Pharmaceutical Statistics Using SAS: A Practical Guide

Pharmaceutical Statistics Using SAS: A Practical Guide

公卫百科

By: Alex Dmitrienko, Christy Chuang-Stein, and Ralph D'Agostino
Price: 69.95 USD
464 pages
ISBN: 978-1-59047-886-8
Publisher: SAS Press
Copyright Date: February 2007
Pharmaceutical Statistics Using SAS: A Practical Guide offers extensive coverage of cutting-edge biostatistical methodology used in drug development and the practical problems facing today's drug developers. Written by well-known experts in the pharmaceutical industry Alex Dmitrienko, Christy Chuang-Stein, and Ralph D'Agostino, it provides relevant tutorial material and SAS examples to help readers new to a certain area of drug development quickly understand and learn popular data analysis methods and apply them to real-life problems. Step-by-step, the book introduces a wide range of data analysis problems encountered in drug development and illustrates them using a wealth of case studies from actual pre-clinical experiments and clinical studies. The book also provides SAS code for solving the problems. Among the topics addressed are these:

公卫家园

drug discovery experiments to identify promising chemical compounds
animal studies to assess the toxicological profile of these compounds
clinical pharmacology studies to examine the properties of new drugs in healthy human subjects
Phase II and Phase III clinical trials to establish therapeutic benefits of experimental drugs. 公卫考场
Additional features include a discussion of methodological issues, practical advice from subject-matter experts, and review of relevant regulatory guidelines. Most chapters are self-contained and include a fair amount of high-level introductory material to make them accessible to a broad audience of pharmaceutical scientists. This book will also serve as a useful reference for regulatory scientists as well as academic researchers and graduate students.

公卫家园

1 Statistics in Drug Development 1
By Christy Chuang-Stein and Ralph D’Agostino
1.1 Introduction 1
1.2 Statistical Support to Non-Clinical Activities 2
1.3 Statistical Support to Clinical Testing 3 公卫论坛
1.4 Battling a High Phase III Failure Rate 4
1.5 Do Statisticians Count? 5
1.6 Emerging Opportunities 5
1.7 Summary 6
References 6

2 Modern Classification Methods for Drug Discovery 7
By Kjell Johnson and William Rayens 公卫百科
2.1 Introduction 7
2.2 Motivating Example 9
2.3 Boosting 10
2.4 Model Building 27
2.5 Partial Least Squares for Discrimination 33
2.6 Summary 42
References 42

3 Model Building Techniques in Drug Discovery 45
By Kimberly Crimin and Thomas Vidmar 公卫百科
3.1 Introduction 45
3.2 Example: Solubility Data 46
3.3 Training and Test Set Selection 47
3.4 Variable Selection 51
3.5 Statistical Procedures for Model Building 58
3.6 Determining When a New Observation Is Not in a Training Set 61

公卫考场

3.7 Using SAS Enterprise Miner 63
3.8 Summary 67
References 67

4 Statistical Considerations in Analytical Method Validation 69
By Bruno Boulanger, Viswanath Devanaryan, Walth`ere Dew´e, and Wendell Smith
4.1 Introduction 69 公卫家园
4.2 Validation Criteria 73
4.3 Response Function or Calibration Curve 74
4.4 Linearity 83
4.5 Accuracy and Precision 85
4.6 Decision Rule 88
4.7 Limits of Quantification and Range of the Assay 92
4.8 Limit of Detection 93
4.9 Summary 93 公卫人
4.10 Terminology 94
References 94

5 Some Statistical Considerations in Nonclinical Safety Assessment 97
By Wherly Hoffman, Cindy Lee, Alan Chiang, Kevin Guo, and Daniel Ness
5.1 Overview of Nonclinical Safety Assessment 97
5.2 Key Statistical Aspects of Toxicology Studies 98
5.3 Randomization in Toxicology Studies 99
5.4 Power Evaluation in a Two-Factor Model for QT Interval 102
5.5 Statistical Analysis of a One-Factor Design with Repeated Measures 106
5.6 Summary 113
Acknowledgments 115
References 115
公卫家园
6 Nonparametric Methods in Pharmaceutical Statistics 117
By Paul Juneau
6.1 Introduction 117
6.2 Two Independent Samples Setting 118
6.3 The One-Way Layout 129
6.4 Power Determination in a Purely Nonparametric Sense 144
Acknowledgments 149
References 149

7 Optimal Design of Experiments in Pharmaceutical Applications 151
By Valerii Fedorov, Robert Gagnon, Sergei Leonov, and Yuehui Wu
7.1 Optimal Design Problem 152
7.2 Quantal Dose-Response Models 159
7.3 Nonlinear Regression Models with a Continuous Response 165 公卫家园
7.4 Regression Models with Unknown Parameters in the Variance Function 169
7.5 Models with a Bounded Response (Beta Models) 172
7.6 Models with a Bounded Response (Logit Link) 176
7.7 Bivariate Probit Models for Correlated Binary Responses 181 公卫人
7.8 Pharmacokinetic Models with Multiple Measurements per Patient 184
Pharmaceutical Statistics Using SAS: A Practical Guide v
7.9 Models with Cost Constraints 190
7.10 Summary 192
References 193

8 Analysis o fHuman Pharmacokinetic Data 197
By Scott Patterson and Brian Smith
8.1 Introduction 197
8.2 Bioequivalence Testing 199
8.3 Assessing Dose Linearity 204
8.4 Summary 209
References 209

9 Allocation in Randomized Clinical Trials 213
By Olga Kuznetsova and Anastasia Ivanova 公卫考场
9.1 Introduction 213
9.2 Permuted Block Randomization 214
9.3 Variations of Permuted Block Randomization 217
9.4 Allocations Balanced on Baseline Covariates 228
9.5 Summary 233
Acknowledgments 233
References 233

10 Sample-Size Analysis for Traditional Hypothesis Testing: 公卫论坛
Concepts and Issues 237
By Ralph G. O’Brien and John Castelloe
10.1 Introduction 238
10.2 Research Question 1: Does “QCA” Decrease Mortality in Children with
Severe Malaria? 240
10.3 p-Values, α, β and Power 241
10.4 A Classical Power Analysis 243
10.5 Beyond α and β: Crucial Type I and Type II Error Rates 249
10.6 Research Question 1, Continued: Crucial Error Rates for Mortality Analysis 251
10.7 Research Question 2: Does “QCA” Affect the “Elysemine : Elysemate”
Ratios (EER)? 253 公卫人
10.8 Crucial Error Rates When the Null Hypothesis Is Likely to Be True 262
10.9 Table of Crucial Error Rates 263
10.10 Summary 263
Acknowledgments 264
References 264
Appendix A Guidelines for “Statistical Considerations” Sections 264
Appendix B SAS Macro Code to Automate the Programming 265

11 Design and Analysis of Dose-Ranging Clinical Studies 273
By Alex Dmitrienko, Kathleen Fritsch, Jason Hsu, and Stephen Ruberg
11.1 Introduction 273
11.2 Design Considerations 277
11.3 Detection of Dose-Response Trends 280
11.4 Regression Modeling 289
11.5 Dose-Finding Procedures 294
11.6 Summary 309
References 310

12 Analysis of Incomplete Data 313
By Geert Molenberghs, Caroline Beunckens, Herbert Thijs, Ivy Jansen, Geert Verbeke, Michael Kenward, and Kristel Van Steen 公卫论坛
12.1 Introduction 314
12.2 Case Studies 316
12.3 Data Setting and Modeling Framework 318
12.4 Simple Methods and MCAR 319
12.5 MAR Methods 320
12.6 Categorical Data 322
12.7 MNAR Modeling 340
12.8 Sensitivity Analysis 347
12.9 Summary 356

公卫人

References 356

13 Reliability and Validity: Assessing the Psychometric Properties of Rating Scales 361
By Douglas Faries and Ilker Yalcin
13.1 Introduction 361
13.2 Reliability 362
13.3 Validity and Other Topics 376
13.4 Summary 382 公卫论坛
References 383

14 Decision Analysis in Drug Development 385
By Carl-Fredrik Burman, Andy Grieve, and Stephen Senn
14.1 Introduction 385
14.2 Introductory Example: Stop or Go? 386
14.3 The Structure of a Decision Analysis 392
14.4 The Go/No Go Problem Revisited 394
14.5 Optimal Sample Size 397
14.6 Sequential Designs in Clinical Trials 406
14.7 Selection of an Optimal Dose 412
14.8 Project Prioritization 421
14.9 Summary 426
Acknowledgments 426
References 426
Index 429
Alex Dmitrienko, Ph.D. 公卫论坛
Alex Dmitrienko, Ph.D., Principal Research Scientist, Eli Lilly and Company, has been actively involved in biostatistical research, published over 40 papers on a variety of statistical topics with clinical trial applications, and co-authored Analysis of Clnical Trials Using SAS: A Practical Guide (SAS Press). His other interests include software implementation of new and existing statistical methods.

公卫论坛

Christy Chuang-Stein, Ph.D.
Christy Chuang-Stein, Ph.D., Site Head, Midwest Statistics, Pfizer, has more than 20 years of experience in the pharmaceutical industry. She has written more than 100 publications in statistical and medical journals and is a co-author of Analysis of Clinical Trials Using SAS: A Practical Guide (SAS Press). Her interests include not only technical subjects dealing with statistical theory and applications, but also the development of pharmaceutical statisticians and the statistics profession in general.

公卫人

Ralph D'Agostino, Sr, Ph.D.
Ralph B. D'Agostino, Sr, Ph.D., is Professor of Mathematics, Statistics and Public Health at Boston University. Ralph has published over 400 papers on clinial trials, epidemiology, health services, and statistical methods, and is the co-author or editor of 7 books. He has been an advisor to the FDA since 1974 and has consulted extensively within the industry.