Causal Inference in Statistics, Social, and Biomedical SciencesCambridge University Press, 6 apr. 2015 - 625 sidor Most questions in social and biomedical sciences are causal in nature: what would happen to individuals, or to groups, if part of their environment were changed? In this groundbreaking text, two world-renowned experts present statistical methods for studying such questions. This book starts with the notion of potential outcomes, each corresponding to the outcome that would be realized if a subject were exposed to a particular treatment or regime. In this approach, causal effects are comparisons of such potential outcomes. The fundamental problem of causal inference is that we can only observe one of the potential outcomes for a particular subject. The authors discuss how randomized experiments allow us to assess causal effects and then turn to observational studies. They lay out the assumptions needed for causal inference and describe the leading analysis methods, including, matching, propensity-score methods, and instrumental variables. Many detailed applications are included, with special focus on practical aspects for the empirical researcher. |
Innehåll
The Basic Framework | 3 |
A Brief History of the Potential Outcomes Approach | 23 |
A Classification of Assignment Mechanisms | 31 |
A Taxonomy of Classical Randomized Experiments | 47 |
Fishers Exact PValues for Completely Randomized Experiments | 57 |
Neymans Repeated Sampling Approach to Completely | 83 |
Regression Methods for Completely Randomized Experiments | 113 |
ModelBased Inference for Completely Randomized Experiments | 141 |
Matching to Improve Balance in Covariate Distributions | 337 |
Trimming to Improve Balance in Covariate Distributions | 359 |
Subclassification on the Propensity Score | 377 |
Matching Estimators | 401 |
A General Method for Estimating Sampling Variances | 433 |
Inference for General Causal Estimands | 461 |
Assessing Unconfoundedness | 479 |
Sensitivity Analysis and Bounds | 496 |
Stratified Randomized Experiments | 187 |
Pairwise Randomized Experiments | 219 |
An Experimental Evaluation of a Labor Market | 240 |
Unconfounded Treatment Assignment | 257 |
Estimating the Propensity Score | 281 |
Assessing Overlap in Covariate Distributions | 309 |
Instrumental Variables Analysis of Randomized Experiments with | 513 |
Instrumental Variables Analysis of Randomized Experiments | 542 |
Conclusions and Extensions | 589 |
Author Index | 605 |
Andra upplagor - Visa alla
Causal Inference for Statistics, Social, and Biomedical Sciences: An ... Guido W. Imbens,Donald B. Rubin Begränsad förhandsgranskning - 2015 |
Vanliga ord och fraser
active treatment analysis approach aspirin assess assignment mechanism assignment vector average effect average treatment effect balance barbiturate Bi(j blocks causal effects causal estimand chapter completely randomized experiment compliers conditional distribution control group control units covariate distributions covariate values discuss earnings equal estimated propensity score example exclusion restriction focus full sample Imbens imputation instrumental variables ITT effect least squares likelihood function linearized propensity score lottery data matching estimator methods missing potential outcomes model-based nevertakers Neyman noncompliers normal distribution null hypothesis observed outcomes p-value pair parameters population posterior distribution pre-treatment variables prior distribution quantile receipt of treatment regression function Rubin sampling variance Section specification strata stratum subclassification subsample super-population Table Tdif test statistic treated and control treated units treatment group treatment indicator treatment status trimmed sample unconfoundedness unit-level W₁ Wobs X₁ Ymis Yobs zero στ
