Abstract #301603

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 #301603
Activity Number: 252
Type: Contributed
Date/Time: Tuesday, August 5, 2003 : 10:30 AM to 12:20 PM
Sponsor: Section on Government Statistics
Abstract - #301603
Title: Impact of Mass Imputation on Longitudinal Data Analysis
Author(s): Michelle Simard*+ and Dominic Grenier
Companies: Statistics Canada and Statistics Canada
Address: 2500-K, Tunney's Pasture, Ottawa, ON, K1A 0T6, Canada
Keywords: total nonresponse, ; nonresponse mechanism ; mass imputation ; longitudinal analysis ; reweighting
Abstract:

Longitudinal survey data are a rich source for analysis of social phenomenon. However, these datasets are often undermined by partial nonresponse and total wave nonresponse, which contributes to sample attrition that increases at each survey cycle. Mass imputation of records consists of giving non-respondents a full set of values. These values can be obtained using different methods, for example, with donors judiciously chosen. Mass imputation has the advantage of increasing the number of effective records on which we can complete longitudinal analyses. However, estimates and/or some longitudinal analysis results might be affected by this imputation, particularly trend estimates. The extent of the mass imputation effect can vary based on the types of estimator and the analysis itself, but also based on the non-response mechanism, the nonresponse rate, and the attrition pattern. This empirical study will present results of simulations completed using Statistics Canada's National Longitudinal Survey of Children and Youth data. This study explores and attempts to assess the impact of mass imputation on some longitudinal data analyses.

  • 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