The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
Activity Number:
|
182
|
Type:
|
Contributed
|
Date/Time:
|
Monday, July 30, 2012 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Government Statistics
|
Abstract - #304637 |
Title:
|
Tests for Homogeneity of Multinomial Proportions for Sparse Data
|
Author(s):
|
Martin Klein*+ and Peter Linton and Bimal Sinha
|
Companies:
|
and U.S. Census Bureau and University of Maryland Baltimore County
|
Address:
|
8369 Tamar Drive, Columbia, MD, 21045, United States
|
Keywords:
|
Categorical data ;
Homogeneity testing ;
Monte Carlo methods ;
Simulation ;
Sparse data
|
Abstract:
|
It is well known that the standard chi-squared test for testing the homogeneity of multinomial proportions performs poorly in terms of maintaining the stipulated Type I error for sparse data. We will review several tests which have been proposed to remedy this situation, and also provide some new tests. A comparison of all the tests based on extensive simulations will be presented. As an application, we consider tabular decennial census data at the block or tract level, which can be quite sparse. This application arises from a larger goal of building a model that is suitable for generating a synthetic version of the decennial census microdata.
|
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 2012 program
|
2012 JSM Online Program Home
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.