Activity Number:
|
107
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 12, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Survey Research Methods*
|
Abstract - #301975 |
Title:
|
Jackknife Variance Estimation for Two-Phase Samples: An Application to the Study on Personnel Need for Special Education (SPeNSE)
|
Author(s):
|
Hyunshik Lee*+ and Jae-Kwang Kim
|
Affiliation(s):
|
Westat, Inc. and Westat, Inc.
|
Address:
|
1650 Research Blvd., Rockville, MD, 20850, USA
|
Keywords:
|
Double expansion estimator ; reweighted estimator ; relication ; finite population correction
|
Abstract:
|
The two-Phase sample design is often employed in sample surveys for various reasons. Variance estimation of such design needs special care since the variance due to first-phase sampling has to be estimated using the second-phase sample. It is somewhat easier to do this if the first-phase sample is selected with-replacement or can be treated as such. However, the SPeNSE sample selected by a two-phase sample design does not fall in this category since the first-phase sample was selected with a high sampling rate in some strata. This paper presents a way of incorporating the first-phase finite population correction in the jackknife variance estimation for the SPeNSE sample.
|