Biostatistical Methods In Epidemiology 1st Edition Newman Sc by Newman S.c., (2001) 9780471369141, 0471369144 instant download after payment.

Preface

The aim of this book is to provide an overview of statistical methods that are important

in the analysis of epidemiologic data, the emphasis being on nonregression

techniques. The book is intended as a classroom text for students enrolled in an epidemiology

or biostatistics program, and as a reference for established researchers.

The choice and organization of material is based on my experience teaching biostatistics

to epidemiology graduate students at the University of Alberta. In that setting

I emphasize the importance of exploring data using nonregression methods prior

to undertaking a more elaborate regression analysis. It is my conviction that most of

what there is to learn from epidemiologic data can usually be uncovered using nonregression

techniques.

I assume that readers have a background in introductory statistics, at least to the

stage of simple linear regression. Except for the Appendices, the level of mathematics

used in the book is restricted to basic algebra, although admittedly some of the

formulas are rather complicated expressions. The concept of confounding, which is

central to epidemiology, is discussed at length early in the book. To the extent permitted

by the scope of the book, derivations of formulas are provided and relationships

among statistical methods are identified. In particular, the correspondence between

odds ratio methods based on the binomial model, and hazard ratio methods based

on the Poisson model are emphasized (Breslow and Day, 1980, 1987). Historically,

odds ratio methods were developed primarily for the analysis of case-control data.

Students often find the case-control design unintuitive, and this can adversely affect

their understanding of the odds ratio methods. Here, I adopt the somewhat unconventional

approach of introducing odds ratio methods in the setting of closed cohort

studies. Later in the book, it is shown how these same techniques can be adapted

to the case-control design, as well as to the analysis of censored survival data. One

of the attractive features of statistics is that different theoretical approaches often

lead to nearly identical numerical results. I have attempted to demonstrate this phenomenon

empirically by analyzing the same data sets using a variety of statistical

techniques.

I wish to expressmy indebtedness to Allan Donner, Sander Greenland, John Hsieh,

David Streiner, and Stephen Walter, who generously provided comments on a draft

manuscript. I am especially grateful to Sander Greenland for his advice on the topic

of confounding, and to John Hsieh who introduced me to life table theory when I was a student. The reviewers did not have the opportunity to read the final manuscript

and so I alone am responsible for whatever shortcomings there may be in the book.

I also wish to acknowledge the professionalism and commitment demonstrated by

Steve Quigley and Lisa Van Horn of John Wiley & Sons. I am most interested in

receiving your comments, which can be sent by e-mail using a link at the website

www.stephennewman.com.

Prior to entering medicine and then epidemiology, I was deeply interested in a

particularly elegant branch of theoretical mathematics called Galois theory. While

studying the historical roots of the topic, I encountered a monograph having a preface

that begins with the sentence “I wrote this book for myself.” (Hadlock, 1978). After

this remarkable admission, the author goes on to explain that he wanted to construct

his own path through Galois theory, approaching the subject as an enquirer rather

than an expert. Not being formally trained as a mathematical statistician, I embarked

upon the writing of this book with a similar sense of discovery. The learning process

was sometimes arduous, but it was always deeply rewarding. Even though I wrote

this book partly “for myself,” it is my hope that others will find it useful.