|
Activity Number:
|
252
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #308544 |
|
Title:
|
Estimating the Distribution of Distances for a Large-Scale Complex Survey
|
|
Author(s):
|
Jianqiang Wang*+ and Jean Opsomer
|
|
Companies:
|
Iowa State University and Iowa State University
|
|
Address:
|
CSSM, Ames, IA, 50011,
|
|
Keywords:
|
distance metric ; kernel estimation ; empirical distribution ; estimating equations ; generalized median
|
|
Abstract:
|
Many finite populations targeted by sample surveys consist of homogenous subpopulations with respect to the variables being collected. We propose a sample-based estimator for the subpopulation distribution functions of the distances between the elements and the subpopulation centers, and explore several definitions of distance in the data and different ways to define the subpopulation centers. We describe the theoretical properties of the estimator, and propose a variance estimator. We discuss a procedure to identify outliers in large-scale surveys that takes advantage of the estimated subpopulation distribution functions, and apply it to data from the National Resources Inventory.
|
- 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 2007 program |
