Kim, Jae Kwang,  1968- <br/><br/>
Statistical methods for handling incomplete data / 
Jae Kwang Kim, Department of Statistics Iowa State University, USA, Jun Shao, Department of Statistics University of Wisconsin - Madison, USA. 
 - xi, 211 pages ;  25 cm 
<br/><br/>Includes bibliographical references (pages 201-207) and index. 
<br/><br/>Introduction<br/>Introduction<br/>Outline<br/>How to Use This Book<br/><br/><br/>Likelihood-Based Approach<br/>Introduction<br/>Observed Likelihood<br/>Mean Score Approach<br/>Observed Information<br/><br/><br/><br/><br/><br/>Computation<br/>Introduction<br/>Factoring Likelihood Approach<br/>EM Algorithm<br/>Monte Carlo Computation<br/>Monte Carlo EM<br/>Data Augmentation<br/><br/><br/><br/><br/><br/>Imputation<br/>Introduction<br/>Basic Theory for Imputation<br/>Variance Estimation after Imputation<br/>Replication Variance Estimation<br/>Multiple Imputation<br/>Fractional Imputation<br/><br/><br/>Propensity Scoring Approach<br/>Introduction<br/>Regression Weighting Method<br/>Propensity Score Method<br/>Optimal Estimation<br/>Doubly Robust Method<br/>Empirical Likelihood Method<br/>Nonparametric Method<br/><br/><br/>Nonignorable Missing Data<br/>Nonresponse Instrument<br/>Conditional Likelihood Approach<br/>Generalized Method of Moments (GMM) Approach<br/>Pseudo Likelihood Approach<br/>Exponential Tilting (ET) Model<br/>Latent Variable Approach<br/>Callbacks<br/>Capture-Recapture (CR) Experiment<br/><br/><br/>Longitudinal and Clustered Data<br/>Ignorable Missing Data<br/>Nonignorable Monotone Missing Data<br/>Past-Value-Dependent Missing Data<br/>Random-Effect-Dependent Missing Data<br/><br/><br/>Application to Survey Sampling<br/>Introduction<br/>Calibration Estimation<br/>Propensity Score Weighting Method<br/>Fractional Imputation<br/>Fractional Hot Deck Imputation<br/>Imputation for Two-Phase Sampling<br/>Synthetic Imputation<br/><br/><br/><br/><br/><br/>Statistical Matching<br/>Introduction<br/>Instrumental Variable Approach<br/>Measurement Error Models<br/>Causal Inference<br/><br/><br/><br/><br/><br/>Bibliography<br/><br/><br/>Index 
<br/><br/> "With the advances in statistical computing, there has been a rapid development of techniques and applications in missing data analysis. This book aims to cover the most up-to-date statistical theories and computational methods for analyzing incomplete data through (1)vigorous treatment of statistical theories on likelihood-based inference with missing data, (2) comprehensive treatment of computational techniques and theories on imputation, and (3) most up-to-date treatment of methodologies involving propensity score weighting, nonignorable missing, longitudinal missing, survey sampling application, and statistical matching. The book is suitable for use as a textbook for a graduate course in statistics departments or as a reference book for those interested in this area. Some of the research ideas introduced in the book can be developed further for specific applications"-- 
<br/><br/><label>ISBN: </label>9781439849637 (hardback : acidfree paper) 
<br/><br/><label>LCCN: </label>2013010114 
<br/><br/><label>Subjects--Topical Terms: </label><br/>Missing observations (Statistics)<br/>Multiple imputation (Statistics)<br/>MATHEMATICS / Probability & Statistics / General.
<br/><br/><label>LC Class. No.: </label>QA276.8  / .K55 2014 
<br/><br/><label>Dewey Class. No.: </label>519.54 KIM S