Causality in a Social World - Moderation, Mediation and Spill-Over

Informationen zum Autor Guanglei Hong , University of Chicago, Department of Comparative Human Development, USA. Klappentext Causality in a Social World introduces innovative new statistical research and strategies for investigating moderated intervention effects, mediated intervention effects, and spill-over effects using experimental or quasi-experimental data.The book uses potential outcomes to define causal effects, explains and evaluates identification assumptions using application examples, and compares innovative statistical strategies with conventional analysis methods. Whilst highlighting the crucial role of good research design and the evaluation of assumptions required for identifying causal effects in the context of each application, the author demonstrates that improved statistical procedures will greatly enhance the empirical study of causal relationship theory.Applications focus on interventions designed to improve outcomes for participants who are embedded in social settings, including families, classrooms, schools, neighbourhoods, and workplaces. Zusammenfassung Causality in a Social World introduces innovative new statistical research and strategies for investigating moderated intervention effects, mediated intervention effects, and spill-over effects using experimental or quasi-experimental data. Inhaltsverzeichnis Preface xv Part I Overview 1 1 Introduction 3 1.1 Concepts of moderation, mediation, and spill-over 3 1.2 Weighting methods for causal inference 10 1.3 Objectives and organization of the book 11 1.4 How is this book situated among other publications on related topics? 12 2 Review of causal inference concepts and methods 18 2.1 Causal inference theory 18 2.2 Applications to Lord's paradox and Simpson's paradox 27 2.3 Identification and estimation 34 3 Review of causal inference designs and analytic methods 40 3.1 Experimental designs 40 3.2 Quasiexperimental designs 44 3.3 Statistical adjustment methods 46 3.4 Propensity score 55 4 Adjustment for selection bias through weighting 76 4.1 Weighted estimation of population parameters in survey sampling 77 4.2 Weighting adjustment for selection bias in causal inference 80 4.3 MMWS 86 5 Evaluations of multivalued treatments 100 5.1 Defining the causal effects of multivalued treatments 100 5.2 Existing designs and analytic methods for evaluating multivalued treatments 102 5.3 MMWS for evaluating multivalued treatments 112 5.4 Summary 123 Part II Moderation 127 6 Moderated treatment effects: concepts and existing analytic methods 129 6.1 What is moderation? 129 6.2 Experimental designs and analytic methods for investigating explicit moderators 136 6.3 Existing research designs and analytic methods for investigating implicit moderators 142 7 Marginal mean weighting through stratification for investigating moderated treatment effects 159 7.1 Existing methods for moderation analyses with quasiexperimental data 159 7.2 MMWS estimation of treatment effects moderated by individual or contextual characteristics 168 7.3 MMWS estimation of the joint effects of concurrent treatments 174 8 Cumulative effects of time-varying treatments 185 8.1 Causal effects of treatment sequences 186 8.2 Existing strategies for evaluating time-varying treatments 190 8.3 MMWS for evaluating 2-year treatment sequences 195 8.4 MMWS for evaluating multiyear sequences of multivalued treatments 204 8.5 Conclusion 207 Part III Mediation 211 9 Concepts of mediated treatment effects and experimental designs for investigating causal mechanisms 213 9.1 Introduction 214 9.2 ...

List of contents

Preface xv
 
Part I Overview 1
 
1 Introduction 3
 
1.1 Concepts of moderation, mediation, and spill-over 3
 
1.1.1 Moderated treatment effects 5
 
1.1.2 Mediated treatment effects 7
 
1.1.3 Spill-over effects of a treatment 8
 
1.2 Weighting methods for causal inference 10
 
1.3 Objectives and organization of the book 11
 
1.4 How is this book situated among other publications on related topics? 12
 
2 Review of causal inference concepts and methods 18
 
2.1 Causal inference theory 18
 
2.1.1 Attributes versus causes 18
 
2.1.2 Potential outcomes and individual-specific causal effects 19
 
2.1.3 Inference about population average causal effects 22
 
2.2 Applications to Lord's paradox and Simpson's paradox 27
 
2.2.1 Lord's paradox 27
 
2.2.2 Simpson's paradox 31
 
2.3 Identification and estimation 34
 
2.3.1 Selection bias 35
 
2.3.2 Sampling bias 35
 
2.3.3 Estimation efficiency 36
 
Appendix 2.1: Potential bias in a prima facie effect 36
 
Appendix 2.2: Application of the causal inference theory to Lord's paradox 37
 
3 Review of causal inference designs and analytic methods 40
 
3.1 Experimental designs 40
 
3.1.1 Completely randomized designs 40
 
3.1.2 Randomized block designs 41
 
3.1.3 Covariance adjustment for improving efficiency 43
 
3.1.4 Multilevel experimental designs 43
 
3.2 Quasiexperimental designs 44
 
3.2.1 Nonequivalent comparison group designs 44
 
3.2.2 Other quasiexperimental designs 45
 
3.3 Statistical adjustment methods 46
 
3.3.1 ANCOVA and multiple regression 46
 
3.3.2 Matching and stratification 50
 
3.3.3 Other statistical adjustment methods 51
 
3.4 Propensity score 55
 
3.4.1 What is a propensity score? 56
 
3.4.2 Balancing property of the propensity score 57
 
3.4.3 Pooling conditional treatment effect estimate: Matching, stratification, and covariance adjustment 60
 
Appendix 3.A: Potential bias due to the omission of treatment-by-covariate interaction 70
 
Appendix 3.B: Variable selection for the propensity score model 71
 
4 Adjustment for selection bias through weighting 76
 
4.1 Weighted estimation of population parameters in survey sampling 77
 
4.1.1 Simple random sample 77
 
4.1.2 Proportionate sample 78
 
4.1.3 Disproportionate sample 79
 
4.2 Weighting adjustment for selection bias in causal inference 80
 
4.2.1 Experimental result 81
 
4.2.2 Quasiexperimental result 81
 
4.2.3 Sample weight for bias removal 82
 
4.2.4 IPTW for bias removal 84
 
4.3 MMWS 86
 
4.3.1 Theoretical rationale 86
 
4.3.2 MMWS analytic procedure 91
 
4.3.3 Inherent connection and major distinctions between MMWS and IPTW 93
 
Appendix 4.A: Proof of MMWS-adjusted mean observed outcome being unbiased for the population average potential outcome 95
 
Appendix 4.B: Derivation of MMWS for estimating the treatment effect on the treated 96
 
Appendix 4.C: Theoretical equivalence of MMWS and IPTW 97
 
Appendix 4.D: Simulations comparing MMWS and IPTW under misspecifications of the functional form of a propensity score model 97
 
5 Evaluations of multivalued treatments 100
 
5.1 Defining the causal effects of multivalued treatments 100
 
5.2 Existing designs and analytic methods for evaluating multivalued treatments 102
 
5.2.1 Experimental designs and analysis 102
 
5.2.2 Quasiexperimental designs and analysis 105<

Product details

• Authors: Hong, G Hong, Guanglei Hong, Hong Guanglei
• Publisher: Wiley, John and Sons Ltd
• Languages: English
• Product format: Hardback
• Released: 14.08.2015
• EAN: 9781118332566
• ISBN: 978-1-118-33256-6
• No. of pages: 448
• Subjects: Natural sciences, medicine, IT, technology > Mathematics > Probability theory, stochastic theory, mathematical statistics; Statistik, Soziologie, Sociology, Sozialwissenschaften, Statistics, Soziologische Forschungsmethoden, Research Methodologies, Statistics for Social Sciences, Statistik in den Sozialwissenschaften, Soziologie am Arbeitsplatz, Sociology of Organizations & Work