{"product_id":"network-metaanalysis-for-decisionmaking-9781118647509","title":"Network MetaAnalysis for DecisionMaking","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003eA practical guide to network meta-analysis with examples and code    In the evaluation of healthcare, rigorous methods of quantitative assessment are necessary to establish which interventions are effective and cost-effective.\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003e\u003cp\u003ePreface xiii\u003c\/p\u003e \u003cp\u003eList of Abbreviations xxi\u003c\/p\u003e \u003cp\u003eAbout the Companion Website xxv\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 Introduction to Evidence Synthesis 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e1.1 Introduction 1\u003c\/p\u003e \u003cp\u003e1.2 Why Indirect Comparisons and Network Meta-Analysis? 2\u003c\/p\u003e \u003cp\u003e1.3 Some Simple Methods 4\u003c\/p\u003e \u003cp\u003e1.4 An Example of a Network Meta-Analysis 6\u003c\/p\u003e \u003cp\u003e1.5 Assumptions Made by Indirect Comparisons and Network Meta-Analysis 9\u003c\/p\u003e \u003cp\u003e1.6 Which Trials to Include in a Network 12\u003c\/p\u003e \u003cp\u003e1.6.1 The Need for a Unique Set of Trials 12\u003c\/p\u003e \u003cp\u003e1.7 The Definition of Treatments and Outcomes: Network Connectivity 14\u003c\/p\u003e \u003cp\u003e1.7.1 Lumping and Splitting 14\u003c\/p\u003e \u003cp\u003e1.7.2 Relationships Between Multiple Outcomes 15\u003c\/p\u003e \u003cp\u003e1.7.3 How Large Should a Network Be? 15\u003c\/p\u003e \u003cp\u003e1.8 Summary 16\u003c\/p\u003e \u003cp\u003e1.9 Exercises 16\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 The Core Model 19\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e2.1 Bayesian Meta-Analysis 19\u003c\/p\u003e \u003cp\u003e2.2 Development of the Core Models 20\u003c\/p\u003e \u003cp\u003e2.2.1 Worked Example: Meta-Analysis of Binomial Data 21\u003c\/p\u003e \u003cp\u003e2.2.1.1 Model Specification: Two Treatments 21\u003c\/p\u003e \u003cp\u003e2.2.1.2 WinBUGS Implementation: Two Treatments 25\u003c\/p\u003e \u003cp\u003e2.2.2 Extension to Indirect Comparisons and Network Meta-Analysis 32\u003c\/p\u003e \u003cp\u003e2.2.2.1 Incorporating Multi-Arm Trials 35\u003c\/p\u003e \u003cp\u003e2.2.3 Worked Example: Network Meta-Analysis 36\u003c\/p\u003e \u003cp\u003e2.2.3.1 WinBUGS Implementation 37\u003c\/p\u003e \u003cp\u003e2.3 Technical Issues in Network Meta-Analysis 50\u003c\/p\u003e \u003cp\u003e2.3.1 Choice of Reference Treatment 50\u003c\/p\u003e \u003cp\u003e2.3.2 Choice of Prior Distributions 51\u003c\/p\u003e \u003cp\u003e2.3.3 Choice of Scale 53\u003c\/p\u003e \u003cp\u003e2.3.4 Connected Networks 54\u003c\/p\u003e \u003cp\u003e2.4 Advantages of a Bayesian Approach 55\u003c\/p\u003e \u003cp\u003e2.5 Summary of Key Points and Further Reading 56\u003c\/p\u003e \u003cp\u003e2.6 Exercises 57\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Model Fit, Model Comparison and Outlier Detection 59\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e3.1 Introduction 59\u003c\/p\u003e \u003cp\u003e3.2 Assessing Model Fit 60\u003c\/p\u003e \u003cp\u003e3.2.1 Deviance 60\u003c\/p\u003e \u003cp\u003e3.2.2 Residual Deviance 61\u003c\/p\u003e \u003cp\u003e3.2.3 Zero Counts* 62\u003c\/p\u003e \u003cp\u003e3.2.4 Worked Example: Full Thrombolytic Treatments Network 62\u003c\/p\u003e \u003cp\u003e3.2.4.1 Posterior Mean Deviance, D̅model 62\u003c\/p\u003e \u003cp\u003e3.2.4.2 Posterior Mean Residual Deviance, D̅res 64\u003c\/p\u003e \u003cp\u003e3.3 Model Comparison 66\u003c\/p\u003e \u003cp\u003e3.3.1 Effective Number of Parameters, pD 68\u003c\/p\u003e \u003cp\u003e3.3.2 Deviance Information Criterion (DIC) 69\u003c\/p\u003e \u003cp\u003e3.3.2.1 *Leverage Plots 70\u003c\/p\u003e \u003cp\u003e3.3.3 Worked Example: Full Thrombolytic Treatments Network 70\u003c\/p\u003e \u003cp\u003e3.4 Outlier Detection in Network Meta-Analysis 75\u003c\/p\u003e \u003cp\u003e3.4.1 Outlier Detection in Pairwise Meta-Analysis 75\u003c\/p\u003e \u003cp\u003e3.4.2 Predictive Cross-Validation for Network Meta-Analysis 79\u003c\/p\u003e \u003cp\u003e3.4.3 Note on Multi-Arm Trials 85\u003c\/p\u003e \u003cp\u003e3.4.4 WinBUGS Code: Predictive Cross-Validation for Network Meta-Analysis 86\u003c\/p\u003e \u003cp\u003e3.5 Summary and Further Reading 89\u003c\/p\u003e \u003cp\u003e3.6 Exercises 90\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Generalised Linear Models 93\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e4.1 A Unified Framework for Evidence Synthesis 93\u003c\/p\u003e \u003cp\u003e4.2 The Generic Network Meta-Analysis Models 94\u003c\/p\u003e \u003cp\u003e4.3 Univariate Arm-Based Likelihoods 99\u003c\/p\u003e \u003cp\u003e4.3.1 Rate Data: Poisson Likelihood and Log Link 99\u003c\/p\u003e \u003cp\u003e4.3.1.1 WinBUGS Implementation 100\u003c\/p\u003e \u003cp\u003e4.3.1.2 Example: Dietary Fat 101\u003c\/p\u003e \u003cp\u003e4.3.1.3 Results: Dietary Fat 104\u003c\/p\u003e \u003cp\u003e4.3.2 Rate Data: Binomial Likelihood and Cloglog Link 105\u003c\/p\u003e \u003cp\u003e4.3.2.1 WinBUGS Implementation 107\u003c\/p\u003e \u003cp\u003e4.3.2.2 Example: Diabetes 109\u003c\/p\u003e \u003cp\u003e4.3.2.3 Results: Diabetes 112\u003c\/p\u003e \u003cp\u003e4.3.3 Continuous Data: Normal Likelihood and Identity Link 114\u003c\/p\u003e \u003cp\u003e4.3.3.1 Before\/After Studies: Change from Baseline Measures 115\u003c\/p\u003e \u003cp\u003e4.3.3.2 Standardised Mean Differences 115\u003c\/p\u003e \u003cp\u003e4.3.3.3 WinBUGS Implementation 116\u003c\/p\u003e \u003cp\u003e4.3.3.4 Example: Parkinson’s 117\u003c\/p\u003e \u003cp\u003e4.3.3.5 Results: Parkinson’s 119\u003c\/p\u003e \u003cp\u003e4.4 Contrast-Based Likelihoods 120\u003c\/p\u003e \u003cp\u003e4.4.1 Continuous Data: Treatment Differences 121\u003c\/p\u003e \u003cp\u003e4.4.1.1 Multi-Arm Trials with Treatment Differences (Trial-Based Summaries) 122\u003c\/p\u003e \u003cp\u003e4.4.1.2 *WinBUGS Implementation 123\u003c\/p\u003e \u003cp\u003e4.4.1.3 Example: Parkinson’s (Treatment Differences as Data) 125\u003c\/p\u003e \u003cp\u003e4.4.1.4 Results: Parkinson’s (Treatment Differences as Data) 127\u003c\/p\u003e \u003cp\u003e4.5 *Multinomial Likelihoods 127\u003c\/p\u003e \u003cp\u003e4.5.1 Ordered Categorical Data: Multinomial Likelihood and Probit Link 128\u003c\/p\u003e \u003cp\u003e4.5.1.1 WinBUGS Implementation 132\u003c\/p\u003e \u003cp\u003e4.5.1.2 Example: Psoriasis 133\u003c\/p\u003e \u003cp\u003e4.5.1.3 Results: Psoriasis 137\u003c\/p\u003e \u003cp\u003e4.5.2 Competing Risks: Multinomial Likelihood and Log Link 138\u003c\/p\u003e \u003cp\u003e4.5.2.1 WinBUGS Implementation 140\u003c\/p\u003e \u003cp\u003e4.5.2.2 Example: Schizophrenia 141\u003c\/p\u003e \u003cp\u003e4.5.2.3 Results: Schizophrenia 143\u003c\/p\u003e \u003cp\u003e4.6 *Shared Parameter Models 146\u003c\/p\u003e \u003cp\u003e4.6.1 Example: Parkinson’s (Mixed Treatment Difference and Arm-Level Data) 147\u003c\/p\u003e \u003cp\u003e4.6.2 Results: Parkinson’s (Mixed Treatment Difference and Arm-Level Data) 148\u003c\/p\u003e \u003cp\u003e4.7 Choice of Prior Distributions 149\u003c\/p\u003e \u003cp\u003e4.8 Zero Cells 149\u003c\/p\u003e \u003cp\u003e4.9 Summary of Key Points and Further Reading 150\u003c\/p\u003e \u003cp\u003e4.10 Exercises 151\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Network Meta-Analysis Within Cost-Effectiveness Analysis 155\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e5.1 Introduction 155\u003c\/p\u003e \u003cp\u003e5.2 Sources of Evidence for Relative Treatment Effects and the Baseline Model 156\u003c\/p\u003e \u003cp\u003e5.3 The Baseline Model 158\u003c\/p\u003e \u003cp\u003e5.3.1 Estimating the Baseline Model in WinBUGS 158\u003c\/p\u003e \u003cp\u003e5.3.2 Alternative Computation Methods for the Baseline Model 162\u003c\/p\u003e \u003cp\u003e5.3.3 *Arm-Based Meta-Analytic Models 162\u003c\/p\u003e \u003cp\u003e5.3.4 Baseline Models with Covariates 164\u003c\/p\u003e \u003cp\u003e5.3.4.1 Using Aggregate Data 164\u003c\/p\u003e \u003cp\u003e5.3.4.2 Risk Equations for the Baseline Model Basedon Individual Patient Data 165\u003c\/p\u003e \u003cp\u003e5.4 The Natural History Model 165\u003c\/p\u003e \u003cp\u003e5.5 Model Validation and Calibration Through Multi-Parameter Synthesis 167\u003c\/p\u003e \u003cp\u003e5.6 Generating the Outputs Required for Cost-Effectiveness Analysis 169\u003c\/p\u003e \u003cp\u003e5.6.1 Generating a CEA 169\u003c\/p\u003e \u003cp\u003e5.6.2 Heterogeneity in the Context of Decision-Making 170\u003c\/p\u003e \u003cp\u003e5.7 Strategies to Implement Cost-Effectiveness Analyses 173\u003c\/p\u003e \u003cp\u003e5.7.1 Bayesian Posterior Simulation: One-Stage Approach 174\u003c\/p\u003e \u003cp\u003e5.7.2 Bayesian Posterior Simulation: Two-Stage Approach 174\u003c\/p\u003e \u003cp\u003e5.7.3 Multiple Software Platforms and Automation of Network Meta-Analysis 175\u003c\/p\u003e \u003cp\u003e5.8 Summary and Further Reading 177\u003c\/p\u003e \u003cp\u003e5.9 Exercises 178\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 Adverse Events and Other Sparse Outcome Data 179\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e6.1 Introduction 179\u003c\/p\u003e \u003cp\u003e6.2 Challenges Regarding the Analysis of Sparse Data in Pairwise and Network Meta-Analysis 180\u003c\/p\u003e \u003cp\u003e6.2.1 Network Structure and Connectivity 182\u003c\/p\u003e \u003cp\u003e6.2.2 Assessing Convergence and Model Fit 182\u003c\/p\u003e \u003cp\u003e6.3 Strategies to Improve the Robustness of Estimation of Effects from Sparse Data in Network Meta-Analysis 183\u003c\/p\u003e \u003cp\u003e6.3.1 Specifying Informative Prior Distributions for Response in Trial Reference Groups 183\u003c\/p\u003e \u003cp\u003e6.3.2 Specifying an Informative Prior Distribution for the Between Study Variance Parameters 184\u003c\/p\u003e \u003cp\u003e6.3.3 Specifying Reference Group Responses as Exchangeable with Random Effects 184\u003c\/p\u003e \u003cp\u003e6.3.4 Situational Modelling Extensions 185\u003c\/p\u003e \u003cp\u003e6.3.5 Specification of Informative Prior Distributions Versus Use of Continuity Corrections 186\u003c\/p\u003e \u003cp\u003e6.4 Summary and Further Reading 186\u003c\/p\u003e \u003cp\u003e6.5 Exercises 187\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Checking for Inconsistency 189\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e7.1 Introduction 189\u003c\/p\u003e \u003cp\u003e7.2 Network Structure 190\u003c\/p\u003e \u003cp\u003e7.2.1 Inconsistency Degrees of Freedom 191\u003c\/p\u003e \u003cp\u003e7.2.2 Defining Inconsistency in the Presence of Multi-Arm Trials 192\u003c\/p\u003e \u003cp\u003e7.3 Loop Specific Tests for Inconsistency 195\u003c\/p\u003e \u003cp\u003e7.3.1 Networks with Independent Tests for Inconsistency 195\u003c\/p\u003e \u003cp\u003e7.3.1.1 Bucher Method for Single Loops of Evidence 195\u003c\/p\u003e \u003cp\u003e7.3.1.2 Example: HIV 196\u003c\/p\u003e \u003cp\u003e7.3.1.3 Extension of Bucher Method to Networks with Multiple Loops: Enuresis Example 197\u003c\/p\u003e \u003cp\u003e7.3.1.4 Obtaining the ‘Direct’ Estimates of Inconsistency 199\u003c\/p\u003e \u003cp\u003e7.3.2 Methods for General Networks 200\u003c\/p\u003e \u003cp\u003e7.3.2.1 Repeat Application of the Bucher Method 201\u003c\/p\u003e \u003cp\u003e7.3.2.2 A Back-Calculation Method 202\u003c\/p\u003e \u003cp\u003e7.3.2.3 *Variance Measures of Inconsistency 202\u003c\/p\u003e \u003cp\u003e7.3.2.4 *Node-Splitting 203\u003c\/p\u003e \u003cp\u003e7.4 A Global Test for Loop Inconsistency 205\u003c\/p\u003e \u003cp\u003e7.4.1 Inconsistency Model with Unrelated Mean Relative Effects 206\u003c\/p\u003e \u003cp\u003e7.4.2 Example: Full Thrombolytic Treatments Network 210\u003c\/p\u003e \u003cp\u003e7.4.2.1 Adjusted Standard Errors for Multi-Arm Trials 214\u003c\/p\u003e \u003cp\u003e7.4.3 Example: Parkinson’s 215\u003c\/p\u003e \u003cp\u003e7.4.4 Example: Diabetes 218\u003c\/p\u003e \u003cp\u003e7.5 Response to Inconsistency 219\u003c\/p\u003e \u003cp\u003e7.6 The Relationship between Heterogeneity and Inconsistency 221\u003c\/p\u003e \u003cp\u003e7.7 Summary and Further Reading 223\u003c\/p\u003e \u003cp\u003e7.8 Exercises 225\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 Meta-Regression for Relative Treatment Effects 227\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e8.1 Introduction 227\u003c\/p\u003e \u003cp\u003e8.2 Basic Concepts 229\u003c\/p\u003e \u003cp\u003e8.2.1 Types of Covariate 229\u003c\/p\u003e \u003cp\u003e8.3 Heterogeneity, Meta-Regression and Predictive Distributions 232\u003c\/p\u003e \u003cp\u003e8.3.1 Worked Example: BCG Vaccine 233\u003c\/p\u003e \u003cp\u003e8.3.2 Implications of Heterogeneity in Decision Making 236\u003c\/p\u003e \u003cp\u003e8.4 Meta-Regression Models for Network Meta-Analysis 238\u003c\/p\u003e \u003cp\u003e8.4.1 Baseline Risk 241\u003c\/p\u003e \u003cp\u003e8.4.2 WinBUGS Implementation 242\u003c\/p\u003e \u003cp\u003e8.4.3 Meta-Regression with a Continuous Covariate 245\u003c\/p\u003e \u003cp\u003e8.4.3.1 BCG Vaccine Example: Pairwise Meta-Regression with a Continuous Covariate 245\u003c\/p\u003e \u003cp\u003e8.4.3.2 Certolizumab Example: Network Meta-Regression with Continuous Covariate 247\u003c\/p\u003e \u003cp\u003e8.4.3.3 Certolizumab Example: Network Meta-Regression on Baseline Risk 252\u003c\/p\u003e \u003cp\u003e8.4.4 Subgroup Effects 255\u003c\/p\u003e \u003cp\u003e8.4.4.1 Statins Example: Pairwise Meta-Analysis with Subgroups 256\u003c\/p\u003e \u003cp\u003e8.5 Individual Patient Data in Meta-Regression 257\u003c\/p\u003e \u003cp\u003e8.6 Models with Treatment-Level Covariates 261\u003c\/p\u003e \u003cp\u003e8.6.1 Accounting for Dose 261\u003c\/p\u003e \u003cp\u003e8.6.2 Class Effects Models 263\u003c\/p\u003e \u003cp\u003e8.6.3 Treatment Combination Models 264\u003c\/p\u003e \u003cp\u003e8.7 Implications of Meta-Regression for Decision Making 266\u003c\/p\u003e \u003cp\u003e8.8 Summary and Further Reading 268\u003c\/p\u003e \u003cp\u003e8.9 Exercises 269\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 Bias Adjustment Methods 273\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e9.1 Introduction 273\u003c\/p\u003e \u003cp\u003e9.2 Adjustment for Bias Based on Meta-Epidemiological Data 275\u003c\/p\u003e \u003cp\u003e9.3 Estimation and Adjustment for Bias in Networks of Trials 278\u003c\/p\u003e \u003cp\u003e9.3.1 Worked Example: Fluoride Therapies for the Prevention of Caries in Children 279\u003c\/p\u003e \u003cp\u003e9.3.2 Extensions 285\u003c\/p\u003e \u003cp\u003e9.3.3 Novel Agent Effects 286\u003c\/p\u003e \u003cp\u003e9.3.4 Small-Study Effects 287\u003c\/p\u003e \u003cp\u003e9.3.5 Industry Sponsor Effects 287\u003c\/p\u003e \u003cp\u003e9.3.6 Accounting for Missing Data 288\u003c\/p\u003e \u003cp\u003e9.4 Elicitation of Internal and External Bias Distributions from Experts 289\u003c\/p\u003e \u003cp\u003e9.5 Summary and Further Reading 290\u003c\/p\u003e \u003cp\u003e9.6 Exercises 291\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 *Network Meta-Analysis of Survival Outcomes 293\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e10.1 Introduction 293\u003c\/p\u003e \u003cp\u003e10.2 Time-to-Event Data 294\u003c\/p\u003e \u003cp\u003e10.2.1 Individual Patient Data 294\u003c\/p\u003e \u003cp\u003e10.2.2 Reported Summary Data 295\u003c\/p\u003e \u003cp\u003e10.2.3 Kaplan–Meier Estimate of the Survival Function 295\u003c\/p\u003e \u003cp\u003e10.3 Parametric Survival Functions 296\u003c\/p\u003e \u003cp\u003e10.4 The Relative Treatment Effect 298\u003c\/p\u003e \u003cp\u003e10.5 Network Meta-Analysis of a Single Effect Measure per Study 300\u003c\/p\u003e \u003cp\u003e10.5.1 Proportion Alive, Median Survival and Hazard Ratio as Reported Treatment Effects 300\u003c\/p\u003e \u003cp\u003e10.5.2 Network Meta-Analysis of Parametric Survival Curves: Single Treatment Effect 300\u003c\/p\u003e \u003cp\u003e10.5.3 Shared Parameter Models 301\u003c\/p\u003e \u003cp\u003e10.5.4 Limitations 302\u003c\/p\u003e \u003cp\u003e10.6 Network Meta-Analysis with Multivariate Treatment Effects 302\u003c\/p\u003e \u003cp\u003e10.6.1 Multidimensional Network Meta-Analysis Model 302\u003c\/p\u003e \u003cp\u003e10.6.1.1 Weibull 302\u003c\/p\u003e \u003cp\u003e10.6.1.2 Gompertz 303\u003c\/p\u003e \u003cp\u003e10.6.1.3 Log-Logistic and Log-Normal 303\u003c\/p\u003e \u003cp\u003e10.6.1.4 Fractional Polynomial 304\u003c\/p\u003e \u003cp\u003e10.6.1.5 Splines 304\u003c\/p\u003e \u003cp\u003e10.6.2 Evaluation of Consistency 304\u003c\/p\u003e \u003cp\u003e10.6.3 Meta-Regression 305\u003c\/p\u003e \u003cp\u003e10.7 Data and Likelihood 305\u003c\/p\u003e \u003cp\u003e10.7.1 Likelihood with Individual Patient Data 305\u003c\/p\u003e \u003cp\u003e10.7.2 Discrete or Piecewise Constant Hazards as Approximate Likelihood 306\u003c\/p\u003e \u003cp\u003e10.7.3 Conditional Survival Probabilities as Approximate Likelihood 307\u003c\/p\u003e \u003cp\u003e10.7.4 Reconstructing Kaplan–Meier Data 307\u003c\/p\u003e \u003cp\u003e10.7.5 Constructing Interval Data 308\u003c\/p\u003e \u003cp\u003e10.8 Model Choice 308\u003c\/p\u003e \u003cp\u003e10.9 Presentation of Results 309\u003c\/p\u003e \u003cp\u003e10.10 Illustrative Example 310\u003c\/p\u003e \u003cp\u003e10.11 Network Meta-Analysis of Survival Outcomes for Cost-Effectiveness Evaluations 319\u003c\/p\u003e \u003cp\u003e10.12 Summary and Further Reading 320\u003c\/p\u003e \u003cp\u003e10.13 Exercises 322\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 *Multiple Outcomes 323\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e11.1 Introduction 323\u003c\/p\u003e \u003cp\u003e11.2 Multivariate Random Effects Meta-Analysis 324\u003c\/p\u003e \u003cp\u003e11.3 Multinomial Likelihoods and Extensions of Univariate Methods 327\u003c\/p\u003e \u003cp\u003e11.4 Chains of Evidence 328\u003c\/p\u003e \u003cp\u003e11.4.1 A Decision Tree Structure: Coronary Patency 328\u003c\/p\u003e \u003cp\u003e11.4.2 Chain of Evidence with Relative Risks: Neonatal Early Onset Group B Strep 330\u003c\/p\u003e \u003cp\u003e11.5 Follow-Up to Multiple Time Points: Gastro-Esophageal Reflux Disease 332\u003c\/p\u003e \u003cp\u003e11.6 Multiple Outcomes Reported in Different Ways: Influenza 335\u003c\/p\u003e \u003cp\u003e11.7 Simultaneous Mapping and Synthesis 337\u003c\/p\u003e \u003cp\u003e11.8 Related Outcomes Reported in Different Ways: Advanced Breast Cancer 342\u003c\/p\u003e \u003cp\u003e11.9 Repeat Observations for Continuous Outcomes: Fractional Polynomials 344\u003c\/p\u003e \u003cp\u003e11.10 Synthesis for Markov Models 345\u003c\/p\u003e \u003cp\u003e11.11 Summary and Further Reading 347\u003c\/p\u003e \u003cp\u003e11.12 Exercises 349\u003c\/p\u003e \u003cp\u003e\u003cb\u003e12 Validity of Network Meta-Analysis 351\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e12.1 Introduction 351\u003c\/p\u003e \u003cp\u003e12.2 What Are the Assumptions of Network Meta-Analysis? 352\u003c\/p\u003e \u003cp\u003e12.2.1 Exchangeability 352\u003c\/p\u003e \u003cp\u003e12.2.2 Other Terminologies and Their Relation to Exchangeability 353\u003c\/p\u003e \u003cp\u003e12.3 Direct and Indirect Comparisons: Some Thought Experiments 355\u003c\/p\u003e \u003cp\u003e12.3.1 Direct Comparisons 356\u003c\/p\u003e \u003cp\u003e12.3.2 Indirect Comparisons 359\u003c\/p\u003e \u003cp\u003e12.3.3 Under What Conditions Is Evidence Synthesis Likely to Be Valid? 362\u003c\/p\u003e \u003cp\u003e12.4 Empirical Studies of the Consistency Assumption 363\u003c\/p\u003e \u003cp\u003e12.5 Quality of Evidence Versus Reliability of Recommendation 365\u003c\/p\u003e \u003cp\u003e12.5.1 Theoretical Treatment of Validity of Network Meta-Analysis 365\u003c\/p\u003e \u003cp\u003e12.5.2 GRADE Assessment of Quality of Evidence from a Network Meta-Analyses 366\u003c\/p\u003e \u003cp\u003e12.5.3 Reliability of Recommendations Versus Quality of Evidence: The Role of Sensitivity Analysis 368\u003c\/p\u003e \u003cp\u003e12.6 Summary and Further Reading 369\u003c\/p\u003e \u003cp\u003e12.7 Exercises 373\u003c\/p\u003e \u003cp\u003eSolutions to Exercises 375\u003c\/p\u003e \u003cp\u003eAppendices 401\u003c\/p\u003e \u003cp\u003eReferences 409\u003c\/p\u003e \u003cp\u003eIndex 447\u003c\/p\u003e","brand":"John Wiley \u0026 Sons Inc","offers":[{"title":"Default Title","offer_id":49406899749207,"sku":"9781118647509","price":53.96,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0817\/1739\/5799\/files\/9781118647509.jpg?v=1730497491","url":"https:\/\/bookcurl.com\/products\/network-metaanalysis-for-decisionmaking-9781118647509","provider":"Book Curl","version":"1.0","type":"link"}