Applied Missing Data Analysis (eBook)

Craig K. Enders is Associate Professor in the Quantitative Psychology concentration in the Department of Psychology at Arizona State University. The majority of his research focuses on analytic issues related to missing data analyses. He also does research in the area of structural equation modeling and multilevel modeling. Dr. Enders is a member of the American Psychological Association and is also active in the American Educational Research Association.

1. An Introduction to Missing Data1.1 Introduction1.2 Chapter Overview1.3 Missing Data Patterns1.4 A Conceptual Overview of Missing Data Theory1.5 A More Formal Description of Missing Data Theory1.6 Why Is the Missing Data Mechanism Important?1.7 How Plausible Is the Missing at Random Mechanism?1.8 An Inclusive Analysis Strategy1.9 Testing the Missing Completely at Random Mechanism1.10 Planned Missing Data Designs1.11 The Three-Form Design1.12 Planned Missing Data for Longitudinal Designs1.13 Conducting Power Analyses for Planned Missing Data Designs1.14 Data Analysis Example1.15 Summary1.16 Recommended Readings2. Traditional Methods for Dealing with Missing Data2.1 Chapter Overview2.2 An Overview of Deletion Methods2.3 Listwise Deletion2.4 Pairwise Deletion2.5 An Overview of Single Imputation Techniques2.6 Arithmetic Mean Imputation2.7 Regression Imputation2.8 Stochastic Regression Imputation2.9 Hot-Deck Imputation2.10 Similar Response Pattern Imputation2.11 Averaging the Available Items2.12 Last Observation Carried Forward2.13 An Illustrative Simulation Study2.14 Summary2.15 Recommended Readings3. An Introduction to Maximum Likelihood Estimation3.1 Chapter Overview3.2 The Univariate Normal Distribution3.3 The Sample Likelihood3.4 The Log-Likelihood3.5 Estimating Unknown Parameters3.6 The Role of First Derivatives3.7 Estimating Standard Errors3.8 Maximum Likelihood Estimation with Multivariate Normal Data3.9 A Bivariate Analysis Example3.10 Iterative Optimization Algorithms3.11 Significance Testing Using the Wald Statistic3.12 The Likelihood Ratio Test Statistic3.13 Should I Use the Wald Test or the Likelihood Ratio Statistic?3.14 Data Analysis Example 13.15 Data Analysis Example 23.16 Summary3.17 Recommended Readings4. Maximum Likelihood Missing Data Handling  4.1 Chapter Overview4.2 The Missing Data Log-Likelihood4.3 How Do the Incomplete Data Records Improve Estimation?4.4 An Illustrative Computer Simulation Study4.5 Estimating Standard Errors with Missing Data4.6 Observed Versus Expected Information4.7 A Bivariate Analysis Example4.8 An Illustrative Computer Simulation Study4.9 An Overview of the EM Algorithm4.10 A Detailed Description of the EM Algorithm4.11 A Bivariate Analysis Example4.12 Extending EM to Multivariate Data4.13 Maximum Likelihood Software Options4.14 Data Analysis Example 14.15 Data Analysis Example 24.16 Data Analysis Example 34.17 Data Analysis Example 44.18 Data Analysis Example 54.19 Summary4.20 Recommended Readings5. Improving the Accuracy of Maximum Likelihood Analyses5.1 Chapter Overview5.2 The Rationale for an Inclusive Analysis Strategy5.3 An Illustrative Computer Simulation Study5.4 Identifying a Set of Auxiliary Variables5.5 Incorporating Auxiliary Variables Into a Maximum Likelihood Analysis5.6 The Saturated Correlates Model5.7 The Impact of Non-Normal Data5.8 Robust Standard Errors5.9 Bootstrap Standard Errors5.10 The Rescaled Likelihood Ratio Test5.11 Bootstrapping the Likelihood Ratio Statistic5.12 Data Analysis Example 15.13 Data Analysis Example 25.14 Data Analysis Example 35.15 Summary5.16 Recommended Readings6. An Introduction to Bayesian Estimation6.1 Chapter Overview6.2 What Makes Bayesian Statistics Different?6.3 A Conceptual Overview of Bayesian Estimation6.4 Bayes’ Theorem6.5 An Analysis Example6.6 How Does Bayesian Estimation Apply to Multiple Imputation?6.7 The Posterior Distribution of the Mean6.8 The Posterior Distribution of the Variance6.9 The Posterior Distribution of a Covariance Matrix6.10 Summary6.11 Recommended Readings7. The Impu