JSM 2004 - Toronto

Abstract #301614

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); 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 2004 Program page
Activity Number: 233
Type: Contributed
Date/Time: Tuesday, August 10, 2004 : 12:00 PM to 1:50 PM
Sponsor: Social Statistics Section
Abstract - #301614
Title: Comparison of Imputation Methods in Behavioral Science Research: A Small Longitudinal Study of Sexual Counseling after Prostate Cancer
Author(s): Dawen Sui*+ and Leslie R. Schover and Juwon Song and Andrea L. Canada and Leah E. Neese
Companies: University of Texas M.D. Anderson Cancer Center and University of Texas M.D. Anderson Cancer Center and University of Texas M.D. Anderson Cancer Center and University of Texas M.D. Anderson Cancer Center and University of Texas M.D. Anderson Cancer Center
Address: 1515 Holcombe Blvd.-243, Houston, TX, 77030,
Keywords: longitudinal study ; missing data ; imputation ; general linear mixed model ; behavioral science study
Abstract:

The purpose of this paper is to compare imputation methods in handing missing data in a small longitudinal dataset from a pilot, randomized trial of two formats of sexual counseling for couples in which the man had been treated for localized prostate cancer. Fifty-one couples completed the counseling. Both men and their partners filled out self-report questionnaires on entry to the study, at the last session of the intervention, and three-month and six-month follow-up. The responses of interest in this analysis include several individual multiple-choice items. Traditionally, mean imputation is used to estimate the value of scales composed of multiple items, only some of which have missing values. In this study, single and multiple imputation strategies are selected to impute individual missing items, and then imputed values are used to calculate the subscales and response variables. Distributions of the responses are considered to select an appropriate imputation technique. The characteristics of the model fits, parameter estimates, standard deviations, and p values from a general linear mixed model are compared using the complete dataset, traditional mean imputation.

  • 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 2004 program

JSM 2004 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 March 2004