Methods and Applications of Statistics in Clinical Trials, Volume 2: Planning, Analysis, and Inferential Methods

Table of contents

1. Cover
2. Half Title page
3. Title page
4. Copyright page
5. Contributors
6. Preface
7. Chapter 1: Analysis of Over- and Underdispersed Data
   1. 1.1 Introduction
   2. 1.2 Overdispersed Binomial and Count Models
   3. 1.3 Other Approaches to Account for Overdispersion
   4. 1.4 Underdispersion
   5. 1.5 Software Notes
   6. References
8. Chapter 2: Analysis of Variance (ANOVA)
   1. 2.1 Introduction
   2. 2.2 Factors, Levels, Effects, and Cells
   3. 2.3 Cell Means Model
   4. 2.4 One-Way Classification
   5. 2.5 Parameter Estimation
   6. 2.6 The R(.) Notation—Partitioning Sum of Squares
   7. 2.7 ANOVA—Hypothesis of Equal Means
   8. 2.8 Multiple Comparisons
   9. 2.9 Two-Way Crossed Classification
   10. 2.10 Balanced and Unbalanced Data
   11. 2.11 Interaction Between Rows and Columns
   12. 2.12 Analysis of Variance Table
   13. References
9. Chapter 3: Assessment of Health-Related Quality of Life
   1. 3.1 Introduction
   2. 3.2 Choice of HRQOL Instruments
   3. 3.3 Establishment of Clear Objectives in HRQOL Assessments
   4. 3.4 Methods for HRQOL Assessment
   5. 3.5 HRQOL as the Primary End Point
   6. 3.6 Interpretation of HRQOL Results
   7. 3.7 Examples
   8. 3.8 Conclusion
   9. References
   10. Further Reading
10. Chapter 4: Bandit Processes and Response-Adaptive Clinical Trials: The Art of Exploration Versus Exploitation
    1. 4.1 Introduction
    2. 4.2 Exploration Versus Exploitation with Complete Observations
    3. 4.3 Exploration Versus Exploitation with Censored Observations
    4. 4.4 Conclusion
    5. References
11. Chapter 5: Bayesian Dose-Finding Designs in Healthy Volunteers
    1. 5.1 Introduction
    2. 5.2 A Bayesian Decision-Theoretic Design
    3. 5.3 An Example of Dose Escalation in Healthy Volunteer Studies
    4. 5.4 Discussion
    5. References
12. Chapter 6: Bootstrap
    1. 6.1 Introduction
    2. 6.2 Plug-In Principle
    3. 6.3 Monte Carlo Sampling— The “Second Bootstrap Principle”
    4. 6.4 Bias and Standard Error
    5. 6.5 Examples
    6. 6.6 Model Stability
    7. 6.7 Accuracy of Bootstrap Distributions
    8. 6.8 Bootstrap Confidence Intervals
    9. 6.9 Hypothesis Testing
    10. 6.10 Planning Clinical Trials
    11. 6.11 How Many Bootstrap Samples Are Needed
    12. 6.12 Additional References
    13. References
13. Chapter 7: Conditional Power in Clinical Trial Monitoring
    1. 7.1 Introduction
    2. 7.2 Conditional Power
    3. 7.3 Weight-Averaged Conditional Power or Bayesian Predictive Power
    4. 7.4 Conditional Power of a Different Kind: Discordance Probability
    5. 7.5 Analysis of a Randomized Trial
    6. 7.6 Conditional Power: Pros and Cons
    7. References
14. Chapter 8: Cost-Effectiveness Analysis
    1. 8.1 Introduction
    2. 8.2 Definitions and Design Issues
    3. 8.3 Cost and Effectiveness Data
    4. 8.4 The Analysis of Costs and Outcomes
    5. 8.5 Robustness and Generalizability in Cost-Effectiveness Analysis
    6. References
    7. Further Reading
15. Chapter 9: Cox-Type Proportional Hazards Models
    1. 9.1 Introduction
    2. 9.2 Cox Model for Univariate Failure Time Data Analysis
    3. 9.3 Marginal Models for Multivariate Failure Time Data Analysis
    4. 9.4 Practical Issues in Using the Cox Model
    5. 9.5 Examples
    6. 9.6 Extensions
    7. 9.7 Softwares and Codes
    8. References
    9. Further Reading
16. Chapter 10: Empirical Likelihood Methods in Clinical Experiments
    1. 10.1 Introduction
    2. 10.2 Classical EL: Several Ingredients for Theoretical Evaluations
    3. 10.3 The Relationship Between Empirical Likelihood and Bootstrap Methodologies
    4. 10.4 Bayes Methods Based on Empirical Likelihoods
    5. 10.5 Mixtures of Likelihoods
    6. 10.6 An Example: ROC Curve Analyses Based on Empirical Likelihoods
    7. 10.7 Applications of Empirical Likelihood Methodology in Clinical Trials or Other Data Analyses
    8. 10.8 Concluding Remarks
    9. Appendix
    10. References
17. Chapter 11: Frailty Models
    1. 11.1 Introduction
    2. 11.2 Univariate Frailty Models
    3. 11.3 Multivariate Frailty Models
    4. 11.4 Software
    5. References
18. Chapter 12: Futility Analysis
    1. 12.1 Introduction
    2. 12.2 Common Statistical Approaches to Futility Monitoring
    3. 12.3 Examples
    4. 12.4 Discussion
    5. References
    6. Further Reading
19. Chapter 13: Imaging Science in Medicine I: Overview
    1. 13.1 Introduction
    2. 13.2 Advances in Medical Imaging
    3. 13.3 Evolutionary Developments in Imaging
    4. 13.4 Conclusion
    5. References
20. Chapter 14: Imaging Science in Medicine, II: Basics of X-Ray Imaging
    1. 14.1 Introduction to Medical Imaging: Different Ways of Creating Visible Contrast Among Tissues
    2. 14.2 What the Body Does to the X-Ray Beam: Subject Contrast From Differential Attenuation of the X-Ray Beam by Various Tissues
    3. 14.3 What the X-Ray Beam Does to the Body: Known Medical Benefits Versus Possible Radiogenic Risks
    4. 14.4 Capturing the Visual Image: Analog (20th Century) X-Ray Image Receptors
21. Chapter 15: Imaging Science in Medicine, III: Digital (21st Century) X-Ray Imaging
    1. 15.1 The Computer in Medical Imaging
    2. 15.2 The Digital Planar X-Ray Modalities: Computed Radiography and Digital Radiography and Fluoroscopy
    3. 15.3 Digital Fluoroscopy and Digital Subtraction Angiography
    4. 15.4 Digital Tomosynthesis: Planar Imaging in Three Dimensions
    5. 15.5 Computed Tomography: Superior Contrast in Three-Dimensional X-Ray Attenuation Maps
22. Chapter 16: Intention-to-Treat Analysis
    1. 16.1 Introduction
    2. 16.2 Missing Information
    3. 16.3 The Intention-to-Treat Design
    4. 16.4 Efficiency of the Intent-to-Treat Analysis
    5. 16.5 Compliance-Adjusted Analyses
    6. 16.6 Conclusion
    7. References
    8. Further Reading
23. Chapter 17: Interim Analyses
    1. 17.1 Introduction
    2. 17.2 Opportunities and Dangers of Interim Analyses
    3. 17.3 The Development of Techniques for Conducting Interim Analyses
    4. 17.4 Methodology for Interim Analyses
    5. 17.5 An Example: Statistics for Lamivudine
    6. 17.6 Interim Analyses in Practice
    7. 17.7 Conclusions
    8. References
24. Chapter 18: Interrater Reliability
    1. 18.1 Definition
    2. 18.2 The Importance of Reliability in Clinical Trials
    3. 18.3 How Large a Reliability Coefficient Is Large Enough?
    4. 18.4 Design and Analysis of Reliability Studies
    5. 18.5 Estimate of the Reliability Coefficient—Parametric
    6. 18.6 Estimation of the Reliability Coefficient— Nonparametric
    7. 18.7 Estimation of the Reliability Coefficient—Binary
    8. 18.8 Estimation of the Reliability Coefficient—Categorical
    9. 18.9 Strategies to Increase Reliability (Spearman–Brown Projection)
    10. 18.10 Other Types of Reliabilities
    11. References
25. Chapter 19: Intrarater Reliability
    1. 19.1 Introduction
    2. 19.2 Intrarater Reliability for Continuous Scores
    3. 19.3 Nominal Scale Score Data
    4. 19.4 Ordinal and Interval Score Data
    5. 19.5 Concluding Remarks
    6. References
    7. Further Reading
26. Chapter 20: Kaplan—Meier Plot
    1. 20.1 Introduction
    2. 20.2 Estimation of Survival Function
    3. 20.3 Additional Topics
    4. References
27. Chapter 21: Logistic Regression
    1. 21.1 Introduction
    2. 21.2 Fitting the Logistic Regression Model
    3. 21.3 The Multiple Logistic Regression Model
    4. 21.4 Fitting the Multiple Logistic Regression Model
    5. 21.5 Example
    6. 21.6 Testing for the Significance of the Model
    7. 21.7 Interpretation of the Coefficients of the Logistic Regression Model
    8. 21.8 Dichotomous Independent Variable
    9. 21.9 Polytomous Independent Variable
    10. 21.10 Continuous Independent Variable
    11. 21.11 Multivariate Case
    12. References
28. Chapter 22: Metadata
    1. 22.1 Introduction
    2. 22.2 History/Background
    3. 22.3 Data Set Metadata
    4. 22.4 Analysis Results Metadata
    5. 22.5 Regulatory Submission Metadata
    6. References
29. Chapter 23: Microarray
    1. 23.1 Introduction
    2. 23.2 What is a Microarray?
    3. 23.3 Other Array Technologies
    4. 23.4 Define Objectives of the Study
    5. 23.5 Experimental Design for Microarray
    6. 23.6 Data Extraction
    7. 23.7 Microarray Informatics
    8. 23.8 Statistical Analysis
    9. 23.9 Annotation
    10. 23.10 Pathway, GO, and Class-Level Analysis Tools
    11. 23.11 Validation of Microarray Experiments
    12. 23.12 Conclusions
    13. References
30. Chapter 24: Multi-Armed Bandits, Gittins Index, and Its Calculation
    1. 24.1 Introduction
    2. 24.2 Mathematical Formulation of Multi-Armed Bandits
    3. 24.3 Off-Line Algorithms for Computing Gittins Index
    4. 24.4 On-Line Algorithms for Computing Gittins Index
    5. 24.5 Computing Gittins Index for the Bernoulli Sampling Process
    6. 24.6 Conclusion
    7. References
31. Chapter 25: Multiple Comparisons
    1. 25.1 Introduction
    2. 25.2 Strong and Weak Control of the FWE
    3. 25.3 Criteria for Deciding Whether Adjustment is Necessary
    4. 25.4 Implicit Multiplicity: Two-Tailed Testing
    5. 25.5 Specific Multiple Comparison Procedures
    6. References
32. Chapter 26: Multiple Evaluators
    1. 26.1 Introduction
    2. 26.2 Agreement for Continuous Data
    3. 26.3 Agreement for Categorical Data
    4. 26.4 Summary and Discussion
    5. References
33. Chapter 27: Noncompartmental Analysis
    1. 27.1 Introduction
    2. 27.2 Terminology
    3. 27.3 Objectives and Features of Noncompartmental Analysis
    4. 27.4 Comparison of Noncompartmental and Compartmental Models
    5. 27.5 Assumptions of NCA and Its Reported Descriptive Statistics
    6. 27.6 Calculation Formulas for NCA
    7. 27.7 Guidelines for Performance of NCA Based on Numerical Integration
    8. 27.8 Conclusions and Perspectives
    9. References
    10. Further Reading
34. Chapter 28: Nonparametric ROC Analysis for Diagnostic Trials
    1. 28.1 Introduction
    2. 28.2 Different Aspects of Study Design
    3. 28.3 Nonparametric Models and Hypotheses
    4. 28.4 Point Estimator
    5. 28.5 Asymptotic Distribution and Variance Estimator
    6. 28.6 Derivation of the Confidence Interval
    7. 28.7 Statistical Tests
    8. 28.8 Adaptations for Cluster Data
    9. 28.9 Results of a Diagnostic Study
    10. 28.10 Summary and Final Remarks
    11. References
35. Chapter 29: Optimal Biological Dose for Molecularly Targeted Therapies
    1. 29.1 Introduction
    2. 29.2 Phase I Dose-Finding Designs for Cytotoxic Agents
    3. 29.3 Phase I Dose-Finding Designs for Molecularly Targeted Agents
    4. 29.4 Discussion
    5. References
    6. Further Reading
36. Chapter 30: Over- and Underdispersion Models
    1. 30.1 Introduction
    2. 30.2 Count Dispersion Models
    3. 30.3 Count Explanatory Models
    4. 30.4 Summary and Final Remarks
    5. References
37. Chapter 31: Permutation Tests in Clinical Trials
    1. 31.1 Randomization Inference—Introduction
    2. 31.2 Permutation Tests—How They Work
    3. 31.3 Normal Approximation to Permutation Tests
    4. 31.4 Analyze as You Randomize
    5. 31.5 Interpretation of Permutation Analysis Results
    6. 31.6 Summary
    7. References
38. Chapter 32: Pharmacoepidemiology, Overview
    1. 32.1 Introduction
    2. 32.2 The Case-Crossover Design
    3. 32.3 Confounding Bias
    4. 32.4 Risk Functions Over Time
    5. 32.5 Probabilistic Approach for Causality Assessment
    6. 32.6 Methods Based on Prescription Data
    7. References
39. Chapter 33: Population Pharmacokinetic and Pharmacodynamic Methods
    1. 33.1 Introduction
    2. 33.2 Terminology
    3. 33.3 Fixed Effects Models
    4. 33.4 Random Effects Models
    5. 33.5 Model Building and Parameter Estimation
    6. 33.6 Software
    7. 33.7 Model Evaluation
    8. 33.8 Stochastic Simulation
    9. 33.9 Experimental Design
    10. 33.10 Applications
    11. References
    12. Further Reading
40. Chapter 34: Proportions: Inferences and Comparisons
    1. 34.1 Introduction
    2. 34.2 One-Sample Case
    3. 34.3 Two Independent Samples
    4. 34.4 Note on Software
    5. References
41. Chapter 35: Publication Bias
    1. 35.1 Publication Bias and the Validity of Research Reviews
    2. 35.2 Research on Publication Bias
    3. 35.3 Data Suppression Mechanisms Related to Publication Bias
    4. 35.4 Prevention of Publication Bias
    5. 35.5 Assessment of Publication Bias
    6. 35.6 Impact of Publication Bias
    7. References
    8. Further Reading
42. Chapter 36: Quality of Life
    1. 36.1 Background
    2. 36.2 Measuring Health-Related Quality of Life
    3. 36.3 Development and Validation of HRQoL Measures
    4. 36.4 Use in Research Studies
    5. 36.5 Interpretation/Clinical Significance
    6. 36.6 Conclusions
    7. References
43. Chapter 37: Relative Risk Modeling
    1. 37.1 Introduction
    2. 37.2 Why Model Relative Risks?
    3. 37.3 Data Structures and Likelihoods
    4. 37.4 Approaches to Model Specification
    5. 37.5 Mechanistic Models
    6. References
44. Chapter 38: Sample Size Considerations for Morbidity/Mortality Trials
    1. 38.1 Introduction
    2. 38.2 General Framework for Sample Size Calculation
    3. 38.3 Choice of Test Statistics
    4. 38.4 Adjustment of Treatment Effect
    5. 38.5 Informative Noncompliance
    6. References
45. Chapter 39: Sample Size for Comparing Means
    1. 39.1 Introduction
    2. 39.2 One-Sample Design
    3. 39.3 Two-Sample Parallel Design
    4. 39.4 Two-Sample Crossover Design
    5. 39.5 Multiple-Sample One-Way ANOVA
    6. 39.6 Multiple-Sample Williams Design
    7. 39.7 Discussion
    8. References
46. Chapter 40: Sample Size for Comparing Proportions
    1. 40.1 Introduction
    2. 40.2 One-Sample Design
    3. 40.3 Two-Sample Parallel Design
    4. 40.4 Two-Sample Crossover Design
    5. 40.5 Relative Risk—Parallel Design
    6. 40.6 Relative Risk—Crossover Design
    7. 40.7 Discussion
    8. References
47. Chapter 41: Sample Size for Comparing Time-to-Event Data
    1. 41.1 Introduction
    2. 41.2 Exponential Model
    3. 41.3 Cox’s Proportional Hazards Model
    4. 41.4 Log-Rank Test
    5. 41.5 Discussion
    6. References
48. Chapter 42: Sample Size for Comparing Variabilities
    1. 42.1 Introduction
    2. 42.2 Comparing Intrasubject Variabilities
    3. 42.3 Comparing Intersubject Variabilities
    4. 42.4 Comparing Total Variabilities
    5. 42.5 Discussion
    6. References
49. Chapter 43: Screening, Models of
    1. 43.1 Introduction
    2. 43.2 What is Screening?
    3. 43.3 Why Use Modeling?
    4. 43.4 Characteristics of Screening Models
    5. 43.5 A Simple Disease and Screening Model
    6. 43.6 Analytic Models for Cancer
    7. 43.7 Simulation Models for Cancer
    8. 43.8 Model Fitting and Validation
    9. 43.9 Models for Other Diseases
    10. 43.10 Current State and Future Directions
    11. References
50. Chapter 44: Screening Trials
    1. 44.1 Introduction
    2. 44.2 Design Issues
    3. 44.3 Sample Size
    4. 44.5 Analysis
    5. 44.6 Trial Monitoring
    6. References
51. Chapter 45: Secondary Efficacy End Points
    1. 45.1 Introduction
    2. 45.2 Literature Review
    3. 45.3 Review of Methodology for Multiplicity Adjustment and Gatekeeping Strategies for Secondary End Points
    4. 45.4 Summary
    5. References
    6. Further Reading
52. Chapter 46: Sensitivity, Specificity, and Receiver Operator Characteristic (ROC) Methods
    1. 46.1 Evaluating a Single Binary Test Against a Binary Criterion
    2. 46.2 Evaluation of a Single Binary Test: ROC Methods
    3. 46.3 Evaluation of a Test Response Measured on an Ordinal Scale: ROC Methods
    4. 46.4 Evaluation of Multiple Different Tests
    5. 46.5 The Optimal Sequence of Tests
    6. 46.6 Sampling and Measurement Issues
    7. 46.7 Summary
    8. References
53. Chapter 47: Software for Genetics/Genomics
    1. 47.1 Introduction
    2. 47.2 Data Management
    3. 47.3 Genetic Analysis
    4. 47.4 Genomic Analysis
    5. 47.5 Other
    6. References
    7. Further Reading
54. Chapter 48: Stability Study Designs
    1. 48.1 Introduction
    2. 48.2 Stability Study Designs
    3. 48.3 Criteria for Design Comparison
    4. 48.4 Stability Protocol
    5. 48.5 Basic Design Considerations
    6. 48.6 Conclusions
    7. References
55. Chapter 49: Subgroup Analysis
    1. 49.1 Introduction
    2. 49.2 The Dilemma of Subgroup Analysis
    3. 49.3 Planned Versus Unplanned Subgroup Analysis
    4. 49.4 Frequentist Methods
    5. 49.5 Testing Treatment by Subgroup Interactions
    6. 49.6 Subgroup Analyses in Positive Clinical Trials
    7. 49.7 Confidence Intervals for Treatment Effects within Subgroups
    8. 49.8 Bayesian Methods
    9. References
56. Chapter 50: Survival Analysis, Overview
    1. 50.1 Introduction
    2. 50.2 History
    3. 50.3 Survival Analysis Concepts
    4. 50.4 Nonparametric Estimation and Testing
    5. 50.5 Parametric Inference
    6. 50.6 Comparison with Expected Survival
    7. 50.7 The Cox Regression Model
    8. 50.8 Other Regression Models for Survival Data
    9. 50.9 Multistate Models
    10. 50.10 Other Kinds of Incomplete Observation
    11. 50.11 Multivariate Survival Analysis
    12. 50.12 Concluding Remarks
    13. References
57. Chapter 51: The FDA and Regulatory Issues
    1. 51.1 Caveat
    2. 51.2 Introduction
    3. 51.3 Chronology of Drug Regulation in the United States
    4. 51.4 FDA Basic Structure
    5. 51.5 IND Application Process
    6. 51.6 Drug Development and Approval Time Frame
    7. 51.7 NDA Process
    8. 51.8 U.S. Pharmacopeia and FDA
    9. 51.9 CDER Freedom of Information Electronic Reading Room
    10. 51.10 Conclusion
58. Chapter 52: The Kappa Index
    1. 52.1 Introduction
    2. 52.2 The Kappa Index
    3. 52.3 Inference for Kappa via Generalized Estimating Equations
    4. 52.4 The Dependence of Kappa on Marginal Rates
    5. 52.5 General Remarks
    6. References
59. Chapter 53: Treatment Interruption
    1. 53.1 Introduction
    2. 53.2 Therapeutic TI Studies in HIV/AIDS
    3. 53.3 Management of Chronic Disease
    4. 53.4 Analytic Treatment Interruption in Therapeutic Vaccine Trials
    5. 53.5 Randomized Discontinuation Designs
    6. 53.6 Final Comments
    7. References
60. Chapter 54: Trial Reports: Improving Reporting, Minimizing Bias, and Producing Better Evidence-Based Practice
    1. 54.1 Introduction
    2. 54.2 Reporting Issues in Clinical Trials
    3. 54.3 Moral Obligation to Improve the Reporting of Trials
    4. 54.4 Consequences of Poor Reporting of Trials
    5. 54.5 Distinguishing Between Methodological and Reporting Issues
    6. 54.6 One Solution to Poor Reporting: CONSORT 2010 and CONSORT Extensions
    7. 54.7 Impact of CONSORT
    8. 54.8 Guidance for Reporting Randomized Trial Protocols: SPIRIT
    9. 54.9 Trial Registration
    10. 54.10 Final Thoughts
    11. References
61. Chapter 55: U.S. Department of Veterans Affairs Cooperative Studies Program
    1. 55.1 Introduction
    2. 55.2 History of the Cooperative Studies Program (CSP)
    3. 55.3 Organization and Functioning of the CSP
    4. 55.4 Roles of the Biostatistician and Pharmacist in the CSP
    5. 55.5 Ongoing and Completed Cooperative Studies (1972–2000)
    6. 55.6 Current Challenges and Opportunities
    7. 55.7 Concluding Remarks
    8. References
62. Chapter 56: Women’s Health Initiative: Statistical Aspects and Selected Early Results
    1. 56.1 Introduction
    2. 56.2 WHI Clinical Trial and Observational Study
    3. 56.3 Study Organization
    4. 56.4 Principal Clinical Trial Comparisons, Power Calculations, and Safety and Data Monitoring
    5. 56.5 Biomarkers and Intermediate Outcomes
    6. 56.6 Data Management and Computing Infrastructure
    7. 56.7 Quality Assurance Program Overview
    8. 56.8 Early Results from the WHI Clinical Trial
    9. 56.9 Summary and Discussion
    10. References
63. Chapter 57: World Health Organization (WHO): Global Health Situation
    1. 57.1 Introduction
    2. 57.2 Program Activities to the End of the Twentieth Century
    3. 57.3 Vision for the Use and Generation of Data in the First Quarter of the Twenty-First Century
    4. Reference
    5. Further Reading
64. Index