|
Activity Number:
|
389
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #306267 |
|
Title:
|
A Weighting Class Adjustment Estimator in a Continuous Domain
|
|
Author(s):
|
Breda Munoz*+ and Virginia M. Lesser and Leigh Harrod
|
|
Companies:
|
RTI International and Oregon State University and Oregon State University
|
|
Address:
|
3040 Cornwallis Road, Research Triangle Park, NC, 27709-2194,
|
|
Keywords:
|
environmental surveys ; missing data ; continuous domain ; Horvitz-Thompson estimator ; weighting class adjustment
|
|
Abstract:
|
Environmental phenomena are the result of random processes that evolve in space and/or time. Environmental surveys are not exempt of missing data issues. Therefore, analysis results when the missing data problem is ignored may be biased, depending on the missing data mechanism. The missing at random (MAR) mechanism assumes that given the observed data, the probability of missing data depends on covariates only. A weighting class adjustment is a common technique used by survey analysts for missing data when the missing mechanism is assumed MAR. In complex surveys, this technique has been used for finite population sampling data. However, the weighting class adjustment has not been used for continuous populations. We extend the concept of weighting class adjustment to the continuous domain and develop an unbiased weighting class adjustment estimator under a stratified sampling assumption.
|
