|
Activity Number:
|
17
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, August 3, 2008 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #300573 |
|
Title:
|
Confidence Intervals for a Finite Population Median Based on the Sign Test
|
|
Author(s):
|
Suzanne Dubnicka*+
|
|
Companies:
|
Kansas State University
|
|
Address:
|
Department of Statistics, Manhattan, KS, 66056,
|
|
Keywords:
|
Horvitz-Thompson estimator ; norm-based inference ; superpopulation model
|
|
Abstract:
|
The construction of a confidence interval for the median of a finite population under unequal probability sampling will be discussed. A model-assisted approach makes use of the L1-norm to motivate the estimating function, which is then used to develop a unified approach to inference that includes not only confidence intervals but hypothesis tests and point estimates. The resulting hypothesis test is analogous to the ordinary sign test. We rely on large sample theory in most cases, and we will discuss the use of the Hartley-Rao variance approximation for cases in which second-order inclusion probabilities are difficult to obtain. Confidence intervals under simple random sampling without replacement, stratified random sampling, and cluster sampling will be explicitly illustrated.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2008 program |
