Clinical trials: a methodologic perspective
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Hoboken, NJ
Wiley-Interscience
2005
|
| Ausgabe: | 2. ed. |
| Schriftenreihe: | Wiley series in probability and statistics
|
| Schlagworte: | |
| Online-Zugang: | Contributor biographical information Publisher description Table of contents only Inhaltsverzeichnis |
| Beschreibung: | XXVII, 687 S. graph. Darst. |
| ISBN: | 0471727814 9780471727811 |
Internformat
MARC
| LEADER | 00000nam a2200000zc 4500 | ||
|---|---|---|---|
| 001 | BV023042822 | ||
| 003 | DE-604 | ||
| 005 | 20121203 | ||
| 007 | t | ||
| 008 | 071210s2005 xxud||| |||| 00||| eng d | ||
| 010 | |a 2005040833 | ||
| 020 | |a 0471727814 |c cloth : alk. paper |9 0-471-72781-4 | ||
| 020 | |a 9780471727811 |9 978-0-471-72781-1 | ||
| 035 | |a (OCoLC)57682616 | ||
| 035 | |a (DE-599)BVBBV023042822 | ||
| 040 | |a DE-604 |b ger |e aacr | ||
| 041 | 0 | |a eng | |
| 044 | |a xxu |c US | ||
| 049 | |a DE-355 |a DE-29T |a DE-188 |a DE-578 | ||
| 050 | 0 | |a R853.C55 | |
| 082 | 0 | |a 610/.72 | |
| 084 | |a XF 3400 |0 (DE-625)152765: |2 rvk | ||
| 100 | 1 | |a Piantadosi, Steven |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Clinical trials |b a methodologic perspective |c Steven Piantadosi |
| 250 | |a 2. ed. | ||
| 264 | 1 | |a Hoboken, NJ |b Wiley-Interscience |c 2005 | |
| 300 | |a XXVII, 687 S. |b graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 0 | |a Wiley series in probability and statistics | |
| 650 | 7 | |a Clinical trials |2 gtt | |
| 650 | 7 | |a Ensaios clínicos (pesquisa e planejamento) (estatísticas e dados numéricos) |2 larpcal | |
| 650 | 7 | |a Ensaios clínicos (pesquisa e planejamento) (métodos) |2 larpcal | |
| 650 | 7 | |a Estatística (métodos) |2 larpcal | |
| 650 | 7 | |a Statistische methoden |2 gtt | |
| 650 | 4 | |a Études cliniques - Méthodes statistiques | |
| 650 | 4 | |a Statistik | |
| 650 | 4 | |a Clinical trials |x Statistical methods | |
| 650 | 4 | |a Biomedical Research |x methods | |
| 650 | 4 | |a Research |x methods | |
| 650 | 4 | |a Clinical Trials |x methods | |
| 650 | 4 | |a Statistics |x methods | |
| 650 | 0 | 7 | |a Methode |0 (DE-588)4038971-6 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Medizin |0 (DE-588)4038243-6 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Experiment |0 (DE-588)4015999-1 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Klinisches Experiment |0 (DE-588)4164223-5 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Klinisches Experiment |0 (DE-588)4164223-5 |D s |
| 689 | 0 | 1 | |a Methode |0 (DE-588)4038971-6 |D s |
| 689 | 0 | |5 DE-604 | |
| 689 | 1 | 0 | |a Experiment |0 (DE-588)4015999-1 |D s |
| 689 | 1 | 1 | |a Medizin |0 (DE-588)4038243-6 |D s |
| 689 | 1 | 2 | |a Methode |0 (DE-588)4038971-6 |D s |
| 689 | 1 | |8 1\p |5 DE-604 | |
| 856 | 4 | |u http://www.loc.gov/catdir/enhancements/fy0623/2005040833-b.html |3 Contributor biographical information | |
| 856 | 4 | |u http://www.loc.gov/catdir/enhancements/fy0623/2005040833-d.html |3 Publisher description | |
| 856 | 4 | |u http://www.loc.gov/catdir/enhancements/fy0623/2005040833-t.html |3 Table of contents only | |
| 856 | 4 | 2 | |m HBZ Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=016246318&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-016246318 | ||
| 883 | 1 | |8 1\p |a cgwrk |d 20201028 |q DE-101 |u https://d-nb.info/provenance/plan#cgwrk | |
Datensatz im Suchindex
| _version_ | 1804137272015060992 |
|---|---|
| adam_text | CONTENTS
Preface xxi
Preface to the First Edition xxv
1 Preliminaries 1
1.1 Introduction, 1
1.2 Audience and Scope, 2
1.3 Other Sources of Knowledge, 4
1.3.1 Terminology, 5
1.3.2 Review of Notation and Terminology Is Helpful, 6
1.4 Examples, Data, and Programs, 6
1.5 Summary, 7
2 Clinical Trials as Research 9
2.1 Introduction, 9
2.1.1 Clinical Reasoning Is Based on the Case History, 10
2.1.2 Statistical Reasoning Emphasizes Inference Based on Designed
Data Production, 12
2.1.3 Clinical and Statistical Reasoning Converge in Research, 13
2.2 Denning Clinical Trials Formally, 14
2.2.1 Mixing of Clinical and Statistical Reasoning Is Recent, 14
2.2.2 Clinical Trials Are Rigorously Defined, 16
2.2.3 Experiments Can Be Misunderstood, 17
2.2.4 Clinical Trials as Science, 18
2.2.5 Trials and Statistical Methods Fit within a Spectrum of
Clinical Research, 19
v
vi CONTENTS
2.3 Practicalities of Usage, 20
2.3.1 Predicates for a Trial, 20
2.3.2 Trials Can Provide Confirmatory Evidence, 20
2.3.3 Clinical Trials Are Unwieldy, Messy, and Reliable, 21
2.3.4 Other Methods Are Valid for Making Some Clinical
Inferences, 23
2.3.5 Trials Are Difficult to Apply in Some Circumstances, 25
2.3.6 Randomized Studies Can Be Initiated Early, 25
2.4 Summary, 26
2.5 Questions for Discussion, 26
3 Why Clinical Trials Are Ethical 29
3.1 Introduction, 29
3.1.1 Science and Ethics Share Objectives, 30
3.1.2 Equipoise and Uncertainty, 31
3.2 Duality, 32
3.2.1 Clinical Trials Sharpen, but Do Not Create, the Issue, 32
3.2.2 A Gene Therapy Tragedy Illustrates Duality, 32
3.2.3 Research and Practice Are Convergent, 33
3.2.4 The Hippocratic Tradition Does Not Proscribe Clinical
Trials, 36
3.2.5 Physicians Always Have Multiple Roles, 38
3.3 Historically Derived Principles of Ethics, 41
3.3.1 Nuremberg Contributed an Awareness of the Worst Problems, 41
3.3.2 High Profile Mistakes Were Made in the United States, 42
3.3.3 The Helsinki Declaration Was Widely Adopted, 42
3.3.4 Other International Guidelines Have Been Proposed, 44
3.3.5 Institutional Review Boards Provide Ethical Oversight, 45
3.3.6 Ethical Principles Relevant to Clinical Trials, 46
3.4 Contemporary Foundational Principles, 48
3.4.1 Collaborative Partnership, 48
3.4.2 Scientific Value, 49
3.4.3 Scientific Validity, 49
3.4.4 Fair Subject Selection, 49
3.4.5 Favorable Risk Benefit, 50
3.4.6 Independent Review, 50
3.4.7 Informed Consent, 51
3.4.8 Respect for Subjects, 52
3.5 Methodologic Reflections, 53
3.5.1 Practice Based on Unproven Treatments Is Not Ethical, 53
3.5.2 Ethics Considerations Are Important Determinants of Design, 55
3.5.3 Specific Methods Have Justification, 57
CONTENTS vii
3.6 Professional Conduct, 59
3.6.1 Conflict of Interest, 59
3.6.2 Professional Statistical Ethics, 61
3.7 Summary, 63
3.8 Questions for Discussion, 63
4 Contexts for Clinical Trials 65
4.1 Introduction, 65
4.1.1 Some Ways to Learn about Trials in a Given Context, 66
4.1.2 Issues of Context, 67
4.2 Drugs, 68
4.2.1 Are Drugs Special?, 70
4.2.2 Why Trials Are Used Extensively for Drugs, 71
4.3 Devices, 72
4.3.1 Use of Trials for Medical Devices, 73
4.3.2 Are Devices Different from Drugs?, 74
4.3.3 Case Study, 76
4.4 Prevention, 76
4.4.1 The Prevention versus Therapy Dichotomy Is Overworked, 77
4.4.2 Vaccines and Biologicals, 78
4.4.3 A Perspective on Risk Benefit, 79
4.4.4 Methodology and Framework for Prevention Trials, 81
4.5 Complementary and Alternative Medicine, 82
4.5.1 The Essential Paradox of CAM and Clinical Trials, 84
4.5.2 Why Trials Have Not Been Used Extensively in CAM, 85
4.5.3 Some Principles for Rigorous Evaluation, 87
4.6 Surgery and Skill Dependent Therapies, 88
4.6.1 Why Trials Have Not Been Used Extensively in Surgery, 90
4.6.2 Reasons Why Some Surgical Therapies Require Less Rig¬
orous Study Designs, 92
4.6.3 Sources of Variation, 92
4.6.4 Difficulties of Inference, 93
4.6.5 Control of Observer Bias Is Possible, 94
4.6.6 Illustrations from an Emphysema Surgery Trial, 95
4.7 A Brief View of Some Other Contexts, 101
4.7.1 Screening Trials, 101
4.7.2 Diagnostic Trials, 103
4.7.3 Radiotherapy, 103
4.8 Summary, 104
4.9 Questions for Discussion, 105
5 Statistical Perspectives 107
5.1 Introduction, 107
viii CONTENTS
5.2 Differences in Statistical Perspectives, 108
5.2.1 Models and Parameters, 108
5.2.2 Philosophy of Inference Divides Statisticians, 108
5.2.3 Resolution, 109
5.2.4 Points of Agreement, 110
5.3 Frequentist, 112
5.3.1 Binomial Case Study, 113
5.3.2 Other Issues, 114
5.4 Bayesian, 115
5.4.1 Choice of a Prior Distribution Is a Source of Contention, 116
5.4.2 Binomial Case Study, 117
5.4.3 Bayesian Inference Is Different, 119
5.5 Likelihood, 120
5.5.1 Binomial Case Study, 121
5.5.2 Likelihood Based Design, 122
5.6 Afterthoughts, 123
5.6.1 Statistical Procedures Are Not Standardized, 123
5.6.2 Practical Controversies Related to Statistics Exist, 123
5.7 Summary, 125
5.8 Questions for Discussion, 125
6 Clinical Trials as Experimental Designs 127
6.1 Introduction, 127
6.1.1 Trials Are Relatively Simple Experimental Designs, 128
6.1.2 Study Design Is Critical for Inference, 129
6.2 Goals of Experimental Design, 129
6.2.1 Control of Random Error and Bias Is the Goal, 129
6.2.2 Conceptual Simplicity Is Also a Goal, 130
6.2.3 Encapsulation of Subjectivity, 131
6.2.4 Leech Case Study, 131
6.3 Trial Terminology, 132
6.3.1 Drug Development Traditionally Recognizes Four Trial
Designs, 132
6.3.2 Descriptive Terminology Is Broader and Recognizes More
Types of Trials, 133
6.4 Design Concepts, 134
6.4.1 The Foundations of Design Are Observation and Theory, 134
6.4.2 A Lesson from the Women s Health Initiative, 136
6.4.3 Experiments Use Three Components of Design, 137
6.5 Survey of Developmental Trial Designs, 143
6.5.1 Early Development, 143
6.5.2 Middle Development, 144
6.5.3 Late Development, 148
CONTENTS ix
6.6 Special Design Issues, 151
6.6.1 Placebos, 151
6.6.2 Equivalence or Noninferiority, 154
6.6.3 Nonuniformity of Effect, 154
6.6.4 Randomized Discontinuation, 155
6.6.5 Hybrid Designs May Be Needed for Resolving Special
Questions, 156
6.6.6 Clinical Trials Cannot Meet Some Objectives, 156
6.7 Importance of the Protocol Document, 157
6.7.1 Protocols Have Many Functions, 158
6.7.2 Deviations from Protocol Specifications Are Common, 159
6.7.3 Protocols Are Structured, Logical, and Complete, 160
6.8 Summary, 164
6.9 Questions for Discussion, 165
7 Random Error and Bias 167
7.1 Introduction, 167
7.2 Random Error, 169
7.2.1 Hypothesis Tests versus Significance Tests, 169
7.2.2 Hypothesis Tests Are Subject to Two Types of Random
Error, 170
7.2.3 Type I Errors Are Relatively Easy to Control, 171
7.2.4 The Properties of Confidence Intervals Are Similar, 171
7.2.5 Using a One or Two Sided Hypothesis Test Is Not the
Right Question, 172
7.2.6 P Values Quantify the Type I Error, 173
7.2.7 Type II Errors Depend on the Clinical Difference of
Interest, 173
7.2.8 Post hoc Power Calculations Are not Helpful, 175
7.3 Clinical Biases, 176
7.3.1 Relative Size of Random Error and Bias Is Important, 176
7.3.2 Bias Arises from Numerous Sources, 176
7.3.3 Controlling Structural Bias Is Conceptually Simple, 179
7.4 Statistical Bias, 182
7.4.1 Some Statistical Bias Can Be Corrected, 183
7.4.2 Unbiasedness Is Not the Only Desirable Attribute of an
Estimator, 183
7.5 Summary, 185
7.6 Questions for Discussion, 185
8 Objectives and Outcomes 187
8.1 Introduction, 187
X CONTENTS
8.2 Objectives, 188
8.2.1 Estimation Is the Most Common Objective, 188
8.2.2 Selection Can Also Be an Objective, 189
8.2.3 Objectives Require Various Scales of Measurement, 189
8.3 Outcomes, 190
8.3.1 Mixed Outcomes and Predictors, 190
8.3.2 Criteria for Evaluating Outcomes, 191
8.3.3 Prefer Hard or Objective Outcomes, 191
8.3.4 Outcomes Can Be Quantitative or Qualitative, 192
8.3.5 Measures Are Useful and Efficient Outcomes, 192
8.3.6 Some Outcomes Are Summarized as Counts, 193
8.3.7 Ordered Categories Are Commonly Used for Severity or
Toxicity, 193
8.3.8 Unordered Categories Are Sometimes Used, 193
8.3.9 Dichotomies Are Simple Summaries, 194
8.3.10 Event Times May Be Censored, 194
8.3.11 Event Time Data Require Two Numerical Values, 196
8.3.12 Censoring and Lost to Follow up Are Not the Same, 197
8.3.13 Survival and Disease Progression, 198
8.3.14 Composite Outcomes Instead of Censoring, 199
8.3.15 Waiting for Good Events Complicates Censoring, 199
8.4 Surrogate Outcomes, 200
8.4.1 Surrogate Outcomes Are Disease Specific, 201
8.4.2 Surrogate Outcomes Can Make Trials More Efficient, 204
8.4.3 Surrogate Outcomes Have Significant Limitations, 205
8.5 Some Special Endpoints, 207
8.5.1 Repeated Measurements Are not Common in Clinical Tri¬
als, 207
8.5.2 Patient Reported Outcomes, 207
8.6 Summary, 208
8.7 Questions for Discussion, 209
9 Translational Clinical Trials 211
9.1 Introduction, 211
9.1.1 Translational Setting and Outcomes, 212
9.1.2 Character and Definition, 213
9.1.3 Small Does Not Mean Translational, 214
9.2 Information from Translational Trials, 214
9.2.1 Parameter Uncertainty versus Outcome Uncertainty, 214
9.2.2 Entropy, 215
9.2.3 Empirical Entropy Is Biased, 216
9.2.4 Variance, 216
9.2.5 Sample Size for Translational Trials, 218
CONTENTS xi
9.3 Summary, 220
9.4 Questions for Discussion, 221
10 Dose Finding Designs 223
10.1 Introduction, 223
10.2 Principles, 224
10.2.1 What Does Phase I Mean?, 224
10.2.2 Distinguish Dose Safety from Dose Efficacy, 226
10.2.3 Dose Optimality Is a Design Definition, 226
10.2.4 The General Dose Finding Problem Is Unsolved, 227
10.2.5 Unavoidable Subjectivity, 228
10.2.6 Sample Size Is an Outcome of Dose Finding Studies, 229
10.2.7 Idealized Dose Finding Design, 229
10.3 Fibonacci and Related Dose Ranging, 230
10.3.1 Some Historical Designs, 231
10.3.2 Typical Design, 231
10.3.3 Operating Characteristics Can Be Calculated, 232
10.3.4 Modifications, Strengths, and Weaknesses, 234
10.4 Designs Used for Dose Finding, 236
10.4.1 Mathematical Models Facilitate Inferences, 236
10.4.2 Continual Reassessment Method, 237
10.4.3 Pharmacokinetic Measurements Might Be Used to Improve
CRM Dose Escalations, 240
10.4.4 The CRM Is an Attractive Design to Criticize, 241
10.4.5 CRM Example, 241
10.4.6 Can Randomization Be Used in Phase I or TM Trials?, 242
10.4.7 Phase I Data Have Other Uses, 242
10.5 More General Dose Finding Issues, 242
10.5.1 Dose Finding Is Not Always One Dimensional, 243
10.5.2 Dual Dose Finding, 244
10.5.3 Optimizing Safety and Efficacy Jointly, 247
10.6 Summary, 250
10.7 Questions for Discussion, 250
11 Sample Size and Power 251
11.1 Introduction, 251
11.2 Principles, 252
11.2.1 What Is Precision?, 253
11.2.2 What Is Power?, 253
11.2.3 What Is Evidence?, 254
11.2.4 Sample Size and Power Calculations Are Approximations, 255
11.2.5 The Relationship between Power/Precision and Sample Size
Is Quadratic, 256
xii CONTENTS
11.3 Early Developmental Trials, 256
11.3.1 Translational Trials, 256
11.3.2 Dose Finding Trials, 258
11.4 Safety and Activity Studies, 258
11.4.1 Simple SA Designs Can Use Fixed Sample Size, 259
11.4.2 Exact Binomial Confidence Limits Are Helpful, 260
11.4.3 Bayesian Binomial Confidence Intervals, 263
11.4.4 A Bayesian Approach Can Use Prior Information, 264
11.4.5 Likelihood Based Approach for Proportions, 266
11.4.6 Confidence Intervals for a Mean Provide a Sample Size
Approach, 267
11.4.7 Confidence Intervals for Event Rates Can Determine
Sample Size, 268
11.4.8 Likelihood Based Approach for Event Rates, 271
11.4.9 Ineffective or Unsafe Treatments Should Be Discarded
Early, 271
11.4.10 Two Stage Designs Are Efficient, 272
11.4.11 Randomized SA Trials, 273
11.5 Comparative Trials, 277
11.5.1 How to Choose Type I and II Error Rates, 277
11.5.2 Comparisons Using the / Test Are a Good Learning
Example, 278
11.5.3 Likelihood Based Approach, 280
11.5.4 Dichotomous Responses Are More Complex, 282
11.5.5 Hazard Comparisons Yield Similar Equations, 283
11.5.6 Parametric and Nonparametric Equations Are Connected, 286
11.5.7 Accommodating Unbalanced Treatment Assignments, 286
11.5.8 A Simple Accrual Model Can Also Be Incorporated, 288
11.5.9 Noninferiority, 290
11.6 ES Trials, 295
11.6.1 Model Rare Events with the Poisson Distribution, 295
11.6.2 Likelihood Approach for Poisson Rates, 296
11.7 Other Considerations, 297
11.7.1 Cluster Randomization Requires Increased Sample Size, 297
11.7.2 Simple Cost Optimization, 298
11.7.3 Increase the Sample Size for Nonadherence, 299
11.7.4 Simulated Lifetables Can Be a Simple Design Tool, 301
11.7.5 Sample Size for Prognostic Factor Studies, 302
11.7.6 Computer Programs Simplify Calculations, 303
11.7.7 Simulation Is a Powerful and Flexible Design Alternative, 304
11.7.8 Power Curves are Sigmoid Shaped, 304
11.8 Summary, 305
11.9 Questions for Discussion, 306
CONTENTS xiii
12 The Study Cohort 309
12.1 Introduction, 309
12.2 Defining the Study Cohort, 310
12.2.1 Active Sampling or Enrichment, 310
12.2.2 Participation May Select Subjects with Better Prognosis, 311
12.2.3 Define the Study Population Using Eligibility and
Exclusion Criteria, 314
12.2.4 Quantitative Selection Criteria versus False Precision, 316
12.2.5 Comparative Trials Are Not Sensitive to Selection, 317
12.3 Anticipating Accrual, 318
12.3.1 Using a Run in Period, 318
12.3.2 Estimate Accrual Quantitatively, 319
12.4 Inclusiveness, Representation, and Interactions, 322
12.4.1 Inclusiveness Is a Worthy Goal, 322
12.4.2 Barriers Can Hinder Trial Participation, 322
12.4.3 Efficacy versus Effectiveness Trials, 323
12.4.4 Representation: Politics Blunders into Science, 324
12.5 Summary, 329
12.6 Questions for Discussion, 330
13 Treatment Allocation 331
13.1 Introduction, 331
13.2 Randomization, 332
13.2.1 Randomization Controls the Influence of Unknown Fac¬
tors, 333
13.2.2 Haphazard Assignments Are Not Random, 335
13.2.3 Simple Randomization Can Yield Imbalances, 335
13.3 Constrained Randomization, 336
13.3.1 Blocking Improves Balance, 336
13.3.2 Blocking and Stratifying Balances Prognostic Factors, 337
13.3.3 Other Considerations Regarding Blocking, 339
13.4 Adaptive Allocation, 340
13.4.1 Urn Designs Also Improve Balance, 340
13.4.2 Minimization Yields Tight Balance, 341
13.4.3 Play the Winner, 342
13.5 Other Issues Regarding Randomization, 343
13.5.1 Administration of the Randomization, 343
13.5.2 Computers Generate Pseudorandom Numbers, 345
13.5.3 Randomization Justifies Type I Errors, 345
13.6 Unequal Treatment Allocation, 349
13.6.1 Subsets May Be of Interest, 350
13.6.2 Treatments May Differ Greatly in Cost, 350
13.6.3 Variances May Be Different, 350
xiv CONTENTS
13.7 Randomization before Consent, 351
13.8 Summary, 352
13.9 Questions for Discussion, 352
14 Treatment Effects Monitoring 355
14.1 Introduction, 355
14.1.1 Motives for Monitoring, 356
14.1.2 Components of Responsible Monitoring, 357
14.1.3 Trials Can Be Stopped for a Variety of Reasons, 357
14.1.4 There Is Tension in the Decision to Stop, 358
14.2 Administrative Issues in Trial Monitoring, 359
14.2.1 Monitoring of Single Center Studies Relies on Periodic
Investigator Reporting, 360
14.2.2 Composition and Organization of the TEMC, 361
14.2.3 Complete Objectivity Is Not Ethical, 364
14.3 Organizational Issues Related to Data, 366
14.3.1 The TEMC Assesses Baseline Comparability, 366
14.3.2 The TEMC Reviews Accrual and Expected Time to Study
Completion, 367
14.3.3 Timeliness of Data and Reporting Lags, 367
14.3.4 Data Quality Is a Major Focus of the TEMC, 368
14.3.5 The TEMC Reviews Safety and Toxicity Data, 368
14.3.6 Efficacy Differences Are Assessed by the TEMC, 369
14.3.7 The TEMC Should Address a Few Practical Questions
Specifically, 369
14.3.8 The TEMC Mechanism Has Potential Weaknesses, 371
14.4 Statistical Methods for Monitoring, 371
14.4.1 There Are Several Approaches to Evaluating Incomplete
Evidence, 371
14.4.2 Likelihood Methods, 373
14.4.3 Bayesian Methods, 378
14.4.4 Decision Theoretic Methods, 381
14.4.5 Frequentist Methods, 381
14.4.6 Other Monitoring Tools, 387
14.4.7 Some Software, 392
14.5 Summary, 392
14.6 Questions for Discussion, 393
15 Counting Subjects and Events 395
15.1 Introduction, 395
15.2 Nature of Some Specific Data Imperfections, 396
15.2.1 Evaluability Criteria Are a Methodologic Error, 397
CONTENTS xv
15.2.2 Statistical Methods Can Cope with Some Types of Missing
Data, 398
15.2.3 Protocol Nonadherence Is Common, 400
15.3 Treatment Nonadherence, 402
15.3.1 Intention to Treat Is a Policy of Inclusion, 402
15.3.2 Coronary Drug Project Results Illustrate the Pitfalls of
Exclusions based on Nonadherence, 403
15.3.3 Statistical Studies Support the ITT Approach, 403
15.3.4 Trials Can Be Viewed as Tests of Treatment Policy, 404
15.3.5 ITT Analyses Cannot Always Be Applied, 404
15.3.6 Trial Inferences Depend on the Experimental Design, 406
15.4 Summary, 406
15.5 Questions for Discussion, 407
16 Estimating Clinical Effects 409
16.1 Introduction, 409
16.1.1 Structure Aids Data Interpretation, 410
16.1.2 Estimates of Risk Are Natural and Useful, 411
16.2 Dose Finding and PK Trials, 412
16.2.1 Pharmacokinetic Models Are Essential for Analyzing DF
Trials, 412
16.2.2 A Two Compartment Model Is Simple but Realistic, 413
16.2.3 PK Models Are Used by Model Fitting , 416
16.3 SA Studies, 417
16.3.1 Mesothelioma Clinical Trial Example, 417
16.3.2 Summarize Risk for Dichotomous Factors, 418
16.3.3 Nonparametric Estimates of Survival
Are Robust, 420
16.3.4 Parametric (Exponential) Summaries of Survival Are Effi¬
cient, 421
16.4 Comparative Efficacy Trials (Phase III), 423
16.4.1 Examples of CTE Trials Used in This Section, 424
16.4.2 Continuous Measures Estimate Treatment Differences, 426
16.4.3 Baseline Measurements Can Increase Precision, 426
16.4.4 Nonparametric Survival Comparisons, 427
16.4.5 Risk (Hazard) Ratios and Confidence Intervals Are Clini¬
cally Useful Data Summaries, 429
16.4.6 Statistical Models Are Helpful Tools. 431
16.4.7 P Values Do Not Measure Evidence, 432
16.5 Strength of Evidence through Support Intervals, 434
16.5.1 Support Intervals Are Based on the Likelihood Function, 434
16.5.2 Support Intervals Can Be Used with Any Outcome, 435
16.6 Special Methods of Analysis, 436
xvi CONTENTS
16.6.1 The Bootstrap Is Based on Resampling, 437
16.6.2 Some Clinical Questions Require Other Special Methods
of Analysis, 438
16.7 Exploratory or Hypothesis Generating Analyses, 442
16.7.1 Clinical Trial Data Lend Themselves to Exploratory Anal¬
yses, 442
16.7.2 Multiple Tests Multiply Type I Errors, 442
16.7.3 Kinds of Multiplicity, 443
16.7.4 Subgroup Analyses Are Error Prone, 443
16.8 Summary, 446
16.9 Questions for Discussion, 447
17 Prognostic Factor Analyses 453
17.1 Introduction, 453
17.1.1 Studying Prognostic Factors Is Broadly Useful, 454
17.1.2 Prognostic Factors Can Be Constant or Time Varying, 455
17.2 Model Based Methods, 456
17.2.1 Models Combine Theory and Data, 456
17.2.2 The Scale of Measurements (Coding) May Be Important, 457
17.2.3 Use Flexible Covariate Models, 457
17.2.4 Building Parsimonious Models Is the Next Step, 459
17.2.5 Incompletely Specified Models May Yield Biased Estimates, 464
17.2.6 Study Second Order Effects (Interactions), 465
17.2.7 PFAs Can Help Describe Risk Groups, 466
17.2.8 Power and Sample Size for PFAs, 470
17.3 Adjusted Analyses of Comparative Trials, 470
17.3.1 What Should We Adjust For?, 471
17.3.2 What Can Happen?, 472
17.4 Non Model Based Methods for PFAs, 475
17.4.1 Recursive Partitioning Uses Dichotomies, 475
17.4.2 Neural Networks Are Used for Pattern Recognition, 476
17.5 Summary, 477
17.6 Questions for Discussion, 478
18 Reporting and Authorship 479
18.1 Introduction, 479
18.2 General Issues in Reporting, 480
18.2.1 Uniformity of Reporting Can Improve Comprehension, 481
18.2.2 Quality of the Literature, 482
18.2.3 Peer Review Is the Only Game in Town, 482
18.2.4 Publication Bias Can Distort Impressions Based on the
Literature, 483
18.3 Clinical Trial Reports, 484
CONTENTS xvii
18.3.1 General Considerations, 485
18.3.2 Employ a Complete Outline for CTE Reporting, 490
18.4 Authorship, 494
18.4.1 Inclusion and Ordering, 495
18.4.2 Responsibility of Authorship, 496
18.4.3 Authorship Models, 496
18.4.4 Some Other Practicalities, 498
18.5 Alternative Ways to Disseminate Results, 499
18.6 Summary, 499
18.7 Questions for Discussion, 500
19 Factorial Designs 501
19.1 Introduction, 501
19.2 Characteristics of Factorial Designs, 502
19.2.1 Interactions or Efficiency, but Not Both Simultaneously, 502
19.2.2 Factorial Designs Are Defined by Their Structure, 502
19.2.3 Factorial Designs Can Be Made Efficient, 504
19.3 Treatment Interactions, 505
19.3.1 Factorial Designs Are the Only Way to Study Interactions, 505
19.3.2 Interactions Depend on the Scale of Measurement, 507
19.3.3 The Interpretation of Main Effects Depends on Interac¬
tions, 507
19.3.4 Analyses Can Employ Linear Models, 508
19.4 Examples of Factorial Designs, 509
19.5 Partial, Fractional, and Incomplete Factorials, 511
19.5.1 Use Partial Factorial Designs When Interactions Are Absent, 511
19.5.2 Incomplete Designs Present Special Problems, 512
19.6 Summary, 512
19.7 Questions for Discussion, 513
20 Crossover Designs 515
20.1 Introduction, 515
20.1.1 Other Ways of Giving Multiple Treatments Are Not
Crossovers, 516
20.1.2 Treatment Periods May Be Randomly Assigned, 516
20.2 Advantages and Disadvantages, 517
20.2.1 Crossover Designs Can Increase Precision, 517
20.2.2 A Crossover Design Might Improve Recruitment, 518
20.2.3 Carryover Effects Are a Potential Problem, 518
20.2.4 Dropouts Have Strong Effects, 519
20.2.5 Analysis Is More Complex Than Parallel Groups Designs, 519
20.2.6 Prerequisites Are Needed to Apply Crossover Designs, 520
20.3 Analysis, 520
xviii CONTENTS
20.3.1 Analysis Can Be Based on a Cell Means Model, 521
20.3.2 Other Issues in Analysis, 525
20.3.3 Classic Case Study, 525
20.4 Summary, 526
20.5 Questions for Discussion, 527
21 Meta Analyses 529
21.1 Introduction, 529
21.1.1 Meta Analyses Formalize Synthesis and Increase Precision, 530
21.2 A Sketch of Meta Analysis Methods, 531
21.2.1 Meta Analysis Necessitates Prerequisites, 531
21.2.2 Many Studies Are Potentially Relevant, 532
21.2.3 Select Studies, 533
21.2.4 Plan the Statistical Analysis, 533
21.2.5 Summarize the Data Using Observed and Expected, 534
21.3 Other Issues, 536
21.3.1 Meta Analyses Have Practical and Theoretical Limitations, 536
21.3.2 Meta Analysis Has Taught Useful Lessons, 537
21.4 Summary, 537
21.5 Questions for Discussion, 538
22 Misconduct and Fraud in Clinical Research 539
22.1 Introduction, 539
22.1.1 Integrity and Accountability Are Critically Important, 540
22.1.2 Fraud and Misconduct Are Difficult to Define, 541
22.2 Research Practices, 544
22.2.1 Misconduct Has Been Uncommon, 545
22.2.2 Causes of Misconduct, 546
22.3 General Approach to Allegations of Misconduct, 547
22.3.1 Government, 547
22.3.2 Institutions, 549
22.3.3 Problem Areas, 550
22.4 Characteristics of Some Misconduct Cases, 551
22.4.1 Darsee Case, 551
22.4.2 Poisson (NSABP) Case, 553
22.4.3 Two Recent Cases from Germany, 556
22.5 Lessons, 557
22.5.1 Recognizing Fraud or Misconduct, 557
22.5.2 Misconduct Cases Yield Other Lessons, 559
22.6 Clinical Investigators Responsibilities, 560
22.6.1 General Responsibilities, 560
22.6.2 Additional Responsibilities Related to INDs, 561
22.6.3 Sponsor Responsibilities, 562
CONTENTS xix
22.7 Summary, 562
22.8 Questions for Discussion, 563
Appendices
A Data and Programs 565
A.I Introduction, 565
A.2 Data, 566
A.3 Design Programs, 566
A.3.1 Power and Sample Size Program, 566
A.3.2 Blocked Stratified Randomization, 567
A.3.3 Continual Reassessment Method, 567
A.4 Mathematica Code, 567
B Notation and Terminology 569
B.I Introduction, 569
B.2 Notation, 569
B.2.1 Greek Letters, 570
B.2.2 Roman Letters, 571
B.2.3 Other Symbols, 572
B.3 Terminology and Concepts, 572
C Abbreviations 587
D Nuremberg Code 591
E Declaration of Helsinki 593
E.I Introduction, 593
E.2 Basic Principles for All Medical Research, 594
F NCI Data and Safety Monitoring Policy 599
F.I Introduction, 599
F.2 Responsibility for Data and Safety Monitoring, 599
F.3 Requirement for Data and Safety Monitoring Boards, 600
F.4 Responsibilities of the DSMB, 600
F.5 Membership, 600
F.6 Meetings, 601
F.7 Recommendations from the DSMB, 601
F.8 Release of Outcome Data, 602
F.9 Confidentiality Procedures, 602
F.10 Conflict of Interest, 602
xx CONTENTS
G NIH Data and Safety Monitoring Policy 605
G.I Background, 605
G.2 Principles of Monitoring Data and Safety, 606
G.3 Practical and Implementation Issues: Oversight of Monitoring, 606
G.4 Institutes and Centers Responsibilities, 606
G.5 Performance of Data and Safety Monitoring, 607
G.6 Examples of Monitoring Operations, 608
H Royal Statistical Society Code of Conduct 609
H.I Introduction, 609
H.2 Constitutional Authority, 609
H.3 Rules of Professional Conduct, 609
H.3.1 The Public Interest, 610
H.3.2 Duty to Employers and Clients, 610
H.3.3 Duty to the Profession, 610
H.3.4 Disciplinary Procedures, 611
Bibliography 613
Author Index 659
Subject Index 675
|
| adam_txt |
CONTENTS
Preface xxi
Preface to the First Edition xxv
1 Preliminaries 1
1.1 Introduction, 1
1.2 Audience and Scope, 2
1.3 Other Sources of Knowledge, 4
1.3.1 Terminology, 5
1.3.2 Review of Notation and Terminology Is Helpful, 6
1.4 Examples, Data, and Programs, 6
1.5 Summary, 7
2 Clinical Trials as Research 9
2.1 Introduction, 9
2.1.1 Clinical Reasoning Is Based on the Case History, 10
2.1.2 Statistical Reasoning Emphasizes Inference Based on Designed
Data Production, 12
2.1.3 Clinical and Statistical Reasoning Converge in Research, 13
2.2 Denning Clinical Trials Formally, 14
2.2.1 Mixing of Clinical and Statistical Reasoning Is Recent, 14
2.2.2 Clinical Trials Are Rigorously Defined, 16
2.2.3 Experiments Can Be Misunderstood, 17
2.2.4 Clinical Trials as Science, 18
2.2.5 Trials and Statistical Methods Fit within a Spectrum of
Clinical Research, 19
v
vi CONTENTS
2.3 Practicalities of Usage, 20
2.3.1 Predicates for a Trial, 20
2.3.2 Trials Can Provide Confirmatory Evidence, 20
2.3.3 Clinical Trials Are Unwieldy, Messy, and Reliable, 21
2.3.4 Other Methods Are Valid for Making Some Clinical
Inferences, 23
2.3.5 Trials Are Difficult to Apply in Some Circumstances, 25
2.3.6 Randomized Studies Can Be Initiated Early, 25
2.4 Summary, 26
2.5 Questions for Discussion, 26
3 Why Clinical Trials Are Ethical 29
3.1 Introduction, 29
3.1.1 Science and Ethics Share Objectives, 30
3.1.2 Equipoise and Uncertainty, 31
3.2 Duality, 32
3.2.1 Clinical Trials Sharpen, but Do Not Create, the Issue, 32
3.2.2 A Gene Therapy Tragedy Illustrates Duality, 32
3.2.3 Research and Practice Are Convergent, 33
3.2.4 The Hippocratic Tradition Does Not Proscribe Clinical
Trials, 36
3.2.5 Physicians Always Have Multiple Roles, 38
3.3 Historically Derived Principles of Ethics, 41
3.3.1 Nuremberg Contributed an Awareness of the Worst Problems, 41
3.3.2 High Profile Mistakes Were Made in the United States, 42
3.3.3 The Helsinki Declaration Was Widely Adopted, 42
3.3.4 Other International Guidelines Have Been Proposed, 44
3.3.5 Institutional Review Boards Provide Ethical Oversight, 45
3.3.6 Ethical Principles Relevant to Clinical Trials, 46
3.4 Contemporary Foundational Principles, 48
3.4.1 Collaborative Partnership, 48
3.4.2 Scientific Value, 49
3.4.3 Scientific Validity, 49
3.4.4 Fair Subject Selection, 49
3.4.5 Favorable Risk Benefit, 50
3.4.6 Independent Review, 50
3.4.7 Informed Consent, 51
3.4.8 Respect for Subjects, 52
3.5 Methodologic Reflections, 53
3.5.1 Practice Based on Unproven Treatments Is Not Ethical, 53
3.5.2 Ethics Considerations Are Important Determinants of Design, 55
3.5.3 Specific Methods Have Justification, 57
CONTENTS vii
3.6 Professional Conduct, 59
3.6.1 Conflict of Interest, 59
3.6.2 Professional Statistical Ethics, 61
3.7 Summary, 63
3.8 Questions for Discussion, 63
4 Contexts for Clinical Trials 65
4.1 Introduction, 65
4.1.1 Some Ways to Learn about Trials in a Given Context, 66
4.1.2 Issues of Context, 67
4.2 Drugs, 68
4.2.1 Are Drugs Special?, 70
4.2.2 Why Trials Are Used Extensively for Drugs, 71
4.3 Devices, 72
4.3.1 Use of Trials for Medical Devices, 73
4.3.2 Are Devices Different from Drugs?, 74
4.3.3 Case Study, 76
4.4 Prevention, 76
4.4.1 The Prevention versus Therapy Dichotomy Is Overworked, 77
4.4.2 Vaccines and Biologicals, 78
4.4.3 A Perspective on Risk Benefit, 79
4.4.4 Methodology and Framework for Prevention Trials, 81
4.5 Complementary and Alternative Medicine, 82
4.5.1 The Essential Paradox of CAM and Clinical Trials, 84
4.5.2 Why Trials Have Not Been Used Extensively in CAM, 85
4.5.3 Some Principles for Rigorous Evaluation, 87
4.6 Surgery and Skill Dependent Therapies, 88
4.6.1 Why Trials Have Not Been Used Extensively in Surgery, 90
4.6.2 Reasons Why Some Surgical Therapies Require Less Rig¬
orous Study Designs, 92
4.6.3 Sources of Variation, 92
4.6.4 Difficulties of Inference, 93
4.6.5 Control of Observer Bias Is Possible, 94
4.6.6 Illustrations from an Emphysema Surgery Trial, 95
4.7 A Brief View of Some Other Contexts, 101
4.7.1 Screening Trials, 101
4.7.2 Diagnostic Trials, 103
4.7.3 Radiotherapy, 103
4.8 Summary, 104
4.9 Questions for Discussion, 105
5 Statistical Perspectives 107
5.1 Introduction, 107
viii CONTENTS
5.2 Differences in Statistical Perspectives, 108
5.2.1 Models and Parameters, 108
5.2.2 Philosophy of Inference Divides Statisticians, 108
5.2.3 Resolution, 109
5.2.4 Points of Agreement, 110
5.3 Frequentist, 112
5.3.1 Binomial Case Study, 113
5.3.2 Other Issues, 114
5.4 Bayesian, 115
5.4.1 Choice of a Prior Distribution Is a Source of Contention, 116
5.4.2 Binomial Case Study, 117
5.4.3 Bayesian Inference Is Different, 119
5.5 Likelihood, 120
5.5.1 Binomial Case Study, 121
5.5.2 Likelihood Based Design, 122
5.6 Afterthoughts, 123
5.6.1 Statistical Procedures Are Not Standardized, 123
5.6.2 Practical Controversies Related to Statistics Exist, 123
5.7 Summary, 125
5.8 Questions for Discussion, 125
6 Clinical Trials as Experimental Designs 127
6.1 Introduction, 127
6.1.1 Trials Are Relatively Simple Experimental Designs, 128
6.1.2 Study Design Is Critical for Inference, 129
6.2 Goals of Experimental Design, 129
6.2.1 Control of Random Error and Bias Is the Goal, 129
6.2.2 Conceptual Simplicity Is Also a Goal, 130
6.2.3 Encapsulation of Subjectivity, 131
6.2.4 Leech Case Study, 131
6.3 Trial Terminology, 132
6.3.1 Drug Development Traditionally Recognizes Four Trial
Designs, 132
6.3.2 Descriptive Terminology Is Broader and Recognizes More
Types of Trials, 133
6.4 Design Concepts, 134
6.4.1 The Foundations of Design Are Observation and Theory, 134
6.4.2 A Lesson from the Women's Health Initiative, 136
6.4.3 Experiments Use Three Components of Design, 137
6.5 Survey of Developmental Trial Designs, 143
6.5.1 Early Development, 143
6.5.2 Middle Development, 144
6.5.3 Late Development, 148
CONTENTS ix
6.6 Special Design Issues, 151
6.6.1 Placebos, 151
6.6.2 Equivalence or Noninferiority, 154
6.6.3 Nonuniformity of Effect, 154
6.6.4 Randomized Discontinuation, 155
6.6.5 Hybrid Designs May Be Needed for Resolving Special
Questions, 156
6.6.6 Clinical Trials Cannot Meet Some Objectives, 156
6.7 Importance of the Protocol Document, 157
6.7.1 Protocols Have Many Functions, 158
6.7.2 Deviations from Protocol Specifications Are Common, 159
6.7.3 Protocols Are Structured, Logical, and Complete, 160
6.8 Summary, 164
6.9 Questions for Discussion, 165
7 Random Error and Bias 167
7.1 Introduction, 167
7.2 Random Error, 169
7.2.1 Hypothesis Tests versus Significance Tests, 169
7.2.2 Hypothesis Tests Are Subject to Two Types of Random
Error, 170
7.2.3 Type I Errors Are Relatively Easy to Control, 171
7.2.4 The Properties of Confidence Intervals Are Similar, 171
7.2.5 Using a One or Two Sided Hypothesis Test Is Not the
Right Question, 172
7.2.6 P Values Quantify the Type I Error, 173
7.2.7 Type II Errors Depend on the Clinical Difference of
Interest, 173
7.2.8 Post hoc Power Calculations Are not Helpful, 175
7.3 Clinical Biases, 176
7.3.1 Relative Size of Random Error and Bias Is Important, 176
7.3.2 Bias Arises from Numerous Sources, 176
7.3.3 Controlling Structural Bias Is Conceptually Simple, 179
7.4 Statistical Bias, 182
7.4.1 Some Statistical Bias Can Be Corrected, 183
7.4.2 Unbiasedness Is Not the Only Desirable Attribute of an
Estimator, 183
7.5 Summary, 185
7.6 Questions for Discussion, 185
8 Objectives and Outcomes 187
8.1 Introduction, 187
X CONTENTS
8.2 Objectives, 188
8.2.1 Estimation Is the Most Common Objective, 188
8.2.2 Selection Can Also Be an Objective, 189
8.2.3 Objectives Require Various Scales of Measurement, 189
8.3 Outcomes, 190
8.3.1 Mixed Outcomes and Predictors, 190
8.3.2 Criteria for Evaluating Outcomes, 191
8.3.3 Prefer "Hard" or Objective Outcomes, 191
8.3.4 Outcomes Can Be Quantitative or Qualitative, 192
8.3.5 Measures Are Useful and Efficient Outcomes, 192
8.3.6 Some Outcomes Are Summarized as Counts, 193
8.3.7 Ordered Categories Are Commonly Used for Severity or
Toxicity, 193
8.3.8 Unordered Categories Are Sometimes Used, 193
8.3.9 Dichotomies Are Simple Summaries, 194
8.3.10 Event Times May Be Censored, 194
8.3.11 Event Time Data Require Two Numerical Values, 196
8.3.12 Censoring and Lost to Follow up Are Not the Same, 197
8.3.13 Survival and Disease Progression, 198
8.3.14 Composite Outcomes Instead of Censoring, 199
8.3.15 Waiting for Good Events Complicates Censoring, 199
8.4 Surrogate Outcomes, 200
8.4.1 Surrogate Outcomes Are Disease Specific, 201
8.4.2 Surrogate Outcomes Can Make Trials More Efficient, 204
8.4.3 Surrogate Outcomes Have Significant Limitations, 205
8.5 Some Special Endpoints, 207
8.5.1 Repeated Measurements Are not Common in Clinical Tri¬
als, 207
8.5.2 Patient Reported Outcomes, 207
8.6 Summary, 208
8.7 Questions for Discussion, 209
9 Translational Clinical Trials 211
9.1 Introduction, 211
9.1.1 Translational Setting and Outcomes, 212
9.1.2 Character and Definition, 213
9.1.3 Small Does Not Mean Translational, 214
9.2 Information from Translational Trials, 214
9.2.1 Parameter Uncertainty versus Outcome Uncertainty, 214
9.2.2 Entropy, 215
9.2.3 Empirical Entropy Is Biased, 216
9.2.4 Variance, 216
9.2.5 Sample Size for Translational Trials, 218
CONTENTS xi
9.3 Summary, 220
9.4 Questions for Discussion, 221
10 Dose Finding Designs 223
10.1 Introduction, 223
10.2 Principles, 224
10.2.1 What Does "Phase I" Mean?, 224
10.2.2 Distinguish Dose Safety from Dose Efficacy, 226
10.2.3 Dose Optimality Is a Design Definition, 226
10.2.4 The General Dose Finding Problem Is Unsolved, 227
10.2.5 Unavoidable Subjectivity, 228
10.2.6 Sample Size Is an Outcome of Dose Finding Studies, 229
10.2.7 Idealized Dose Finding Design, 229
10.3 Fibonacci and Related Dose Ranging, 230
10.3.1 Some Historical Designs, 231
10.3.2 Typical Design, 231
10.3.3 Operating Characteristics Can Be Calculated, 232
10.3.4 Modifications, Strengths, and Weaknesses, 234
10.4 Designs Used for Dose Finding, 236
10.4.1 Mathematical Models Facilitate Inferences, 236
10.4.2 Continual Reassessment Method, 237
10.4.3 Pharmacokinetic Measurements Might Be Used to Improve
CRM Dose Escalations, 240
10.4.4 The CRM Is an Attractive Design to Criticize, 241
10.4.5 CRM Example, 241
10.4.6 Can Randomization Be Used in Phase I or TM Trials?, 242
10.4.7 Phase I Data Have Other Uses, 242
10.5 More General Dose Finding Issues, 242
10.5.1 Dose Finding Is Not Always One Dimensional, 243
10.5.2 Dual Dose Finding, 244
10.5.3 Optimizing Safety and Efficacy Jointly, 247
10.6 Summary, 250
10.7 Questions for Discussion, 250
11 Sample Size and Power 251
11.1 Introduction, 251
11.2 Principles, 252
11.2.1 What Is Precision?, 253
11.2.2 What Is Power?, 253
11.2.3 What Is Evidence?, 254
11.2.4 Sample Size and Power Calculations Are Approximations, 255
11.2.5 The Relationship between Power/Precision and Sample Size
Is Quadratic, 256
xii CONTENTS
11.3 Early Developmental Trials, 256
11.3.1 Translational Trials, 256
11.3.2 Dose Finding Trials, 258
11.4 Safety and Activity Studies, 258
11.4.1 Simple SA Designs Can Use Fixed Sample Size, 259
11.4.2 Exact Binomial Confidence Limits Are Helpful, 260
11.4.3 Bayesian Binomial Confidence Intervals, 263
11.4.4 A Bayesian Approach Can Use Prior Information, 264
11.4.5 Likelihood Based Approach for Proportions, 266
11.4.6 Confidence Intervals for a Mean Provide a Sample Size
Approach, 267
11.4.7 Confidence Intervals for Event Rates Can Determine
Sample Size, 268
11.4.8 Likelihood Based Approach for Event Rates, 271
11.4.9 Ineffective or Unsafe Treatments Should Be Discarded
Early, 271
11.4.10 Two Stage Designs Are Efficient, 272
11.4.11 Randomized SA Trials, 273
11.5 Comparative Trials, 277
11.5.1 How to Choose Type I and II Error Rates, 277
11.5.2 Comparisons Using the / Test Are a Good Learning
Example, 278
11.5.3 Likelihood Based Approach, 280
11.5.4 Dichotomous Responses Are More Complex, 282
11.5.5 Hazard Comparisons Yield Similar Equations, 283
11.5.6 Parametric and Nonparametric Equations Are Connected, 286
11.5.7 Accommodating Unbalanced Treatment Assignments, 286
11.5.8 A Simple Accrual Model Can Also Be Incorporated, 288
11.5.9 Noninferiority, 290
11.6 ES Trials, 295
11.6.1 Model Rare Events with the Poisson Distribution, 295
11.6.2 Likelihood Approach for Poisson Rates, 296
11.7 Other Considerations, 297
11.7.1 Cluster Randomization Requires Increased Sample Size, 297
11.7.2 Simple Cost Optimization, 298
11.7.3 Increase the Sample Size for Nonadherence, 299
11.7.4 Simulated Lifetables Can Be a Simple Design Tool, 301
11.7.5 Sample Size for Prognostic Factor Studies, 302
11.7.6 Computer Programs Simplify Calculations, 303
11.7.7 Simulation Is a Powerful and Flexible Design Alternative, 304
11.7.8 Power Curves are Sigmoid Shaped, 304
11.8 Summary, 305
11.9 Questions for Discussion, 306
CONTENTS xiii
12 The Study Cohort 309
12.1 Introduction, 309
12.2 Defining the Study Cohort, 310
12.2.1 Active Sampling or Enrichment, 310
12.2.2 Participation May Select Subjects with Better Prognosis, 311
12.2.3 Define the Study Population Using Eligibility and
Exclusion Criteria, 314
12.2.4 Quantitative Selection Criteria versus False Precision, 316
12.2.5 Comparative Trials Are Not Sensitive to Selection, 317
12.3 Anticipating Accrual, 318
12.3.1 Using a Run in Period, 318
12.3.2 Estimate Accrual Quantitatively, 319
12.4 Inclusiveness, Representation, and Interactions, 322
12.4.1 Inclusiveness Is a Worthy Goal, 322
12.4.2 Barriers Can Hinder Trial Participation, 322
12.4.3 Efficacy versus Effectiveness Trials, 323
12.4.4 Representation: Politics Blunders into Science, 324
12.5 Summary, 329
12.6 Questions for Discussion, 330
13 Treatment Allocation 331
13.1 Introduction, 331
13.2 Randomization, 332
13.2.1 Randomization Controls the Influence of Unknown Fac¬
tors, 333
13.2.2 Haphazard Assignments Are Not Random, 335
13.2.3 Simple Randomization Can Yield Imbalances, 335
13.3 Constrained Randomization, 336
13.3.1 Blocking Improves Balance, 336
13.3.2 Blocking and Stratifying Balances Prognostic Factors, 337
13.3.3 Other Considerations Regarding Blocking, 339
13.4 Adaptive Allocation, 340
13.4.1 Urn Designs Also Improve Balance, 340
13.4.2 Minimization Yields Tight Balance, 341
13.4.3 Play the Winner, 342
13.5 Other Issues Regarding Randomization, 343
13.5.1 Administration of the Randomization, 343
13.5.2 Computers Generate Pseudorandom Numbers, 345
13.5.3 Randomization Justifies Type I Errors, 345
13.6 Unequal Treatment Allocation, 349
13.6.1 Subsets May Be of Interest, 350
13.6.2 Treatments May Differ Greatly in Cost, 350
13.6.3 Variances May Be Different, 350
xiv CONTENTS
13.7 Randomization before Consent, 351
13.8 Summary, 352
13.9 Questions for Discussion, 352
14 Treatment Effects Monitoring 355
14.1 Introduction, 355
14.1.1 Motives for Monitoring, 356
14.1.2 Components of Responsible Monitoring, 357
14.1.3 Trials Can Be Stopped for a Variety of Reasons, 357
14.1.4 There Is Tension in the Decision to Stop, 358
14.2 Administrative Issues in Trial Monitoring, 359
14.2.1 Monitoring of Single Center Studies Relies on Periodic
Investigator Reporting, 360
14.2.2 Composition and Organization of the TEMC, 361
14.2.3 Complete Objectivity Is Not Ethical, 364
14.3 Organizational Issues Related to Data, 366
14.3.1 The TEMC Assesses Baseline Comparability, 366
14.3.2 The TEMC Reviews Accrual and Expected Time to Study
Completion, 367
14.3.3 Timeliness of Data and Reporting Lags, 367
14.3.4 Data Quality Is a Major Focus of the TEMC, 368
14.3.5 The TEMC Reviews Safety and Toxicity Data, 368
14.3.6 Efficacy Differences Are Assessed by the TEMC, 369
14.3.7 The TEMC Should Address a Few Practical Questions
Specifically, 369
14.3.8 The TEMC Mechanism Has Potential Weaknesses, 371
14.4 Statistical Methods for Monitoring, 371
14.4.1 There Are Several Approaches to Evaluating Incomplete
Evidence, 371
14.4.2 Likelihood Methods, 373
14.4.3 Bayesian Methods, 378
14.4.4 Decision Theoretic Methods, 381
14.4.5 Frequentist Methods, 381
14.4.6 Other Monitoring Tools, 387
14.4.7 Some Software, 392
14.5 Summary, 392
14.6 Questions for Discussion, 393
15 Counting Subjects and Events 395
15.1 Introduction, 395
15.2 Nature of Some Specific Data Imperfections, 396
15.2.1 Evaluability Criteria Are a Methodologic Error, 397
CONTENTS xv
15.2.2 Statistical Methods Can Cope with Some Types of Missing
Data, 398
15.2.3 Protocol Nonadherence Is Common, 400
15.3 Treatment Nonadherence, 402
15.3.1 Intention to Treat Is a Policy of Inclusion, 402
15.3.2 Coronary Drug Project Results Illustrate the Pitfalls of
Exclusions based on Nonadherence, 403
15.3.3 Statistical Studies Support the ITT Approach, 403
15.3.4 Trials Can Be Viewed as Tests of Treatment Policy, 404
15.3.5 ITT Analyses Cannot Always Be Applied, 404
15.3.6 Trial Inferences Depend on the Experimental Design, 406
15.4 Summary, 406
15.5 Questions for Discussion, 407
16 Estimating Clinical Effects 409
16.1 Introduction, 409
16.1.1 Structure Aids Data Interpretation, 410
16.1.2 Estimates of Risk Are Natural and Useful, 411
16.2 Dose Finding and PK Trials, 412
16.2.1 Pharmacokinetic Models Are Essential for Analyzing DF
Trials, 412
16.2.2 A Two Compartment Model Is Simple but Realistic, 413
16.2.3 PK Models Are Used by "Model Fitting", 416
16.3 SA Studies, 417
16.3.1 Mesothelioma Clinical Trial Example, 417
16.3.2 Summarize Risk for Dichotomous Factors, 418
16.3.3 Nonparametric Estimates of Survival
Are Robust, 420
16.3.4 Parametric (Exponential) Summaries of Survival Are Effi¬
cient, 421
16.4 Comparative Efficacy Trials (Phase III), 423
16.4.1 Examples of CTE Trials Used in This Section, 424
16.4.2 Continuous Measures Estimate Treatment Differences, 426
16.4.3 Baseline Measurements Can Increase Precision, 426
16.4.4 Nonparametric Survival Comparisons, 427
16.4.5 Risk (Hazard) Ratios and Confidence Intervals Are Clini¬
cally Useful Data Summaries, 429
16.4.6 Statistical Models Are Helpful Tools. 431
16.4.7 P Values Do Not Measure Evidence, 432
16.5 Strength of Evidence through Support Intervals, 434
16.5.1 Support Intervals Are Based on the Likelihood Function, 434
16.5.2 Support Intervals Can Be Used with Any Outcome, 435
16.6 Special Methods of Analysis, 436
xvi CONTENTS
16.6.1 The Bootstrap Is Based on Resampling, 437
16.6.2 Some Clinical Questions Require Other Special Methods
of Analysis, 438
16.7 Exploratory or Hypothesis Generating Analyses, 442
16.7.1 Clinical Trial Data Lend Themselves to Exploratory Anal¬
yses, 442
16.7.2 Multiple Tests Multiply Type I Errors, 442
16.7.3 Kinds of Multiplicity, 443
16.7.4 Subgroup Analyses Are Error Prone, 443
16.8 Summary, 446
16.9 Questions for Discussion, 447
17 Prognostic Factor Analyses 453
17.1 Introduction, 453
17.1.1 Studying Prognostic Factors Is Broadly Useful, 454
17.1.2 Prognostic Factors Can Be Constant or Time Varying, 455
17.2 Model Based Methods, 456
17.2.1 Models Combine Theory and Data, 456
17.2.2 The Scale of Measurements (Coding) May Be Important, 457
17.2.3 Use Flexible Covariate Models, 457
17.2.4 Building Parsimonious Models Is the Next Step, 459
17.2.5 Incompletely Specified Models May Yield Biased Estimates, 464
17.2.6 Study Second Order Effects (Interactions), 465
17.2.7 PFAs Can Help Describe Risk Groups, 466
17.2.8 Power and Sample Size for PFAs, 470
17.3 Adjusted Analyses of Comparative Trials, 470
17.3.1 What Should We Adjust For?, 471
17.3.2 What Can Happen?, 472
17.4 Non Model Based Methods for PFAs, 475
17.4.1 Recursive Partitioning Uses Dichotomies, 475
17.4.2 Neural Networks Are Used for Pattern Recognition, 476
17.5 Summary, 477
17.6 Questions for Discussion, 478
18 Reporting and Authorship 479
18.1 Introduction, 479
18.2 General Issues in Reporting, 480
18.2.1 Uniformity of Reporting Can Improve Comprehension, 481
18.2.2 Quality of the Literature, 482
18.2.3 Peer Review Is the Only Game in Town, 482
18.2.4 Publication Bias Can Distort Impressions Based on the
Literature, 483
18.3 Clinical Trial Reports, 484
CONTENTS xvii
18.3.1 General Considerations, 485
18.3.2 Employ a Complete Outline for CTE Reporting, 490
18.4 Authorship, 494
18.4.1 Inclusion and Ordering, 495
18.4.2 Responsibility of Authorship, 496
18.4.3 Authorship Models, 496
18.4.4 Some Other Practicalities, 498
18.5 Alternative Ways to Disseminate Results, 499
18.6 Summary, 499
18.7 Questions for Discussion, 500
19 Factorial Designs 501
19.1 Introduction, 501
19.2 Characteristics of Factorial Designs, 502
19.2.1 Interactions or Efficiency, but Not Both Simultaneously, 502
19.2.2 Factorial Designs Are Defined by Their Structure, 502
19.2.3 Factorial Designs Can Be Made Efficient, 504
19.3 Treatment Interactions, 505
19.3.1 Factorial Designs Are the Only Way to Study Interactions, 505
19.3.2 Interactions Depend on the Scale of Measurement, 507
19.3.3 The Interpretation of Main Effects Depends on Interac¬
tions, 507
19.3.4 Analyses Can Employ Linear Models, 508
19.4 Examples of Factorial Designs, 509
19.5 Partial, Fractional, and Incomplete Factorials, 511
19.5.1 Use Partial Factorial Designs When Interactions Are Absent, 511
19.5.2 Incomplete Designs Present Special Problems, 512
19.6 Summary, 512
19.7 Questions for Discussion, 513
20 Crossover Designs 515
20.1 Introduction, 515
20.1.1 Other Ways of Giving Multiple Treatments Are Not
Crossovers, 516
20.1.2 Treatment Periods May Be Randomly Assigned, 516
20.2 Advantages and Disadvantages, 517
20.2.1 Crossover Designs Can Increase Precision, 517
20.2.2 A Crossover Design Might Improve Recruitment, 518
20.2.3 Carryover Effects Are a Potential Problem, 518
20.2.4 Dropouts Have Strong Effects, 519
20.2.5 Analysis Is More Complex Than Parallel Groups Designs, 519
20.2.6 Prerequisites Are Needed to Apply Crossover Designs, 520
20.3 Analysis, 520
xviii CONTENTS
20.3.1 Analysis Can Be Based on a Cell Means Model, 521
20.3.2 Other Issues in Analysis, 525
20.3.3 Classic Case Study, 525
20.4 Summary, 526
20.5 Questions for Discussion, 527
21 Meta Analyses 529
21.1 Introduction, 529
21.1.1 Meta Analyses Formalize Synthesis and Increase Precision, 530
21.2 A Sketch of Meta Analysis Methods, 531
21.2.1 Meta Analysis Necessitates Prerequisites, 531
21.2.2 Many Studies Are Potentially Relevant, 532
21.2.3 Select Studies, 533
21.2.4 Plan the Statistical Analysis, 533
21.2.5 Summarize the Data Using Observed and Expected, 534
21.3 Other Issues, 536
21.3.1 Meta Analyses Have Practical and Theoretical Limitations, 536
21.3.2 Meta Analysis Has Taught Useful Lessons, 537
21.4 Summary, 537
21.5 Questions for Discussion, 538
22 Misconduct and Fraud in Clinical Research 539
22.1 Introduction, 539
22.1.1 Integrity and Accountability Are Critically Important, 540
22.1.2 Fraud and Misconduct Are Difficult to Define, 541
22.2 Research Practices, 544
22.2.1 Misconduct Has Been Uncommon, 545
22.2.2 Causes of Misconduct, 546
22.3 General Approach to Allegations of Misconduct, 547
22.3.1 Government, 547
22.3.2 Institutions, 549
22.3.3 Problem Areas, 550
22.4 Characteristics of Some Misconduct Cases, 551
22.4.1 Darsee Case, 551
22.4.2 Poisson (NSABP) Case, 553
22.4.3 Two Recent Cases from Germany, 556
22.5 Lessons, 557
22.5.1 Recognizing Fraud or Misconduct, 557
22.5.2 Misconduct Cases Yield Other Lessons, 559
22.6 Clinical Investigators' Responsibilities, 560
22.6.1 General Responsibilities, 560
22.6.2 Additional Responsibilities Related to INDs, 561
22.6.3 Sponsor Responsibilities, 562
CONTENTS xix
22.7 Summary, 562
22.8 Questions for Discussion, 563
Appendices
A Data and Programs 565
A.I Introduction, 565
A.2 Data, 566
A.3 Design Programs, 566
A.3.1 Power and Sample Size Program, 566
A.3.2 Blocked Stratified Randomization, 567
A.3.3 Continual Reassessment Method, 567
A.4 Mathematica Code, 567
B Notation and Terminology 569
B.I Introduction, 569
B.2 Notation, 569
B.2.1 Greek Letters, 570
B.2.2 Roman Letters, 571
B.2.3 Other Symbols, 572
B.3 Terminology and Concepts, 572
C Abbreviations 587
D Nuremberg Code 591
E Declaration of Helsinki 593
E.I Introduction, 593
E.2 Basic Principles for All Medical Research, 594
F NCI Data and Safety Monitoring Policy 599
F.I Introduction, 599
F.2 Responsibility for Data and Safety Monitoring, 599
F.3 Requirement for Data and Safety Monitoring Boards, 600
F.4 Responsibilities of the DSMB, 600
F.5 Membership, 600
F.6 Meetings, 601
F.7 Recommendations from the DSMB, 601
F.8 Release of Outcome Data, 602
F.9 Confidentiality Procedures, 602
F.10 Conflict of Interest, 602
xx CONTENTS
G NIH Data and Safety Monitoring Policy 605
G.I Background, 605
G.2 Principles of Monitoring Data and Safety, 606
G.3 Practical and Implementation Issues: Oversight of Monitoring, 606
G.4 Institutes and Centers Responsibilities, 606
G.5 Performance of Data and Safety Monitoring, 607
G.6 Examples of Monitoring Operations, 608
H Royal Statistical Society Code of Conduct 609
H.I Introduction, 609
H.2 Constitutional Authority, 609
H.3 Rules of Professional Conduct, 609
H.3.1 The Public Interest, 610
H.3.2 Duty to Employers and Clients, 610
H.3.3 Duty to the Profession, 610
H.3.4 Disciplinary Procedures, 611
Bibliography 613
Author Index 659
Subject Index 675 |
| any_adam_object | 1 |
| any_adam_object_boolean | 1 |
| author | Piantadosi, Steven |
| author_facet | Piantadosi, Steven |
| author_role | aut |
| author_sort | Piantadosi, Steven |
| author_variant | s p sp |
| building | Verbundindex |
| bvnumber | BV023042822 |
| callnumber-first | R - Medicine |
| callnumber-label | R853 |
| callnumber-raw | R853.C55 |
| callnumber-search | R853.C55 |
| callnumber-sort | R 3853 C55 |
| callnumber-subject | R - General Medicine |
| classification_rvk | XF 3400 |
| ctrlnum | (OCoLC)57682616 (DE-599)BVBBV023042822 |
| dewey-full | 610/.72 |
| dewey-hundreds | 600 - Technology (Applied sciences) |
| dewey-ones | 610 - Medicine and health |
| dewey-raw | 610/.72 |
| dewey-search | 610/.72 |
| dewey-sort | 3610 272 |
| dewey-tens | 610 - Medicine and health |
| discipline | Medizin |
| discipline_str_mv | Medizin |
| edition | 2. ed. |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02859nam a2200685zc 4500</leader><controlfield tag="001">BV023042822</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20121203 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">071210s2005 xxud||| |||| 00||| eng d</controlfield><datafield tag="010" ind1=" " ind2=" "><subfield code="a">2005040833</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">0471727814</subfield><subfield code="c">cloth : alk. paper</subfield><subfield code="9">0-471-72781-4</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780471727811</subfield><subfield code="9">978-0-471-72781-1</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)57682616</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV023042822</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">aacr</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="044" ind1=" " ind2=" "><subfield code="a">xxu</subfield><subfield code="c">US</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-355</subfield><subfield code="a">DE-29T</subfield><subfield code="a">DE-188</subfield><subfield code="a">DE-578</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">R853.C55</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">610/.72</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">XF 3400</subfield><subfield code="0">(DE-625)152765:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Piantadosi, Steven</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Clinical trials</subfield><subfield code="b">a methodologic perspective</subfield><subfield code="c">Steven Piantadosi</subfield></datafield><datafield tag="250" ind1=" " ind2=" "><subfield code="a">2. ed.</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Hoboken, NJ</subfield><subfield code="b">Wiley-Interscience</subfield><subfield code="c">2005</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XXVII, 687 S.</subfield><subfield code="b">graph. Darst.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="0" ind2=" "><subfield code="a">Wiley series in probability and statistics</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Clinical trials</subfield><subfield code="2">gtt</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Ensaios clínicos (pesquisa e planejamento) (estatísticas e dados numéricos)</subfield><subfield code="2">larpcal</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Ensaios clínicos (pesquisa e planejamento) (métodos)</subfield><subfield code="2">larpcal</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Estatística (métodos)</subfield><subfield code="2">larpcal</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Statistische methoden</subfield><subfield code="2">gtt</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Études cliniques - Méthodes statistiques</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Statistik</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Clinical trials</subfield><subfield code="x">Statistical methods</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Biomedical Research</subfield><subfield code="x">methods</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Research</subfield><subfield code="x">methods</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Clinical Trials</subfield><subfield code="x">methods</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Statistics</subfield><subfield code="x">methods</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Methode</subfield><subfield code="0">(DE-588)4038971-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Medizin</subfield><subfield code="0">(DE-588)4038243-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Experiment</subfield><subfield code="0">(DE-588)4015999-1</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Klinisches Experiment</subfield><subfield code="0">(DE-588)4164223-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Klinisches Experiment</subfield><subfield code="0">(DE-588)4164223-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Methode</subfield><subfield code="0">(DE-588)4038971-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="689" ind1="1" ind2="0"><subfield code="a">Experiment</subfield><subfield code="0">(DE-588)4015999-1</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2="1"><subfield code="a">Medizin</subfield><subfield code="0">(DE-588)4038243-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2="2"><subfield code="a">Methode</subfield><subfield code="0">(DE-588)4038971-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2=" "><subfield code="8">1\p</subfield><subfield code="5">DE-604</subfield></datafield><datafield tag="856" ind1="4" ind2=" "><subfield code="u">http://www.loc.gov/catdir/enhancements/fy0623/2005040833-b.html</subfield><subfield code="3">Contributor biographical information</subfield></datafield><datafield tag="856" ind1="4" ind2=" "><subfield code="u">http://www.loc.gov/catdir/enhancements/fy0623/2005040833-d.html</subfield><subfield code="3">Publisher description</subfield></datafield><datafield tag="856" ind1="4" ind2=" "><subfield code="u">http://www.loc.gov/catdir/enhancements/fy0623/2005040833-t.html</subfield><subfield code="3">Table of contents only</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">HBZ Datenaustausch</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=016246318&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-016246318</subfield></datafield><datafield tag="883" ind1="1" ind2=" "><subfield code="8">1\p</subfield><subfield code="a">cgwrk</subfield><subfield code="d">20201028</subfield><subfield code="q">DE-101</subfield><subfield code="u">https://d-nb.info/provenance/plan#cgwrk</subfield></datafield></record></collection> |
| id | DE-604.BV023042822 |
| illustrated | Illustrated |
| index_date | 2024-07-02T19:21:16Z |
| indexdate | 2024-07-09T21:09:39Z |
| institution | BVB |
| isbn | 0471727814 9780471727811 |
| language | English |
| lccn | 2005040833 |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-016246318 |
| oclc_num | 57682616 |
| open_access_boolean | |
| owner | DE-355 DE-BY-UBR DE-29T DE-188 DE-578 |
| owner_facet | DE-355 DE-BY-UBR DE-29T DE-188 DE-578 |
| physical | XXVII, 687 S. graph. Darst. |
| publishDate | 2005 |
| publishDateSearch | 2005 |
| publishDateSort | 2005 |
| publisher | Wiley-Interscience |
| record_format | marc |
| series2 | Wiley series in probability and statistics |
| spelling | Piantadosi, Steven Verfasser aut Clinical trials a methodologic perspective Steven Piantadosi 2. ed. Hoboken, NJ Wiley-Interscience 2005 XXVII, 687 S. graph. Darst. txt rdacontent n rdamedia nc rdacarrier Wiley series in probability and statistics Clinical trials gtt Ensaios clínicos (pesquisa e planejamento) (estatísticas e dados numéricos) larpcal Ensaios clínicos (pesquisa e planejamento) (métodos) larpcal Estatística (métodos) larpcal Statistische methoden gtt Études cliniques - Méthodes statistiques Statistik Clinical trials Statistical methods Biomedical Research methods Research methods Clinical Trials methods Statistics methods Methode (DE-588)4038971-6 gnd rswk-swf Medizin (DE-588)4038243-6 gnd rswk-swf Experiment (DE-588)4015999-1 gnd rswk-swf Klinisches Experiment (DE-588)4164223-5 gnd rswk-swf Klinisches Experiment (DE-588)4164223-5 s Methode (DE-588)4038971-6 s DE-604 Experiment (DE-588)4015999-1 s Medizin (DE-588)4038243-6 s 1\p DE-604 http://www.loc.gov/catdir/enhancements/fy0623/2005040833-b.html Contributor biographical information http://www.loc.gov/catdir/enhancements/fy0623/2005040833-d.html Publisher description http://www.loc.gov/catdir/enhancements/fy0623/2005040833-t.html Table of contents only HBZ Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=016246318&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis 1\p cgwrk 20201028 DE-101 https://d-nb.info/provenance/plan#cgwrk |
| spellingShingle | Piantadosi, Steven Clinical trials a methodologic perspective Clinical trials gtt Ensaios clínicos (pesquisa e planejamento) (estatísticas e dados numéricos) larpcal Ensaios clínicos (pesquisa e planejamento) (métodos) larpcal Estatística (métodos) larpcal Statistische methoden gtt Études cliniques - Méthodes statistiques Statistik Clinical trials Statistical methods Biomedical Research methods Research methods Clinical Trials methods Statistics methods Methode (DE-588)4038971-6 gnd Medizin (DE-588)4038243-6 gnd Experiment (DE-588)4015999-1 gnd Klinisches Experiment (DE-588)4164223-5 gnd |
| subject_GND | (DE-588)4038971-6 (DE-588)4038243-6 (DE-588)4015999-1 (DE-588)4164223-5 |
| title | Clinical trials a methodologic perspective |
| title_auth | Clinical trials a methodologic perspective |
| title_exact_search | Clinical trials a methodologic perspective |
| title_exact_search_txtP | Clinical trials a methodologic perspective |
| title_full | Clinical trials a methodologic perspective Steven Piantadosi |
| title_fullStr | Clinical trials a methodologic perspective Steven Piantadosi |
| title_full_unstemmed | Clinical trials a methodologic perspective Steven Piantadosi |
| title_short | Clinical trials |
| title_sort | clinical trials a methodologic perspective |
| title_sub | a methodologic perspective |
| topic | Clinical trials gtt Ensaios clínicos (pesquisa e planejamento) (estatísticas e dados numéricos) larpcal Ensaios clínicos (pesquisa e planejamento) (métodos) larpcal Estatística (métodos) larpcal Statistische methoden gtt Études cliniques - Méthodes statistiques Statistik Clinical trials Statistical methods Biomedical Research methods Research methods Clinical Trials methods Statistics methods Methode (DE-588)4038971-6 gnd Medizin (DE-588)4038243-6 gnd Experiment (DE-588)4015999-1 gnd Klinisches Experiment (DE-588)4164223-5 gnd |
| topic_facet | Clinical trials Ensaios clínicos (pesquisa e planejamento) (estatísticas e dados numéricos) Ensaios clínicos (pesquisa e planejamento) (métodos) Estatística (métodos) Statistische methoden Études cliniques - Méthodes statistiques Statistik Clinical trials Statistical methods Biomedical Research methods Research methods Clinical Trials methods Statistics methods Methode Medizin Experiment Klinisches Experiment |
| url | http://www.loc.gov/catdir/enhancements/fy0623/2005040833-b.html http://www.loc.gov/catdir/enhancements/fy0623/2005040833-d.html http://www.loc.gov/catdir/enhancements/fy0623/2005040833-t.html http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=016246318&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT piantadosisteven clinicaltrialsamethodologicperspective |