Extending the Utility of Federal Data Bases. Surveys Meeting Standards for Precision

05/01/2000

Section 3.6 discussed the ability of the surveys to produce reasonable precision in the analysis of the subpopulations or for crossclassifications within these subpopulations. ("Reasonable precision" is based on a subjective judgment of the importance of meeting the various standards described earlier, i.e., CVs of 30 percent, 20 percent, and 10 percent for prevalence rates of .01, .05, .10, .15, and .20.) We will use the same criteria to evaluate the analytic ability of combinations of several years of survey data. As in the case of data for a single year, some studies may need greater precision and others less, and analysts should consider whether they need to modify the summary below.

Three or 5-year averages for CPS supplemental items collected in a single month for a given year would provide sample sizes large enough to satisfy analytic needs for most Hispanic subgroups, although only limited cross-classifications would be possible for Cuban-Americans. Fairly detailed analyses would be possible for American Indians or Alaska Natives, and for Chinese and Filipinos. Less detailed cross-classifications would be available for most of the other API subgroups, and only simple distributions of Hawaiian would have reasonable reliability.

The NHIS Hispanic sample is quite large, and a 2 or 3-year combination will provide quite reliable data, including cross-classifications, for all Hispanic subgroups, and moderately detailed cross-classifications for Cuban-Americans. A 5-year average will permit quite detailed analysis. A 5-year average of the American Indian or Alaska Native data set will satisfy almost all the requirements. A 3-year average could be used for Chinese and Filipinos, but 5 years are probably necessary for the other API subgroups.

NHANES has a very large sample of Mexican-American and averaging over time will permit fairly detailed cross-classification analyses. The sample was deliberately set up with multi-year averages in mind. None of the other minority subgroups would be helped enough for even simple prevalence rates to have adequate precision.

Table 4-1.
Effective sample sizes for Hispanic subgroups, using combined years of data
Data set Total Mexican-
American
Puerto
Rican
Cuban Central or
South American
Other Hispanic
CPSMarch
   2 years 12,537 37,727 1,324 523 1,875 1,086
   3 years 16,891 10,411 1,784 704 2,527 1,463
   5 years 24,773 15,269 2,617 1,033 3,706 2,145
CPSMonthly
   2 years 6,274 3,863 663 262 940 546
   3 years 8,453 5,204 893 353 1,267 736
   5 years 12,398 7,633 1,310 518 1,858 1,079
NHIS
   2 years 24,654 15,441 2,620 1,298 3,495 1,802
   3 years 33,217 20,804 3,530 1,748 4,709 2,428
   5 years 48,718 30,512 5,178 2,564 6,907 3,561
NIS
   2 years 6,232 4,534 511 127 676 386
   3 years 8,397 6,109 689 171 911 520
   5 years 12,316 8,960 1,010 251 1,337 762
NHANES
   2 years 3,164 3,000 48 20 64 32
   3 years 4,746 4,500 72 30 96 48
   5 years 7,910 7,500 120 50 160 80
MEPS
   2 years 7,480 5,080 835 314 1,064 187
   3 years 10,078 6,844 1,125 423 1,433 252
   5 years 14,781 10,039 1,650 620 2,103 370
MCBS
   2 years 705 386 63 102 78 75
   3 years 950 520 86 137 106 101
   5 years 1,393 762 125 201 155 149
NHSDA
   2 years 3,796 2,406 401 160 548 282
   3 years 5,114 3,242 540 216 738 380
   5 years 7,501 4,755 792 317 1,082 558
NOTE:
The sample cases for each data set reflect the population coverage of the respective surveys. For example, CPS-March covers all persons in the civilian noninstitutional population, whereas NSFG covers women 15 to 44 years of age. The descriptions of the respective data sets note the appropriate population coverage.
Table 4-2.
Effective sample sizes for API subgroups, using combined years of data
Data set Total API Chinese Filipino Japanese Asian Indian Korean Vietnamese Hawaiian Other
CPSMarch
   2 years 5,072 1,107 947 573 551 539 418 139 630
   3 years 6,833 1,492 1,276 792 743 727 563 187 848
   5 years 10,022 2,188 1,871 1,132 1,089 1,066 825 274 1,244
CPSMonthly
   2 years 5,072 1,107 947 573 551 539 418 139 630
   3 years 6,833 1,492 1,276 772 743 727 563 187 848
   5 years 10,022 2,188 1,871 1,132 1,089 1,066 825 274 1,244
NHIS
   2 years 4,063 934 800 441 396 423 441 139 489
   3 years 5,474 1,258 1,078 594 533 569 594 187 659
   5 years 8,029 1,848 1,581 871 782 835 871 274 967
NIS
   2 years 1,506 341 292 175 169 165 129 43 192
   3 years 2,030 459 394 236 227 222 173 59 259
   5 years 2,977 673 578 347 333 327 254 86 380
NHANES
   2 years 226 54 43 26 25 25 19 6 28
   3 years 340 81 65 39 38 38 29 10 42
   5 years 566 134 108 64 63 63 48 16 69
MEPS
   2 years 596 120 135 50 89 77 35 13 79
   3 years 804 162 182 67 107 92 43 18 107
   5 years 1,178 237 267 99 176 152 69 26 156
MCBS
   2 years 229 52 43 27 25 25 20 7 28
   3 years 308 70 59 36 34 34 27 9 38
   5 years 452 102 86 53 50 50 40 13 56
NHSDA
   2 years 531 120 102 62 58 58 45 15 68
   3 years 716 162 137 83 79 79 61 20 92
   5 years 1,049 238 201 122 116 116 89 30 135
NOTE:
The sample cases for each data set reflect the population coverage of the respective surveys. For example, CPS-March covers all persons in the civilian noninstitutional population, whereas NSFG covers women 15 to 44 years of age. The descriptions of the respective data sets note the appropriate population coverage.
Table 4-3.
Effective sample sizes for American Indians or Alaska Natives
using combined years of data
Data set American Indian or Alaska Native
CPSMarch
   2 years 1,782
   3 years 2,401
   5 years 3,521
CPSMonthly
   2 years 1,782
   3 years 2,401
   5 years 3,521
NHIS
   2 years 1,089
   3 years 1,467
   5 years 2,152
NIS
   2 years 591
   3 years 797
   5 years 1,168
NHANES
   2 years 47
   3 years 71
   5 years 118
MEPS
   2 years 299
   3 years 403
   5 years 591
MCBS
   2 years 38
   3 years 52
   5 years 76
NHSDA
   2 years 125
   3 years 169
   5 years 248
NOTE:
The sample cases for each data set reflect the population coverage of the respective surveys. For example, CPS covers persons in the civilian noninstitutional population, whereas NSFG covers women 15 to 44 years of age. The descriptions of the respective data sets note the appropriate population coverage.

The Mexican-American samples in the NIS, MEPS, and NHSDA, are fairly large and even 2-year combinations will permit fairly detailed cross-classifications. Five-year combinations are necessary for most of the other Hispanic subgroups. Five years will permit simple analyses of NIS in most of the API subgroups and for American Indians or Alaska Natives. However, even 5 years is not sufficient for the API subgroups and American Indians or Alaska Natives for MEPS and NHSDA. The MCBS sample of minorities is so small that 5 years fails to satisfy most of the precision requirements, except for Mexican-Americans, for whom simple distributions are possible, but not detailed cross-classifications.