This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 611
Type: Topic Contributed
Date/Time: Thursday, August 5, 2010 : 8:30 AM to 10:20 AM
Sponsor: Social Statistics Section
Abstract - #307065
Title: The Impact of Measurement Error in Auxiliary Variables on Model-Based Estimation of Finite Population Totals: A Simulation Study
Author(s): Brady West*+
Companies: Institute for Social Research
Address: Survey Methodology Program, Ann Arbor, MI, 48103,
Keywords: Model-based Estimation ; Prediction Theory ; Finite Population Totals ; Auxiliary Variables ; Finite Population Sampling ; Measurement Error
Abstract:

Model-based prediction theory for finite population sampling and inference (Valliant et al., 2000) largely assumes that auxiliary variables are available for all units in the target population. These auxiliary variables play many important roles in prediction theory, including selection of balanced samples, model fitting, and ultimately prediction of values for non-sample cases and subsequent estimation of population parameters. Auxiliary variables are generally assumed to be measured without error, and very little work has considered the impact of this error on the performance of model-based estimators of finite population totals. This paper uses simulations to examine this impact, and contrasts the simulation results with theoretical expectations under no measurement error. Samples with weighted balance and minimal model estimators are found to perform best in the presence of error.


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 2010 program




2010 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.