Activity Number:
|
405
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 15, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Survey Research Methods*
|
Abstract - #301696 |
Title:
|
Successive Sampling with Varying Probabilities without Replacement in the National Longitudinal Study of Adolescent Health
|
Author(s):
|
Jianmin Wang*+ and Pranab Sen and Chirayath Suchindran
|
Affiliation(s):
|
Gynecologic Oncology Group and University of North Carolina, Chapel Hill and University of North Carolina, Chapel Hill
|
Address:
|
Elm & Carlton Streets, Buffalo, New York, 14263-0001, U. S. A.
|
Keywords:
|
Survey Sampling ; Horvitz-Thompson Estimator ; Finite population ; Large sample
|
Abstract:
|
The National Longitudinal Study of Adolescent Health used the successive sampling with varying probabilities without replacement in collecting several health-related information from adolescents. In order to fully implement this sampling scheme in the data analysis, we propose an approximate Horvitz-Thompson estimator (AHTE) based on the approximation of the first order inclusion probabilities. The sufficient conditions under which the vector of the AHTE approximately has multivariate normal distributions are found. The method of estimating the asymptotic variance-covariance matrix of the AHTE is derived. The applicability of these methods is verified by simulation experiments conducted on a real population data. The multivariate normality of the AHTE is mainly influenced by the weighted frequency of ratio of study variables to the selection probabilities. The data from the National Longitudinal Study of Adolescent Health are analyzed by the developed methods to estimate the proportion of public high schools with sex education program in tenth grade and the percentage of teachers with master's degrees or higher.
|