Design and Analysis of Non-Inferiority Trials (Chapman & Hall CRC Biostatistics Series)

The increased use of non-inferiority analysis has been accompanied by a proliferation of research on the design and analysis of non-inferiority studies. Using examples from real clinical trials, Design and Analysis of Non-Inferiority Trials brings together this body of research and confronts the issues involved in the design of a non-inferiority trial. Each chapter begins with a non-technical introduction, making the text easily understood by those without prior knowledge of this type of trial. Topics covered include: A variety of issues of non-inferiority trials, including multiple comparisons, missing data, analysis population, the use of safety margins, the internal consistency of non-inferiority inference, the use of surrogate endpoints, trial monitoring, and equivalence trials Specific issues and analysis methods when the data are binary, continuous, and time-to-event The history of non-inferiority trials and the design and conduct considerations for a non-inferiority trial The strength of evidence of an efficacy finding and how to evaluate the effect size of an active control therapy A comprehensive discussion on the purpose and issues involved with non-inferiority trials, Design and Analysis of Non-inferiority Trials will assist current and future scientists and statisticians on the optimal design of non-inferiority trials and in assessing the quality of non-inferiority comparisons done in practice. Design and Analysis of Non-Inferiority Trials......Page 1 Contents......Page 4 Preface......Page 10 1.1 Definition of Non-Inferiority......Page 12 1.2 Reasons for Non-Inferiority Trials......Page 14 1.3 Different Types of Comparisons......Page 18 1.4 A History of Non-Inferiority Trials......Page 21 References......Page 24 2.1 Introduction......Page 26 2.2 External Validity and Assay Sensitivity......Page 27 2.3 Critical Steps and Issues......Page 28 2.3.1 Historical Evidence of Sensitivity to Drug Effects......Page 29 2.3.2 Designing a Trial......Page 30 2.3.3 Selecting the Margin......Page 31 2.3.4 Study Conduct and Analysis Populations......Page 38 2.4 Sizing a Study......Page 41 2.5 Example of Anti-Infectives......Page 47 References......Page 51 3.1 Introduction......Page 53 3.2.2 Bayesian False-Positive Rate......Page 54 3.2.3 Relative Evidence between the Null and Alternative Hypotheses......Page 57 3.2.4 Additional Considerations......Page 59 3.3 Reproducibility......Page 60 3.3.2 Predicting Future and Hypothetical Outcomes......Page 62 References......Page 66 4.1 Introduction......Page 67 4.2.2 Modeling the Active Control Effect......Page 68 4.2.3 Extrapolating to the Non-Inferiority Trial......Page 69 4.2.4 Potential Biases and Random Highs......Page 72 4.3 Meta-Analysis Methods......Page 84 4.3.1 Fixed Effects Meta-Analysis......Page 85 4.3.2 Peto’s Method......Page 86 4.3.3 Random-Effects Meta-Analysis......Page 87 4.3.4 Sampling Distributions......Page 88 4.3.5 Concerns of Random-Effects Meta-Analyses......Page 91 4.3.6 Adjusting over Effect Modifiers......Page 95 4.4 Bayesian Meta-Analyses......Page 97 References......Page 99 5.1 Introduction......Page 101 5.2.1 Hypotheses and Tests......Page 102 5.3.1 Introduction......Page 108 5.3.2 Retention Fraction and Hypotheses......Page 109 5.3.3.2 Absolute Metrics......Page 112 5.3.4 Synthesis Methods as Prediction Interval Methods......Page 118 5.3.6 Bayesian Synthesis Methods......Page 120 5.3.7 Application......Page 125 5.3.8 Sample Size Determination......Page 127 5.4.1 Introduction......Page 130 5.4.2 Comparison of Methods......Page 131 5.4.3 Asymptotic Results......Page 134 5.4.4 More on Type I Error Rates......Page 138 5.4.4.1 Non-Inferiority Trial Size Depends on Estimation of Active Control Effect......Page 141 5.4.4.2 Incorporating Regression to Mean Bias......Page 142 5.5 A Case in Oncology......Page 151 5.5.1 Applying the Arithmetic Definition of Retention Fraction......Page 152 5.5.2 Applying the Geometric Definition of Retention Fraction......Page 153 5.5.3 Power of Such Procedures......Page 154 References......Page 156 6.1 Introduction......Page 158 6.2.1 Superiority over Placebo......Page 161 6.2.2 Non-Inferior to Active Control......Page 163 6.3 Bayesian Analyses......Page 169 References......Page 174 7.1 Introduction......Page 175 7.2 Comparing Multiple Groups to an Active Control......Page 176 7.2.1 Unordered Treatments: Subset Selection......Page 177 7.2.2 Ordered Treatments: Subset Selection......Page 178 7.3 Non-Inferiority on Multiple Endpoints......Page 179 7.3.1 Multiple Endpoints in a Single Family......Page 180 7.3.2 Multiple Endpoints in Multiple Families......Page 182 7.3.3 Further Considerations......Page 183 7.4.1 Testing Superiority after Achieving Non-Inferiority......Page 184 7.4.2 Testing Non-Inferiority after Failing Superiority......Page 186 References......Page 187 8.1 Introduction......Page 189 8.2.1 Potential Impact of Missing Data......Page 190 8.2.2 Preventing Missing Data......Page 192 8.2.3 Missing Data Mechanisms......Page 194 8.2.4 Assessing Missing Data Mechanisms......Page 195 8.2.5.1 Handling Ignorable Missing Data in Non-Inferiority Analyses......Page 197 8.2.5.2 Handling Non-Ignorable Missing Data......Page 201 8.3 Analysis Sets......Page 204 8.3.1 Different Analysis Populations......Page 205 8.3.2 Influence of Analysis Population on Conclusions......Page 206 8.3.3 Further Considerations......Page 211 References......Page 212 9.1 Introduction......Page 214 9.2 Considerations for Safety Study......Page 216 9.2.1 Safety Endpoint Considerations......Page 217 9.2.2 Design Considerations......Page 218 9.2.3.1 Ruling Out a Meaningful Risk Increase Compared to Placebo......Page 219 9.2.3.2 Ruling Out a Meaningful Risk Increase Compared to an Active Control......Page 220 9.2.3.3 Indirect Comparison to Placebo......Page 222 9.3 Cardiovascular Risk in Antidiabetic Therapy......Page 223 References......Page 225 10.1 Introduction......Page 226 10.2 Interaction Tests......Page 227 10.2.1 Test Procedures......Page 229 10.2.2 Internal Consistency......Page 231 10.2.3 Conclusions and Recommendations......Page 232 10.3 Surrogate Endpoints......Page 233 10.4 Adaptive Designs......Page 237 10.4.1 Group Sequential Designs......Page 238 10.4.2 Changing the Sample Size or the Primary Objective......Page 242 10.5 Equivalence Comparisons......Page 244 10.5.1 Data Scales......Page 245 10.5.2 Two One-Sided Tests Approach......Page 246 10.5.3 Distribution-Based Approaches......Page 247 10.5.4 Lot Consistency......Page 249 References......Page 254 11.1 Introduction......Page 257 11.2.1 Hypotheses and Issues......Page 259 11.2.2 Exact Methods......Page 260 11.2.2.1 Exact Confidence Intervals......Page 263 11.2.3 Asymptotic Methods......Page 265 11.2.4 Comparisons of Confidence Interval Methods......Page 268 11.2.4.1 Inferences on a Single Proportion......Page 269 11.2.4.2 Inferences for a Difference in Proportions......Page 270 11.2.5 Sample Size Determination......Page 274 11.2.5.1 Optimal Randomization Ratio......Page 277 11.3.2 Exact Methods......Page 279 11.3.2.1 Exact Conditional Non-Inferiority Test......Page 280 11.3.3 Asymptotic Methods......Page 284 11.3.4 Comparisons of Methods......Page 285 11.3.5 Sample-Size Determination......Page 289 11.3.5.1 Optimal Randomization Ratio......Page 292 11.4.1 Hypotheses......Page 295 11.4.2 Exact Methods......Page 296 11.4.3 Asymptotic Methods......Page 297 11.4.4 Sample Size Determination......Page 298 11.5 Bayesian Methods......Page 299 11.6 Stratified and Adjusted Analyses......Page 303 11.6.1 Adjusted Rates......Page 304 11.6.2 Adjusted Estimators......Page 306 11.7 Variable Margins......Page 310 11.8 Matched-Pair Designs......Page 314 11.8.1 Difference in Two Correlated Proportions......Page 315 11.8.2 Ratio of Two Correlated Proportions......Page 317 References......Page 320 12.1 Introduction......Page 324 12.2.1 Hypotheses and Issues......Page 325 12.2.2 Exact and Distribution-Free Methods......Page 326 12.2.3 Normalized Methods......Page 327 12.2.3.1 Test Statistics......Page 328 12.2.4 Bayesian Methods......Page 331 12.2.5 Sample Size Determination......Page 336 12.3.2 Exact and Distribution-Free Methods......Page 339 12.3.3.1 Test Statistics......Page 340 12.3.4 Bayesian Methods......Page 343 12.3.5 Sample Size Determination......Page 345 12.4 Analyses Involving Medians......Page 347 12.4.1 Hypotheses and Issues......Page 348 12.4.2 Nonparametric Methods......Page 349 12.4.3 Asymptotic Methods......Page 356 12.5 Ordinal Data......Page 358 References......Page 360 13.1 Introduction......Page 362 13.2 Censoring......Page 366 13.3 Exponential Distributions......Page 368 13.3.1 Confidence Intervals for a Difference in Means......Page 369 13.3.2 Confidence Intervals for the Hazard Ratio (Ratio of Means)......Page 371 13.4 Nonparametric Inference Based on a Hazard Ratio......Page 373 13.4.1 Event and Sample Size Determination......Page 380 13.4.2 Proportional Hazards Assessment Procedures......Page 382 13.5.1 Landmark Analyses......Page 385 13.5.2 Analyses on Medians......Page 389 13.6 Comparisons over Preset Intervals......Page 394 References......Page 397 A.1.1 p-Values......Page 399 A.1.2 Confidence Intervals......Page 405 A.1.3 Comparing and Contrasting Confidence Intervals and p-Values......Page 408 A.1.4.1 Exact and Permutation Methods......Page 409 A.1.4.2 Asymptotic Methods......Page 412 A.2.1 Posterior Probabilities and Credible Intervals......Page 414 A.2.2 Prior and Posterior Distributions......Page 416 A.2.3 Statistical Inference......Page 419 A.3.1.1 Exact Confidence Intervals and Credible Intervals Using a Jeffreys Prior......Page 423 A.3.1.2 Comparison Involving a Retention Fraction......Page 425 A.3.1.3 Likelihood Function for a Non-Inferiority Trial......Page 427 A.3.2 Dealing with More than One Comparison......Page 429 A.4.1 Stratification......Page 431 A.4.2 Analyses......Page 433 References......Page 435 C......Page 437 F......Page 438 L......Page 439 N......Page 440 S......Page 441 Z......Page 442 "The increased use of non-inferiority analysis has been accompanied by a proliferation of research on the design and analysis of non-inferiority studies. Design and Analysis of Non-Inferiority Trials brings together this body of research and confronts the issues involved in the design of a non-inferiority trial. Using examples from real clinical trials, the book discusses general and regulatory issues and illustrates how they affect analysis. Each chapter begins with a non-technical introduction, so the subject is easily understood by those without prior knowledge of non-inferiority clinical trials. The book also provides detailed mathematical approaches along with their mathematical properties"--Provided by publisher.