[Springer Series in Pharmaceutical Statistics] Statistical Remedies for Medical Researchers ||

"This book illustrates numerous statistical practices that are commonly used by medical researchers, but which have severe flaws that may not be obvious. For each example, it provides one or more alternative statistical methods that avoid misleading or incorrect inferences being made. The technical level is kept to a minimum to make the book accessible to non-statisticians. At the same time, since many of the examples describe methods used routinely by medical statisticians with formal statistical training, the book appeals to a broad readership in the medical research community." -- Prové de l'editor Preface Contents 1 Why Bother with Statistics? 1.1 Some Unexpected Problems 1.2 Expert Opinion 1.3 The Innocent Bystander Effect 1.4 Gambling and Medicine 1.5 Testing Positive 1.6 Bayes' Law and Hemophilia 2 Frequentists and Bayesians 2.1 Statistical Inference 2.2 Frequentist Statistics 2.3 Bayesian Statistics 3 Knocking Down the Straw Man 3.1 Designing Clinical Trials 3.2 A Common Phase II Design 3.3 A Common Misinterpretation 3.4 Not Testing Hypotheses 3.5 Random Standards 3.6 A Fake Null Hypothesis 3.7 Monitoring Toxicity and Response 4 Science and Belief 4.1 Theory Versus Practice 4.2 Technology and Cherry-Picking 4.3 Is a New Treatment Any Good? 4.4 The Las Vegas Effect 5 The Perils of P-Values 5.1 Counting Cows 5.2 A Sacred Ritual 5.3 A Dataset with Four P-Values 5.4 Bayes Factors 5.5 Computing Sample Sizes 5.6 Not-So-Equivalent Studies 5.7 Acute Respiratory Distress Syndrome 5.8 The Multiple Testing Problem 5.9 Type S Error 5.10 A Simple Bayesian Alternative to P-Values 5.11 Survival Analysis Without P-Values 5.12 The P-Value War 6 Flipping Coins 6.1 Farming and Medicine 6.2 How Not to Compare Treatments 6.3 Counterfactuals and Causality 6.4 Why Randomize? 6.5 Stratifying by Subgroups 6.6 Inverse Probability-Weighted Survival Analysis 6.7 Bias Correction by Matching 6.8 A Bayesian Rationale for Randomization 6.9 Outcome-Adaptive Randomization 7 All Mixed Up 7.1 The Billion Dollar Computation 7.2 Accounting for Uncertainty and Bias 7.3 Predicting Phase III Success 7.4 A Paradoxical Clinical Trial 8 Sex, Biomarkers, and Paradoxes 8.1 A Paradox 8.2 Batting Averages 8.3 A Magic Biomarker 8.4 Plotting Regression Data 9 Crippling New Treatments 9.1 Phase I Trials 9.2 Choosing the Wrong Dose in Phase I 9.3 Phase I–II Designs 10 Just Plain Wrong 10.1 Clinical Trial Design, Belief, and Ethics 10.2 A Futile Futility Rule 10.3 The Evaluability Game 10.4 The Fox, the Farmer, and the Chickens 10.5 Planned Confounding 10.6 Select-and-Test Designs 11 Getting Personal 11.1 From Bench to Bedside 11.2 Age Discrimination 11.3 Comparing Treatments Precisely 11.4 A Subgroup-Specific Phase II–III Design 11.5 Precision Pharmacokinetic Dosing 12 Multistage Treatment Regimes 12.1 The Triangle of Death 12.2 Observe, Act, Repeat 12.3 SMART Designs 12.4 Repeat or Switch Away 12.5 A Semi-SMART Design Appendix References Index