NotesFAQContact Us
Search Tips
ERIC Number: ED434133
Record Type: Non-Journal
Publication Date: 1998-Oct
Pages: 55
Abstractor: N/A
A Bootstrap Variance Estimator for Systematic PPS Sampling. Working Paper Series.
Kaufman, Steven
In large multipurpose surveys, it is common to select the sample systematically proportional to some measure of size (PPS) that is correlated with an important variable of interest. Assuming the frame is sorted in a useful deterministic manner, systematic sample methodologies provide an additional control on the sample allocation, beyond the control provided from the stratification. This makes it less likely to select a "bad sample." This should reduce the variability of the estimates as compared to a comparable nonsystematic selection procedure. The problem with systematic samples is that variance estimators are biased. This paper presents a bootstrap variance estimator, which can have less bias than standard methodologies, such as half-sample replication. The results will be demonstrated with a simulation study based on an important National Center for Education Statistics survey, the Schools and Staffing Survey. An appendix demonstrates the consistency of the proposed estimators. (Contains 8 tables and 12 references.) (Author/SLD)
U.S. Department of Education, Office of Educational Research and Improvement, National Center for Education Statistics, 555 New Jersey Avenue, N.W., Room 400, Washington, DC 20208-5652; Tel: 202-219-1831.
Publication Type: Reports - Descriptive
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: National Center for Education Statistics (ED), Washington, DC.