The 2002 Current Population Survey (CPS) served as a tool for testing a sample expansion of the Annual Demographic Supplement and as a bridge to introduce new Census 2000-based population controls. The following section discusses the effects these methodological changes had on educational attainment.
The Census Bureau tested a 28,000 household expansion in the interviewed sample for the CPS Annual Demographic Supplement in 2002. The original sample size of approximately 50,000 interviewed households for the 2002 CPS Annual Demographic Supplement was increased to approximately 78,000. The primary goal of the sample expansion was to produce more reliable estimates of low-income children without health insurance for the State Children's Health Insurance Program (SCHIP) through reduced variances. Although the SCHIP sample expansion was specifically targeted toward producing better children's health insurance estimates at the state level, other state estimates, as well as national estimates, improved. Further information about the SCHIP sample expansion is available on the internet at: www.bls.census.gov/cps/ads/adsmain.htm.
Change in Population Controls
The procedure used in developing estimates for the entire civilian noninstitutional population for the Current Population Survey (CPS) involves the weighting of sample results to independent estimates of the population by sex, age, race, and Hispanic/non-Hispanic categories. These independent estimates are developed by using civilian noninstitutional population counts from the decennial censuses and projecting them forward to current years using data on births, deaths, and net migration. Beginning with the 2001 CPS Annual Demographic Supplement, the independent estimates used as control totals for the CPS are based on civilian noninstitutional population benchmarks consistent with Census 2000.
Effects of the Sample Expansion on Educational Attainment
Table C-1 displays national-level data for educational attainment from the original and expanded CPS samples from March 2001 and March 2002. The introduction of the expanded sample for March 2001 had very little effect on educational attainment. Changes that were statistically significant are shown in Table C-1, column 51. Among the population 25 years and over, there was a statistically significant increase in the percent with an associate degree. There was a decrease in the proportion with a high school degree as their highest degree attained. Among the non-Hispanic White population (25 years and over), the proportion with a bachelor's degree or higher increased.
Effects of the Census 2000 Population Controls on Educational Attainment
Weighting the estimates with 2000 population controls, instead of the 1990 census controls used in previous reports, had very little effect on educational attainment in 2001. The only statistically significant change in educational attainment due to the use of the 2000 population controls in 2001 was the 0.9 percentage point decrease in the percent of people with a high school degree or higher among the population age 25 to 29 years old (see Table C-1, column 3).
There were, however, several statistically significant differences between the 2001 and 2002 expanded samples using the 2000 population controls (see Table C-1, column 7). The differences between the two sets of estimates were 1.3 percentage points or less. Statistically significant differences occurred for the proportions of the population 25 years and over with the following levels of educational attainment: 1.) some college, no degree, 2.) bachelor's degree, 3.) master's degree, 4.) bachelor's degree or higher. All of these proportions increased from 2001 to 2002, except for the proportion of the population with some college, no degree, which declined by 0.4 percentage points. The proportion of the population with a bachelor's degree or higher increased the most (0.6 percentage points). Increases in the percent of the population 25 years and over with a bachelor's degree or higher also occurred among females (0.8 percentage points), Whites (0.6 percentage points), Blacks (1.3 percentage points), and non-Hispanic Whites (0.7 percentage points).
There were also statistically significant differences in the percent of high school graduates and higher among men (25 years and over), the 30 to 34 year age group, and the 60 to 64 year age group. While the percent with a high school degree or higher among the 30 to 34 year age group declined by 0.6 percentage points, it increased among the 60 to 64 year age group by 1.3 percentage points. The percent of men (25 years and over) with a high school degree or higher decreased.
For further information about CPS weighting procedures, see Technical Paper 63RV, available at www.bls.census.gov/cps/tp/tp63.htm.