JSM 2012 Home

JSM 2012 Online Program

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: 294
Type: Contributed
Date/Time: Tuesday, July 31, 2012 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract - #305939
Title: The Implications of Software Choice for Handling Missing Data in the Presence of Interaction Effects Involving at Least One Categorical Variable
Author(s): Aya A Mitani*+ and Allison W Kurian and Amar K Das and Manisha Desai
Companies: Stanford University and Stanford University and Stanford University and Stanford University
Address: 642 Chenery St, SAN FRANCISCO, CA, 94131, United States
Keywords: Missing data ; Multiple imputation ; Interaction effects ; Categorical predictors ; SAS ; STATA
Abstract:

Multiple imputation of interaction terms can be challenging. Two main methods include passive imputation, which places constraints on the interaction term given the main effects, and active imputation, which treats the interaction term independently from the main effects. In his study examining the bias resulting from packages including SAS procedures that employ both methods based on a joint modeling (JM) approach, Von Hippel (2009) found that active imputation leads to less biased estimates. When missing variables include nominal categorical variables, however, a fully conditional specification (FCS) approach may be preferred over JM. Through simulations, we compare properties of estimates resulting from FCS-based imputation among SAS's active, and STATA's active and passive imputation methods. We provide guidelines for making sensible analysis choices based on our findings, and illustrate differences among the choices using real data from a breast cancer study.


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.