>> Home >> Bookstore >> Biostatistics and epidemiology >> Multiple Imputation and Its Application

Click to enlarge
See the back cover

Multiple Imputation and Its Application

$57.75 each

James R. Carpenter and Michael G. Kenward
Publisher: Wiley
Copyright: 2013
ISBN-13: 978-0-470-74052-1
Pages: 345; hardcover
Price: $57.75

Comment from the Stata technical group

Multiple Imputation and its Application, by James R. Carpenter and Michael G. Kenward, provides an excellent review of multiple imputation (MI) from basic to advanced concepts. MI is a statistical method for analyzing incomplete data. The flexibility of the MI procedure has prompted its use in a wide variety of applications. This book describes the rationale for MI and its underlying assumptions in a broad range of statistical settings, and demonstrates the use of this procedure for handling missing data in complex data structures.

The text provides a good mixture of theory and practice. Throughout the book, the concepts are illustrated with real data examples.

The book is divided into three parts: foundations, MI for cross-sectional data, and advanced topics. The first part reviews the basic concepts of missing data, such as types of missing data and missing-data assumptions, and of multiple imputation, such as the MI procedure and its justification. The second part describes the use of MI for handling missing values in cross-sectional data, including the imputation of different types of data (continuous, binary, ordinal, etc.), and for handling nonlinearities and interactions during imputation. The third part discusses the advanced use of MI for dealing with missing data in complex data structures such as survival data and multilevel data. Other important advanced topics are covered, including the handling of survey weights during imputation, sensitivity analysis, and robust MI.

Table of contents

View table of contents >>

The Stata Blog: Not Elsewhere Classified Find us on Facebook Follow us on Twitter LinkedIn Google+ Watch us on YouTube