상세정보

Review of the First Edition

"The goal of this book, as stated by the authors, is to fill the knowledge gap that exists between developed statistical methods and the applications of these methods. Overall, this book achieves the goal successfully and does a nice job. I would highly recommend it …The example-based approach is easy to follow and makes the book a very helpful desktop reference for many biostatistics methods."?Journal of Statistical Software

Clinical Trial Data Analysis Using R and SAS, Second Edition provides a thorough presentation of biostatistical analyses of clinical trial data with step-by-step implementations using R and SAS. The book’s practical, detailed approach draws on the authors’ 30 years’ experience in biostatistical research and clinical development. The authors develop step-by-step analysis code using appropriate R packages and functions and SAS PROCS, which enables readers to gain an understanding of the analysis methods and R and SAS implementation so that they can use these two popular software packages to analyze their own clinical trial data.

• Adds SAS programs along with the R programs for clinical trial data analysis.
• Updates all the statistical analysis with updated R packages.
• Includes correlated data analysis with multivariate analysis of variance.
• Applies R and SAS to clinical trial data from hypertension, duodenal ulcer, beta blockers, familial andenomatous polyposis, and breast cancer trials.
• Covers the biostatistical aspects of various clinical trials, including treatment comparisons, time-to-event endpoints, longitudinal clinical trials, and bioequivalence trials.

This book will provide a thorough presentation of clinical trial methodology with detailed step-by-step illustrations on implementation in software R/SAS. The examples will be based on actual experience of the authors in many areas of clinical drug development. Actual examples of clinical trials will be presented and after understanding the application, various statistical methods appropriate for analysis of clinical trial data will be identified. The second edition will add new chapters, new datasets and SAS coverage.

정보제공 :

Cover -- Half Title -- Title Page -- Copyright Page -- Dedication -- Contents -- List of Figures -- List of Tables -- Preface for the Second Edition -- Preface for the First Edition -- About the Authors -- 1 Introduction to R -- 1.1 What is R? -- 1.2 Steps on Installing R and Updating R Packages -- 1.2.1 First Step: Install R Base System -- 1.2.2 Second Step: Installing and Updating R Packages -- 1.2.3 Steps to Get Help and Documentation -- 1.3 R for Clinical Trials -- 1.4 A Simple Simulated Clinical Trial -- 1.4.1 Data Simulation -- 1.4.1.1 R Functions -- 1.4.1.2 Data Generation and Manipulation -- 1.4.1.3 Basic R Graphics -- 1.4.2 Data Analysis -- 1.5 Summary and Recommendations for Further Reading -- 1.6 Appendix: SAS Programs -- 2 Overview of Clinical Trials -- 2.1 Introduction -- 2.2 Phases of Clinical Trials and Objectives -- 2.2.1 Phase 0 Trials -- 2.2.2 Phase I Trials -- 2.2.3 Phase II Trials -- 2.2.4 Phase III Trials -- 2.2.5 Phase IV Trials -- 2.3 The Clinical Development Plan -- 2.4 Biostatistical Aspects of a Protocol -- 2.4.1 Background or Rationale -- 2.4.2 Objective -- 2.4.3 Plan of Study -- 2.4.3.1 Study Population -- 2.4.3.2 Study Design -- 2.4.3.3 Problem Management -- 2.4.4 Statistical Analysis Section -- 2.4.4.1 Study Objectives as Statistical Hypotheses -- 2.4.4.2 Endpoints -- 2.4.4.3 Statistical Methods -- 2.4.4.4 Statistical Monitoring Procedures -- 2.4.5 Statistical Design Considerations -- 2.4.6 Subset Analyses -- 2.5 Concluding Remarks -- 3 Treatment Comparisons in Clinical Trials -- 3.1 Data from Clinical Trials -- 3.1.1 Diastolic Blood Pressure -- 3.1.2 Clinical Trial on Duodenal Ulcer Healing -- 3.2 Statistical Models for Treatment Comparisons -- 3.2.1 Models for Continuous Endpoints -- 3.2.1.1 Student''s t-Tests -- 3.2.1.2 One-Way Analysis of Variance (ANOVA) -- 3.2.1.3 Multi-Way ANOVA: Factorial Design -- 3.2.1.4 Multivariate Analysis of Variance (MANOVA) -- 3.2.2 Models for Categorical Endpoints: Pearson''s χ[Sup(2)]-test -- 3.3 Data Analysis in R -- 3.3.1 Analysis of the DBP Trial -- 3.3.1.1 Preliminary Data analysis -- 3.3.1.2 t-test -- 3.3.1.3 Bootstrapping Method -- 3.3.1.4 One-Way ANOVA for Time Changes -- 3.3.1.5 Two-Way ANOVA for Interaction -- 3.3.1.6 MANOVA for Treatment Difference -- 3.3.2 Analysis of Duodenal Ulcer Healing Trial -- 3.3.2.1 Using Pearson''s χ[Sup(2)]-test -- 3.3.2.2 Using Contingency Table -- 3.4 Summary and Conclusions -- 3.5 Appendix: SAS Programs -- 4 Treatment Comparisons in Clinical Trials with Covariates -- 4.1 Data from Clinical Trials -- 4.1.1 Diastolic Blood Pressure -- 4.1.2 Clinical Trials for Betablockers -- 4.1.3 Clinical Trial on Familial Adenomatous Polyposis -- 4.2 Statistical Models Incorporating Covariates -- 4.2.1 ANCOVA Models for Continuous Endpoints -- 4.2.2 Logistic Regression for Binary/Binomial Endpoints -- 4.2.3 Poisson Regression for Clinical Endpoint with Counts -- 4.2.4 Overdispersion -- 4.3 Data Analysis in R -- 4.3.1 Analysis of DBP Trial -- 4.3.1.1 Analysis of.
Baseline Data -- 4.3.1.2 ANCOVA of DBP Change from Baseline -- 4.3.1.3 MANCOVA for DBP Change from Baseline -- 4.3.2 Analysis of Betablocker Trial -- 4.3.3 Analysis of Data from Familial Adenomatous Polyposis Trial -- 4.4 Summary and Conclusions -- 4.5 Appendix: SAS Programs -- 5 Analysis of Clinical Trials with Time-to-Event Endpoints -- 5.1 Clinical Trials with Time-to-Event Data -- 5.1.1 Phase II Trial of Patients with Stage-2 Breast Carcinoma -- 5.1.2 Breast Cancer Trial with Interval-Censored Data -- 5.2 Statistical Models -- 5.2.1 Primary Functions and Definitions -- 5.2.1.1 The Hazard Function -- 5.2.1.2 The Survival Function -- 5.2.1.3 The Death Density Function -- 5.2.1.4 Relationships between These Functions -- 5.2.2 Parametric Models -- 5.2.2.1 The Exponential Model -- 5.2.2.2 The Weibull Model -- 5.2.2.3 The Rayleigh Model -- 5.2.2.4 The Gompertz Model -- 5.2.2.5 The Lognormal Model -- 5.3 Statistical Methods for Right-Censored Data -- 5.3.1 Nonparametric Models: Kaplan-Meier Estimator -- 5.3.2 Cox Proportion Hazards Regression -- 5.4 Statistical Methods for Interval-Censored Data -- 5.4.1 Turnbull''s Nonparametric Estimator -- 5.4.2 Parametric Likelihood Estimation with Covariates -- 5.4.3 Semiparametric Estimation: the IntCox -- 5.5 Step-by-Step Implementations in R -- 5.5.1 Stage-2 Breast Carcinoma -- 5.5.1.1 Fit Kaplan-Meier -- 5.5.1.2 Fit Weibull Parametric Model -- 5.5.1.3 Fit Cox Regression Model -- 5.5.2 Breast Cancer with Interval-Censored Data -- 5.5.2.1 Fit Turnbull''s Nonparametric Estimator -- 5.5.2.2 Fit Turnbull''s Nonparametric Estimator Using R Package interval -- 5.5.2.3 Fitting Parametric Models -- 5.5.2.4 Testing Treatment Effect Using Semiparametric Estimation: IntCox -- 5.5.2.5 Testing Treatment Effect Using Semiparametric Estimation: ictest -- 5.6 Summary and Discussions -- 5.7 Appendix: SAS Programs -- 6 Longitudinal Data Analysis for Clinical Trials -- 6.1 Clinical Trials -- 6.1.1 Diastolic Blood Pressure Data -- 6.1.2 Clinical Trial on Duodenal Ulcer Healing -- 6.2 Statistical Models -- 6.2.1 Linear Mixed Models -- 6.2.2 Generalized Linear Mixed Models -- 6.2.3 Generalized Estimating Equation -- 6.3 Longitudinal Data Analysis for Clinical Trials -- 6.3.1 Analysis of Diastolic Blood Pressure Data -- 6.3.1.1 Data Graphics and Response Feature Analysis -- 6.3.1.2 Longitudinal Modeling -- 6.3.2 Analysis of Cimetidine Duodenal Ulcer Trial -- 6.3.2.1 Preliminary Analysis -- 6.3.2.2 Fit Logistic Regression to Binomial Data -- 6.3.2.3 Fit Generalized Linear Mixed Model -- 6.3.2.4 Fit GEE -- 6.4 Summary and Discussion -- 6.5 Appendix: SAS Programs -- 7 Sample Size Determination and Power Calculations in Clinical Trials -- 7.1 Pre-requisites for Sample Size Determination -- 7.2 Comparison of Two Treatment Groups with Continuous Endpoints -- 7.2.1 Fundamentals -- 7.2.2 Basic Formula for Sample Size Calculation -- 7.2.3 R Function power.t.test -- 7.2.4 Unequal Variance: samplesize Package -- 7.3 Two Binomial Proportions --.
7.3.1 R Function power.prop.test -- 7.3.2 R Library: pwr -- 7.3.3 R Function nBinomial in gsDesign library -- 7.4 Time-to-Event Endpoint -- 7.5 Design of Group Sequential Trials -- 7.5.1 Introduction -- 7.5.2 gsDesign -- 7.6 Longitudinal Trials -- 7.6.1 Longitudinal Trial with Continuous Endpoint -- 7.6.1.1 The Model Setting -- 7.6.1.2 Sample Size Calculations -- 7.6.1.3 Power Calculation -- 7.6.1.4 Example and R Illustration -- 7.6.2 Longitudinal Binary Endpoint -- 7.6.2.1 Approximate Sample Size Calculation -- 7.6.2.2 Example and R Implementation -- 7.7 Relative Changes and Coefficient of Variation -- 7.7.1 Introduction -- 7.7.2 Sample Size Calculation Formula -- 7.7.3 Example and R Implementation -- 7.8 Concluding Remarks -- 7.9 Appendix: SAS Programs -- 8 Meta-Analysis of Clinical Trials -- 8.1 Data from Clinical Trials -- 8.1.1 Clinical Trials for Betablockers: Binary Data -- 8.1.2 Data for Cochrane Collaboration Logo: Binary Data -- 8.1.3 Clinical Trials on Amlodipine: Continuous Data -- 8.2 Statistical Models for Meta-Analysis -- 8.2.1 Clinical Hypotheses and Effect Size -- 8.2.2 Fixed-Effects Meta-Analysis Model: The Weighted Average -- 8.2.3 Random-Effects Meta-Analysis Model: DerSimonian-Laird -- 8.2.4 Publication Bias -- 8.3 Data Analysis in R -- 8.3.1 Analysis of Betablocker Trials -- 8.3.1.1 Fitting the Fixed-Effects Model -- 8.3.1.2 Fitting the Random-Effects Model -- 8.3.2 Meta-Analysis for Cochrane Collaboration Logo -- 8.3.3 Analysis of Amlodipine Trial Data -- 8.3.3.1 Load the Library and Data -- 8.3.3.2 Fit the Fixed-Effects Model -- 8.3.3.3 Fit the Random-Effects Model -- 8.4 Summary and Conclusions -- 8.5 Appendix: SAS Programs -- 9 Bayesian Methods in Clinical Trials -- 9.1 Bayesian Models -- 9.1.1 Bayes'' Theorem -- 9.1.2 Posterior Distributions for Some Standard Distributions -- 9.1.2.1 Normal Distribution with Known Variance -- 9.1.2.2 Normal Distribution with Unknown Variance -- 9.1.2.3 Normal Regression -- 9.1.2.4 Binomial Distribution -- 9.1.2.5 Multinomial Distribution -- 9.1.3 Simulation from the Posterior Distribution -- 9.1.3.1 Direct Simulation -- 9.1.3.2 Importance Sampling -- 9.1.3.3 Gibbs Sampling -- 9.1.3.4 Metropolis-Hastings Algorithm -- 9.2 R Packages in Bayesian Modeling -- 9.2.1 Introduction -- 9.2.2 R Packages using WinBUGS -- 9.2.2.1 R2WinBUGS -- 9.2.2.2 BRugs -- 9.2.2.3 rbugs -- 9.2.2.4 Typical Usage -- 9.2.3 MCMCpack -- 9.3 MCMC Simulations -- 9.3.1 Normal-Normal Model -- 9.3.2 Beta-Binomial Model -- 9.4 Bayesian Data Analysis -- 9.4.1 Blood Pressure Data: Bayesian Linear Regression -- 9.4.2 Binomial Data: Bayesian Logistic Regression -- 9.4.3 Count Data: Bayesian Poisson Regression -- 9.4.4 Comparing Two Treatments -- 9.5 Summary and Discussion -- 9.6 Appendix: SAS Programs -- 10 Bioequivalence Clinical Trials -- 10.1 Data from Bioequivalence Clinical Trials -- 10.1.1 Data from Chow and Liu (2009) -- 10.1.2 Bioequivalence Trial on Cimetidine Tablets -- 10.2 Bioequivalence Clinical Trial Endpoints -- .