|Sponsor:||U.S. Department of Justice (DoJ)/Bureau of Justice Statistics (BJS)|
|Description:||The National Crime Victimization Surveys (NCVS) series, previously called the National Crime Surveys (NCS), has been collecting data on personal and household victimization through an ongoing survey of a nationally representative sample of residential addresses since 1973. The four primary objectives of the effort include: 1) to develop detailed information about the victims and consequences of crime; 2) to estimate the number and types of crimes not reported to the police; 3) to provide uniform measures of selected types of crimes; and 4) to permit comparisons over time and geographic areas. Basic demographic information such as age, race, gender, and income is also collected to enable analysis of crime by various subpopulations.|
|Relevant Policy Issues:||Rates of Involvement with Justice System, Lifetime Probability of Being a Victim of a Violent Crime, Lifetime Probability of Being a Victim of a Non-violent Crime, Domestic Violence Rates, Child Maltreatment Rates, Factors Contributing to Disparities in Involvement with Justice System and Outcomes.|
|Unit of Analysis:||Individuals, Households, Crime Incidents|
|Identification of AI/AN/NA:||Respondents are allowed to select all race categories that apply from the following:
|AI/AN/NA Population in Data Set:||In the combined incident-level file for 1992-2004, there are 162,736 incidents of which 1,621 are incidents where the informant for the household in which there had been an incident is AI/AN (alone or as part of a multiple race designation). Native Hawaiians and Other Pacific Islanders cannot be distinguished from Asians in most of the concatenated incident-level file; however, beginning in 2003, a new race categorization was adopted that allows NH/PI persons to be identified from that time forward. In this incident-level file, there are 71 incidents where the informant was NH/PI (alone or as part of a multiple race designation).|
|AI/AN/NA Subpopulations:||It is possible to isolate individuals who identify themselves as American Indian or Alaska Native and indicate that they reside on Indian lands. (Question 12 asks Are your living quarters located on an American Indian reservation or on Indian lands?)|
|Geographic Scope:||The geographic scope of the study is national. Geographic identifiers include urban or rural; region; and central city of a Metropolitan Statistical Area (MSA), MSA but not in central city, or not MSA. Geographic analysis is possible for all of these. Also, as noted previously, it is also possible to identify individuals reporting that their residence is on Indian lands.|
|Date or Frequency:||The NCVS is a semiannual study with data available beginning 1973. Respondents are interviewed every 6 months for a total of seven interviews over a 3-year period. After the seventh interview the household leaves the panel and a new household is rotated in to the sample.|
|Data Collection Methodology:||The first and fifth interviews are face-to-face; the rest are by telephone.|
|Participation:||Optional, without incentives|
|Response Rate:||Survey documentation states that the NCS and NCVS have consistently obtained a response rate of about 95 percent.|
|Sampling Methodology:||The NCVS sample consists of approximately 50,000 sample housing units selected with a stratified, multi-stage cluster design. The first stage consists of selecting a sample of Enumeration Districts (EDs) from designated Primary Sampling Units (counties, groups of counties, or large metropolitan areas). (EDs are established for each decennial Census and are geographic areas ranging in size from a city block to several hundred square miles, and usually encompassing a population of 750 to 1,500 persons.) In the second stage, each selected ED is divided into segments (clusters of about four housing units each), and a sample of segments is selected. The sample of housing units is divided into six rotation groups, and each group is interviewed every six months for a period of three-and-a-half years.|
|Analysis:||Use of standard statistical tests with these data would not be accurate because these tests assume independence among observations and a simple, random sample design. The NCVS uses a complex, clustered sampling design in which observations are not independent. Survey documentation presents instructions for two methods to calculate variances for NCVS data that avoid these problems, computing generalized variances and using direct variance calculation methods designed for complex survey design.|
|Strengths:||Data are collected on key policy issues, primarily justice system issues. There are multiple years of data available. Documention is strong and there is a user-friendly on-line analytical tool for the incident-level data.|
|Limitations:||The full NVS data set is hierarchical. It is not a flat individual-level data set as are most survey data sources. The file is organized into a hierarchical format which corresponds to variations in household composition and in the occurrence of incidents of victimization. Hierarchical data sets have varying record lengths, and each record is stored sequentially in the data file. Hierarchical storage is a benefit as it greatly reduces the size and space needed to store and process the data; however, stronger programming skills may be required to correctly analyze a file of this type compared to the traditional file.|
|Other:||Data are available on-line in aggregated form. Data for 1992-2004 are available for downloading. Data for 1992-2003 can be analyzed on-line (incident-level file) or downloaded.
A series of changes has occurred recently with modifications to the questions, placing more emphasis on hot topics of crime, which may provide challenges for multi-year comparisons. Some topics included in 2004 were identity theft, credit card theft and multiple crime situations involving personal information.
|Access Requirements and Use Restrictions:||The data are available to the public at no cost.|
|Contact Information:||For data and documentation:
National Archive of Criminal Justice Data
Institute for Social Research
P.O. Box 1248
Ann Arbor, MI 48106
Data can be accessed at: http://webapp.icpsr.umich.edu/cocoon/NACJD-STUDY/04276.xml.
|Reports of Interest:||The National Archive of Criminal Justice Data provides lists of publications from the NVS data. A list of publications for the 1992-2003 data can be found at http://www.icpsr.umich.edu/cgi-bin/CITATIONS/search?study=3995&method=study&path=NACJD.
A list of publications for the 1992-2004 data can be found at: http://www.icpsr.umich.edu/cgi/CITATIONS/search?study=4276&method=study&path=NACJD.
"report.pdf" (pdf, 1.56Mb)
"apa.pdf" (pdf, 107.76Kb)
"apb.pdf" (pdf, 88.97Kb)
"apc.pdf" (pdf, 233.07Kb)