Abstract #302042

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

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 2003 Program page
JSM 2003 Abstract #302042
Activity Number: 453
Type: Contributed
Date/Time: Thursday, August 7, 2003 : 8:30 AM to 10:20 AM
Sponsor: Section on Government Statistics
Abstract - #302042
Title: Triple System Estimation with Erroneous Enumerations and Heterogeneity
Author(s): G. Gordon Brown*+ and Paul P. Biemer and Dean H. Judson and Christopher A. Wiesen
Companies: RTI International and RTI International and U.S. Census Bureau and RTI International
Address: 103 Beaver Pine Way, Cary, NC, 27511-5956,
Keywords: latent class analysis ; capture-recapture ; census ; multiple systems
Abstract:

The primary goal of this research is to produce a series of models that can provide unbiased estimates of the number of residence, N, in a census region using data generated from a three-list system (i.e., Triple System Estimation). To produce such an estimate, a given model would have to account for (a) erroneous enumerations, (b) latent heterogeneity of enumeration probabilities, © list specific enumerations probabilities, and (d) pair-wise correlation of the enumeration errors among the lists. Our results indicate that, with only three lists, an unbiased estimate of undercount from an identifiable model that can account for (a)-(d) does not exist mainly due to insufficient degrees of freedom to model (a)-(d). However, if some model parameters are known, the number of parameters to be estimated are reduced and it is possible to specify identifiable TSE models that account for (a)-(d). Despite the bias in the TSE estimators we considered, several TSE estimators showed less bias for N than the typical dual system estimate (DSE). Thus, TSE may have more value for evaluating census coverage accuracy than DSE.

  • 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 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003