There are many books on medical statistics which explain to the physician how to calculate various common statistics and how to perform various tests. Many of them present a simplified and distorted view of statistics which gives no impression of the philosophical difficulties the science has to confront. This book aims to explain the statistical issues in drug development to non-statisticians, so enabling them to work more easily alongside their statistical colleagues in planning, analysing and interpreting clinical trials. Commercial pressures mean that the stakes are high in drug development and regulatory standards mean that much that is done is examined very closely. As a consequence the non-statistician working in drug development has to have a considerable appreciation of statistical issues, which this book can provide.

Editions compared | Extra words by chapter |

Editions compared | Extra words by chapter |

"This book would be useful for statisticians wanting to learn more about drug development,
whether they are advanced undergraduate, masters or doctoral students. It would
also be useful for experienced statisticians considering a switch to drug development statistics.
Even statisticians who are very knowledgeable about drug development will likely
find many parts of this book useful... In conclusion, for the
appropriate audience, it would be hard to find a better written (or more enjoyable) book on
this topic."

Amit K Chowdhry, *JRSS A *

"Throughout this book, we could see the purpose of this
book is not to present an authoritative prescription as to how
to deal with each statistical issue during drug development.
Instead, the objective is to make the reader think about genuine
statistical controversies in drug development. In many cases, the
issues are deep and complicated, and thinking about them will
increase understanding about scientific problems involved with
drug development...
Only when drug developers are aware of all potential pros and
cons of the statistical methodologies being applied to clinical
trials can they ensure a proper conduct of the trial with highest
quality."

Jie Cui and Haoda Fu,* The American Statistician*

"This is a wonderful book, on multiple levels...To me, the insights given in this book are useful not only
individually, but especially when absorbed in the whole, as
all things are connected. I highly recommend this book."

Jason C Hsu, *Biometrics*.

"In short, this excellent book should serve to inspire both statisticians and life
scientists. The content is of obvious interest to those working in the pharmaceutical
industry, regulatory bodies, and medical research institutes; however, the
book also should be appealling to anyone wanting to learn more about how statistical
procedures are used to make decisions that have profound implications
on all of our lives." Joseph Cavanaugh, * JASA*

"Overall, I can highly recommend this book of admirable clarity to readers in regulatory bodies,
in the pharmaceutical industry and in universities working on clinical trials for drug development.
It is ideal for readers who do not simply want to be told what to do, but who want to get to the bottom
of statistical approaches and their interpretations in medical settings." Ludwig Hothorn, *Statistics in Medicine*

"Statisticians with limited experience in drug development will greatly benefit from seeing the careful layout
of controversies that are unique to this arena. I especially loved the description of the controversies associated
with intention-to-treat analysis and random effects in a multicenter trial....This book is an outstanding effort from
a statistician of heroic proportions. Someone like me is only capable of sitting on the curb and applauding wildly."
Steve Simon * Journal of Biopharmaceutical Statistics*

"For statisticians, this should be required reading for anyone considering or starting out on a career in clinical
drug development. I am also quite sure that most experienced statisticians would find this a useful book to dip
into on occasion ... . This book will not disappoint." Phil Woodward. *Journal of the Royal Statistical Society*

"This is a great reference for scientists and statisticians as well." Michael R Chernik on * Amazon.com*

"...enjoy Senn's humour and marvel at the twists and turns which challenge most of
our (I now find) over-simplified beliefs on the subject. Even if you don't understand
it all, or at all, you will certainly emerge knowing the difference between a statistician
and a subgroup analysis (one is a harmless drudge, the other an aimless dredge).
As for me, I am still reading and learning and pondering the nature of a fourth category of
book: (d) read it now and again and again, more slowly (sits by the decanter and exercises the brain)?"
Elliot Brown,* The Lancet*

"This is a highly readable book, written by a statistician who has worked in the
pharmaceutical industry, and has the rare ability to communicate comprehensibly to non-statisticians.....
I recommend the book highly." Diana Elbourne *ISI Short Book Reviews *

"...the book also covers many excellent topics and I feel I will continue to use the book
to a great extent....I believe this book is for statisticians and non-statisticians alike, and
anyone can benefit from it...My last point concerns the use of various quotes and anecdotes.
These added much to the enjoyment of the book.." Alun Bedding *SPIN *

"Senn has done a great service in laying bare the current state of the science and discussing
the many points of contention. The book is essential reading for anyone wanting to understand the
statistical problems currently facing drug development in particular, and medical statistics in general."
Sean McGuigan, *Health Economics*

"Stephen Senn has a wry sense of humour, and a terrific turn of phrase that makes the book interesting....
Senn scatters his book with fun quotes and jokes, and those of you who lecture often could do worse than get the
book for these alone. They are very witty." *Bandolier*

"It was a great pleasure to read this book. The controversial issues in drug development presented in
the second part were dealt with especially well. Whatever their discipline, I highly recommend that all
clinical researchers add this book to their libraries." Stephen Ogenstad, *Applied Clinical Trials*

"It is rare that I have found a book with which I am in so much agreement. ... The book is a pleasure to read.
It is attractively designed. A colleague has stated 'for a statistical book, it's a real page-turner.'"
P.A Lachenbruch, *Controlled Clinical Trials*.

"Whether this book will truly appeal to life scientists can only be answered by them. Given the motivation
to understand the statistical issues existing in their subject this text would be an excellent place to start.
As for statisticians this should be an easily accessible reference for all working in clinical trials and required
reading for those starting out." P.W. Woodward, *The Statistician*

"Thus, in summary, there is a lot to think about in this book. An obvious use of the book is to use it as a
starting point for discussions in various constellations of non-statisticians, junior statisticians, and more experienced
statisticians involved in drug development" Olivier Guilbaud, *Statistics in Medicine*

"He succeeds in stimulating the reader through his superb presentation of the many postures which
might be taken on a given issue...Every pharmaceutical company and regulatory agency should have copies
of this book available for its employees...If you are involved in the drug development and approval process,
make time to read this book and consider the statistical issues contained within."
Thomas E Bradstreet, *Statistical Methods in Medical Research*

"Professor Senn is almost always correct and now, in his most recent book, he explains clearly
and in a very readable fashion why." Brian Everitt, *Statistical Methods in Medical Research*

"The book is a fine model for a book that presents a set of statistical issues...if
I am fortunate enough to find a new job with a pharmaceutical company, this will be the first book
that I will study." *Technometrics*

"...piu che esperto..." *Statistica Applicata*

ACE Inhibitor. Angiotensin converting enzyme inhibitor. A treatment for hypertension. The ace of hearts in drug development's game of poker

Bioequivalence Study. A study usually carried out on healthy volunteers, and often as a single-dose cross-over, in which, by repeated sampling (usually of blood), it is attempted to show that the pharmacokinetic profile of an experimental treatment is very similar to that of a reference product with the same chemical structure. Such a demonstration is usually taken to mean that there is no need to carry out a full development programme on the experimental treatment, as results which are valid for the reference treatment may be presumed valid for the experimental treatment. By enabling generic companies to avoid the costs of development borne by the major pharmaceutical companies, bioequivalence studies, depending on your view, can either be seen as being a 'free lunch' for the parasites of drug-development, or the weapon by which the double dragons of exclusivity and excess profit may be slain by the shining knights of competition.

Biostatistician. One who has neither the intellect for mathematics nor the commitment for medicine but likes to dabble in both.

Change-over Design. An old-fashioned and minority term for cross-over trial. If you use it you should consider a change-over to cross-over.

EMEA. The European Medicines Agency. The drug regulatory agency of the European Union. A statistician-free zone.

Exploratory Data Analysis. The practice of studying data without preconceived notions as a means of obtaining ill-conceived ones. The art of seeing a Rembrandt in a Jackson Pollock

Glossary. A sort of short commons dictionary in which the omissions are more significant than the entries

Pharmaco-Economics. Drug development's dismal science.

Radix. The original number assumed alive at age 0 (typically 1000 or 100,000) for the purpose of presenting a life table. The root at which time and mortality will gnaw.

Random Variable. A term which has been given many variable, if not entirely random, definitions. Broadly and loosely for our purposes, some measurement which takes on given values with given probabilities

Rank Test. A statistical test, such as for example the Mann-Whitney-Wilcoxon test, carried out on the ranks of the data rather than on the original data. Thus, the statistic used in the test, the rank statistic, is calculated from ranks of the data. Usually such tests are associated with randomisation. Given knowledge of the randomisation procedure, the distribution of the rank statistic is perfectly general under the null hypothesis. The rank is but the guinea stamp. The Mann's the gowd for a' that. Burns.

Simple Carry-over. Carry-over for simple minds. A form of carry-over which lasts for exactly one period and depends on the engendering but not the perturbed treatment and which ought to be spelled 'karry-over' to draw attention to its eccentricity, rarity and unnatural nature. A dream in which mathematics triumphs over biology.

Statistics. 1) A subject which most statisticians find difficult but which many physicians find easy. 2) A sort of elementary form of mathematics which consists of adding things together and occasionally squaring them. Uncontrolled Study. A study without a control group. A means of using prejudice and regression to prove effectiveness. A study where faith must supply what evidence cannot deliver. Z 1) The symbol for a standardised value of a Normal variable. 2) The symbol for the test statistic in Whitehead's boundary approach to sequential clinical trials (see chapter 19). 3) The symbol which R.A. Fisher used to designate half the difference of the natural logarithms of two independent estimates of variances when comparing them. (Nowadays we tend to use the ratio instead, which we compare to the F distribution.) 4) The last entry in this glossary.

Preface

1 Introduction

2 A Brief and Superficial History of Statistics for Drug Developers

3 Design and Interpretation of Clinical Trials as Seen by a Statistician

4 Probability, Bayes, P-Values, Test of Hypotheses and Confidence Intervals

5 The Work of the Pharmaceutical Statistician

6 Allocating Treatments to Patients in Clinical Trials

7 Baselines and Covariate Information

8 The Measurement of Treatment Effects

9 Demographic Sub-groups: Representation and Analysis

10 Multiplicity

11 Intention to Treat, Missing Data and Related Matters

12 One-sided and Two-sided Tests and other issue to do with Significance and P-Values

13 Determining the Sample Size

14 Multi-Centre Trials

15 Active Control Equivalence Studies

16 Meta-Analysis

17 Cross-over Trials

18 N-of-1 Trials

19 Sequential Trials

20 Dose-Finding

21 Concerning Pharmacokinetics and Pharmacodynamics

22 Bioequivalence Studies

23 Safety Data, Drug Monitoring and Pharmaco-Epidemiology

24 Pharmaco-Economics and Portfolio Management

25 Concerning, Pharmacogenetics, Pharmacogenomics and Related Matters

John Wiley's *Statistical Issues in Drug Development Page*