Ajit C. Tamhane - Böcker

Offering a balanced, up-to-date view of multiple comparison procedures, this book refutes the belief held by some statisticians that such procedures have no place in data analysis. With equal emphasis on theory and applications, it establishes the advantages of multiple comparison techniques in reducing error rates and in ensuring the validity of statistical inferences. Provides detailed descriptions of the derivation and implementation of a variety of procedures, paying particular attention to classical approaches and confidence estimation procedures. Also discusses the benefits and drawbacks of other methods. Numerous examples and tables for implementing procedures are included, making this work both practical and informative.

A indispensable guide to understanding and designing modern experiments The tools and techniques of Design of Experiments (DOE) allow researchers to successfully collect, analyze, and interpret data across a wide array of disciplines. Statistical Analysis of Designed Experiments provides a modern and balanced treatment of DOE methodology with thorough coverage of the underlying theory and standard designs of experiments, guiding the reader through applications to research in various fields such as engineering, medicine, business, and the social sciences.The book supplies a foundation for the subject, beginning with basic concepts of DOE and a review of elementary normal theory statistical methods. Subsequent chapters present a uniform, model-based approach to DOE. Each design is presented in a comprehensive format and is accompanied by a motivating example, discussion of the applicability of the design, and a model for its analysis using statistical methods such as graphical plots, analysis of variance (ANOVA), confidence intervals, and hypothesis tests.Numerous theoretical and applied exercises are provided in each chapter, and answers to selected exercises are included at the end of the book. An appendix features three case studies that illustrate the challenges often encountered in real-world experiments, such as randomization, unbalanced data, and outliers. Minitab® software is used to perform analyses throughout the book, and an accompanying FTP site houses additional exercises and data sets.With its breadth of real-world examples and accessible treatment of both theory and applications, Statistical Analysis of Designed Experiments is a valuable book for experimental design courses at the upper-undergraduate and graduate levels. It is also an indispensable reference for practicing statisticians, engineers, and scientists who would like to further their knowledge of DOE.

Useful Statistical Approaches for Addressing Multiplicity IssuesIncludes practical examples from recent trials Bringing together leading statisticians, scientists, and clinicians from the pharmaceutical industry, academia, and regulatory agencies, Multiple Testing Problems in Pharmaceutical Statistics explores the rapidly growing area of multiple comparison research with an emphasis on pharmaceutical applications. In each chapter, the expert contributors describe important multiplicity problems encountered in pre-clinical and clinical trial settings. The book begins with a broad introduction from a regulatory perspective to different types of multiplicity problems that commonly arise in confirmatory controlled clinical trials, before giving an overview of the concepts, principles, and procedures of multiple testing. It then presents statistical methods for analyzing clinical dose response studies that compare several dose levels with a control as well as statistical methods for analyzing multiple endpoints in clinical trials. After covering gatekeeping procedures for testing hierarchically ordered hypotheses, the book discusses statistical approaches for the design and analysis of adaptive designs and related confirmatory hypothesis testing problems. The final chapter focuses on the design of pharmacogenomic studies based on established statistical principles. It also describes the analysis of data collected in these studies, taking into account the numerous multiplicity issues that occur.This volume explains how to solve critical issues in multiple testing encountered in pre-clinical and clinical trial applications. It presents the necessary statistical methodology, along with examples and software code to show how to use the methods in practice.

Provides a foundation in classical parametric methods of regression and classification essential for pursuing advanced topics in predictive analytics and statistical learningThis book covers a broad range of topics in parametric regression and classification including multiple regression, logistic regression (binary and multinomial), discriminant analysis, Bayesian classification, generalized linear models and Cox regression for survival data. The book also gives brief introductions to some modern computer-intensive methods such as classification and regression trees (CART), neural networks and support vector machines.The book is organized so that it can be used by both advanced undergraduate or masters students with applied interests and by doctoral students who also want to learn the underlying theory. This is done by devoting the main body of the text of each chapter with basic statistical methodology illustrated by real data examples. Derivations, proofs and extensions are relegated to the Technical Notes section of each chapter, Exercises are also divided into theoretical and applied. Answers to selected exercises are provided. A solution manual is available to instructors who adopt the text.Data sets of moderate to large sizes are used in examples and exercises. They come from a variety of disciplines including business (finance, marketing and sales), economics, education, engineering and sciences (biological, health, physical and social). All data sets are available at the book’s web site. Open source software R is used for all data analyses. R codes and outputs are provided for most examples. R codes are also available at the book’s web site.Predictive Analytics: Parametric Models for Regression and Classification Using R is ideal for a one-semester upper-level undergraduate and/or beginning level graduate course in regression for students in business, economics, finance, marketing, engineering, and computer science. It is also an excellent resource for practitioners in these fields.