Multiple Imputation for Nonresponse in Surveys by Donald B. Rubin

TABLE OF CONTENTS
Tables and Figures.
Glossary.

1. Introduction.

1.1 Overview.

1.2 Examples of Surveys with Nonresponse.

1.3 Properly Handling Nonresponse.

1.4 Single Imputation.

1.5 Multiple Imputation.

1.6 Numerical Example Using Multiple Imputation.

1.7 Guidance for the Reader.

2. Statistical Background.

2.1 Introduction.

2.2 Variables in the Finite Population.

2.3 Probability Distributions and Related Calculations.

2.4 Probability Specifications for Indicator Variables.

2.5 Probability Specifications for (X,Y).

2.6 Bayesian Inference for a Population Quality.

2.7 Interval Estimation.

2.8 Bayesian Procedures for Constructing Interval Estimates, Including Significance Levels and Point Estimates.

2.9 Evaluating the Performance of Procedures.

2.10 Similarity of Bayesian and Randomization-Based Inferences in Many Practical Cases.

Demonstrates how nonresponse in sample surveys and censuses can be handled by replacing each missing value with two or more multiple imputations. Clearly illustrates the advantages of modern computing to such handle surveys, and demonstrates the benefit of this statistical technique for researchers who must analyze them. Also presents the background for Bayesian and frequentist theory. After establishing that only standard complete-data methods are needed to analyze a multiply-imputed set, the text evaluates procedures in general circumstances, outlining specific procedures for creating imputations in both the ignorable and nonignorable cases. Examples and exercises reinforce ideas, and the interplay of Bayesian and frequentist ideas presents a unified picture of modern statistics.