Software Comparisons

Comparisons of Software Applications for Multiple Imputation

Title: “Missing Something? Multiple Imputation software might help find missing value data.”
Author(s): Ken Deal
Source: Marketing Research
Volume: Fall 2004 Page: 44 — 46

Abstract:
Missing data in marketing research is a problem that’s rarely discussed and too often ignored. On top of our problem of declining response rates, we have respondents who can’t or don’t want to answer every question. The imputation of missing values should never be used as a quick fix for poor fieldwork or inadequate designs. However, survey researchers live with the reality of missing data and we should understand that there are different approaches to resolving this issue, appreciate those differences, know when to use each procedure, and have access to computing applications that support the alternatives.

Download complete article (PDF, 2.1 MB)
Title: “Multiple Imputation in Practice: Comparison of Software Packages for Regression Models With Missing Variables”
Author(s): Nicholas J. Horton; Stuart R. Lipsitz
Source: The American Statistician
Volume: 55 Number: 3 Page: 244 — 254
Publisher: American Statistical Association
Acknowledgment: Reprinted with permission from The American Statistician.

Abstract:
Missing data frequently complicates data analysis for scientific investigations. The development of statistical methods to address missing data has been an active area of research in recent decades. Multiple imputation, originally proposed by Rubin in a public use dataset setting, is a general purpose method for analyzing datasets with missing data that is broadly applicable to a variety of missing data settings. We review multiple imputation as an analytic strategy for missing data. We describe and evaluate a number of software packages that implement this procedure, and contrast the interface, features, and results. We compare the packages, and detail shortcomings and useful features. The comparisons are illustrated using examples from an artificial dataset and a study of child psychopathology. We suggest additional features as well as discuss limitations and cautions to consider when using multiple imputation as an analytic strategy for incomplete data settings.

Download complete article (PDF, 252 KB)