Skip to content. Skip to navigation

PRI Computer Core Help

Get Connected: USER GROUPS
PRI Statistical Software Users
PSU SAS Users; TALK
Statistical Software Forums; FEEDS
Subscribe to Population RSS Feeds

You are here: PRI → Core Services → Help → Statistical and Analytical Methods → Missing Data Imputation

Dealing with missing data

Document Actions

Multiple imputation is one method that can be used to take care of missing data. While listwise deletion removes cases with any missing value and FIML (full information maximum likelihood) uses all information that respondents supply, multiple imputation imputes values for the missing values so that all cases may be used in the analysis.

Books

Allison, Paul D. (2001). Missing Data. Sage Publications, Inc. (Order Information | Data Files for this Book | Paper [PDF] )
Little, R.J.A. & Rubin, D.B. (2002). Statistical analysis with missing data. New York, Wiley. 2nd edition.
Schafer, J.L. (1997). Analysis of incomplete multivariate data. London: Chapman & Hall.

Articles

Rubin, D.B. (1996). "Multiple imputation after 18+ years." Journal of the American Statistical Association, 91, 434, 473-489, with discussion 507-515, rejoinder 515-517, and extensive references 486-489.

General overviews

Imputation Methods Document A survey of multiple imputation software packages. How-to's, tips and pitfalls.

Missing Data Imputation On Thursday, February 16, 2006, David Johnson gave a presentation about missing data and data imputation. This handout describes various software packages that handle missing data.

Missing Data Imputation -- Output On Thursday, February 16, 2006, David Johnson gave a presentation about missing data and data imputation. This handout displays output from various software.

Multiple Imputation Do you have questions or have you made useful discoveries about multiple imputation? Share and discuss here.

SAS Imputation (2006 version) Using PROC MI and PROC MIANALYZE in SAS

Also of interest

Multiple Imputation Online Multiple Imputation Online page, with lots of useful information

PSU Methodology Center -- Missing Data Resources A set of introductory pages that give an overview of the missing-data problem and free software for multiple imputation developed by Dr. Schafer is available here.

The multiple imputation FAQ page (J.L. Schafer) Provides basic information about multiple imputation (MI) in the form of answers to Frequently Asked Questions (FAQs).

Wikipedia Imputation (statistics) page Wikipedia Imputation (statistics) page

for PRI affiliates...