Dealing with Missing Data in Educational Research

The IES toolkit consists of a review paper that provides an accessible overview of foundational concepts from the missing data literature, including descriptions of classic and cutting-edge missing data handling procedures. The accompanying software tutorial document provides annotated analysis scripts and outputs for 20 real-data analysis examples. The analysis scripts and data are available below, and tutorial videos are found on the Videos page.
Download Toolkit
Example 1: ML Linear Regression With Multivariate Normal Data
Example 2: ML Binary Logistic Regression
Example 3: ML Linear Regression With Binary and Ordinal Predictors
Example 4: ML Linear Regression With an Interaction
Example 5: ML Regression With a Curvilinear Effect
Example 6: MCMC Linear Regression With Multivariate Normal Data
Example 7: MCMC Binary Logistic Regression
Example 8: MCMC Linear Regression With Binary and Ordinal Predictors
Example 9: MCMC Linear Regression With a Multicategorical Predictor
Example 10: MCMC Linear Regression With an Interaction
Example 11: MCMC Regression With a Curvilinear Effect
Example 12: Fully Conditional Specification (MICE) Imputation for a Paired t-Test
Example 13: Fully Conditional Specification Imputation for Regression
Example 14: Fully Conditional Specification Imputation With Categorical Variables
Example 15: Multilevel Fully Conditional Specification Imputation
Example 16: MCMC Multilevel Regression With Random Intercepts
Example 17: MCMC Multilevel Regression With Random Slopes and Interaction
Example 18: MCMC Three-Level Growth Model With an Interaction
Example 19: ML and MCMC Selection Model for Regression
Example 20: ML and MCMC Pattern Mixture Model for Regression

The work reported here was supported by the Institute of Educational Sciences, U.S. Department of Education, through Grant R305D220001 to UCLA. The opinions expressed are those of the author and do not represent views of the Institute or the U.S. Department of Education

Craig Enders, PI