ERIC Number: ED167567
Record Type: Non-Journal
Publication Date: 1975-Feb
Reference Count: N/A
Effects of Stratification, Clustering, and Unequal Weighting on the Variances of NLS Statistics. 22U-884-3.
Moore, R. P.; Shah, B. V.
The average design effects for statistics estimated from the base-year National Longitudinal Study data are presented. Attempts to partition the effects into those due to stratification, clustering, and unequal weighting are discussed. The expected increases in subpopulation sample sizes due to oversampling are calculated and compared with the actual increases observed in the base-year survey. The effects on variances of oversampling and other factors which lead to unequal weighting are approximated and the optimum oversampling rates for several subpopulations are estimated. Several stratification variables are ranked from most to least effective in reducing the variances of survey estimates. (Author/CTM)
Publication Type: Reports - Research
Education Level: N/A
Authoring Institution: Research Triangle Inst., Durham, NC. Statistics Research Div.
Identifiers - Assessments and Surveys: National Longitudinal Study of the High School Class of 1972