Guanglei Hong,
G Hong
John Wiley & Sons
e druk, 2015
9781118332566
Causality in a Social World – Moderation, Mediation and Spill–over
Moderation, Mediation and Spill–over
Specificaties
Gebonden, 444 blz.
|
Engels
John Wiley & Sons |
e druk, 2015
ISBN13: 9781118332566
Rubricering
Levertijd ongeveer 8 werkdagen
Samenvatting
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.
Specificaties
ISBN13:9781118332566
Taal:Engels
Bindwijze:gebonden
Aantal pagina's:444
Uitgever:John Wiley & Sons
Hoofdrubriek:Naslagwerken, Mens en maatschappij
Inhoudsopgave
Preface xv
<p>Part I Overview 1</p>
<p>1 Introduction 3</p>
<p>1.1 Concepts of moderation, mediation, and spill–over 3</p>
<p>1.2 Weighting methods for causal inference 10</p>
<p>1.3 Objectives and organization of the book 11</p>
<p>1.4 How is this book situated among other publications on related topics? 12</p>
<p>2 Review of causal inference concepts and methods 18</p>
<p>2.1 Causal inference theory 18</p>
<p>2.2 Applications to Lord s paradox and Simpson s paradox 27</p>
<p>2.3 Identification and estimation 34</p>
<p>3 Review of causal inference designs and analytic methods 40</p>
<p>3.1 Experimental designs 40</p>
<p>3.2 Quasiexperimental designs 44</p>
<p>3.3 Statistical adjustment methods 46</p>
<p>3.4 Propensity score 55</p>
<p>4 Adjustment for selection bias through weighting 76</p>
<p>4.1 Weighted estimation of population parameters in survey sampling 77</p>
<p>4.2 Weighting adjustment for selection bias in causal inference 80</p>
<p>4.3 MMWS 86</p>
<p>5 Evaluations of multivalued treatments 100</p>
<p>5.1 Defining the causal effects of multivalued treatments 100</p>
<p>5.2 Existing designs and analytic methods for evaluating multivalued treatments 102</p>
<p>5.3 MMWS for evaluating multivalued treatments 112</p>
<p>5.4 Summary 123</p>
<p>Part II Moderation 127</p>
<p>6 Moderated treatment effects: concepts and existing analytic methods 129</p>
<p>6.1 What is moderation? 129</p>
<p>6.2 Experimental designs and analytic methods for investigating explicit moderators 136</p>
<p>6.3 Existing research designs and analytic methods for investigating implicit moderators 142</p>
<p>7 Marginal mean weighting through stratification for investigating moderated treatment effects 159</p>
<p>7.1 Existing methods for moderation analyses with quasiexperimental data 159</p>
<p>7.2 MMWS estimation of treatment effects moderated by individual or contextual characteristics 168</p>
<p>7.3 MMWS estimation of the joint effects of concurrent treatments 174</p>
<p>8 Cumulative effects of time–varying treatments 185</p>
<p>8.1 Causal effects of treatment sequences 186</p>
<p>8.2 Existing strategies for evaluating time–varying treatments 190</p>
<p>8.3 MMWS for evaluating 2–year treatment sequences 195</p>
<p>8.4 MMWS for evaluating multiyear sequences of multivalued treatments 204</p>
<p>8.5 Conclusion 207</p>
<p>Part III Mediation 211</p>
<p>9 Concepts of mediated treatment effects and experimental designs for investigating causal mechanisms 213</p>
<p>9.1 Introduction 214</p>
<p>9.2 Path coefficients 215</p>
<p>9.3 Potential outcomes and potential mediators 216</p>
<p>9.4 Causal effects with counterfactual mediators 219</p>
<p>9.5 Population causal parameters 222</p>
<p>9.6 Experimental designs for studying causal mediation 225</p>
<p>10 Existing analytic methods for investigating causal mediation mechanisms 238</p>
<p>10.1 Path analysis and SEM 239</p>
<p>10.2 Modified regression approach 246</p>
<p>10.3 Marginal structural models 250</p>
<p>10.4 Conditional structural models 252</p>
<p>10.5 Alternative weighting methods 254</p>
<p>10.6 Resampling approach 256</p>
<p>10.7 IV method 257</p>
<p>10.8 Principal stratification 259</p>
<p>10.9 Sensitivity analysis 261</p>
<p>10.10 Conclusion 265</p>
<p>11 Investigations of a simple mediation mechanism 273</p>
<p>11.1 Application example: national evaluation of welfare–to–work strategies 274</p>
<p>11.2 RMPW rationale 277</p>
<p>11.3 Parametric RMPW procedure 287</p>
<p>11.4 Nonparametric RMPW procedure 290</p>
<p>11.5 Simulation results 292</p>
<p>11.6 Discussion 295</p>
<p>12 RMPW extensions to alternative designs and measurement 301</p>
<p>12.1 RMPW extensions to mediators and outcomes of alternative distributions 301</p>
<p>12.2 RMPW extensions to alternative research designs 306</p>
<p>12.3 Alternative decomposition of the treatment effect 321</p>
<p>13 RMPW extensions to studies of complex mediation mechanisms 325</p>
<p>13.1 RMPW extensions to moderated mediation 325</p>
<p>13.2 RMPW extensions to concurrent mediators 328</p>
<p>13.3 RMPW extensions to consecutive mediators 340</p>
<p>13.4 Discussion 355</p>
<p>Part IV Spill–over 363</p>
<p>14 Spill–over of treatment effects: concepts and methods 365</p>
<p>14.1 Spill–over: A nuisance, a trifle, or a focus? 365</p>
<p>14.2 Stable versus unstable potential outcome values: An example from agriculture 367</p>
<p>14.3 Consequences for causal inference when spill–over is overlooked 369</p>
<p>14.4 Modified framework of causal inference 371</p>
<p>14.5 Identification: Challenges and solutions 376</p>
<p>14.6 Analytic strategies for experimental and quasiexperimental data 384</p>
<p>14.7 Summary 387</p>
<p>15 Mediation through spill–over 391</p>
<p>15.1 Definition of mediated effects through spill–over in a cluster randomized trial 393</p>
<p>15.2 Identification and estimation of the spill–over effect in a cluster randomized design 395</p>
<p>15.3 Definition of mediated effects through spill–over in a multisite trial 402</p>
<p>15.4 Identification and estimation of spill–over effects in a multisite trial 406</p>
<p>15.5 Consequences of omitting spill–over effects in causal mediation analyses 412</p>
<p>15.6 Quasiexperimental application 416</p>
<p>15.7 Summary 419</p>
<p>Index 423</p>
<p>Part I Overview 1</p>
<p>1 Introduction 3</p>
<p>1.1 Concepts of moderation, mediation, and spill–over 3</p>
<p>1.2 Weighting methods for causal inference 10</p>
<p>1.3 Objectives and organization of the book 11</p>
<p>1.4 How is this book situated among other publications on related topics? 12</p>
<p>2 Review of causal inference concepts and methods 18</p>
<p>2.1 Causal inference theory 18</p>
<p>2.2 Applications to Lord s paradox and Simpson s paradox 27</p>
<p>2.3 Identification and estimation 34</p>
<p>3 Review of causal inference designs and analytic methods 40</p>
<p>3.1 Experimental designs 40</p>
<p>3.2 Quasiexperimental designs 44</p>
<p>3.3 Statistical adjustment methods 46</p>
<p>3.4 Propensity score 55</p>
<p>4 Adjustment for selection bias through weighting 76</p>
<p>4.1 Weighted estimation of population parameters in survey sampling 77</p>
<p>4.2 Weighting adjustment for selection bias in causal inference 80</p>
<p>4.3 MMWS 86</p>
<p>5 Evaluations of multivalued treatments 100</p>
<p>5.1 Defining the causal effects of multivalued treatments 100</p>
<p>5.2 Existing designs and analytic methods for evaluating multivalued treatments 102</p>
<p>5.3 MMWS for evaluating multivalued treatments 112</p>
<p>5.4 Summary 123</p>
<p>Part II Moderation 127</p>
<p>6 Moderated treatment effects: concepts and existing analytic methods 129</p>
<p>6.1 What is moderation? 129</p>
<p>6.2 Experimental designs and analytic methods for investigating explicit moderators 136</p>
<p>6.3 Existing research designs and analytic methods for investigating implicit moderators 142</p>
<p>7 Marginal mean weighting through stratification for investigating moderated treatment effects 159</p>
<p>7.1 Existing methods for moderation analyses with quasiexperimental data 159</p>
<p>7.2 MMWS estimation of treatment effects moderated by individual or contextual characteristics 168</p>
<p>7.3 MMWS estimation of the joint effects of concurrent treatments 174</p>
<p>8 Cumulative effects of time–varying treatments 185</p>
<p>8.1 Causal effects of treatment sequences 186</p>
<p>8.2 Existing strategies for evaluating time–varying treatments 190</p>
<p>8.3 MMWS for evaluating 2–year treatment sequences 195</p>
<p>8.4 MMWS for evaluating multiyear sequences of multivalued treatments 204</p>
<p>8.5 Conclusion 207</p>
<p>Part III Mediation 211</p>
<p>9 Concepts of mediated treatment effects and experimental designs for investigating causal mechanisms 213</p>
<p>9.1 Introduction 214</p>
<p>9.2 Path coefficients 215</p>
<p>9.3 Potential outcomes and potential mediators 216</p>
<p>9.4 Causal effects with counterfactual mediators 219</p>
<p>9.5 Population causal parameters 222</p>
<p>9.6 Experimental designs for studying causal mediation 225</p>
<p>10 Existing analytic methods for investigating causal mediation mechanisms 238</p>
<p>10.1 Path analysis and SEM 239</p>
<p>10.2 Modified regression approach 246</p>
<p>10.3 Marginal structural models 250</p>
<p>10.4 Conditional structural models 252</p>
<p>10.5 Alternative weighting methods 254</p>
<p>10.6 Resampling approach 256</p>
<p>10.7 IV method 257</p>
<p>10.8 Principal stratification 259</p>
<p>10.9 Sensitivity analysis 261</p>
<p>10.10 Conclusion 265</p>
<p>11 Investigations of a simple mediation mechanism 273</p>
<p>11.1 Application example: national evaluation of welfare–to–work strategies 274</p>
<p>11.2 RMPW rationale 277</p>
<p>11.3 Parametric RMPW procedure 287</p>
<p>11.4 Nonparametric RMPW procedure 290</p>
<p>11.5 Simulation results 292</p>
<p>11.6 Discussion 295</p>
<p>12 RMPW extensions to alternative designs and measurement 301</p>
<p>12.1 RMPW extensions to mediators and outcomes of alternative distributions 301</p>
<p>12.2 RMPW extensions to alternative research designs 306</p>
<p>12.3 Alternative decomposition of the treatment effect 321</p>
<p>13 RMPW extensions to studies of complex mediation mechanisms 325</p>
<p>13.1 RMPW extensions to moderated mediation 325</p>
<p>13.2 RMPW extensions to concurrent mediators 328</p>
<p>13.3 RMPW extensions to consecutive mediators 340</p>
<p>13.4 Discussion 355</p>
<p>Part IV Spill–over 363</p>
<p>14 Spill–over of treatment effects: concepts and methods 365</p>
<p>14.1 Spill–over: A nuisance, a trifle, or a focus? 365</p>
<p>14.2 Stable versus unstable potential outcome values: An example from agriculture 367</p>
<p>14.3 Consequences for causal inference when spill–over is overlooked 369</p>
<p>14.4 Modified framework of causal inference 371</p>
<p>14.5 Identification: Challenges and solutions 376</p>
<p>14.6 Analytic strategies for experimental and quasiexperimental data 384</p>
<p>14.7 Summary 387</p>
<p>15 Mediation through spill–over 391</p>
<p>15.1 Definition of mediated effects through spill–over in a cluster randomized trial 393</p>
<p>15.2 Identification and estimation of the spill–over effect in a cluster randomized design 395</p>
<p>15.3 Definition of mediated effects through spill–over in a multisite trial 402</p>
<p>15.4 Identification and estimation of spill–over effects in a multisite trial 406</p>
<p>15.5 Consequences of omitting spill–over effects in causal mediation analyses 412</p>
<p>15.6 Quasiexperimental application 416</p>
<p>15.7 Summary 419</p>
<p>Index 423</p>