{"product_id":"causality-9780470665565","title":"Causality","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003e\u003cp\u003e\u003cb\u003eA state of the art volume on statistical causality\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003ci\u003eCausality: Statistical Perspectives and Applications\u003c\/i\u003e presents a wide-ranging collection of seminal contributions by renowned experts in the field, providing a thorough treatment of all aspects of statistical causality. It covers the various formalisms in current use, methods for applying them to specific problems, and the special requirements of a range of examples from medicine, biology and economics to political science.\u003c\/p\u003e \u003cp\u003eThis book:\u003c\/p\u003e \u003cul\u003e \u003cli\u003eProvides a clear account and comparison of formal languages, concepts and models for statistical causality.\u003c\/li\u003e \u003cli\u003eAddresses examples from medicine, biology, economics and political science to aid the reader''s understanding.\u003c\/li\u003e \u003cli\u003eIs authored by leading experts in their field.\u003c\/li\u003e \u003cli\u003eIs written in an accessible style.\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003ePostgraduates, professional statisticians and researchers in academia and industry will benefit from this book.\u003c\/p\u003e\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003e\u003cp\u003eList of contributors xv\u003c\/p\u003e \u003cp\u003e\u003cb\u003eAn overview of statistical causality xvii\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eCarlo Berzuini, Philip Dawid and Luisa Bernardinelli\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 Statistical causality: Some historical remarks 1\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eD.R. Cox\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e1.1 Introduction 1\u003c\/p\u003e \u003cp\u003e1.2 Key issues 2\u003c\/p\u003e \u003cp\u003e1.3 Rothamsted view 2\u003c\/p\u003e \u003cp\u003e1.4 An earlier controversy and its implications 3\u003c\/p\u003e \u003cp\u003e1.5 Three versions of causality 4\u003c\/p\u003e \u003cp\u003e1.6 Conclusion 4\u003c\/p\u003e \u003cp\u003eReferences 4\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 The language of potential outcomes 6\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eArvid Sjölander\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e2.1 Introduction 6\u003c\/p\u003e \u003cp\u003e2.2 Definition of causal effects through potential outcomes 7\u003c\/p\u003e \u003cp\u003e2.2.1 Subject-specific causal effects 7\u003c\/p\u003e \u003cp\u003e2.2.2 Population causal effects 8\u003c\/p\u003e \u003cp\u003e2.2.3 Association versus causation 9\u003c\/p\u003e \u003cp\u003e2.3 Identification of population causal effects 9\u003c\/p\u003e \u003cp\u003e2.3.1 Randomized experiments 9\u003c\/p\u003e \u003cp\u003e2.3.2 Observational studies 11\u003c\/p\u003e \u003cp\u003e2.4 Discussion 11\u003c\/p\u003e \u003cp\u003eReferences 13\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Structural equations, graphs and interventions 15\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eIlya Shpitser\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e3.1 Introduction 15\u003c\/p\u003e \u003cp\u003e3.2 Structural equations, graphs, and interventions 16\u003c\/p\u003e \u003cp\u003e3.2.1 Graph terminology 16\u003c\/p\u003e \u003cp\u003e3.2.2 Markovian models 17\u003c\/p\u003e \u003cp\u003e3.2.3 Latent projections and semi-Markovian models 19\u003c\/p\u003e \u003cp\u003e3.2.4 Interventions in semi-Markovian models 19\u003c\/p\u003e \u003cp\u003e3.2.5 Counterfactual distributions in NPSEMs 20\u003c\/p\u003e \u003cp\u003e3.2.6 Causal diagrams and counterfactual independence 22\u003c\/p\u003e \u003cp\u003e3.2.7 Relation to potential outcomes 22\u003c\/p\u003e \u003cp\u003eReferences 23\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 The decision-theoretic approach to causal inference 25\u003cbr\u003e \u003c\/b\u003e\u003ci\u003ePhilip Dawid\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e4.1 Introduction 25\u003c\/p\u003e \u003cp\u003e4.2 Decision theory and causality 26\u003c\/p\u003e \u003cp\u003e4.2.1 A simple decision problem 26\u003c\/p\u003e \u003cp\u003e4.2.2 Causal inference 27\u003c\/p\u003e \u003cp\u003e4.3 No confounding 28\u003c\/p\u003e \u003cp\u003e4.4 Confounding 29\u003c\/p\u003e \u003cp\u003e4.4.1 Unconfounding 29\u003c\/p\u003e \u003cp\u003e4.4.2 Nonconfounding 30\u003c\/p\u003e \u003cp\u003e4.4.3 Back-door formula 31\u003c\/p\u003e \u003cp\u003e4.5 Propensity analysis 33\u003c\/p\u003e \u003cp\u003e4.6 Instrumental variable 34\u003c\/p\u003e \u003cp\u003e4.6.1 Linear model 36\u003c\/p\u003e \u003cp\u003e4.6.2 Binary variables 36\u003c\/p\u003e \u003cp\u003e4.7 Effect of treatment of the treated 37\u003c\/p\u003e \u003cp\u003e4.8 Connections and contrasts 37\u003c\/p\u003e \u003cp\u003e4.8.1 Potential responses 37\u003c\/p\u003e \u003cp\u003e4.8.2 Causal graphs 39\u003c\/p\u003e \u003cp\u003e4.9 Postscript 40\u003c\/p\u003e \u003cp\u003eAcknowledgements 40\u003c\/p\u003e \u003cp\u003eReferences 40\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Causal inference as a prediction problem: Assumptions, identification and evidence synthesis 43\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eSander Greenland\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e5.1 Introduction 43\u003c\/p\u003e \u003cp\u003e5.2 A brief commentary on developments since 1970 44\u003c\/p\u003e \u003cp\u003e5.2.1 Potential outcomes and missing data 45\u003c\/p\u003e \u003cp\u003e5.2.2 The prognostic view 45\u003c\/p\u003e \u003cp\u003e5.3 Ambiguities of observational extensions 46\u003c\/p\u003e \u003cp\u003e5.4 Causal diagrams and structural equations 47\u003c\/p\u003e \u003cp\u003e5.5 Compelling versus plausible assumptions, models and inferences 47\u003c\/p\u003e \u003cp\u003e5.6 Nonidentification and the curse of dimensionality 50\u003c\/p\u003e \u003cp\u003e5.7 Identification in practice 51\u003c\/p\u003e \u003cp\u003e5.8 Identification and bounded rationality 53\u003c\/p\u003e \u003cp\u003e5.9 Conclusion 54\u003c\/p\u003e \u003cp\u003eAcknowledgments 55\u003c\/p\u003e \u003cp\u003eReferences 55\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 Graph-based criteria of identifiability of causal questions 59\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eIlya Shpitser\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e6.1 Introduction 59\u003c\/p\u003e \u003cp\u003e6.2 Interventions from observations 59\u003c\/p\u003e \u003cp\u003e6.3 The back-door criterion, conditional ignorability, and covariate adjustment 61\u003c\/p\u003e \u003cp\u003e6.4 The front-door criterion 63\u003c\/p\u003e \u003cp\u003e6.5 Do-calculus 64\u003c\/p\u003e \u003cp\u003e6.6 General identification 65\u003c\/p\u003e \u003cp\u003e6.7 Dormant independences and post-truncation constraints 68\u003c\/p\u003e \u003cp\u003eReferences 69\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Causal inference from observational data: A Bayesian predictive approach 71\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eElja Arjas\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e7.1 Background 71\u003c\/p\u003e \u003cp\u003e7.2 A model prototype 72\u003c\/p\u003e \u003cp\u003e7.3 Extension to sequential regimes 76\u003c\/p\u003e \u003cp\u003e7.4 Providing a causal interpretation: Predictive inference from data 80\u003c\/p\u003e \u003cp\u003e7.5 Discussion 82\u003c\/p\u003e \u003cp\u003eAcknowledgement 83\u003c\/p\u003e \u003cp\u003eReferences 83\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 Assessing dynamic treatment strategies 85\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eCarlo Berzuini, Philip Dawid, and Vanessa Didelez\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e8.1 Introduction 85\u003c\/p\u003e \u003cp\u003e8.2 Motivating example 86\u003c\/p\u003e \u003cp\u003e8.3 Descriptive versus causal inference 87\u003c\/p\u003e \u003cp\u003e8.4 Notation and problem definition 88\u003c\/p\u003e \u003cp\u003e8.5 HIV example continued 89\u003c\/p\u003e \u003cp\u003e8.6 Latent variables 89\u003c\/p\u003e \u003cp\u003e8.7 Conditions for sequential plan identifiability 90\u003c\/p\u003e \u003cp\u003e8.7.1 Stability 90\u003c\/p\u003e \u003cp\u003e8.7.2 Positivity 91\u003c\/p\u003e \u003cp\u003e8.8 Graphical representations of dynamic plans 92\u003c\/p\u003e \u003cp\u003e8.9 Abdominal aortic aneurysm surveillance 94\u003c\/p\u003e \u003cp\u003e8.10 Statistical inference and computation 95\u003c\/p\u003e \u003cp\u003e8.11 Transparent actions 97\u003c\/p\u003e \u003cp\u003e8.12 Refinements 98\u003c\/p\u003e \u003cp\u003e8.13 Discussion 99\u003c\/p\u003e \u003cp\u003eAcknowledgements 99\u003c\/p\u003e \u003cp\u003eReferences 99\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 Causal effects and natural laws: Towards a conceptualization of causal counterfactuals for nonmanipulable exposures, with application to the effects of race and sex 101\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eTyler J. VanderWeele and Miguel A. Hernán\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e9.1 Introduction 101\u003c\/p\u003e \u003cp\u003e9.2 Laws of nature and contrary to fact statements 102\u003c\/p\u003e \u003cp\u003e9.3 Association and causation in the social and biomedical sciences 103\u003c\/p\u003e \u003cp\u003e9.4 Manipulation and counterfactuals 103\u003c\/p\u003e \u003cp\u003e9.5 Natural laws and causal effects 104\u003c\/p\u003e \u003cp\u003e9.6 Consequences of randomization 107\u003c\/p\u003e \u003cp\u003e9.7 On the causal effects of sex and race 108\u003c\/p\u003e \u003cp\u003e9.8 Discussion 111\u003c\/p\u003e \u003cp\u003eAcknowledgements 112\u003c\/p\u003e \u003cp\u003eReferences 112\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 Cross-classifications by joint potential outcomes 114\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eArvid Sjölander\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e10.1 Introduction 114\u003c\/p\u003e \u003cp\u003e10.2 Bounds for the causal treatment effect in randomized trials with imperfect compliance 115\u003c\/p\u003e \u003cp\u003e10.3 Identifying the complier causal effect in randomized trials with imperfect compliance 119\u003c\/p\u003e \u003cp\u003e10.4 Defining the appropriate causal effect in studies suffering from truncation by death 121\u003c\/p\u003e \u003cp\u003e10.5 Discussion 123\u003c\/p\u003e \u003cp\u003eReferences 124\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 Estimation of direct and indirect effects 126\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eStijn Vansteelandt\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e11.1 Introduction 126\u003c\/p\u003e \u003cp\u003e11.2 Identification of the direct and indirect effect 127\u003c\/p\u003e \u003cp\u003e11.2.1 Definitions 127\u003c\/p\u003e \u003cp\u003e11.2.2 Identification 129\u003c\/p\u003e \u003cp\u003e11.3 Estimation of controlled direct effects 132\u003c\/p\u003e \u003cp\u003e11.3.1 G-computation 132\u003c\/p\u003e \u003cp\u003e11.3.2 Inverse probability of treatment weighting 133\u003c\/p\u003e \u003cp\u003e11.3.3 G-estimation for additive and multiplicative models 137\u003c\/p\u003e \u003cp\u003e11.3.4 G-estimation for logistic models 141\u003c\/p\u003e \u003cp\u003e11.3.5 Case-control studies 142\u003c\/p\u003e \u003cp\u003e11.3.6 G-estimation for additive hazard models 143\u003c\/p\u003e \u003cp\u003e11.4 Estimation of natural direct and indirect effects 146\u003c\/p\u003e \u003cp\u003e11.5 Discussion 147\u003c\/p\u003e \u003cp\u003eAcknowledgements 147\u003c\/p\u003e \u003cp\u003eReferences 148\u003c\/p\u003e \u003cp\u003e\u003cb\u003e12 The mediation formula: A guide to the assessment of causal pathways in nonlinear models 151\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eJudea Pearl\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e12.1 Mediation: Direct and indirect effects 151\u003c\/p\u003e \u003cp\u003e12.1.1 Direct versus total effects 151\u003c\/p\u003e \u003cp\u003e12.1.2 Controlled direct effects 152\u003c\/p\u003e \u003cp\u003e12.1.3 Natural direct effects 154\u003c\/p\u003e \u003cp\u003e12.1.4 Indirect effects 156\u003c\/p\u003e \u003cp\u003e12.1.5 Effect decomposition 157\u003c\/p\u003e \u003cp\u003e12.2 The mediation formula: A simple solution to a thorny problem 157\u003c\/p\u003e \u003cp\u003e12.2.1 Mediation in nonparametric models 157\u003c\/p\u003e \u003cp\u003e12.2.2 Mediation effects in linear, logistic, and probit models 159\u003c\/p\u003e \u003cp\u003e12.2.3 Special cases of mediation models 164\u003c\/p\u003e \u003cp\u003e12.2.4 Numerical example 169\u003c\/p\u003e \u003cp\u003e12.3 Relation to other methods 170\u003c\/p\u003e \u003cp\u003e12.3.1 Methods based on differences and products 170\u003c\/p\u003e \u003cp\u003e12.3.2 Relation to the principal-strata direct effect 171\u003c\/p\u003e \u003cp\u003e12.4 Conclusions 173\u003c\/p\u003e \u003cp\u003eAcknowledgments 174\u003c\/p\u003e \u003cp\u003eReferences 175\u003c\/p\u003e \u003cp\u003e\u003cb\u003e13 The sufficient cause framework in statistics, philosophy and the biomedical and social sciences 180\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eTyler J. VanderWeele\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e13.1 Introduction 180\u003c\/p\u003e \u003cp\u003e13.2 The sufficient cause framework in philosophy 181\u003c\/p\u003e \u003cp\u003e13.3 The sufficient cause framework in epidemiology and biomedicine 181\u003c\/p\u003e \u003cp\u003e13.4 The sufficient cause framework in statistics 185\u003c\/p\u003e \u003cp\u003e13.5 The sufficient cause framework in the social sciences 185\u003c\/p\u003e \u003cp\u003e13.6 Other notions of sufficiency and necessity in causal inference 187\u003c\/p\u003e \u003cp\u003e13.7 Conclusion 188\u003c\/p\u003e \u003cp\u003eAcknowledgements 189\u003c\/p\u003e \u003cp\u003eReferences 189\u003c\/p\u003e \u003cp\u003e\u003cb\u003e14 Analysis of interaction for identifying causal mechanisms 192\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eCarlo Berzuini, Philip Dawid, Hu Zhang and Miles Parkes\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e14.1 Introduction 192\u003c\/p\u003e \u003cp\u003e14.2 What is a mechanism? 193\u003c\/p\u003e \u003cp\u003e14.3 Statistical versus mechanistic interaction 193\u003c\/p\u003e \u003cp\u003e14.4 Illustrative example 194\u003c\/p\u003e \u003cp\u003e14.5 Mechanistic interaction defined 196\u003c\/p\u003e \u003cp\u003e14.6 Epistasis 197\u003c\/p\u003e \u003cp\u003e14.7 Excess risk and superadditivity 197\u003c\/p\u003e \u003cp\u003e14.8 Conditions under which excess risk and superadditivity indicate the presence of mechanistic interaction 200\u003c\/p\u003e \u003cp\u003e14.9 Collapsibility 201\u003c\/p\u003e \u003cp\u003e14.10 Back to the illustrative study 202\u003c\/p\u003e \u003cp\u003e14.11 Alternative approaches 204\u003c\/p\u003e \u003cp\u003e14.12 Discussion 204\u003c\/p\u003e \u003cp\u003eEthics statement 205\u003c\/p\u003e \u003cp\u003eFinancial disclosure 205\u003c\/p\u003e \u003cp\u003eReferences 206\u003c\/p\u003e \u003cp\u003e\u003cb\u003e15 Ion channels as a possible mechanism of neurodegeneration in multiple sclerosis 208\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eLuisa Bernardinelli, Carlo Berzuini, Luisa Foco, and Roberta Pastorino\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e15.1 Introduction 208\u003c\/p\u003e \u003cp\u003e15.2 Background 209\u003c\/p\u003e \u003cp\u003e15.3 The scientific hypothesis 209\u003c\/p\u003e \u003cp\u003e15.4 Data 210\u003c\/p\u003e \u003cp\u003e15.5 A simple preliminary analysis 211\u003c\/p\u003e \u003cp\u003e15.6 Testing for qualitative interaction 213\u003c\/p\u003e \u003cp\u003e15.7 Discussion 214\u003c\/p\u003e \u003cp\u003eAcknowledgments 216\u003c\/p\u003e \u003cp\u003eReferences 216\u003c\/p\u003e \u003cp\u003e\u003cb\u003e16 Supplementary variables for causal estimation 218\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eRoland R. Ramsahai\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e16.1 Introduction 218\u003c\/p\u003e \u003cp\u003e16.2 Multiple expressions for causal effect 220\u003c\/p\u003e \u003cp\u003e16.3 Asymptotic variance of causal estimators 222\u003c\/p\u003e \u003cp\u003e16.4 Comparison of causal estimators 222\u003c\/p\u003e \u003cp\u003e16.4.1 Supplement C with L or not 223\u003c\/p\u003e \u003cp\u003e16.4.2 Supplement L with C or not 224\u003c\/p\u003e \u003cp\u003e16.4.3 Replace C with L or not 225\u003c\/p\u003e \u003cp\u003e16.5 Discussion 226\u003c\/p\u003e \u003cp\u003eAcknowledgements 226\u003c\/p\u003e \u003cp\u003eAppendices 227\u003c\/p\u003e \u003cp\u003e16.A Estimator given all X’s recorded 227\u003c\/p\u003e \u003cp\u003e16.B Derivations of asymptotic variances 227\u003c\/p\u003e \u003cp\u003e16.C Expressions with correlation coefficients 229\u003c\/p\u003e \u003cp\u003e16.D Derivation of I’s 230\u003c\/p\u003e \u003cp\u003e16.E Relation between ρ2 rl|t and ρ2 rl|c 231\u003c\/p\u003e \u003cp\u003eReferences 232\u003c\/p\u003e \u003cp\u003e\u003cb\u003e17 Time-varying confounding: Some practical considerations in a likelihood framework 234\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eRhian Daniel, Bianca De Stavola and Simon Cousens\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e17.1 Introduction 234\u003c\/p\u003e \u003cp\u003e17.2 General setting 235\u003c\/p\u003e \u003cp\u003e17.2.1 Notation 235\u003c\/p\u003e \u003cp\u003e17.2.2 Observed data structure 235\u003c\/p\u003e \u003cp\u003e17.2.3 Intervention strategies 236\u003c\/p\u003e \u003cp\u003e17.2.4 Potential outcomes 237\u003c\/p\u003e \u003cp\u003e17.2.5 Time-to-event outcomes 237\u003c\/p\u003e \u003cp\u003e17.2.6 Causal estimands 238\u003c\/p\u003e \u003cp\u003e17.3 Identifying assumptions 238\u003c\/p\u003e \u003cp\u003e17.4 G-computation formula 239\u003c\/p\u003e \u003cp\u003e17.4.1 The formula 239\u003c\/p\u003e \u003cp\u003e17.4.2 Plug-in regression estimation 240\u003c\/p\u003e \u003cp\u003e17.5 Implementation by Monte Carlo simulation 242\u003c\/p\u003e \u003cp\u003e17.5.1 Simulating an end-of-study outcome 242\u003c\/p\u003e \u003cp\u003e17.5.2 Simulating a time-to-event outcome 242\u003c\/p\u003e \u003cp\u003e17.5.3 Inference 242\u003c\/p\u003e \u003cp\u003e17.5.4 Losses to follow-up 243\u003c\/p\u003e \u003cp\u003e17.5.5 Software 243\u003c\/p\u003e \u003cp\u003e17.6 Analyses of simulated data 243\u003c\/p\u003e \u003cp\u003e17.6.1 The data 243\u003c\/p\u003e \u003cp\u003e17.6.2 Regimes to be compared 244\u003c\/p\u003e \u003cp\u003e17.6.3 Parametric modelling choices 245\u003c\/p\u003e \u003cp\u003e17.6.4 Results 246\u003c\/p\u003e \u003cp\u003e17.7 Further considerations 249\u003c\/p\u003e \u003cp\u003e17.7.1 Parametric model misspecification 249\u003c\/p\u003e \u003cp\u003e17.7.2 Competing events 249\u003c\/p\u003e \u003cp\u003e17.7.3 Unbalanced measurement times 250\u003c\/p\u003e \u003cp\u003e17.8 Summary 251\u003c\/p\u003e \u003cp\u003eReferences 251\u003c\/p\u003e \u003cp\u003e\u003cb\u003e18 ‘Natural experiments’ as a means of testing causal inferences 253\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eMichael Rutter\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e18.1 Introduction 253\u003c\/p\u003e \u003cp\u003e18.2 Noncausal interpretations of an association 253\u003c\/p\u003e \u003cp\u003e18.3 Dealing with confounders 255\u003c\/p\u003e \u003cp\u003e18.4 ‘Natural experiments’ 256\u003c\/p\u003e \u003cp\u003e18.4.1 Genetically sensitive designs 257\u003c\/p\u003e \u003cp\u003e18.4.2 Children of twins (CoT) design 259\u003c\/p\u003e \u003cp\u003e18.4.3 Strategies to identify the key environmental risk feature 261\u003c\/p\u003e \u003cp\u003e18.4.4 Designs for dealing with selection bias 263\u003c\/p\u003e \u003cp\u003e18.4.5 Instrumental variables to rule out reverse causation 264\u003c\/p\u003e \u003cp\u003e18.4.6 Regression discontinuity (RD) designs to deal with unmeasured confounders 265\u003c\/p\u003e \u003cp\u003e18.5 Overall conclusion on ‘natural experiments’ 266\u003c\/p\u003e \u003cp\u003e18.5.1 Supported causes 266\u003c\/p\u003e \u003cp\u003e18.5.2 Disconfirmed causes 267\u003c\/p\u003e \u003cp\u003eAcknowledgement 267\u003c\/p\u003e \u003cp\u003eReferences 268\u003c\/p\u003e \u003cp\u003e\u003cb\u003e19 Nonreactive and purely reactive doses in observational studies 273\u003cbr\u003e \u003c\/b\u003e\u003ci\u003ePaul R. Rosenbaum\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e19.1 Introduction: Background, example 273\u003c\/p\u003e \u003cp\u003e19.1.1 Does a dose–response relationship provide information that distinguishes treatment effects from biases due to unmeasured covariates? 273\u003c\/p\u003e \u003cp\u003e19.1.2 Is more chemotherapy for ovarian cancer more effective or more toxic? 274\u003c\/p\u003e \u003cp\u003e19.2 Various concepts of dose 277\u003c\/p\u003e \u003cp\u003e19.2.1 Some notation: Covariates, outcomes, and treatment assignment in matched pairs 277\u003c\/p\u003e \u003cp\u003e19.2.2 Reactive and nonreactive doses of treatment 278\u003c\/p\u003e \u003cp\u003e19.2.3 Three test statistics that use doses in different ways 279\u003c\/p\u003e \u003cp\u003e19.2.4 Randomization inference in randomized experiments 280\u003c\/p\u003e \u003cp\u003e19.2.5 Sensitivity analysis 281\u003c\/p\u003e \u003cp\u003e19.2.6 Sensitivity analysis in the example 283\u003c\/p\u003e \u003cp\u003e19.3 Design sensitivity 284\u003c\/p\u003e \u003cp\u003e19.3.1 What is design sensitivity? 284\u003c\/p\u003e \u003cp\u003e19.3.2 Comparison of design sensitivity with purely reactive doses 286\u003c\/p\u003e \u003cp\u003e19.4 Summary 287\u003c\/p\u003e \u003cp\u003eReferences 287\u003c\/p\u003e \u003cp\u003e\u003cb\u003e20 Evaluation of potential mediators in randomised trials of complex interventions (psychotherapies) 290\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eRichard Emsley and Graham Dunn\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e20.1 Introduction 290\u003c\/p\u003e \u003cp\u003e20.2 Potential mediators in psychological treatment trials 291\u003c\/p\u003e \u003cp\u003e20.3 Methods for mediation in psychological treatment trials 293\u003c\/p\u003e \u003cp\u003e20.4 Causal mediation analysis using instrumental variables estimation 297\u003c\/p\u003e \u003cp\u003e20.5 Causal mediation analysis using principal stratification 301\u003c\/p\u003e \u003cp\u003e20.6 Our motivating example: The SoCRATES trial 302\u003c\/p\u003e \u003cp\u003e20.6.1 What are the joint effects of sessions attended and therapeutic alliance on the PANSS score at 18 months? 303\u003c\/p\u003e \u003cp\u003e20.6.2 What is the direct effect of random allocation on the PANSS score at 18 months and how is this influenced by the therapeutic alliance? 304\u003c\/p\u003e \u003cp\u003e20.6.3 Is the direct effect of the number of sessions attended on the PANSS score at 18 months influenced by therapeutic alliance? 305\u003c\/p\u003e \u003cp\u003e20.7 Conclusions 305\u003c\/p\u003e \u003cp\u003eAcknowledgements 306\u003c\/p\u003e \u003cp\u003eReferences 307\u003c\/p\u003e \u003cp\u003e\u003cb\u003e21 Causal inference in clinical trials 310\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eKrista Fischer and Ian R. White\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e21.1 Introduction 310\u003c\/p\u003e \u003cp\u003e21.2 Causal effect of treatment in randomized trials 312\u003c\/p\u003e \u003cp\u003e21.2.1 Observed data and notation 312\u003c\/p\u003e \u003cp\u003e21.2.2 Defining the effects of interest via potential outcomes 312\u003c\/p\u003e \u003cp\u003e21.2.3 Adherence-adjusted ITT analysis 314\u003c\/p\u003e \u003cp\u003e21.3 Estimation for a linear structural mean model 316\u003c\/p\u003e \u003cp\u003e21.3.1 A general estimation procedure 316\u003c\/p\u003e \u003cp\u003e21.3.2 Identifiability and closed-form estimation of the parameters in a linear SMM 317\u003c\/p\u003e \u003cp\u003e21.3.3 Analysis of the EPHT trial 319\u003c\/p\u003e \u003cp\u003e21.4 Alternative approaches for causal inference in randomized trials comparing experimental treatment with a control 321\u003c\/p\u003e \u003cp\u003e21.4.1 Principal stratification 321\u003c\/p\u003e \u003cp\u003e21.4.2 SMM for the average treatment effect on the treated (ATT) 322\u003c\/p\u003e \u003cp\u003e21.5 Discussion 324\u003c\/p\u003e \u003cp\u003eReferences 325\u003c\/p\u003e \u003cp\u003e\u003cb\u003e22 Causal inference in time series analysis 327\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eMichael Eichler\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e22.1 Introduction 327\u003c\/p\u003e \u003cp\u003e22.2 Causality for time series 328\u003c\/p\u003e \u003cp\u003e22.2.1 Intervention causality 328\u003c\/p\u003e \u003cp\u003e22.2.2 Structural causality 331\u003c\/p\u003e \u003cp\u003e22.2.3 Granger causality 332\u003c\/p\u003e \u003cp\u003e22.2.4 Sims causality 334\u003c\/p\u003e \u003cp\u003e22.3 Graphical representations for time series 335\u003c\/p\u003e \u003cp\u003e22.3.1 Conditional distributions and chain graphs 336\u003c\/p\u003e \u003cp\u003e22.3.2 Path diagrams and Granger causality graphs 337\u003c\/p\u003e \u003cp\u003e22.3.3 Markov properties for Granger causality graphs 338\u003c\/p\u003e \u003cp\u003e22.4 Representation of systems with latent variables 339\u003c\/p\u003e \u003cp\u003e22.4.1 Marginalization 341\u003c\/p\u003e \u003cp\u003e22.4.2 Ancestral graphs 342\u003c\/p\u003e \u003cp\u003e22.5 Identification of causal effects 343\u003c\/p\u003e \u003cp\u003e22.6 Learning causal structures 346\u003c\/p\u003e \u003cp\u003e22.7 A new parametric model 349\u003c\/p\u003e \u003cp\u003e22.8 Concluding remarks 351\u003c\/p\u003e \u003cp\u003eReferences 352\u003c\/p\u003e \u003cp\u003e\u003cb\u003e23 Dynamic molecular networks and mechanisms in the biosciences: A statistical framework 355\u003cbr\u003e \u003c\/b\u003e\u003ci\u003eClive G. Bowsher\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e23.1 Introduction 355\u003c\/p\u003e \u003cp\u003e23.2 SKMs and biochemical reaction networks 356\u003c\/p\u003e \u003cp\u003e23.3 Local independence properties of SKMs 358\u003c\/p\u003e \u003cp\u003e23.3.1 Local independence and kinetic independence graphs 358\u003c\/p\u003e \u003cp\u003e23.3.2 Local independence and causal influence 361\u003c\/p\u003e \u003cp\u003e23.4 Modularisation of SKMs 362\u003c\/p\u003e \u003cp\u003e23.4.1 Modularisations and dynamic independence 362\u003c\/p\u003e \u003cp\u003e23.4.2 MIDIA Algorithm 363\u003c\/p\u003e \u003cp\u003e23.5 Illustrative example – MAPK cell signalling 365\u003c\/p\u003e \u003cp\u003e23.6 Conclusion 369\u003c\/p\u003e \u003cp\u003e23.7 Appendix: SKM regularity conditions 369\u003c\/p\u003e \u003cp\u003eAcknowledgements 370\u003c\/p\u003e \u003cp\u003eReferences 370\u003c\/p\u003e \u003cp\u003eIndex 371\u003c\/p\u003e","brand":"John Wiley \u0026 Sons Inc","offers":[{"title":"Default Title","offer_id":49525385593175,"sku":"9780470665565","price":67.95,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0817\/1739\/5799\/files\/9780470665565.jpg?v=1731860316","url":"https:\/\/bookcurl.com\/products\/causality-9780470665565","provider":"Book Curl","version":"1.0","type":"link"}