Applied Bayesian Modeling and Causal Inference from IncompleteData PerspectivesDonald B. Rubin, Andrew Gelman, XiaoLi Meng This book brings together a collection of articles on statistical methods relating to missing data analysis, including multiple imputation, propensity scores, instrumental variables, and Bayesian inference. Covering new research topics and realworld examples which do not feature in many standard texts. The book is dedicated to Professor Don Rubin (Harvard). Don Rubin has made fundamental contributions to the study of missing data. Key features of the book include:

What people are saying  Write a review
We haven't found any reviews in the usual places.
Contents
An overview of methods for causal inference from observational  3 
Matching in observational studies by Paul R Rosenbaum  15 
Estimating causal effects in nonexperimental studies  25 
Medication cost sharing and drug spending in Medicare  37 
A comparison of experimental and observational data analyses  49 
Fixing broken experiments using the propensity score  61 
The propensity score with continuous treatments  73 
Causal inference with instrumental variables by Junni L Zhang  85 
Multimodality in mixture models and factor models by Eric Loken  203 
Modeling the covariance and correlation matrix of repeated measures  215 
a simple robust alternative to logistic and probit  227 
Using EM and data augmentation for the competing risks model  239 
Mixed effects models and the EM algorithm  253 
The samplingimportance resampling algorithm by KimHung Li  265 
Whither applied Bayesian inference? by Bradley P Carlin  279 
Efficient EMtype algorithms for fitting spectral lines in highenergy  285 
Principal stratification by Constantine E Frangakis  97 
Bridging across changes in classification systems by Nathaniel  117 
Representing the Census undercount by multiple imputation  129 
Statistical disclosure techniques based on multiple imputation  141 
examples from the National  153 
Propensity score estimation with missing data  163 
Sensitivity to nonignorability in frequentist inference  175 
Statistical modeling and computation by D Michael Titterington  189 
Treatment effects in beforeafter data by Andrew Gelman  195 
Improved predictions of lynx trappings using a biological model  297 
Record linkage using finite mixture models by Michael D Larsen  309 
Identifying likely duplicates by record linkage in a survey  319 
Applying structural equation models with incomplete data  331 
Perceptual scaling by Ying Nian Wu ChengEn Guo  343 
References  361 
401  
Other editions  View all
Common terms and phrases
2004 John Wiley adjustment Applied Bayesian Modeling approach approximation assumptions average Bayesian inference bias block causal effect Causal Inference census chapter codes computation conditional distribution control groups correlation cost sharing covariance matrix data set Estep ECME Edition EM algorithm emission line equation estimand estimated propensity score example factor function Gelman and XL Gibbs sampler given households Imbens IncompleteData Perspectives indicator intervals iteration latent variable model latent variables linear loglikelihood logistic regression lynx matching matrix maximum likelihood estimates MCMC mean measured Meng methods missing data mixture models Modeling and Causal multiple imputation multivariate observational studies pairs parameters population posterior distribution postterm potential outcomes predictive pretreatment principal stratification prior distribution probability probit problem procedure proficiency random effects record linkage regression model resampling Rosenbaum and Rubin sample Section simulation SIR algorithm sparse coding Statistical Table treated treatment effect treatment group units values variance vector weighted
Popular passages
Page 366  Speroff T, Dawson Nv, et al. The effectiveness of right heart catheterization in the initial care of critically ill patients.