases in 50 States and DC

Non-institutional group quarters in 50 States and DC

Frame and sample selection: Census Bureau

Housing units including housing units on military bases in 50 States and DC

Non-institutional group quarters in 50 States and DC excluding college dormitories

Frame and sample selection: Census Bureau

Sample Design Multi-stage sampling design

2001 panel designed for National but not State estimates although 45 States are coded - 2004 panel designed for State estimates

Sample designated at beginning of each new panel

Multi-stage sampling design for underlying monthly survey

Designed for State estimates with sub-State samples in NY and CA and estimates for MSAs over 500,000

Sample expanded in 2001 to improve State-specific estimates of children in low-income families without health insurance

Sample Unit Household in housing unit or group quarter

Includes persons who "usually reside" in unit e.g. most college students in dormitories usually reside with parents

May contain multiple families and/or unrelated individuals

Household in housing unit or group quarter

Includes persons who "usually reside" in unit e.g. most college students in dormitories usually reside with parents

May contain multiple families and/or unrelated individuals

Oversamples Low income areas Hispanics, non-Whites, and Whites with children 18 or younger
Response Thresholds Interview must obtain household roster, relationships, names, demographics, labor force and types of income

Files contain actual or imputed data on all persons in responding households

Interview must obtain household roster, relationships, names, demographics and labor force data (CPS-1)

File contains actual or imputed data on all persons in responding households

Initial Response Rate 2001 panel initial response: 87.7% 2003 Supplement month response to CPS-1: 92.2%

Supplement data is imputed for CPS-1 responders who refuse to answer Supplement

TABLE II.2B. SURVEY AND SAMPLE DESIGN
  2002 American Community Survey 2002 Medical Expenditure Panel Survey Household Component
Sample Frame Housing units including housing units on military bases in 50 States and DC

Puerto Rico added in 2005

No group quarters through 2005

After 2005, all group quarters, including barracks and institutions

Frame and sample selection: Census Bureau

Families or individuals with successful prior year NHIS interview

NHIS frame consists of housing units including housing units on military bases and non-institutional group quarters in 50 States and DC

Frame and sample selection: AHRQ and SSS for MEPS subsample of NHIS responders

Sample Design Multi-stage sampling design at the county level

Designed for State and sub-State estimates with estimates for areas of 65,000 or more annually and 3-year estimates for areas of 20,000 or more and 5-year estimates for geographic areas regardless of size including census tracts

Samples from families and unrelated individuals interviewed for NHIS the previous year, except those in college dormitories

Designed for National but not State estimates

Sample Unit Household in housing unit (or group quarter after 2005)

Includes persons who currently (not "usually") reside in unit e.g. college students in student housing are single individuals

Only one family is identified but may contain multiple unrelated individuals

Family or individual in housing unit or group quarter

Includes persons who "usually reside" in unit

College students in student housing always merged back into parental family

Oversamples Small governmental units Blacks, Hispanics, Asians, and families predicted to have income less than 200% of poverty
Response Threshold Interview must obtain two data elements for each person e.g. name and age or age and sex

File contains actual or imputed data on all persons in responding households

Interview must ask all survey questions of all family members

Policy is for non-response to be assigned at family level but file contains partial families

Initial Response Rate 97.3% for 2002 (See "Contact Method" in Table II.4B on how response rate calculated) Including non-response to prior-year NHIS used as sample frame: averages 70%

TABLE II.2C. SURVEY AND SAMPLE DESIGN
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Sample Frame Housing units including housing units on military bases in 50 States and DC

Non-institutional group quarters in 50 States and DC

Frame and sample selection: Census Bureau

Medicare enrollees (Part A and/or Part B) as of January 1 of each year located in 50 States, DC, and Puerto Rico

Housing units, non-institutional and institutional group quarters except prisons and facilities for the criminally insane

Frame and sample selection: CMS and Westat

Sample Design Multi-stage sampling design

Designed for National but not State estimates

4 separate quarterly samples

Multi-stage sampling design

Designed for National but not State estimates

Sample stratified by age

New 4-year panel started annually to add new enrollees, replace participants expected to be lost or rotated out, and designed to maintain age stratification

Sample Unit Household in housing unit or group quarter

Includes persons who "usually reside" in unit except students away at college

College students in student housing are single individuals

May contain multiple families and/or unrelated individuals

Individual Medicare enrollee
Oversamples Blacks and Hispanics Over-representation of enrollees under 45 and over 80 years old
Response Threshold Interview must obtain household roster, relationships, demographics, and all health data and demographics through education for at least one respondent in a family

File contains actual or imputed data on all persons in responding families

Data on utilization and charges must be present for 2/3 of the Medicare-enrolled days in the year, or be missing for less than 60 days, for sample person to be included in calendar year Cost and Use File

File contains utilization and cost data for all responding persons

Initial Response Rate 89.2% for 2003 Roughly 80%

TABLE II.2D. SURVEY AND SAMPLE DESIGN
  2004 Health and Retirement Study 2003 Panel Study of Income Dynamics
Sample Frame Housing units excluding housing units on military bases in 48 contiguous States and DC in 1992 for 1992 and 1993 cohorts, 1993 cohort also used 1993 Medicare enrollment file as frame

1992 frame (not updated) used for younger 1998 cohort

1998 Medicare enrollment file used for older 1998 cohort

Housing units excluding housing units on military bases in 48 contiguous States and DC in 2004

Frame and sample selection: SRC

SRC component: Housing units in 48 contiguous States and DC in 1968

SEO component: low income families in 48 contiguous States and DC with successful interview in 1967 Survey of Economic Opportunity and who signed data release agreement

Housing units (recent immigrant component) in 48 contiguous States and DC in 1997 for post-1968 immigrants with spouses not in the US in 1968

Frame and sample selection: SRC

Sample Design Multi-stage sampling design

Designed for National but not State estimates

Cohort samples drawn in 1992 (born 1931-1941), 1993 (born 1923 or earlier), 1998 (born 1924-1930 and 1942-1947) and 2004 (born 1948-1953)

1993 and 1998 cohorts (not 2004) adjusted for representation in previously selected samples

SRC component: Multi-stage sampling design

SEO component: "Low" income families with head under 60 years old in metropolitan PSUs where SRC could field interviewers and in a sample of non-metropolitan PSUs in the South (90 total PSUs from 357 in SEO)

1997 redesign removed all non-Black SEO component original families and descendants, reduced total SEO component by 2/3 and added recent immigrant families

Sample Unit Age-eligible person and spouse or partner of any age Families originally selected plus split-off families containing persons or descendants of persons in originally selected families
Oversamples Blacks, Hispanics, and residents of Florida Blacks, low income and urban families (in SEO component)
Response Threshold Interview must update family roster and relationships, and obtain demographics and health data

Files contain actual or imputed data on responding age-eligible persons, current spouse or partner, and former (interviewed) spouses or partners

Interview must update family roster and relationships, and obtain housing, food cost, labor force and income data

File contains actual or imputed data on all responding families

Initial Response Rate 81.4% for 1992 cohort, 80.4% for 1993 cohort, 72.5% and 70.0% for 1998 cohorts and 75.6% for 2004 cohort 79% for SRC component and 71% for selected eligible names/addresses sent to SRC for the SEO component

TABLE II.3A. UNIVERSE DEFINITIONS, INCLUSIONS AND EXCLUSIONS
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Survey Universe and Area Resident civilian noninstitutionalized population of the US plus military living with civilian family members on or off base

50 States and DC

Resident civilian noninstitutionalized population of the US plus military living with civilian family members on or off base

50 States and DC

Non-Institutional Group Quarters Living arrangements other than housing units whose occupants are free to come and go

Includes retirement homes, assisted living facilities, personal or residential care homes, rooming or boarding houses, convents and monasteries, shelters and group homes, and college dormitories if "usual residence"

Military barracks are non-institutional but excluded as not civilian

May include staff of non-institutional or institutional group quarters who do not live in housing units

Living arrangements other than housing units whose occupants are free to come and go

Includes retirement homes, assisted living facilities, personal or residential care homes, rooming or boarding houses, convents and monasteries, shelters and group homes, but not college dormitories

Military barracks are non-institutional but excluded as not civilian

May include staff of non-institutional or institutional group quarters, who do not live in housing units

Institutions Group quarters whose occupants are not free to come and go

Excluded locations include prisons, nursing homes, juvenile detention facilities and residential mental hospitals

Sample persons not interviewed in institutions but return to interview status if they rejoin family unit or establish their own households

Group quarters whose occupants are not free to come and go

Excluded locations include prisons, nursing homes, juvenile detention facilities and residential mental hospitals

Students College students normally included in parental family College students included in parental family
Active Military Person and income included if living with one or more civilian family members age 15 or over on or off base Person and income included if living with one or more civilian family members age 15 or over on or off base
Institutionalized Data on person and income while institutionalized not available Person and prior calendar year income excluded
Decedents Data on person and income available through wave prior to death if not institutionalized at death Person and prior calendar year income excluded
Other Exclusions Unrelated children under age 15 in group quarters such as shelters Unrelated children under age 15 in group quarters such as shelters
TABLE II.3B. UNIVERSE DEFINITIONS, INCLUSIONS AND EXCLUSIONS
  2002 American Community Survey 2002 Medical Expenditure Panel Survey Household Component
Universe and Geographic Area Resident household population of the US through 2004 with Puerto Rico added in 2005

Resident population of the US and Puerto Rico (same as Decennial) for 2006 and subsequent years

Resident civilian noninstitutionalized population of the US as of NHIS interview

Persons institutionalized subsequent to NHIS interview included

50 States and DC

Non-Institutional Group Quarters Living arrangements other than housing units

No distinction between two types of group quarters

All group quarters excluded through 2005

Includes dormitories, barracks, retirement homes, assisted living facilities, personal or residential care homes, rooming or boarding houses, convents and monasteries, shelters and group homes, prisons, nursing homes, juvenile detention facilities and residential mental hospitals

Living arrangements other than housing units whose occupants are free to come and go

Includes dormitories, retirement homes, assisted living facilities, personal or residential care homes, rooming or boarding houses, convents and monasteries, shelters and group homes

Military barracks are non-institutional but excluded as not civilian

May include staff of non-institutional or institutional group quarters, who do not live in housing unitsGroup quarters whose occupants are not free to come and go

Excluded locations include prisons, nursing homes, juvenile detention facilities and residential mental hospitals

Institutions
Students Students in dormitories excluded through 2005

Students included where they currently reside -- if in student housing during interview month are single individuals

College students are interviewed in dormitories but included in parental family
Active Military Military in barracks excluded through 2005 Military living with one or more civilian family members on or off base not given person weights but income included
Institutionalized Person and prior 12-month income excluded through 2005 Person excluded but some data and calendar year income while institutionalized available
Decedents Person and prior 12-month income excluded Data on person and income available until death
Other Exclusions None Unrelated minors (usually under age 18) in households or group quarter if not foster children
TABLE II.3C. UNIVERSE DEFINITIONS, INCLUSIONS AND EXCLUSIONS
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Universe and Geographic Area Resident civilian noninstitutionalized population of the US

50 States and DC

Current Medicare enrollees in the US and Puerto Rico regardless of living arrangements

50 States, DC, and Puerto Rico

Non-Institutional Group Quarters Living arrangements other than housing units whose occupants are free to come and go

Includes dormitories, retirement homes, assisted living facilities, personal or residential care homes, rooming or boarding houses, convents and monasteries, shelters and group homes

Military barracks are non-institutional but excluded as not civilian

May include staff of non-institutional or institutional group quarters, who do not live in housing units

No hard distinction between types of group quarters

Community interviews conducted with persons in housing units and group quarters that are not skilled nursing homes or otherwise require a facility interview

May include retirement homes, assisted living facilities, personal or residential care homes and other group living arrangements

Institutions Group quarters whose occupants are not free to come and go

Excluded locations include prisons, nursing homes, juvenile detention facilities and residential mental hospitals

Non-institutional shelters for battered women also excluded

Facility interviews with staff proxies conducted with persons in nursing homes, and other residential facilities where sample persons cannot be directly contacted

Excluded locations: prisons and facilities for the criminally insane

Other residential facilities may include retirement homes, assisted living facilities, personal or residential care homes and other group living arrangements

Students Students included where they currently reside -- if in student housing during interview month are single individuals Current student status not ascertained
Active Military Military living with one or more civilian family members on or off base not given person weights but income included Current military status not ascertained
Institutionalized Person and prior calendar year income excluded Person and prior 12-month income included
Decedents Person and prior calendar year income excluded Data on person and income available until death
Other Exclusions Unrelated minors (usually under age 18) in households or group quarter if not foster children None

TABLE II.3D. UNIVERSE DEFINITIONS, INCLUSIONS AND EXCLUSIONS
  2004 Health and Retirement Study 2003 Panel Study of Income Dynamics
Universe and Geographic Area Age-eligible resident household population of the US excluding households on military bases at time of selection, and spouses or partners regardless of age or whether institutionalized

Sample frames restricted to 48 contiguous States and DC but sample persons followed and interviewed wherever they move, including other countries

Members of original 1968 sample and 1997 recent immigrant sample of resident household population, and their descendants

Sample frames restricted to 48 contiguous States and DC but sample persons followed and interviewed wherever they move, including other countries

Non-Institutional Group Quarters Living arrangements other than housing units

No distinction between two types of group quarters

At time of selection, sample persons including those ages 70 or over (1993 cohort) and 74 or over (older 1998 cohort) limited to residents of housing units and exclude residents of group quarters

Excluded locations include retirement homes, assisted living facilities, personal or residential care homes, rooming or boarding houses, prisons, nursing homes, and residential mental hospitals

Sample persons followed and interviewed regardless of subsequent living arrangements or institutionalization

Living arrangements other than housing units

No distinction between two types of group quarters

Excluded locations include retirement homes, assisted living facilities, personal or residential care homes, rooming or boarding houses, prisons, nursing homes, and residential mental hospitals

Sample persons in group quarters interviewed if no sample persons remain in family they left

Sample persons moving to group quarters from family that still contains sample persons excluded, but return to interview status if they rejoin family or establish their own households

Institutions
Students Students living at school excluded from family Treatment follows group quarter rules
Active Military Included if sampled but not identified on public use files Treatment follows group quarter rules
Institutionalized Data on person and prior calendar year income available Treatment follows group quarter rules
Decedents Data on person until death does not include income

If decedent was alive at 2002 interview, prior year (CY2001) income data is available from that interview, otherwise last income data is CY1999

RAND person-based files do not include close-out interviews containing data on size and disposition of estate

Data on person and income available until death
Other Exclusions None None
TABLE II.4A. TIMING AND FIELDWORK
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
New Samples Panels started in 2001, 2004 and 2008

Panels have 4 rotation groups which start in 4 consecutive months

Uses the underlying monthly survey (CPS-1) sample

New rotation group (1/8 of CPS-1 sample) starts each month each year

Duration in Sample Persons in sample household in survey for duration of panel

Persons joining sample household or in households joined by sample persons in survey until no longer living with sample persons

Sample address in sample and its occupants interviewed 4 consecutive months for CPS-1 and supplements, not in survey next 8 months ("resting"), interviewed next 4 consecutive months then retired or rotated out (4-8-4 rotation pattern)

Occupants (same or different) at sample address interviewed

Interview Timing Each rotation group interviewed in a separate month

Fieldwork is continuous during the year

Data collected at a fixed interval of 4 months - three times a year - with 4 one-month reference periods for core questions

Topical modules range from annual to once per panel

Total number of interviews varies panel to panel

Interview conducted in the week containing the 19th of the month

ASEC data collected in February through April, with bulk of data collection in March - prior to 2002 collected only in March

ASEC data collected once per year with prior calendar year reference period

Half of sample addresses in same month of consecutive years are the same

Sample Size 28,000 interviewed households in 2001 panel after wave 2 reduction 78,300 interviewed households in 2003 (2002 income)
Contact Method CAPI (computer assisted personal interviewing) and CATI (computer assisted telephone interviewing) CAPI (computer assisted personal interviewing) and CATI (computer assisted telephone interviewing)
Respondents Persons 15 years or over each respond for self Householder (person who owns or rents housing unit) or a knowledgeable adult household member
Proxies Proxy respondents for 39% of individual interviews One person responds for household
Field Work Census Bureau Census Bureau

TABLE II.4B. TIMING AND FIELDWORK
  2002 American Community Survey 2002 Medical Expenditure Panel Survey Household Component
New Samples Independent sample (1/12 of annual sample) starts each month each year New panel starts every year

Drawn from prior year NHIS respondents for first 2 or 3 quarters

Duration in Sample Sample household in survey once Persons in sample family in survey for duration of panel

Persons joining sample family or in families joined by sample persons in survey until no longer living with sample persons

Interview Timing Questionnaires are mailed each month

Fieldwork is continuous during the year

One-time data collection with prior 12-month reference period ending in month prior to month in which survey is answered

Mail responses accepted through a 3 month response interval

Interviews spaced at approximately 6 month intervals

2 panels in the field simultaneously

Fieldwork is fairly continuous during the year

5 interviews per family with interview to interview reference periods that start 1/1 of first year and end 12/31 of second year

Sample Size 512,768 interviewed households in 2002 (2002 income)

Full implementation sample is 3 million households (2005)

14,700 interviewed families in 2002 HC file (2002 income)
Contact Method Mail out and mail back questionnaire with space for person-level responses on 5 people

Followup by CATI (computer assisted telephone interviewing) if not returned after 1 month or is incomplete or more than 5 persons are listed (about 1/3 of sample completed by CATI)

Followup by CAPI (computer assisted personal interviewing) after 2 months attempted for 1/3 of remaining non-responders, non-contacts and incompletes during 1 more month, with other 2/3 dropped from sample and from non-response computation

CAPI (computer assisted personal interviewing) of each family and of college students in dormitories possibly supplemented by CATI (computer assisted telephone interviewing)
Respondents Householder (person who owns or rents housing unit) or knowledgeable adult household member Person knowledgeable about health of family members
Proxies One person responds for household One person responds for family
Field Work Census Bureau Westat

TABLE II.4C. TIMING AND FIELDWORK
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
New Samples Independent sample (1/4 of annual sample) starts every quarter every year New panel starts every year
Duration in Sample Sample household is in survey once Sample enrollee is in survey for duration of panel, about 4 years
Interview Timing Interviews assigned for each of 52 weeks in year and field staff have 17 days in which to complete each week's interviews

Fieldwork is continuous during the year (rolling sample)

One-time data collection with prior calendar year reference period

Each family in household is separately interviewed

Interviews spaced at approximately 4 month intervals

4 panels in the field simultaneously

Fieldwork is fairly continuous during the year

12 interviews per enrollee with interview to interview reference periods

Sample Size Over 36,000 interviewed families in 2003 (2002 income) Over 12,000 enrollees in 2003 Cost and Use file

Over 16,000 enrollees in 2003 Access to Care file

Contact Method CAPI (computer assisted personal interviewing) CAPI (computer assisted personal interviewing) for community interviews

CAPI (computer assisted personal interviewing) for facility interviews after 1996

Respondents Person knowledgeable about health of family members

Persons 17 years or over may respond for self if present

Enrollee or family member for community interviews

Nursing staff or care-givers and business office staff for facility interviews

Proxies One person responds for family Proxy respondents for 19% of community interviews

Proxy respondents for all facility interviews

Field Work Census Bureau Westat

TABLE II.4D. TIMING AND FIELDWORK
  2004 Health and Retirement Study
2003 Panel Study of Income Dynamics
New Samples New birth cohort (and spouses or partners of any age) added every 6 years Core panel started in 1968

Recent immigrant sample added in 1997

Duration in Sample Age-eligible sample person in survey for life

Spouse or partner of age-eligible person at time of selection in survey for life regardless of age

New spouses or partners of age-eligible persons, or of spouse or partner of age-eligible persons at time of selection, in survey until remarried or re-partnered, according to documentation

Sample persons and their descendants in survey for life

Persons joining sample family or in families joined by sample persons or their descendants in survey until no longer living with sample persons or their descendants

Interview Timing Data collected every two years with prior month or prior calendar year reference periods for most income sources, prior 2 years for Food Stamps and for changes in assets Data collected every two years with prior calendar year reference period for most income sources

Interviews were annual for the 30 years 1968 through 1997

Sample Size 13,650 households interviewed in 2004 (2003 income) including cohort added in 2004 Original sample 2,930 families in SRC component and 1,872 families in SEO component

Recent immigrant sample (1997) 511 families

7,822 families interviewed in 2003 (2002 income)

Contact Method CAPI (computer assisted personal interviewing) for most initial (baseline) interviews except CATI (computer assisted telephone interviewing) for 1993 cohort

CAPI (computer assisted personal interviewing) and CATI (computer assisted telephone interviewing) for subsequent interviews

CATI (computer assisted telephone interviewing)
Respondents Multiple respondents - can differ for each of coverscreen, family, financial, sibling, child, helper, and asset-transfer questionnaires Family head or wife/"wife" (male head of family or legal spouse/unmarried partner)
Proxies Most questionnaires addressed to proxies Proxy respondents for 2% of family interviews
Field Work SRC SRC
TABLE II.5A-B. LONGITUDINAL INCLUSION AND FOLLOW RULES
  2001 Panel of Survey of Income and Program Participation 2002 Medical Expenditure Panel SurveyHousehold Component
Sample Person Movers Followed to new locations within 50 States and DC

Move-outs create new household and at least one new reference person who need not be a sample person

Followed to new locations within 50 States and DC but may be restricted to sample PSUs

Move-outs create new family and at least one new reference person who need not be a sample person

File does not contain any non-sample reference persons

Permanent Additions Children born to sample members Children born to sample members
Temporary Additions Move-ins including new spouses while they live with sample persons

Interviews may not provide full calendar year income

Move-ins including new spouses or partners while they live with sample persons

Move-ins with data on file have calendar year income

Institutionalized Sample persons followed in and out of institutions but not interviewed and no data while institutionalized Sample persons followed in and out of institutions but not interviewed and no data while institutionalized

Includes those institutionalized after prior year NHIS interview

Active Military Followed while living with one or more civilian family members age 15 or over on or off base Followed while living with one or more civilian family members on or off base but not given person weights
Students College students away at school but "usually residing" with parents included in parental family College students are interviewed in dormitories but included in parental family
Decedents No close-out interview

Data as of last interview outside an institution

Proxy close-out interview

Income information obtained for calendar year of death

Re-contact Efforts Refusals always re-contacted each wave No information available
Responding Households Total decreases over life of panel Total decreases over life of panel
Attrition Interview to interview attrition (4 months) averages 6.5% after wave 2 sample reduction MEPS sample first interviewed in NHIS and MEPS 1st interview equivalent to other surveys' 2nd interview

Interview to interview attrition (6 months) averages 2% after 1st interview

2002 Response Rate Average response for interviews covering 2002: 72.5% 2002 Full Year file: 64.7%

TABLE II.5C-D. LONGITUDINAL INCLUSION AND FOLLOW RULES
  2003 Medicare Current Beneficiary Survey 2004 Health and Retirement Study
Sample Person Movers Followed to new locations in a sample PSU in the 50 States, DC, and Puerto Rico Followed to new locations in or out of the US

Move-out of spouse or partner creates new sample family

Permanent Additions No additions No additions
Temporary Additions No additions New spouses or partners of age-eligible person or of former spouse or partner of age-eligible person until remarried or re-partnered, according to documentation

If person on file, prior calendar year income available

Institutionalized Followed in and out of institutions and exact dates obtained

Facility interview in institution and an additional community interview on release

Followed in and out of institutions and income data obtained

Nursing home residents have weights from 2000 forward

Active Military Current military status not ascertained Included if sampled but not identified on public use files
Students Current student status not ascertained Non-sample students living at school during school year classified as institutionalized and excluded
Decedents Proxy close-out interview

Does not obtain income information for year of death

Proxy close-out interview includes information on settled estate

Does not obtain income information for year of death

RAND person-based files do not include close-out interviews

Re-contact Efforts Attempts made to convert refusals To date, refusals re-contacted unless request otherwise
Responding Households Remains fairly constant unless sample size is changed

New panels start annually to add new enrollees, replace participants expected to be lost or rotated out, and maintain sample size and age stratification

Total decreases over time until new cohort added
Attrition Interview to interview attrition (4 months) averages 4% Interview to interview attrition (2 years) averages 7%
2002 Response Rate 2003 Cost and Use file: 69.5% Not applicable
TABLE II.6A. FAMILY DEFINITIONS
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Family Definition Persons related by blood, marriage or adoption Persons related by blood, marriage or adoption
Household Relationships Relationship of every person to household reference person at each interview

Person who owns or rents housing unit at each interview is household reference person and may be either husband or wife

Relationship of every person in household to every other person in household identified in 2nd interview

Relationship of every person to household reference person

Person who owns or rents housing unit is household reference person (householder) and may be either husband or wife

Family Relationships Relationship of every person to family reference person at each interview Relationship of every person to family reference person
Related Subfamilies Married couple with or without never-married children under 18 and single parents with never-married children under 18

Persons and subfamily identified

Married couple with or without never-married children under 18 and single parents with never-married children under 18

Persons and subfamily identified

Unrelated Subfamilies Married couple with or without never-married children under 18 and single parents with never-married children under 18

Persons and subfamily identified

Married couple with or without never-married children under 18 and single parents with never-married children under 18

Persons and subfamily identified

Marriage Legal marriage

Legal spouse identified if present for all persons

Cohabiting (unrelated) partner of reference person identified

Legal marriage

Legal spouse identified if present for all persons

Cohabiting (unrelated) partner of reference person identified

Parents Mother and father each identified if present as well as type of relationship (biological, step, adopted) for all persons One parent identified if present for all persons through 2006

Mother and father each identified if present as well as type of relationship (biological, step, adopted) for all persons after 2006

Alternative Definitions Any required family unit can be constructed  
Differences From CPS No differences  

 

TABLE II.6B. FAMILY DEFINITIONS
  2002 American Community Survey 2002 Medical Expenditure Panel SurveyHousehold Component
Family Definition Persons related by blood, marriage or adoption Persons related by blood, marriage or adoption, including foster relationships and unmarried (opposite or same sex) partners
Household Relationships Relationship of every person to household reference person

Person who owns or rents housing unit is household reference person (householder) and may be either husband or wife

Concept not used
Family Relationships Only when family reference person is household reference person (householder) Relationship of every person to family reference person at each interview
Related Subfamilies Married couple with or without never-married children under 18 and single parents with never-married children under 18

Persons and subfamily identified

Concept not used

Related subfamilies can be constructed

Unrelated Subfamilies Concept not used and cannot be identified

Members treated as unrelated individuals

Concept not used and interview is at family level
Marriage Legal marriage

Presence of legal spouse for all persons but spouse not identified except spouse of reference person

Cohabiting (unrelated) partner of reference person identified

Legal marriage or self-identified cohabitation

Legal spouse identified if present for all persons

Cohabiting partner of reference person or of reference person's parents, and children of partner, identified in relationship codes

Parents Presence of mother and/or father for all children but parent(s) not identified Mother and father each identified if present for all persons
Alternative Definitions Cannot be constructed Identifies members of CPS-defined families as of December 31 but not relationships if CPS family has different reference person than MEPS family
Differences From CPS No unrelated subfamilies, so that members of unrelated subfamilies all become unrelated individuals Unmarried (opposite or same sex) partners, relatives of partner and foster relationships treated as blood or marital relationships

TABLE II.6C. FAMILY DEFINITIONS
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Family Definition Persons related by blood, marriage or adoption, including foster relationships and unmarried (opposite or same sex) partners Families not identified
Household Relationships Relationship of every person to household reference person

Person who owns or rents housing unit is household reference person (householder) and may be either husband or wife

Householder concept not used

Number of persons in household and some information on relationships obtained in community interview

Family Relationships Relationship of every person to family reference person Number of persons related to the enrollee and some information on relationships obtained in community interview
Related Subfamilies Concept not used

Related subfamilies can be constructed

Not identified
Unrelated Subfamilies Concept not used and interview is at family level Not identified
Marriage Legal marriage or self-identified cohabitation

Presence of legal spouse or self-identified partner for all persons but spouse not identified

Cohabiting partner of reference person and children of partner identified in relationship codes

Legal marriage

Presence of legal spouse

Parents Mother and father each identified if present as well as type of relationship (biological, step, adopted) for all persons Not ascertained
Alternative Definitions Income data not available if CPS family constructed Family structure not ascertained
Differences From CPS Unmarried (opposite or same sex) partners, relatives of partner and foster relationships treated as blood or marital relationships Families not identified
TABLE II.6D. FAMILY DEFINITIONS
  2004 Health and Retirement Study
2003 Panel Study of Income Dynamics
Family Definition Persons related by blood, marriage or adoption, including foster relationships and unmarried (opposite or same sex) partners Persons related by blood, marriage or adoption, including foster relationships, unmarried (opposite sex) partners, and unrelated persons (may be same-sex partners) identified as part of family
Household Relationships Terms household and family used interchangeably Concept not used
Family Relationships Relationship of every person in household/family to age-eligible person

Relationship of every person in household/family to spouse or partner of age-eligible person

Information obtained on siblings and children not in household

Relationship of every person in household/family to family head

Family head is always male spouse or partner when present

Legal spouse of head is wife, and unmarried partner of at least one year is "wife"

Related Subfamilies Concept not used Concept not used

Related subfamilies can be constructed

Unrelated Subfamilies Concept not used and interview is at family level Concept not used and interview is at family level
Marriage Legal marriage or self-identified cohabitation

Legal spouse identified in relationship codes for each reference person's parents, siblings, children and grandchildren

Cohabiting partners identified in relationship codes for each reference person's parents, siblings, children and grandchildren

Legal marriage or self-identified (opposite sex) partner of a year or more

Cohabiting partner of reference person of any duration, and children, siblings or parents of partner identified in relationship codes

Parents Mother and father each identified for age-eligible person and spouse or partner and for their children if present Mother and father and type of relationship identified for most persons ever in survey since 1968 in separate Parent Identification and Childbirth and Adoption History Files
Alternative Definitions Income data not available if CPS family constructed Income data not available if CPS family constructed
Differences From CPS Unmarried (opposite or same sex) partners treated as married, relatives of partner treated as relatives of householder, and foster relationships treated as blood relationships Unmarried (opposite sex) partners, relatives of partner, foster relationships, and some unrelated persons (may be same-sex partners) treated as blood or marital relationships

Related subfamilies that previously split off from but rejoined primary family kept as separate families

TABLE II.7A. WORK ACTIVITY AND EARNINGS
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Persons Covered All persons age 15 or over All persons age 15 or over
Reference Interval Monthly and weekly periods in prior 4 months Prior calendar year
Number of Jobs Detail on up to 2 separate jobs and 2 businesses Detail on longest job and longest business
Job or Business Information For Reference Interval Start and end dates and weeks worked

3-digit industry and occupation codes for each job and major industry and 3-digit occupation codes for each business

Class of worker, wage rate and usual hours per week

Monthly earnings or monthly draw from business, and net profit

Weeks worked full time, part time and total

Detailed and major industry and occupation codes

Class of worker and usual hours per week

Wages and salary from longest job, from other work, and total, and self-employment earnings

Unemployment Weekly employment status (e.g. employed, unemployed, not in labor force) Weeks unemployed (seeking work), weeks not in labor force
Job or Business Information For Other Intervals Work history obtained in topical module

Spells of unemployment or not in labor force can be constructed

Current employment status (e.g. employed, unemployed, not in labor force) and duration of current spell of unemployment last week

Current job: 4-digit and major industry and occupation codes

Current job: Class of worker, usual hours and earnings per week, hours last week -- wage rate asked for 1/4 of sample (4th and 8th interviews of each rotation group)

Industry/Occupation 3-digit (236-group) and major (14-group) industry codes based on 1987 North American Industrial Classification System (NAICS) used in 1990 Census

3-digit (501-group) occupation codes, based on 1990 Standard Occupational Classification (SOC) Manual used in 1990 Census

4-digit (270-group), detailed (52-group) and major (14-group) industry codes based on 2002 NAICS

4-digit (509-group), detailed (23-group) and major (11-group) occupation codes based on 2000 SOC Manual

Consistency Edits Hours, pay rate and earnings consistency checked in interview

Monthly earnings and work activity not cross-edited

Hours, pay rate and earnings consistency checked in interview

Earnings always imputed if work activity

TABLE II.7B. WORK ACTIVITY AND EARNINGS
  2002 American Community Survey 2002 Medical Expenditure Panel Survey Household Component
Persons Covered All persons age 15 or over All persons age 16 or over
Reference Interval Prior 12 months Interview to interview, approximately six months
Number of Jobs Not included Detail on current main job at each interview
Job or Business Information For Reference Interval Weeks worked

Usual hours per week

Wages and salary, and self-employment earnings

Start and end dates

Major industry codes and collapsed major occupation codes

Usual hours per week and wage rate

Self-employed in current main job

Unemployment Weeks unemployed or not in labor force (not differentiated) Unemployed or not in labor force (not differentiated) at interview
Job or Business Information For Other Intervals Current employment status (e.g. employed, unemployed, not in labor force) last week

Whether worked in last 5 years

Current main job or most recent job: 3-digit and major industry and occupation codes

Current main job or most recent job: Class of worker

Detail on all jobs held at each interview and/or during interview reference period in separate unedited research file, JOBS
Industry/Occupation 3-digit (265-group) industry codes based on 1997 NAICS, used in 2000 Census

3-digit (509-group) occupation codes based on 2000 SOC Manual, used in 2000 Census

Major (14-group) industry codes based on 2002 NAICS

Collapsed major (9 not 11-group) occupation codes based on 2000 SOC Manual

Consistency Edits Pre-edits to correct issues related to incorrectly filled-out forms

Work activity edited or imputed if earnings present

Earnings edited or imputed if work activity reported

Neither edits of work activity nor imputation based on earnings

Earnings imputed based on work activity for non-response but negative values not edited based on work activity

Type of earnings (wages and salaries vs. self-employment) not edited based on type of work activity

TABLE II.7C. WORK ACTIVITY AND EARNINGS
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Persons Covered All persons age 18 or over All enrollees age 16 or over living in community
Reference Interval Prior calendar year At interview or "current"
Number of Jobs Not included Not included
Job or Business Information For Reference Interval Whether worked and number of months worked

Total amount (internal file) or bracket (public use file) of earnings - wages and salaries not differentiated from self-employmentBrackets on public use file are $5,000 wide below $25,000 and $10,000 wide from $25,000 to $75,000

Recipiency questions on wages and salary and self-employment income

Whether working at a job or business
Unemployment Whether unemployed or not in labor force (not differentiated) for all of prior calendar year Not included
Job or Business Information For Other Intervals Current employment status (e.g. employed, unemployed, not in labor force) last week

Current job: Usual hours per week or hours last week

Not included
Industry/Occupation Not included Not included
Consistency Edits Recipiency of wages and salary or self-employment income not used to edit or impute work activity or earnings

Earnings imputed if work activity reported or imputed

File contains persons reporting receipt of wages and salary or self-employment income without work activity or earnings

Earned income not included
TABLE II.7D. WORK ACTIVITY AND EARNINGS
  2004 Health and Retirement Study
2003 Panel Study of Income Dynamics
Persons Covered Age-eligible sample person and spouse or partner but not other family members Head and wife/"wife" but not other family members
Reference Interval Prior calendar year Prior calendar year
Number of Jobs No detail on jobs or businesses Detail on up to 4 separate jobs or businesses
Job or Business Information For Reference Interval Start and end dates and months worked

Wages and salary, and self-employment earnings

Start and end dates and weeks worked

3-digit industry and occupation codes

Class of worker, wage rate and usual hours per week

Unemployment Months unemployed or not in labor force (not differentiated) Weeks unemployed and weeks not in labor force
Job or Business Information For Other Intervals Current employment status (e.g. employed, unemployed, not in labor force)

Current job: Wage rate and usual hours per week

Current employment status (e.g. employed, unemployed, not in labor force)

Current main job: 3-digit industry and occupation codes

Current main job: Class of worker and wage rate

Industry/Occupation Not on HRS or RAND public use files

Suppressed codes described as major industry and occupation codes (13- and 18-group) used in 1980 Census

3-digit (265-group) industry codes based on 1997 NAICS, used in 2000 Census

3-digit (509-group) occupation codes based on 2000 SOC Manual, used in 2000 Census

Consistency Edits No information available Hours, pay rate and earnings consistency checked in interview

Work activity and earnings consistency checked in interview

Work activity, pay rates, hours and earnings manually edited for consistency

 

TABLE II.8A. PRE-TAX MONEY INCOME
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Reference Period Monthly and 4-month periods in prior 4 months

Monthly and 4-month amounts

Prior calendar year

Allows choice of up to 6 reporting intervals from which annual amounts are calculated

Recall Length Average 3 months maximum 5 months Average 14 ½ months maximum 15 ½ months
Definitions Differ From CPS Self-employment is monthly draw plus net profit (cash basis)

Net profit not asked for sole proprietors or most partnerships not taking a monthly draw

 
Non-CPS Source Included Lump-sum or non-periodic payments such as IRA withdrawals  
CPS Source Excluded Educational benefits  
Amount Detail For Persons Up to 60 sources and amounts of income Over 50 sources and up to 24 amounts of income
Screeners and Brackets Multiple screeners and skip patterns

No brackets

Identifies which of multiple possible sources for an income type (e.g. survivors benefits) to screen into amount questions

No brackets

Persons Covered All persons for Social Security, SSI and TANF

Persons 15 or over for all other income sources

All persons for Social Security, SSI and TANF

Persons 15 or over for all other income sources

Income Reassigned For persons under 15, Social Security, SSI and TANF assigned to a representative payee or guardian For persons under 15, Social Security, SSI and TANF assigned to a representative payee or guardian
Person and Family Totals Sum of detail for persons and family Sum of detail for persons and family

TABLE II.8B. PRE-TAX MONEY INCOME
  2002 American Community Survey 2002 Medical Expenditure Panel SurveyHousehold Component
Reference Period 12 months prior to interview (rolling reference period) with average of July prior year to June current year

Income on internal files (for publications and on-line tables) but not on public use file inflated to calendar year price levels by ratio of average annual CPI to average CPI over reference period - CPI-U through 2005 and 2006 forward by CPI-U-RS

Calendar year

Income information collected in subsequent year is added to same-year file

Annual amount for 12 income sources, monthly amount and months received for 4 sources

Recall Length 12 ½ months Average 15 months maximum 18 months
Definitions Differ From CPS Depends on respondent interpretation of summary descriptions of income sources on mail questionnaire

Reference period -- income cannot be adjusted for differences in productivity, unemployment or other factors from the CPS' calendar year reference period

Internal Revenue Service definitions used for tax filers (1)

Wages omit "above the line" items that are not subject to income taxes such as 401(k) contributions

Self-employment earnings other than sole proprietorships and farm reported with rents, royalties, estates and trusts

Non-CPS Source Included None Lump-sum payments from retirement accounts
CPS Source Excluded None Tax exempt interest for tax filers
Amount Detail for Persons Up to 8 sources and amounts of income Up to 16 sources and amounts of income

Taxable income sources not person-level for joint return filers -- primary filer allocates amounts between self and spouse

Screeners and Brackets No screeners or skips except age

No brackets

Type of tax form used as screener for specific income sources - 1040A short form skips self-employment and other items

"Don't knows" (DKs) offered 10 annual brackets (to $100,000 or more) for most sources, 5 monthly brackets for 4 sources

Persons Covered Persons age 15 or over Persons 16 or over, and persons under 16 who report filing a tax return, for taxable income source (2)

All persons for all other income sources

Income Reassigned No reassignment - income not asked if person under 15 No reassignment
Person and Family Totals Sum of detail for persons and family Sum of detail for persons and family

1. Filers of tax form 1040EZ skip self-employment income questions -- sole proprietorship or farm (Schedules C and F) or other business arrangements (Schedule E).
2. Prior to 2002, non-filers, and refusals/"don't knows" for specific tax form (1040, 1040A or 1040EZ), skipped all questions on taxable income amounts which were then allocated or imputed. Persons filing 1040EZ skipped many questions on taxable income amounts, including Social Security and pensions.

TABLE II.8C. PRE-TAX MONEY INCOME
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Reference Period Prior calendar year

Annual amounts

Summer: Prior calendar year amount (on Cost and Use file)

Fall: Prior 12 months bracket (on Access to Care file)

Allows choice of monthly reporting interval from which annual amount or bracket is calculated

Recall Length Average 18 months maximum 23 months 18 months (summer) or 12 ½ months (fall)
Definitions Differ From CPS Earnings amount includes net income from rental property and unemployment or worker's compensation

Recipiency data groupings conform to CPS definitions (3)

Depends on respondent interpretation of "total income before taxes"
Non-CPS Source Included None None
CPS Source Excluded None None
Amount Detail For Persons One amount (internal file) or bracket (public use file) for total earnings from all sources (See Table II.14 on Ease of Access)

Recipiency but no amounts for up to 10 other sources - file has no imputations of recipiency

One amount or bracket for total income of enrollee or enrollee and spouse from all sources (See Table II.14 on Ease of Access)

13 recipiency items asked in summer but not on file

Screeners and Brackets No screener, skip or brackets on earnings

No screener on total family income -- DKs and refusals asked "over or under $20,000" then offered 24 or 20 brackets

No screeners or skips

Summer: DKs and refusals asked simple unfolding brackets (2 steps) with entry and steps for enrollees with spouse present twice as large as for single enrollees

Fall: "Over or under $25,000" then offered 6 or 5 brackets

Persons Covered Persons 18 or over for earnings All enrollees
Income Reassigned No reassignment since no person-level income No reassignment
Person and Family Totals One amount (internal file) or bracket (public use file) for total income of NHIS-type family (See Table II.14 on Ease of Access)

File contains families with total income less than total earnings

One amount or bracket for enrollee or enrollee and spouse

3. In recipiency (no amounts) data, rental income is grouped with dividends, estates and trusts, and unemployment and worker's compensation are grouped with Veterans payments and family contributions in "other"

TABLE II.8D. PRE-TAX MONEY INCOME
  2004 Health and Retirement Study
2003 Panel Study of Income Dynamics
Reference Period Prior calendar year

Annual amounts for non-retirement income, amount last month for retirement income and SSI

Prior calendar year

Allows choice of up to 6 reporting intervals from which annual amounts are calculated

Recall Length Maximum probably 24 months Average 18 months maximum 24 months
Definitions Differ From CPS Rental income is gross rent before deducting expenses

RAND income totals and groupings do not conform to CPS (4)

None

VA benefit variable includes military retirement

Non-CPS Source Included HRS: No total income re-code but appears to include IRA withdrawals and lump sums such as inheritances

RAND: Lump sums such as inheritances, and Food Stamps

None
CPS Source Excluded Alimony, child support, income from trust funds and royalties, and financial assistance from family or friends (5) None
Amount Detail For Persons 18 non-asset and 8 joint asset sources and amounts for age-eligible person and spouse or partner

Non-self-employment earnings for other family members but no other sources or person-level amounts -- one catchall total

Up to 31 sources and amounts of income excluding Social Security for head and wife/"wife" and which months received

No person-level sources or amounts for other family members and 2002 Social Security only a family total

Screeners and Brackets Multiple screeners and skip patterns

DKs and refusals asked unfolding brackets with item-specific entry points and steps - some items have randomly selected entry points

Multiple screeners and skip patterns

No brackets for income - unfolding brackets used for some asset values and expenses (e.g. medical)

Persons Covered Age-eligible person and spouse or partner Head and wife/"wife"
Income Reassigned No reassignment No reassignment
Person and Family Totals For age-eligible person or spouse or partner separately, sum of detail excluding asset income or self-employment, and as couple, sum of detail

For family, sum of detail for age-eligible person and spouse or partner plus total of other family member income

Sum of detail for head and wife/"wife" excluding Social Security - summary recodes combine income of head and wife/"wife"

For family, sum of detail for head and wife/"wife" plus total family Social Security plus total other family member taxable(6) income and transfer (7) income excluding Social Security

4. There are numerous differences. Except for the household income used to calculate RAND's poverty measure, RAND total income includes Food Stamps. Earnings exclude self-employment, which is included with asset income. Pensions and annuities include not only private but public retirement systems - except military retirement - but with no distinction between disability, retirement and survivors benefits. Other government transfers include Veterans' benefits -- including "military pensions" -- welfare and Food Stamps. The variable SSDI combines SSI and the disability component of Social Security. The Social Security variable includes the old age, survivor and dependents components but not disability. And Unemployment and Workers Compensation is a combination that may also include Workers Compensation survivor benefits.

5. HRS income exclusions vary from year to year. The thousand-page RAND HRS Data Documentation (Version G) includes careful descriptions of wave-to-wave differences and as much of a concordance as is possible.

6. PSID groups earnings from all sources and asset income from all sources under the term "taxable income".

7. PSID groups all government and private transfers except Social Security under the term "transfer income". This includes AFDC/TANF, SSI, other welfare, Veterans benefits including military retirement, Unemployment and Workers Compensation, all retirement, pension, annuity and periodic IRA income, child support, alimony and contributions from relatives or friends.

TABLE II.9A. INCOME ALLOCATION AND TOP-CODING ON PUBLIC USE FILES
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Allocations and Edits Consistency, out-of-range, and logical edits built into CAPI and CATI and then repeated in processing data file Consistency, out-of-range, and logical edits built into CAPI and CATI and then repeated in processing data file
Imputations Statistical match (hot deck) and logical imputations, plus use of prior wave data Statistical match (hot deck) and logical imputations, including Supplement refusals
Rounding Income data not rounded Income data not rounded
Earnings Top-Codes Monthly earnings amounts from a source (main job, other wages and salary, or self-employment including farm) top-coded at $12,500 (equivalent to $150,000 annually) if 4-month sum from that source exceeds $50,000 Wages and salary from longest job top-coded at $200,000

Other wage and salary, self-employment and farm earnings top-coded at $35,000, $50,000 and $25,000 respectively

Value When Top-Coded (Earnings) Average across top-coded records in each of 12 demographic cells for each earnings source (some cells empty or collapsed)

Tabulations on public use file will add to published totals

Average across top-coded records in each of 12 demographic cells for each earnings source (some cells empty or collapsed)

Tabulations on public use file will add to published totals

Other Income Top-Codes No top-codes for Social Security, SSI, TANF, unemployment benefits, Workers Compensation and Veterans payments

Larger of 97th percentile of dollar values or 99.5th percentile of persons 15 or over (whether or not have income)

No top-codes for Social Security, SSI, TANF, unemployment benefits, Workers Compensation and Veterans payments

Larger of 97th percentile of dollar values or 99.5th percentile of persons 15 or over (whether or not have income)

Value When Top-Coded (Other Income) Top-code (no average across top-coded records)

Tabulations on public use file may not add to published totals

Average across top-coded records

Tabulations on public use file will add to published totals

Person and Family Totals Not separately top-coded Not separately top-coded
Other Suppressions Age top-coded at 88

Geographic and event timing (e.g. month of birth) suppression based on disclosure analysis

Age top-coded at 80

Geographic and some suppression of detailed race, occupation and country of birth based on disclosure analysis

TABLE II.9B. INCOME ALLOCATION AND TOP-CODING ON PUBLIC USE FILES
  2002 American Community Survey 2002 Medical Expenditure Panel SurveyHousehold Component
Allocations and Edits Consistency, out-of-range, and logical edits Some out-of-range, and logical edits built into CAPI

Brackets converted to amounts through hot decks

Most wage and salary allocations based on JOBS file but job-specific data in JOBS not used for edits

Imputations Statistical match (hot deck) nearest neighbor imputations Statistical match (hot deck) and logical imputations
Rounding $10 to $1,000 to nearest $10, $1,000 to $50,000 to nearest $100, and above $50,000 to nearest $1,000, after top-coding Income data not rounded
Earnings Top-Codes 2002 wages and salary and self-employment each top-coded at 99.5th percentile nationally - $200,000 and $78,751 - with State-specific top-codes for 2003 and subsequent years Wages and salary and self-employment each top-coded at 99th percentile - amount not documented
Value When Top-Coded (Earnings) State-specific average across top-coded records (uninflated)

Tabulations on public use file will not add to published totals

Top-codes replaced with a "smeared" or randomized value

Tabulations on public use file will add to published totals

Other Income Top-Codes 99.5th percentile nationally for 2002 and State-specific top-codes after 2002 for all other income sources through 2005

No top-codes for Social Security, SSI and TANF after 2005

99th percentile nationally
Value When Top-Coded (Other Income) State-specific average across top-coded records (uninflated)

Tabulations on public use file will not add to published totals

Top-codes replaced with a "smeared" or randomized value

Tabulations on public use file will add to published totals

Person and Family Totals Not separately top-coded

No tabulations on public use file can match published totals because public use file lacks inflation adjustments

Person totals separately top-coded at 99th percentile and replaced with a "smeared" value

Tabulations on public use file will add to published totals

Other Suppressions Interview month and inflation adjustment amount suppressed

Age top-coded at 90 and replaced by State-specific average across top-coded records

Geographic re-codes to aggregate data into micro-areas with populations of approximately 100,000 or more

Random replacements or exchanges of income values

Geographic and possibly other suppression based on disclosure analysis

TABLE II.9C. INCOME ALLOCATION AND TOP-CODING ON PUBLIC USE FILES
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Allocations and Edits Earnings imputed only if work activity reported or imputed Amounts from previous year or from Fall brackets
Imputations Multiple sequential regressions for total family earnings and income -- imputed family earnings divided among persons but not constrained to be less than or equal to family income

NCHS creates 5 files of imputations and recommends that analyses be performed 5 times and results averaged

Summer: Statistical match (hot deck) based on regression analysis (on Cost and Use file)

Fall: Pro-rated among brackets (on Access to Care file)

No imputation flag for income on 2003 Cost and Use file

Rounding No specific rounding of income data No specific rounding of income data
Earnings Top-Codes Total earnings top-coded at $75,000 for public use file brackets

Total earnings top-coded at $999,995 for internal file amounts

Brackets on public use file are $5,000 wide below $25,000 and $10,000 wide from $25,000 to $75,000

 
Value When Top-Coded Top-code (no average across top-coded records)  
Other Income Top-Codes    
Value When Top-Coded    
Person and Family Totals No person totals

Family income top-coded at $75,000 for brackets on public use file with no average across top-coded records - 28% of persons on public use file are in top-coded families

Family income top-coded at $999,995 for internal file amounts

Brackets on public use file are $5,000 wide below $25,000 and $10,000 wide from $25,000 to $75,000

No top-codes
Other Suppressions Imputed covariates for total family earnings and income including numerous health, insurance coverage, socio-demographic and income recipiency variables suppressed and may not be on internal file

Major geographic suppressions

Some geographic suppressions
TABLE II.9D. INCOME ALLOCATION AND TOP-CODING ON PUBLIC USE FILES
  2004 Health and Retirement Study
2003 Panel Study of Income Dynamics
Allocations and Edits HRS: Information not available

RAND performs major consistency, out-of-range, and logical cross-section edits and multiple longitudinal consistency edits

Consistency, out-of-range, and logical cross-section edits
Rounding Income data not rounded Income data not rounded
Imputations HRS: Statistical match (hot deck) including conversions of brackets to amounts - bracket data provided as well so users can perform their own imputations

RAND: Statistical match (hot deck) based on case-specific regression models

Statistical match (hot deck) and logical imputations, plus use of prior wave data
Earnings Top-Codes No apparent top-codes

Values of $2,000,000 are on file and earlier waves have values over $3,500,000

Maximum values of $9,999,999 are de facto top-codes
Value When Top-Coded (Earnings) Probably maximum value Maximum value

Tabulations on public use file will add to published totals

Other Income Top-Codes (Other Income) No apparent top-codes

File contains pension income values over $2,700,000 and asset income values over $3,500,000 -- earlier waves have asset income values over $7,000,000

Maximum values, usually $9,999,999, are de facto top-code

Maximum value for e.g. total family Social Security and total non-taxable income of other family members, is $999,999

Value When Top-Coded Probably maximum value Maximum value

Tabulations on public use file will add to published totals

Person and Family Totals No apparent top-codes Maximum values of $9,999,999 are de facto top-codes
Other Suppressions Major geographic suppressions

Industry, occupation and month and day of birth suppressed to preserve confidentiality

Major geographic suppressions to preserve confidentiality
TABLE II.10A. POVERTY STATUS
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Income Period Covered Constructed intervals that can be monthly or part-year or calendar year for analysis of spells of poverty Prior calendar year
Family Definition Used CPS family but other definitions can be constructed CPS family
Coverage Persons in families with related subfamilies folded in

Persons in unrelated subfamilies

Unrelated individuals

Persons in families with related subfamilies folded in

Persons in unrelated subfamilies

Unrelated individuals

Exclusions From Survey Universe For Poverty Status Unrelated children under 15 Unrelated children under 15

Family counts exclude subfamilies (related and unrelated) but all persons in subfamilies included

Difference From CPS None  
Family Unit Timing Can choose any month for construction of family units and consequent family composition and income amounts Interview month (usually March) an average of 3 months after income reference year
Difference From CPS Family composition and thus income need not match CPS  
Income for Computation Total income of CPS family Total income of CPS family
Difference From CPS Minor income differences noted in Table II.8: educational benefits, lump-sum or non-periodic payments such as IRA withdrawals, measurement of self-employment income  
Poverty Status On File Monthly poverty thresholds - 1/12 of annual threshold inflated by CPI-U to that month -- for each family and subfamily for composition as of that month, but ratio not calculated Calendar year poverty status of CPS family as of the following March (usually) based on CPS income for year
Calculation of Alternatives User can construct monthly, part-year or annual poverty measures, and can use alternate family compositions and/or timing of family composition Official definition and official poverty statistics
TABLE II.10B. POVERTY STATUS
  2002 American Community Survey 2002 Medical Expenditure Panel SurveyHousehold Component
Income Period Covered 12 months prior to interview (rolling reference period) Calendar year of data file (data collected the following year)
Family Definition Used CPS-type family but unrelated subfamilies not identified NHIS-type family for most data including relationship codes

CPS-type family for poverty status

Coverage Persons in families with related subfamilies folded in

Unrelated individuals (includes all persons in unrelated subfamilies)

Persons in families with related subfamilies folded in

Unrelated individuals

Exclusions From Survey Universe For Poverty Status Unrelated children under 15

Persons in group quarters through 2005

After 2005 institutionalized, military in barracks and college students in dormitories

Unrelated minors (usually under age 18) if not foster children

Active military living with civilian family members (but included to determine poverty status of civilian family members)

Difference From CPS Students away at school and persons in unrelated subfamilies are unrelated individuals, with any children under 15 excluded

Civilians in non-institutional group quarters excluded until 2006

Military and unrelated minors age 15 or over excluded
Family Unit Timing Interview month of rolling sample December 31 of income reference year
Difference From CPS Family composition does not lag income reference period Family composition does not lag income reference period
Income for Computation Total income of CPS-type family for prior 12 months Pre-tax money income of CPS-type family for calendar year
Difference From CPS Definitional difference in timing of income but not in income

Poverty status of CPS-type families for the prior 12 months measured during each sample month (rolling reference period) and effectively averaged for the year (rolling sample)

Differs from calendar year poverty status

Income differences noted in Table II.8 due to use of Internal Revenue Service definitions: No "above the line" earnings, or tax-exempt interest and includes taxable IRA withdrawals
Poverty Status On File Ratio of unadjusted rounded income to adjusted thresholds (inflated by CPI-U to 12-month reference period price levels) Calendar year poverty status of CPS-type family as of December 31 based on pre-tax money income for year (8)
Calculation of Alternatives No replication or alternatives possible due to suppression of sample month and rounding Can calculate status of NHIS-type family

8. An apparent error in the algorithm calculating poverty status appears to use the annual (ever-on) family composition and income rather than that as of December 31. AHRQ staff have been informed of this problem.

TABLE II.10C. POVERTY STATUS
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Income Period Covered Prior calendar year Prior 12 months
Family Definition Used NHIS-type family Families not identified
Coverage Persons in families with related subfamilies folded in

Unrelated individuals

Families not identified
Exclusions From Survey Universe For Poverty Status Unrelated minors (usually under age 18) if not foster children

Active military living with civilian family members (but included to determine poverty status of civilian family members)

Poverty status not calculated
Difference From CPS Military and unrelated minors age 15 or over excluded

Unmarried (opposite or same sex) partners, relatives of partnerand foster relationships treated as part of family

Students away at school are unrelated individuals

Poverty status not calculated
Family Unit Timing 1 to 12 months after income reference year (rolling sample) Families not identified
Difference From CPS Family composition lags income reference period by 1 to 12 months compared to an average of 3 months for CPS Families not identified
Income for Computation Total income of NHIS-type family for prior calendar year Family income not ascertained
Difference From CPS No definitional differences in income Family income not ascertained
Poverty Status On File Ratio or bracket for calendar year poverty status of NHIS-type family as of interview month based on pre-tax money income for year (See Table II.14 on Ease of Access)

Brackets on public use file are 25% wide below 200% of poverty and 50% wide from 200 to 500% of poverty

Poverty status not calculated
Calculation of Alternatives None can be calculated since only income amount is total income for NHIS family

Replication or validation possible only via on-site tabulations (See Table II.14 on Ease of Access)

Cannot be calculated since family not identified and family income not ascertained

TABLE II.10D. POVERTY STATUS
  2004 Health and Retirement Study
2003 Panel Study of Income Dynamics
Income Period Covered Prior calendar year Prior calendar year
Family Definition Used RAND: NHIS-type family including related persons other than age-eligible person and spouse or partner NHIS-type family except same-sex partners not identified, and unrelated persons (may be same-sex partners) identified as part of family included
Coverage Persons in families with related subfamilies folded in

Unrelated individual

Persons in families with related subfamilies folded in unless the related subfamily had split off but rejoined primary family

Unrelated individual

Exclusions From Survey Universe For Poverty Status Students away at school Institutionalized, military and students away at school unless no sample persons remain in family they left
Difference From CPS Unmarried (opposite or same sex) partners, relatives of partner and foster relationships treated as part of family but students away at school excluded from family Unmarried (opposite sex) partners, relatives of partner, foster relationships, and some unrelated persons treated as part of family but related subfamilies that had split off but rejoined primary family remain separate families
Family Unit Timing From 1 to 12 months after end of income reference year Average composition during the income reference year
Difference From CPS Family composition lags income reference period by 1 to 12 months compared to an average of 3 months for CPS Family composition is contemporaneous with monthly reference periods
Income for Computation RAND: Total income of age-eligible person and spouse or partner (re-code) with Food Stamps excluded plus earnings and other income of other household members Total income of PSID family for prior calendar year with part-year not full year income for part-year family members
Difference From CPS Income differences noted in Table II.8: Includes lump sums such as inheritances, some sources such as child support excluded, and rental income is gross of expenses No definitional differences in income but part-year family members have only part-year income, not full year
Poverty Status On File RAND: Calendar year poverty status of NHIS-type family as of interview month based on pre-tax money income for year Calendar year threshold for PSID family on file

For families with changes in composition during the year (with part-year family members) threshold is weighted average of thresholds for the various family compositions during the year -- consistent with part-year treatment of income

Calculation of Alternatives Cannot be calculated since no person-level income for family members other than age-eligible person and spouse or partner Cannot be calculated since no person-level income for family members other than head and wife/"wife" and part-year family members have only part-year income

 

TABLE II.11A. NON-CASH BENEFITS AND HEALTH INSURANCE
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Social and Economic Supplement
Food Stamps Monthly recipiency and amount for each person

Start date and benefit history -- first interview

Number of persons and months received in prior calendar year

Total amount in prior calendar year

Other Nutrition Free or reduced-price School Lunch or Breakfast: number of children receiving and which program in prior 4 months

Monthly WIC recipiency and amount for each person

Free or reduced-price School Lunches: number of children receiving in prior calendar year

WIC in prior calendar year for each person

Housing And Energy Current public housing, or other housing assistance if renting

Energy Assistance recipiency and amount in prior 4 months

Current public housing, or other housing assistance if renting

Energy Assistance after October 1 of last year and amount

Welfare To Work Multiple types non-cash welfare assistance (e.g. education, child care, job search, job training) in prior 4 months for each person 7 types non-cash welfare assistance (e.g. education, child care, job search, job training) in prior calendar year for each person
Insurance Information Coverage of each type in each month for each person

Policyholder and coverage unit for up to 4 plans

Insurance coverage is contemporaneous with income

Coverage of each type in prior calendar year for each person

Insurance coverage is contemporaneous with income year

Medicaid Starting month and year of coverage -- first interview Number of months in prior calendar year (each person)
SCHIP Children under 20 Children under 19 without Medicaid
Medicare and Other Public Medicare, TRICARE/CHAMPUS, CHAMPVA, VA or military health care, other public Medicare, CHAMPUS, CHAMPVA, VA or military health care, Indian Health Service, or other government
Work-Related Policyholder, source of coverage and if part of premium paid Policyholder, source of coverage and if part of premium paid
Coverage Outside Household Identifies persons with coverage from outside household and age and relationship of anyone covered outside household Identifies persons with coverage from outside household and whether anyone outside household is covered
Other Private Private or direct purchase Private or direct purchase
Periods of Uninsurance Spells of uninsurance can be constructed Uninsured are those never covered in prior calendar year
TABLE II.11B. NON-CASH BENEFITS AND HEALTH INSURANCE
  2002 American Community Survey 2002 Medical Expenditure Panel Survey Household Component
Food Stamps Received in prior 12 months by anyone in household

Total amount in prior 12 months

Number of months household received in prior calendar year

Monthly amount paid (purchase requirement) and monthly value

Other Nutrition Free or reduced-price School Lunch or Breakfast received in prior 12 months by anyone in household Not included
Housing And Energy Current public housing, Section 8 or other housing assistance

Energy Assistance in prior 12 months

Not included
Welfare To Work Not included Not included
Insurance Information Not included Month-by-month coverage for each person from over 10 sources

Whether HMO or gatekeeper for many sources and other plan and managed care attributes for private coverage

Monthly family cost for private plans

Insurance coverage is contemporaneous with income year

Medicaid Not included No distinction between Medicaid and SCHIP
SCHIP Not included No distinction between Medicaid and SCHIP
Medicare and Other Public Not included Medicare, TRICARE, 2 other public sources, and other State programs
Work-Related Not included Policyholder, source of coverage and if part of premium paid
Coverage Outside Household Not included Identifies persons with coverage from outside household
Other Private Not included Other group, non-group, or source unknown - policyholder
Periods of Uninsurance Not included Whether uninsured in prior 2 calendar years for all persons and when last insured for uninsured

TABLE II.11C. NON-CASH BENEFITS AND HEALTH INSURANCE
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Food Stamps Number of months in prior calendar year for each person Not included
Other Nutrition WIC in prior calendar year for each person Not included
Housing And Energy Current housing assistance if renting Not included
Welfare To Work Non-cash welfare assistance (e.g. job placement, job training, education, child care) in prior calendar year for each person Not included
Insurance Information Current coverage of each type for each person and number of policies for private plans

Annual family cost for private plans

Whether managed care and type of restrictions

Insurance coverage is 1 to 12 months after end of income year

Month-by-month coverage from up to 5 sources of any type

Annualized premium for each plan

Whether HMO for each plan

Policyholder relationship for each plan

Medicaid All persons Month-by-month administrative data with exact coverage type
SCHIP All persons Not included
Medicare and Other Public Medicare Parts A or B or both, TRICARE/CHAMPUS/CHAMP-VA, military health care/VA, Indian Health Service, State-sponsored, or other government Medicare Parts A or B or both
Work-Related Policyholder, source of coverage and if part of premium paid Current or former employer, policyholder, source of coverage and 2-digit industry
Coverage Outside Household Identifies persons with coverage from outside household Not included
Other Private Direct purchase, through a public program, Medi-Gap or Single Service Direct purchase, Medi-Gap or AARP
Periods of Uninsurance Persons covered only by Indian Health Service defined as uninsured

Duration of current spell of uninsurance for uninsured persons

Whether uninsured in prior 12 months for each person and number of months uninsured

Not applicable

TABLE II.11D. NON-CASH BENEFITS AND HEALTH INSURANCE
  2004 Health and Retirement Study 2003 Panel Study of Income Dynamics
Food Stamps Monthly household recipiency since last interview (last 2 years) and amount in last month received Monthly household recipiency January 2001 to interview, total amount each calendar year and current number of recipients
Other Nutrition Any free or subsidized delivered meals ("meals on wheels") for age-eligible person or spouse or partner since last interview Free or reduced-price meals for elderly, Free or Reduced-price School Lunch, Free or Reduced-price School Breakfast, or WIC in prior calendar year for each person
Housing And Energy Current public or subsidized housing if renting Current public or subsidized housing if renting

Energy Assistance last winter and amount

Welfare To Work Not included Not included
Insurance Information Current coverage of specified types for age-eligible person and spouse or partner and number of policies for private plans

Whether HMO for Medicare/Medicaid (not differentiated)

For up to 3 private plans, whether managed care, who else covered, number of years in plan and monthly insurance cost

Insurance coverage is 1 to 12 months after end of income year

Up to 4 sources of coverage during prior 2 years for each person

Reference period for each source of coverage includes income year but sources during income year not determined

Medicaid Any coverage in last 2 years Any coverage in last 2 years for each person
SCHIP   Not separately identified
Medicare and Other Public Medicare and if Part B, or TRICARE/CHAMPUS/CHAMPVA or other military - no other public, e.g. Indian Health Service or VA Medicare, TRICARE/CHAMPUS/CHAMP-VA, military health care/VA, Indian Health Service, State-sponsored, or other government in last 2 years for each person
Work-Related Whether part of premium paid

Selective screens skip some sources of coverage

Any coverage in last 2 years for each person
Coverage Outside Household Not included Not included
Other Private Some source of coverage and whether part of premium paid Direct purchase or Medi-Gap in last 2 years for each person
Periods of Uninsurance If ever uninsured in prior 2 years for persons under 65 Months uninsured in each of prior 2 years for each person

 

TABLE II.12A. PERSON-LEVEL HEALTH AND HEALTH CARE UTILIZATION
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Social and Economic Supplement
Health Status 4 times in panel, at least once per year

Health status during third and fourth quarters of income year

Month of interview

Health status is 2 to 4 months after end of income year

Work Disability Persons 15 or over each interview and work disability history in wave 2 Persons 15 or over
Disability Detailed functional limitations - ADLs and IADLs - twice in panel

Conditions causing limitations or fair/poor health, and duration

Disability days in prior 12 months

Not included
Informal Care Identifies relationship, if in household, and if paid, for up to 2 helpers, and amount paid last month Not included
Inpatient Utilization Total inpatient days in prior 12 months -- annually Not included
Ambulatory Care Number of home or office visits or phone consultations in prior 12 months -- annually

Number of dental care visits in prior 12 months -- annually

Not included
Other Medical Services Summary questions Not included
Prescription Drugs Summary question Not included
Cost of Insurance Cost per person or policy in prior 12 months - annually Not included
Out-Of-Pocket Costs Total in prior 12 months including dental care and prescriptions but not cost of insurance -- annually Not included
Charge or Reimbursement For Covered Services Not included Not included
Total payments Not included Not included
Sources of payments Not included Not included
TABLE II.12B. PERSON-LEVEL HEALTH AND HEALTH CARE UTILIZATION
  2002 American Community Survey 2002 Medical Expenditure Panel SurveyHousehold Component
Health Status Not included Each interview

Health status is contemporaneous with income year

Work Disability Persons 16 or over Work disability each reference period
Disability Summary data on functional limitations for persons 5 or over Detailed functional limitations annually - ADLs and IADLs each interview

Detailed conditions and duration each interview and whether cause limitations or disability days or utilization of health care

Disability days each reference period

Informal Care Not included Whether receives help
Inpatient Utilization Not included 8 event level files for home health, office-based providers, outpatient hospital, emergency room, inpatient hospital, other medical expenses, dental, and prescriptions

Data include dates, condition and procedure codes, provider type, medical or ancillary services, tests, medical supplies, DME, location, total payment, and source of payment including out-of-pocket per day, service or item reported in survey dataSummary variables contain annual utilization, charges, source of payment including out-of-pocket, and expenditure by service type

Ambulatory Care Not included
Other Medical Services Not included
Prescription Drugs Not included
Cost of Insurance Not included By month by policy
Out-Of-Pocket Costs Not included Event level and totals by service type, provider and location
Charge or Reimbursement For Covered Services Not included Event level and totals by service type, provider, location and source of payment
Total payments Not included Event level and totals by service type, provider, location and source of payment
Sources of payments Not included Event level and totals by service type, provider, and location

TABLE II.12C. PERSON-LEVEL HEALTH AND HEALTH CARE UTILIZATION
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Health Status Month of interview

Health status is 1 to 12 months after end of income year

Current health status annually

Health status is during income year

Work Disability Persons 18 or over Detail for persons under 65
Disability Detailed functional limitations - ADLs and IADLs

Conditions causing limitations, duration, and whether chronic

Detailed functional limitations - ADLs and IADLs - annually

Diagnosis, condition and procedure codes for covered medical events from combined administrative and survey data, and from survey data for at-risk plans and uncovered events

Informal Care Not included Whether receives help and number of helpers
Inpatient Utilization Number of stays and total inpatient days in prior 12 months 7 event level files for medical providers, outpatient hospital, dental, inpatient hospital, facility, institutional and prescriptions

Data include dates, diagnosis, condition and procedure codes, provider type, location, medical or ancillary services, tests, medical supplies, DME, total payments, costs and source of payment per day, service or item from administrative and survey data, also a facility time line

Ambulatory Care Home or office visits or phone consultations in last 2 weeks (dental care specifically excluded)

Whether 10 or more medical provider visits in prior 12 months

Other Medical Services Not included Summary files contain total utilization and expenditure for the 7 service types plus home health and hospice
Prescription Drugs Not included
Cost of Insurance Family cost for each policy By month by policy
Out-Of-Pocket Costs Family total (no service detail) including dental care and prescriptions but excluding cost of insurance Event level and totals by service type, provider and location
Charge or Reimbursement For Covered Services Not included Event level and totals by service type, diagnosis, condition, procedure, provider, location and source of payment
Total payments Not included By service type, provider, location and source of payment
Sources of payments Not included By service type, provider, location and event

TABLE II.12D. PERSON-LEVEL HEALTH AND HEALTH CARE UTILIZATION
  2004 Health and Retirement Study
2003 Panel Study of Income Dynamics
Health Status Month of interview (age-eligible person and spouse or partner)

Health status is 1 to 12 months after end of income year

Month of interview (head and wife/"wife")

Health status is 1 to 12 months after end of income year

Work Disability Age-eligible person and spouse or partner Head and wife/"wife"
Disability Detailed functional limitations - ADLs and IADLs

Conditions (not linked to limitations)

Disability days last month

Detailed functional limitations - ADLs and IADLs and whether caused by health problem (head and wife/"wife")

Conditions, whether cause limitations, and duration (head and wife/"wife")

Informal Care Detailed information on amounts and types of assistance, sources of assistance, whether paid and cost last month Whether receives help for each ADL and IADL (head and wife/"wife")
Inpatient Utilization Number of stays and total inpatient days in prior 2 years Total inpatient days in prior 2 years (head and wife/"wife")
Ambulatory Care Number of physician contacts in prior 2 years Not included
Other Medical Services Nursing home: Number of stays and total days in prior 2 years

Summary questions on other services including dental care

Not included
Prescription Drugs Summary question Not included
Cost of Insurance Current monthly cost for Medicare/Medicaid HMO and up to 3 private policies Cost in prior 2 years (combined) for all coverages for family
Out-Of-Pocket Costs Cost in last 2 years separately for inpatient, nursing home, outpatient surgery, physician, dental, home health and other (e.g. social worker) services

Cost in last month for prescriptions

Cost in prior 2 years (combined) for inpatient and nursing home, for doctor, outpatient surgery and dental, and for prescriptions, in-home medical care, special facilities and other services
Charge or Reimbursement For Covered Services Not included Not included
Total payments Not included Cost in prior 2 years (combined) for all family medical care - out-of-pocket expenses plus reimbursed (covered) services
Sources of payments Not included Not included

 

TABLE II.13A. WEIGHTS AND CONTROL TOTALS
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
Basic Schema For Person Weights Selection probabilities adjusted for non-response, attrition and movers, and post-stratified to control totals derived from the CPS Selection probabilities adjusted for non-response and post-stratified to independent monthly control totals developed by the Census Bureau
Cross-Section Weights Person, family and household weights Person, family and household weights
Cross-Section Weight Timing Each month and calendar year March after reference year for all data collection months
Family and/or Household Weight Calculation Person weight of reference person after family equalization process that ensures husbands and wives have the same weights while overall age, sex, and race/ethnicity control totals are maintained

Family equalization averages the weights of the householder and spouse

Person weight of reference person after family equalization process that ensures husbands and wives or partners have the same weights while overall age, sex, and race/ethnicity control totals are maintained

Method of family equalization depends on household composition and sex of reference person -- householder weight is used for spouse or partner, or the weights of the householder and spouse or partner are averaged, or a separate ratio adjustment is calculated

Longitudinal Weights Person, family and household weights

Longitudinal weights for panel

 
Person and Family Universes Anyone with person weight has family and household weights - 3 universes the same Anyone with person weight has family and household weights - 3 universes the same
Person Control Totals Age, sex, race/ethnicity, and marital and family status of householder, by month and rotation group Age, sex, race/ethnicity, and State of residence
Family Control Totals None None
Income Control Totals None None
TABLE II.13B. WEIGHTS AND CONTROL TOTALS
  2002 American Community Survey 2002 Medical Expenditure Panel SurveyHousehold Component
Basic Schema For Person Weights Selection probabilities adjusted for non-response and post-stratified to independent monthly control totals developed by the Census Bureau Selection probabilities adjusted for non-response and attrition and post-stratified to control totals derived from CPS by AHRQ staff
Cross-Section Weights Person and household weights Person weights for restricted universe (see below)

Two family weights -- for CPS-type and NHIS-type families

Cross-Section Weight Timing July 1 of survey year for all data collection months December of calendar year
Family and/or Household Weight Calculation No family weight

Household weight is person weight of female spouse of householder, or householder if not married, to prevent over-representation of husband-wife households

Person weight of reference person - same weights used in CPS-type families and NHIS-type families - then post-stratified to control totals (9)
Longitudinal Weights   Available for persons in individual 2-year panels
Person and Family Universes Anyone with person weight has household weight - 2 universes the same Person universe restricted to original NHIS sample persons and move-ins who were out-of-scope for original NHIS

CPS-type family universe excludes part of person universe but includes move-ins related by blood or marriage (meeting CPS family definition)

Broader NHIS-type family universe adds unmarried partner move-ins and others (meeting NHIS family definition) to CPS-type family universe

Person Control Totals Age, sex, race/ethnicity and county Age, sex, race/ethnicity, Census Region, and MSA/non-MSA (and income)
Family Control Totals None Family type (spouse present or not), family size, age, sex, and race/ethnicity of reference person, MSA/non-MSA, and region for CPS-type families

CPS has no family control totals so family counts depend on CPS method of calculating family weights

Income Control Totals None CPS poverty rates for persons in CPS-type families as of December 31 - crossed with demographic control totals when person weights calculated

9. The impact of the additional sequential post-stratification of family weight can be seen in the following: For persons from the NHIS sample (key) who were respondents and in the universe (in-scope) on December 31 in CPS-type families of size one, the sum of person weights is 3.0 million higher than the sum of their CPS-type family weights. Even when 11 cases with a person-weight but no CPS-type family weight are removed, the difference is still 2.7 million.

TABLE II.13C. WEIGHTS AND CONTROL TOTALS
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
Basic Schema For Person Weights Selection probabilities adjusted for non-response and post-stratified to control totals derived from CPS and provided by Census Bureau Selection probabilities adjusted for non-response and attrition and post-stratified to control totals from Medicare administrative files
Cross-Section Weights Person, family and household weights Person weights
Cross-Section Weight Timing Weights separately calculated for each calendar quarter for control totals as of February 1, May 1, August 1 and November 1

Four quarter average is effectively mid-June of survey year

Ever enrolled during calendar year - not a point in time
Family and/or Household Weight Calculation Person-weight of family member with smallest post-stratification adjustment  
Longitudinal Weights   Multi-year person weight
Person and Family Universes Anyone with person weight has family and household weights - 3 universes the same

Some families with household weights are refusals but family weights not adjusted to compensate

No family weight or universe
Person Control Totals Age, sex, and race/ethnicity

Weights prior to post-stratification also on file

Age, sex, race/ethnicity, MSA/non-MSA, region, and new/existing enrollee status
Family Control Totals None None
Income Control Totals None None

TABLE II.13D. WEIGHTS AND CONTROL TOTALS
  2004 Health and Retirement Study 2003 Panel Study of Income Dynamics
Basic Schema For Person Weights Selection probabilities adjusted for non-response and post-stratified to control totals derived from current March CPS

Nursing home residents have separate weights in 2002 and subsequent years -- decedents have zero weights

Person weights derived from family ("household") weights

Summary description lacks key information

Longitudinal -- Selection probabilities adjusted for attrition and non-response, scaled to arbitrary totals, combining 1968 core and 1997 recent immigrant weights at 93:7 ratio

Cross-section - longitudinal family weights trimmed and post-stratified to family control totals derived from March CPS excluding unrelated subfamilies and secondary individuals - used as person and family weights (10)

Summary description lacks key information

Cross-Section Weights Person and "married or partnered" (family) weights Person and family weights for all interviewed persons, that user may scale or post-stratify
Cross-Section Weight Timing March after reference year March after reference year
Family and/or Household Weight Calculation Relation to person weights not described Longitudinal - family weight is average of person weights

Cross-section - family weight is used for all persons

Longitudinal Weights Not specifically described Updated periodically for attrition and recently revised to reflect sample restorations from re-contact efforts
Person and Family Universes Non-institutionalized with person weights have family weights - 2 universes the same Anyone with person weight has family weight - 2 universes the same but longitudinal and cross-section universes differ
Person Control Totals Age, sex, race/ethnicity, and "married or partnered" status - unmarried opposite-sex persons in same CPS households counted as partners if ages within 20 years

CPS group quarters may be in or out of totals

None

User may scale weights to current CPS or use more detailed demographic control totals

Family Control Totals Age, sex, race/ethnicity, and "married or partnered" status - unmarried opposite-sex persons in same CPS household with age within 20 years counted as partners to create CPS "married or partnered" control total

CPS group quarters may be in or out of totals

Age and race of head, region, and family size (1, 2 or 3+) for primary families and primary individuals excluding unrelated subfamilies and secondary individuals10

CPS has no family control totals so family counts depend on CPS method of calculating family weights

Income Control Totals None None

10. The description applies to the preliminary cross-section weights available when this report was prepared and may not apply fully to the final weights.

 

TABLE II.14A. EASE OF ACCESS
  2001 Panel of Survey of Income and Program Participation 2003 Current Population Survey Annual Socialand Economic Supplement
File Availability All files on-line for download

Can be subset with DataFerret before downloading or used on-line with DataFerret without downloading

All files on-line for download

Can be subset with DataFerret before downloading or used on-line with DataFerret without downloading

On-line table-creator

Files and Structure All files are person-based, include family and household data, but contain 4 months of data that cover different months for each of the 4 rotation groups

9 core files each contain one 4-month wave and separate files each topical modules in various waves

One file with household record followed by family and primary individual record(s) followed by person record(s)
Variable Construction and Calendar Year Data Many summary variables and recodes on files

All calendar year data must be constructed for each person from monthly data in multiple core files

Summary variables and recodes on files - few variable need to be constructed
Survey and File Descriptions Not fully updated from 1996 panel Extensive and detailed technical write-up
Questionnaires On-line and downloadable for core and all modules in easy to read format On-line and downloadable in easy to read format
Data Dictionaries Include alphabetical variable listings

Each variable has short description with question wording and universe description including screen-ins and -outs

Include alphabetical variable listings

Each variable has short description with question wording and universe description including screen-ins and -outs

Interviewer Instructions Not available Clear and spells out content item by item but geared to CAPI
Sample Design and Weights Technical write-up but use is very complex Extensive and detailed technical write-up
Technical Assistance By phone or e-mail for simple and some technical questions By phone or e-mail for simple and technical questions
Glossary Short glossary is part of documentation

More detailed CPS glossary is applicable

Detailed glossary is part of each year's documentation
Typical File Timing 2 to 3 years after fieldwork is complete 5 months after fieldwork is complete

TABLE II.14B. EASE OF ACCESS
  2002 American Community Survey 2002 Medical Expenditure Panel SurveyHousehold Component
File Availability Sub-sample public use files on-line for download lack sample month and inflation adjustment, income amounts are rounded and poverty status on file based on rounded income

Over 700 detail tables using internal files for over 7,000 areas available on-line as well as more summary profiles and tables

All files on-line for download
Files and Structure Household record followed by family and primary individual record(s) followed by person record(s) Person-based file with round-specific data plus separate files with round- and event- specific data on employment, private insurance and health conditions, plus event-level medical services files, and linking files
Variable Construction and Calendar Year Data Rounding and lack of either inflation adjustments or sample month data limit utility of public use files Many variables round-specific and calendar year data must be constructed (not always possible)
Survey and File Descriptions Geared to non-technical general public and to the on-line data products based on internal files

Minimal description of public use file content or limitations including lack of inflation adjustments and rounding

Extensive step-by-step descriptions of procedures of survey, and of processing, editing and preparation of internal files

Extensive information geared to technical user for health, insurance, utilization and expenditures-related files and variables

Summary information on income data

Questionnaires On-line and downloadable in easy to read format On-line and downloadable (42 sections per year)
Data Dictionaries Code lists for the relatively small number of variables with very abbreviated descriptions, in alphabetical not logical order (in 2 main groups) Include alphabetical variable listings

Very abbreviated variable descriptors with no question wording, universe description or screen-ins and -outs

Interviewer Instructions Instruction brochure for mail survey but not CATI guide Not available
Sample Design and Weights Extensive step-by-step descriptions Summary description lacks key information, e.g. impact or validation of post-stratification based on income
Technical Assistance By phone or e-mail for simple and some technical questions Not readily available
Glossary Lengthy, comprehensive, detailed and clear Lengthy glossary devoted almost entirely to medical and health-related terms, e.g. does not define family, or earnings
Typical File Timing 6 months after fieldwork is complete 1½ years after fieldwork is complete

TABLE II.14C. EASE OF ACCESS
  2003 National Health Interview Survey Family Core 2003 Medicare Current Beneficiary Survey
File Availability Public use file on-line for download has income information limited to $5,000- and $10,000-wide brackets

Access to internal files with actual income amounts requires approved analytic plan but files may never be taken off-site

Users obtain and retain only tabular or regression output

Cost was $500 plus $200 per day (or part) on site at RDC

No public use files on-line for download

Files (Access to Care and Cost and Use) are Limited Data Sets but protected off-site use of files allowed

Data use agreement and approved analytic plan required

Cost: $480 per data set includes all claims files

Files and Structure Separate household, family and person files with 5 separate files containing alternative imputation values 9 person-based files with survey or administrative record data, plus facility characteristics, residence time line, person summary and service summary files plus 7 event-level files - 7 bill files are also available
Variable Construction and Calendar Year Data Many summary variables and recodes on files Survey and administrative data from multiple years and sources have already been combined, unduplicated, imputed and placed on a calendar-year basis
Survey and File Descriptions Extensive technical write-up Extensive information geared to technical user that clearly lays out sample, survey, file and data construction
Questionnaires On-line and downloadable in easy to read format On-line and downloadable in easy to read format
Data Dictionaries Public use file -- short variable descriptions with universe, question wording and screen-ins and -outs

Internal file - not available during access application process

For Limited Data Sets -- available on-line for download

Abbreviated variable descriptors with universe, question number, years available and screen-ins and -outs

Interviewer Instructions Clear and spells out content item by item but geared to CAPI Clear and spells out content item by item but geared to CAPI
Sample Design and Weights Technical write-up and file contains weights prior to post-stratification as well as final weights Technical write-up
Technical Assistance By phone or e-mail for simple questions By phone or e-mail
Glossary No separate glossary, only NCHS definitions mostly of health and medical terms, with some incorrect NHIS information (11) No separate glossary
Typical File Timing 6 months after fieldwork is complete 1 year after fieldwork is complete for Access to Care and 2 years for Cost and Use

11. The on-line NCHS definition of family income says, "For purposes of the National Health Interview Survey (NHIS) and National Health and Nutrition Examination Survey (NHANES), all people within a household related to each other by blood, marriage, or adoption constitute a family." See http://www.cdc.gov/nchs/datawh/nchsdefs/familyincome.htm.


TABLE II.14D. EASE OF ACCESS
  2004 Health and Retirement Study 2003 Panel Study of Income Dynamics
File Availability HRS: All files on-line for download

RAND: All files available on-line to download

All files on-line for download

Easy to subset files and automatically link years to download

Files and Structure HRS: Survey year has 37 files for living sample persons plus separate imputation files and files on decedents

Cross-year tracker file for longitudinal work

RAND: Single person-based flat file for each year

Survey year has family file on head and wife/"wife" and family (most data), individual file (has insurance coverage) -- cross-year individual file also available

Various longitudinal files track events and family structure over time, e.g. parent identifier file

Variable Construction and Calendar Year Data HRS: Essentially raw data

RAND: Files have had major consistency checks and edits -- including longitudinal -- with new and (relatively) consistent summary variables created and reconciled for all years

Many summary variables and recodes on files and most data on calendar year basis and/or month-by-month

Comprehensive topical index drills down to question and data dictionary entry for all variables in all years 1968 forward

Survey and File Descriptions Little systematic or technical information beyond grant application information and publications -- some obsolete material (e.g. original incorrect weight calculations) remains Extensive information geared to technical user that clearly tracks survey evolution, changes and supplemental data collections over its 40 year span
Questionnaires On-line and downloadable (37 per year) with CAPI code On-line and downloadable in easy to read format
Data Dictionaries HRS: 37 each year for sample persons and 37 for decedents, each with abbreviated variable descriptors and raw counts

RAND: single data dictionary covers all sample persons for all years, crosswalks constructed variables to HRS names, and documents changes or inconsistencies

For files, years and variables selected for download, custom data dictionary automatically created for selected variables with codes, raw counts and variable list

Each variable entry has text of question, universe for code of "inapplicable", years available and variable name each year

Interviewer Instructions Not available Clear, comprehensive, and spells out content item by item
Sample Design and Weights Summary descriptions lack key information Summary description lacks key information
Technical Assistance Not readily available for non-academic users By phone or e-mail for simple and technical questions
Glossary Minimal 2-page glossary No separate glossary but data dictionary and interviewer instructions provide definitions "as you go"
Typical File Timing 2 years after fieldwork is complete 12 to 14 months after fieldwork is complete

View full report

Preview
Download

"report.pdf" (pdf, 4.33Mb)

Note: Documents in PDF format require the Adobe Acrobat Reader®. If you experience problems with PDF documents, please download the latest version of the Reader®