JSM Preliminary Online Program
This is the preliminary program for the 2006 Joint Statistical Meetings in Seattle, Washington.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2006 Program page

Activity Number: 534
Type: Contributed
Date/Time: Thursday, August 10, 2006 : 10:30 AM to 12:20 PM
Sponsor: Section on Survey Research Methods
Abstract - #306978
Title: Comparing Procedures To Estimate the Measure of Heteroscedasticity and Their Effect on Estimating Totals and Their Variances
Author(s): Kimberly Henry*+ and Richard Valliant
Companies: Internal Revenue Service and University of Michigan
Address: P.O. Box 2608, Statistics of Income Division, Washington, DC, 20013,
Keywords: survey sampling ; prediction approach ; general linear models ; simulation
Abstract:

Estimation of totals is often an objective in survey sampling. With a model-based approach, one factor that can affect the variance and bias of estimated totals is the superpopulation structure. We consider the case when a dependent variable's variance is proportional to some power, called the measure of heteroscedasticity (moh), of the independent variable. For various sample designs, sizes, and estimators, alternative strategies for estimating moh are compared. The strategies' effect on estimates of totals and their variances is then evaluated. Results are extended to a subset of 1040 tax returns taken from the Statistics of Income's Tax Year 2001 Individual Public Use File.

  • 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 2006 program

JSM 2006 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised April, 2006