You are here

Missing Data
Share

Missing Data



August 2001 | 104 pages | SAGE Publications, Inc
Sooner or later anyone who does statistical analysis runs into problems with missing data in which information for some variables is missing for some cases.

Why is this a problem? Because most statistical methods presume that every case has information on all the variables to be included in the analysis. Using numerous examples and practical tips, this book offers a non-technical explanation of the standard methods for missing data (such as listwise or casewise deletion) as well as two newer (and, better) methods, maximum likelihood and multiple imputation. Anyone who has been relying on ad-hoc methods that are statistically inefficient or biased will find this book a welcome and accessible solution to their problems with handling missing data.

 
Series Editor's Introduction
 
1. Introduction
 
2. Assumptions
Missing Completely at Random

 
Missing at Random

 
Ignorable

 
Nonignorable

 
 
3. Conventional Methods
Listwise Deletion

 
Pairwise Deletion

 
Dummy Variable Adjustment

 
Imputation

 
Summary

 
 
4. Maximum Likelihood
Review of Maximum Likelihood

 
ML With Missing Data

 
Contingency Table Data

 
Linear Models With Normally Distributed Data

 
The EM Algorithm

 
EM Example

 
Direct ML

 
Direct ML Example

 
Conclusion

 
 
5. Multiple Imputation: Bascis
Single Random Imputation

 
Multiple Random Imputation

 
Allowing for Random Variation in the Parameter Estimates

 
Multiple Imputation Under the Multivariate Normal Model

 
Data Augmentation for the Multivariate Normal Model

 
Convergence in Data Augmentation

 
Sequential Verses Parallel Chains of Data Augmentation

 
Using the Normal Model for Nonnormal or Categorical Data

 
Exploratory Analysis

 
MI Example 1

 
 
6. Multiple Imputation: Complications
Interactions and Nonlinearities in MI

 
Compatibility of the Imputation Model and the Analysis Model

 
Role of the Dependent Variable in Imputation

 
Using Additional Variables in the Imputation Process

 
Other Parametric Approaches to Multiple Imputation

 
Nonparametric and Partially Parametric Methods

 
Sequential Generalized Regression Models

 
Linear Hypothesis Tests and Likelihood Ratio Tests

 
MI Example 2

 
MI for Longitudinal and Other Clustered Data

 
MI Example 3

 
 
7. Nonignorable Missing Data
Two Classes of Models

 
Heckman's Model for Sample Selection Bias

 
ML Estimation With Pattern-Mixture Models

 
Multiple Imputation With Pattern-Mixture Models

 
 
8. Summary and Conclusion
 
Notes
 
References
 
About the Author

"…an excellent resource for researchers who are conducting multivariate statistical studies."

Richard A. Chechile
Journal of Mathematical Psychology

Preview this book

Paul D. Allison

Paul D. Allison, Ph.D., is Professor of Sociology at the University of Pennsylvania where he teaches graduate courses in methods and statistics. He is also the founder and president of Statistical Horizons LLC which offers short courses on a wide variety of statistical topics.After completing his doctorate in sociology at the University of Wisconsin, he did postdoctoral study in statistics at the University of Chicago and the University of Pennsylvania. He has published eight books and more than 60 articles on topics that include linear regression, log-linear analysis, logistic regression, structural equation models, inequality measures,... More About Author

Purchasing options

Please select a format:

ISBN: 9780761916727
$22.00 

SAGE Knowledge is the ultimate social sciences digital library for students, researchers, and faculty. Hosting more than 4,400 titles, it includes an expansive range of SAGE eBook and eReference content, including scholarly monographs, reference works, handbooks, series, professional development titles, and more.

The platform allows researchers to cross-search and seamlessly access a wide breadth of must-have SAGE book and reference content from one source.