|
Activity Number:
|
252
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #305620 |
|
Title:
|
Confidence Intervals for Quantile Estimation from Complex Survey Data
|
|
Author(s):
|
Babubhai V. Shah*+ and Akhil Vaish
|
|
Companies:
|
SAFAL Institute Inc. and RTI International
|
|
Address:
|
22 Autumn Woods Drive, Durham, NC, 27713,
|
|
Keywords:
|
quantile estimates ; confidence intervals ; complex survey data
|
|
Abstract:
|
A method for estimating quantiles and their confidence intervals based on the paper by Francisco and Fuller (1991) has been implemented in SUDAAN® software. There have been problems encountered in practical application of the Francisco-Fuller method: It requires evaluation of bounds at many points, the resulting limits are, at times, not monotonic or internally consistent, and the accuracy is not very good. The objective of this paper is to develop an improved method that overcomes these problems. The revised method is based on the confidence intervals based on the estimating equations (Godambe 1999). An adjustment to the empirical distribution is proposed to achieve internal consistency and reduce bias.
|
