HOME > 상세정보

상세정보

Causal inference for statistics, social, and biomedical sciences : an introduction

Causal inference for statistics, social, and biomedical sciences : an introduction (11회 대출)

자료유형
단행본
개인저자
Imbens, Guido. Rubin, Donald B.
서명 / 저자사항
Causal inference for statistics, social, and biomedical sciences : an introduction / Guido W. Imbens, Donald B. Rubin.
발행사항
New York :   Cambridge University Press,   2015.  
형태사항
xix, 625 p. : ill. ; 26 cm.
ISBN
9780521885881
서지주기
Includes bibliographical references and index.
일반주제명
Social sciences --Research. Causation. Inference.
000 00000cam u2200205 a 4500
001 000045837468
005 20150716151616
008 150630s2015 nyua b 001 0 eng d
010 ▼a 2014020988
020 ▼a 9780521885881
035 ▼a (KERIS)REF000017490155
040 ▼a DLC ▼b eng ▼c DLC ▼e rda ▼d 211009
050 0 0 ▼a H62 ▼b .I537 2014
082 0 0 ▼a 519.5/4 ▼2 23
084 ▼a 519.54 ▼2 DDCK
090 ▼a 519.54 ▼b I32c
100 1 ▼a Imbens, Guido.
245 1 0 ▼a Causal inference for statistics, social, and biomedical sciences : ▼b an introduction / ▼c Guido W. Imbens, Donald B. Rubin.
260 ▼a New York : ▼b Cambridge University Press, ▼c 2015.
300 ▼a xix, 625 p. : ▼b ill. ; ▼c 26 cm.
504 ▼a Includes bibliographical references and index.
650 0 ▼a Social sciences ▼x Research.
650 0 ▼a Causation.
650 0 ▼a Inference.
700 1 ▼a Rubin, Donald B.
945 ▼a KLPA

No. 소장처 청구기호 등록번호 도서상태 반납예정일 예약 서비스
No. 1 소장처 중앙도서관/서고7층/ 청구기호 519.54 I32c 등록번호 111738783 도서상태 대출가능 반납예정일 예약 서비스 B M
No. 2 소장처 과학도서관/Sci-Info(2층서고)/ 청구기호 519.54 I32c 등록번호 121233526 도서상태 대출가능 반납예정일 예약 서비스 B M
No. 3 소장처 의학도서관/자료실(3층)/ 청구기호 519.54 I32c 등록번호 131050241 도서상태 대출가능 반납예정일 예약 서비스 B
No. 소장처 청구기호 등록번호 도서상태 반납예정일 예약 서비스
No. 1 소장처 중앙도서관/서고7층/ 청구기호 519.54 I32c 등록번호 111738783 도서상태 대출가능 반납예정일 예약 서비스 B M
No. 소장처 청구기호 등록번호 도서상태 반납예정일 예약 서비스
No. 1 소장처 과학도서관/Sci-Info(2층서고)/ 청구기호 519.54 I32c 등록번호 121233526 도서상태 대출가능 반납예정일 예약 서비스 B M
No. 소장처 청구기호 등록번호 도서상태 반납예정일 예약 서비스
No. 1 소장처 의학도서관/자료실(3층)/ 청구기호 519.54 I32c 등록번호 131050241 도서상태 대출가능 반납예정일 예약 서비스 B

컨텐츠정보

목차

CONTENTS
Preface = xvii
PART �� INTRODUCTION
 1 Causality : The Basic Framework = 3
  1.1 Introduction = 3
  1.2 Potential Outcomes = 3
  1.3 Definition of Causal Effects = 5
  1.4 Causal Effects in Common Usage = 7
  1.5 Learning about Causal Effects : Multiple Units = 8
  1.6 The Stable Unit Treatment Value Assumption = 9
  1.7 The Assignment Mechanism : An Introduction = 13
  1.8 Attributes, Pre-Treatment Variables, or Covariates = 15
  1.9 Potential Outcomes and Lord's Paradox = 16
  1.10 Causal Estimands = 18
  1.11 Structure of the Book = 20
  1.12 Samples, Populations, and Super-Populations = 20
  1.13 Conclusion = 21
  Notes = 21
 2 A Brief History of the Potential Outcomes Approach to Causal Inference = 23
  2.1 Introduction = 23
  2.2 Potential Outcomes and the Assignment Mechanism before Neyman = 24
  2.3 Neyman's(1923) Potential Outcome Notation in Randomized Experiments = 25
  2.4 Earlier Hints for Physical Randomizing = 26
  2.5 Fisher's(1925) Proposal to Randomize Treatments to Units = 26
  2.6 The Observed Outcome Notation in Observational Studies for Causal Effects = 27
  2.7 Early Uses of Potential Outcomes in Observational Studies in Social Sciences = 28
  2.8 Potential Outcomes and the Assignment Mechanism in Observational Studies : Rubin(1974) = 29
  Notes = 30
 3 A Classification of Assignment Mechanisms = 31
  3.1 Introduction = 31
  3.2 Notation = 33
  3.3 Assignment Probabilities = 34
  3.4 Restrictions on the Assignment Mechanism = 37
  3.5 Assignment Mechanisms and Super-Populations = 39
  3.6 Randomized Experiments = 40
  3.7 Observational Studies : Regular Assignment Mechanisms = 41
  3.8 Observational Studies : Irregular Assignment Mechanisms = 42
  3.9 Conclusion = 43
  Notes = 43
PART �� CLASSICAL RANDOMIZED EXPERIMENTS
 4 A Taxonomy of Classical Randomized Experiments = 47
  4.1 Introduction = 47
  4.2 Notation = 48
  4.3 Bernoulli Trials = 48
  4.4 Completely Randomized Experiments = 50
  4.5 Stratified Randomized Experiments = 51
  4.6 Paired Randomized Experiments = 52
  4.7 Discussion = 53
  4.8 Conclusion = 55
  Notes = 56
 5 Fisher's Exact P-Values for Completely Randomized Experiments = 57
  5.1 Introduction = 57
  5.2 The Paul et al. Honey Experiment Data = 59
  5.3 A Simple Example with Six Units = 59
  5.4 The Choice of Null Hypothesis = 63
  5.5 The Choice of Statistic = 64
  5.6 A Small Simulation Study = 72
  5.7 Interval Estimates Based on Fisher P-Value Calculations = 74
  5.8 Computation of P-Values = 75
  5.9 Fisher Exact P-Values with Covariates = 78
  5.10 Fisher Exact P-Values for the Honey Data = 80
  5.11 Conclusion = 81
  Notes = 81
 6 Neyman's Repeated Sampling Approach to Completely Randomized Experiments = 83
  6.1 Introduction = 83
  6.2 The Duflo-Hanna-Ryan Teacher-Incentive Experiment Data = 84
  6.3 Unbiased Estimation of the Average Treatment Effect = 85
  6.4 The Sampling Variance of the Neyman Estimator = 87
  6.5 Estimating the Sampling Variance = 92
  6.6 Confidence Intervals and Testing = 95
  6.7 Inference for Population Average Treatment Effects = 98
  6.8 Neyman's Approach with Covariates = 101
  6.9 Results for the Duflo-Hanna-Ryan Teacher-Incentive Data = 102
  6.10 Conclusion = 104
  Notes = 104
  Appendix A : Sampling Variance Calculations = 105
  Appendix B : Random Sampling from a Super-Population = 109
 7 Regression Methods for Completely Randomized Experiments = 113
  7.1 Introduction = 113
  7.2 The LRC-CPPT Cholesterol Data = 115
  7.3 The Super-Population Average Treatment Effects = 116
  7.4 Linear Regression with No Covariates = 118
  7.5 Linear Regression with Additional Covariates = 122
  7.6 Linear Regression with Covariates and Interactions = 125
  7.7 Transformations of the Outcome Variable = 127
  7.8 The Limits on Increases in Precision Due to Covariates = 128
  7.9 Testing for the Presence of Treatment Effects = 129
  7.10 Estimates for LRC-CPPT Cholesterol Data = 131
  7.11 Conclusion = 133
  Notes = 134
  Appendix = 135
 8 Model-Based Inference for Completely Randomized Experiments = 141
  8.1 Introduction = 141
  8.2 The Lalonde NSW Experimental Job-Training Data = 144
  8.3 A Simple Example : Naive and More Sophisticated Approaches to Imputation = 146
  8.4 Bayesian Model-Based Imputation in the Absence of Covariates = 150
  8.5 Simulation Methods in the Model-Based Approach = 163
  8.6 Dependence between Potential Outcomes = 165
  8.7 Model-Based Imputation with Covariates = 169
  8.8 Super-Population Average Treatment Effects = 171
  8.9 A Frequentist Perspective = 172
  8.10 Model-Based Estimates of the Effect of the NSW Program = 174
  8.11 Conclusion = 177
  Notes = 177
  Appendix A : Posterior Distributions for Normal Models = 178
  Appendix B : Analytic Derivations with Known Covariance Matrix = 181
 9 Stratified Randomized Experiments = 187
  9.1 Introduction = 187
  9.2 The Tennesee Project Star Data = 188
  9.3 The Structure of Stratified Randomized Experiments = 189
  9.4 Fisher's Exact P-Values in Stratified Randomized Experiments = 192
  9.5 The Analysis of Stratified Randomized Experiments from Neyman's Repeated Sampling Perspective = 201
  9.6 Regression Analysis of Stratified Randomized Experiments = 205
  9.7 Model-Based Analysis of Stratified Randomized Experiments = 207
  9.8 Design Issues : Stratified versus Completely Randomized Experiments = 211
  9.9 Conclusion = 212
  Notes = 212
  Appendix A : Student-Level Analyses = 213
  Appendix B : Proofs of Theorems 9.1 and 9.2 = 214
 10 Pairwise Randomized Experiments = 219
  10.1 Introduction = 219
  10.2 The Children's Television Workshop Experiment Data = 220
  10.3 Pairwise Randomized Experiments = 220
  10.4 Fisher's Exact P-Values in Pairwise Randomized Experiments = 222
  10.5 The Analysis of Pairwise Randomized Experiments from Neyman's Repeated Sampling Perspective = 224
  10.6 Regression-Based Analysis of Pairwise Randomized Experiments = 229
  10.7 Model-Based Analysis of Pairwise Randomized Experiments = 231
  10.8 Conclusion = 233
  Notes = 234
  Appendix : Proofs = 234
 11 Case Study : An Experimental Evaluation of a Labor Market Program = 240
  11.1 Introduction = 240
  11.2 The San Diego SWIM Program Data = 240
  11.3 Fisher's Exact P-Values = 242
  11.4 Neyman's Repeated Sampling-Based Point Estimates and Large-Sample Confidence Intervals = 245
  11.5 Regression-Based Estimates = 247
  11.6 Model-Based Point Estimates = 250
  11.7 Conclusion = 253
  Notes = 253
PART �� REGULAR ASSIGNMENT MECHANISMS : DESIGN
 12 Unconfounded Treatment Assignment = 257
  12.1 Introduction = 257
  12.2 Regular Assignment Mechanisms = 258
  12.3 Balancing Scores and the Propensity Score = 266
  12.4 Estimation and Inference = 268
  12.5 Design Phase = 276
  12.6 Assessing Unconfoundedness = 278
  12.7 Conclusion = 279
  Notes = 279
 13 Estimating the Propensity Score = 281
  13.1 Introduction = 281
  13.2 The Reinisch et al. Barbituate Exposure Data = 284
  13.3 Selecting the Covariates and Interactions = 285
  13.4 Choosing the Specification of the Propensity Score for the Barbituate Data = 288
  13.5 Constructing Propensity-Score Strata = 290
  13.6 Choosing Strata for the Barbituate Data = 294
  13.7 Assessing Balance Conditional on the Estimated Propensity Score = 296
  13.8 Assessing Covariate Balance for the Barbituate Data = 300
  13.9 Conclusion = 306
  Notes = 306
  Appendix : Logistic Regression = 307
 14 Assessing Overlap in Covariate Distributions = 309
  14.1 Introduction = 309
  14.2 Assessing Balance in Univariate Distributions = 310
  14.3 Direct Assessment of Balance in Multivariate Distributions = 313
  14.4 Assessing Balance in Multivariate Distributions Using the Propensity Score = 314
  14.5 Assessing the Ability to Adjust for Differences in Covariates by Treatment Status = 317
  14.6 Assessing Balance : Four Illustrations = 318
  14.7 Sensitivity of Regression Estimates to Lack of Overlap = 332
  14.8 Conclusion = 336
  Notes = 336
 15 Matching to Improve Balance in Covariate Distributions = 337
  15.1 Introduction = 337
  15.2 The Reinisch et al. Barbituate Exposure Data = 339
  15.3 Selecting a Subsample of Controls through Matching to Improve Balance = 339
  15.4 An Illustration of Propensity Score Matching with Six Observations = 344
  15.5 Theoretical Properties of Matching Procedures = 345
  15.6 Creating Matched Samples for the Barbituate Data = 349
  15.7 Conclusion = 358
  Notes = 358
 16 Trimming to Improve Balance in Covariate Distributions = 359
  16.1 Introduction = 359
  16.2 The Right Heart Catheterization Data = 360
  16.3 An Example with a Single Binary Covariate = 362
  16.4 Selecting a Subsample Based on the Propensity Score = 366
  16.5 The Optimal Subsample for the Right Heart Catheterization Data = 368
  16.6 Conclusion = 373
  Notes = 374
PART �� REGULAR ASSIGNMENT MECHANISMS : ANALYSIS
 17 Subclassification on the Propensity Score = 377
  17.1 Introduction = 377
  17.2 The Imbens-Rubin-Sacerdote Lottery Data = 378
  17.3 Subclassification on the Propensity Score and Bias Reduction = 380
  17.4 Subclassification and the Lottery Data = 385
  17.5 Estimation Based on Subclassification with Additional Bias Reduction = 386
  17.6 Neymanian Inference = 388
  17.7 Average Treatment Effects for the Lottery Data = 390
  17.8 Weighting Estimators and Subclassification = 392
  17.9 Conclusion = 399
  Notes = 399
 18 Matching Estimators = 401
  18.1 Introduction = 401
  18.2 The Card-Krueger New Jersey and Pennsylvania Minimum Wage Data = 404
  18.3 Exact Matching without Replacement = 405
  18.4 Inexact Matching without Replacement = 407
  18.5 Distance Measures = 410
  18.6 Matching and the Card-Krueger Data = 412
  18.7 The Bias of Matching Estimators = 415
  18.8 Bias-Corrected Matching Estimators = 416
  18.9 Matching with Replacement = 424
  18.10 The Number of Matches = 425
  18.11 Matching Estimators for the Average Treatment Effect for the Controls and for the Full Sample = 427
  18.12 Matching Estimates of the Effect of the Minimum Wage Increase = 428
  18.13 Conclusion = 430
  Notes = 431
 19 A General Method for Estimating Sampling Variances for Standard Estimators for Average Causal Effects = 433
  19.1 Introduction = 433
  19.2 The Imbens-Rubin-Sacerdote Lottery Data = 435
  19.3 Estimands = 436
  19.4 The Common Structure of Standard Estimators for Average Treatment Effects = 441
  19.5 A General Formula for the Conditional Sampling Variance = 445
  19.6 A Simple Estimator for the Unit-Level Conditional Sampling Variance = 446
  19.7 An Estimator for the Sampling Variance of [TEX]$$\hat{\tau}$$[/TEX] Conditional on Covariates = 452
  19.8 An Estimator for the Sampling Variance for the Estimator for the Average Effect for the Treated = 452
  19.9 An Estimator for the Sampling Variance for the Population Average Treatment Effect = 454
  19.10 Alternative Estimators for the Sampling Variance = 456
  19.11 Conclusion = 460
  Notes = 460
 20 Inference for General Causal Estimands = 461
  20.1 Introduction = 461
  20.2 The Lalonde NSW Observational Job-Training Data = 462
  20.3 Causal Estimands = 465
  20.4 A Model for the Conditional Potential Outcome Distributions = 468
  20.5 Implementation = 472
  20.6 Results for the Lalonde Data = 473
  20.7 Conclusion = 474
  Notes = 474
PART �� REGULAR ASSIGNMENT MECHANISMS : SUPPLEMENTARY ANALYSES
 21 Assessing Unconfoundedness = 479
  21.1 Introduction = 479
  21.2 Setup = 482
  21.3 Estimating Effects on Pseudo-Outcomes = 482
  21.4 Estimating Effects of Pseudo-Treatments = 485
  21.5 Robustness to the Set of Pre-Treatment Variables = 487
  21.6 The Imbens-Rubin-Sacerdote Lottery Data = 490
  21.7 Conclusion = 495
  Notes = 495
 22 Sensitivity Analysis and Bounds = 496
  22.1 Introduction = 496
  22.2 The Imbens-Rubin-Sacerdote Lottery Data = 497
  22.3 Bounds = 497
  22.4 Binary Outcomes : The Rosenbaum-Rubin Sensitivity Analysis = 500
  22.5 Binary Outcomes : The Rosenbaum Sensitivity Analysis for P-Values = 506
  22.6 Conclusion = 509
  Notes = 509
PART �� REGULAR ASSIGNMENT MECHANISMS WITH NONCOMPLIANCE : ANALYSIS
 23 Instrumental Variables Analysis of Randomized Experiments with One-Sided Noncompliance = 513
  23.1 Introduction = 513
  23.2 The Sommer-Zeger Vitamin A Supplement Data = 516
  23.3 Setup = 517
  23.4 Intention-to-Treat Effects = 519
  23.5 Compliance Status = 522
  23.6 Instrumental Variables = 526
  23.7 Moment-Based Instrumental Variables Estimators = 530
  23.8 Linear Models and Instrumental Variables = 531
  23.9 Naive Analyses : "As-Treated," "Per Protocol," and Unconfoundedness = 535
  23.10 Conclusion = 539
  Notes = 539
  Appendix = 541
 24 Instrumental Variables Analysis of Randomized Experiments with Two-Sided Noncompliance = 542
  24.1 Introduction = 542
  24.2 The Angrist Draft Lottery Data = 543
  24.3 Compliance Status = 544
  24.4 Intention-to-Treat Effects = 546
  24.5 Instrumental Variables = 548
  24.6 Traditional Econometric Methods for Instrumental Variables = 556
  24.7 Conclusion = 559
  Notes = 559
 25 Model-Based Analysis in Instrumental Variable Settings : Randomized Experiments with Two-Sided Noncompliance = 560
  25.1 Introduction = 560
  25.2 The McDonald-Hiu-Tierney Influenza Vaccination Data = 561
  25.3 Covariates = 567
  25.4 Model-Based Instrumental Variables Analyses for Randomized Experiments with Two-Sided Noncompliance = 568
  25.5 Simulation Methods for Obtaining Draws from the Posterior Distribution of the Estimand Given the Data = 574
  25.6 Models for the Influenza Vaccination Data = 578
  25.7 Results for the Influenza Vaccination Data = 581
  25.8 Conclusion = 584
  Notes = 584
PART �� CONCLUSION
 26 Conclusions and Extensions = 589
  Notes = 590
References = 591
Author Index = 605
Subject Index = 609

관련분야 신착자료

Hogg, Robert V. (2021)