66
$\begingroup$

What are the panel's recommendations for books on design of experiments?

Ideally, books should be still in print or available electronically, although that may not always be feasible. If you feel moved to add a few words on what's so good about the book that would be great too.

Also, aim for one book per answer so that voting can help sort the suggestions.

(Community Wiki, please edit the question if you can make it better!)

$\endgroup$
5

18 Answers 18

19
$\begingroup$

For me, the best book around is by George Box:

Statistics for Experimenters: Design, Innovation, and Discovery

of course the book by Maxwell and Delaney is also pretty good: Designing Experiments and Analyzing Data: A Model Comparison Perspective, Second Edition

I personally prefer the first, but they are both top quality. They are a little bit expensive, but you can definitely find a cheap earlier edition for sale.

$\endgroup$
1
  • 1
    $\begingroup$ Very expensive... $\endgroup$
    – SmallChess
    Apr 10, 2015 at 11:34
13
$\begingroup$

Montgomery's Design and Analysis of Experiments is a classic and highly regarded text:

If you are interested in experimental design in a particular field (eg. clinical trials) other more specialised texts may be appropriate.

$\endgroup$
3
  • 1
    $\begingroup$ I had a look at this, and it's perfectly fine but has a bit too much of the feel of an undergraduate text book for my tastes. Not that there's anything wrong with that... $\endgroup$
    – walkytalky
    Aug 27, 2010 at 9:44
  • 1
    $\begingroup$ Very nice book indeed! I've started long ago to reproduce his analysis (with Design Expert and SAS) using R, but never find time to finish it. If you like to check it out, aliquote.org/articles/tech/dae $\endgroup$
    – chl
    Aug 27, 2010 at 11:17
  • 1
    $\begingroup$ I would not recommend this, it contain errors. Many books mentioned in other answers are better! $\endgroup$ Jan 16, 2016 at 21:37
13
$\begingroup$

Ronald Fisher's The Design of Experiments (link is Wikipedia rather than Amazon since it is long out of print) is interesting for historical context. The book is often credited as founding the whole field, and certainly did a lot to promote things like blocking, randomisation and factorial design, though things have moved on a bit since.

As a period document it's quite fascinating, but it's also maddening. In the absence of a common terminology and notation, a lot of time is spent painstakingly explaining things in what now seems comically-stilted English. If you had to use it as a reference to look up how to calculate something you'd probably gnaw your own leg off. But the terribly polite hatchet job on some of Galton's analysis is entertaining.

(I know, I know -- how the readers of tomorrow will laugh at the archaisms of today's scientific literature...)

$\endgroup$
9
$\begingroup$

There are many excellent books on design of experiments. These procedures apply generally and I do not think there are special designs specific to bakery applications. Here are a few of my favorites.

  1. Statistics for Experimenters: Design, Innovation, and Discovery , 2nd Edition [Hardcover] George E. P. Box (Author) J. Stuart Hunter (Author), William G. Hunter (Author)

  2. Design and Analysis of Experiments [Hardcover] Douglas C. Montgomery (Author)

  3. Design of Experiments: An Introduction Based on Linear Models (Chapman & Hall/CRC Texts in Statistical Science) [Hardcover] Max Morris (Author)

  4. Design and Analysis of Experiments (Springer Texts in Statistics) [Hardcover] Angela M. Dean (Author), Daniel Voss (Author)

  5. Experiments: Planning, Analysis, and Optimization (Wiley Series in Probability and Statistics) [Hardcover] C. F. Jeff Wu (Author), Michael S. Hamada (Author)

  6. Statistical Design and Analysis of Experiments, with Applications to Engineering and Science [Hardcover] Robert L. Mason (Author), Richard F. Gunst (Author), James L. Hess (Author)

  7. Statistical Design and Analysis of Experiments (Classics in Applied Mathematics No 22. ) [Paperback] Peter W. M. John (Author)

$\endgroup$
9
$\begingroup$

I am surprised no one mentioned: Statistical Design by George Casella.

$\endgroup$
6
$\begingroup$

Not published yet$^\dagger$, but I'm impatient for Design and analysis of experiments with R

There are not enough books on DoE with R. I'm very reluctant to proprietary software, and R documentation is not always the best.


$^\dagger$

Published December 11, 2014 by Chapman & Hall.

$\endgroup$
1
  • 2
    $\begingroup$ I have been able to review this book. I need to borrow a copy again (now that I have a little more experience with R), but this was a fantastic resource in terms of depth and breadth of experimental designs. I also appreciated the decision tree of designed experiments. $\endgroup$
    – Tavrock
    Mar 30, 2017 at 15:44
4
$\begingroup$

Experiments: Planning, Analysis and Optimization by Wu & Hamada.

I'm only a couple of chapters in, so not yet in a position to recommend confidently, but so far it looks like a good graduate text, reasonably detailed, comprehensive and up-to-date. Has more of a "no nonsense" feel than the Montgomery.

$\endgroup$
4
$\begingroup$

Experimental Design for the Life Sciences, by Ruxton & Colegrave. Aimed primarily at undergraduates.

$\endgroup$
4
$\begingroup$

I have recently reviewed a large collection of DoE books (17), with the following requirements:

  1. Not a cookbook approach but geared towards understanding (hard requirement)
  2. Decently in-depth (hard requirement)
  3. Written with an understanding of the New Causal Revolution (nice-to-have)
  4. Uses Hasse diagrams to simplify understanding of variance structure (nice-to-have)
  5. Has problems or exercises, preferably with solutions, for self-study (must have problems, nice to have solutions)
  6. Does not use SAS (I hate SAS) - or at least has an alternative to SAS (hard requirement)
  7. Utilizes a depth-first approach rather than breadth-first (suits my learning style better - hard requirement)
  8. Geared towards upper-level undergraduate with prerequisites of mathematical statistics and linear models (hard requirement)

The books I reviewed were the following (only first author listed):

  1. Kaltenbach, Statistical Design and Analysis of Biological Experiments
  2. Casella, Statistical Design
  3. Montgomery, Design and Analysis of Experiments, 4th Ed.
  4. Montgomery, Design and Analysis of Experiments, 10th Ed.
  5. Montgomery, Design of Experiments: A Modern Approach
  6. Oehlert, A First Course in Design and Analysis of Experiments
  7. Lawson, Design and Analysis of Experiments with R
  8. Fisher, The Design of Experiments
  9. Morris, Design of Experiments: An Introduction Based on Linear Models
  10. Bailey, Design of Comparative Experiments
  11. Wu, Experiments: Planning, Analysis, and Optimization
  12. Dean, Design and Analysis of Experiments
  13. Box, Statistics for Experimenters
  14. Maxwell, Designing Experiments and Analyzing Data: A Model Comparison Perspective
  15. Mead, Statistical Principles for the Design of Experiments
  16. Cobb, Introduction to Design and Analysis of Experiments
  17. Kuehl, Design of Experiments: Statistical Principles of Research Design and Analysis, 2nd Ed.

I was unable to find any book that had all of the desired characteristics. Indeed, I have come to think that Requirement #3 is not satisfied anywhere.

Requirement #4 is only true for three books in the list (Oehlert, Kaltenbach, and Bailey).

Two books were too advanced (Casella and Morris), though Casella would likely be a terrific graduate-level text.

Very few books had answers to problems, and quite a few had no problems at all (Fisher and Kaltenbach, with Bailey and Mead having too few problems).

A number of books just presented a cookbook approach: here's the design and how you analyze it, with a very limited attempt at getting to the understanding (all the Montgomery books, Oehlert, Lawson, Kuehl). Maxwell was far too wordy, Cobb was too low-level and also very wordy. Wu was breadth-first.

I narrowed it down to two possibilities that looked promising: Dean and Box. I had to read the first few chapters of both to determine that Dean uses a depth-first approach, while Box has a breadth-first approach.

So I have landed on Dean, Voss, and Draguljic Design and Analysis of Experiments as my favored book for self-study, based on my requirements. It fails Requirements #3 and #4 and does not have solutions for problems. But it does well enough on the other requirements to be the best option.

Fisher is worth reading, but is not sufficient on its own to train you to be proficient, as there are no problems to work. He has very good explanations, and it would be a great supplement.

$\endgroup$
3
$\begingroup$

If you're interested in pharmaceutical trials, two books I recommend:

  1. Statistical Issues in Drug Development by Stephen Senn (Amazon link)
  2. Cross-over Trials in Clinical Research by Stephen Senn (Amazon link)
$\endgroup$
3
$\begingroup$

Not really a book but a gentle introduction on DoE in R: An R companion to Experimental Design.

$\endgroup$
3
$\begingroup$

This book gives you a statistical perspective on experimental design:

Casella, G. (2008). Statistical Design. Springer.

$\endgroup$
2
  • 1
    $\begingroup$ Tim, I am noticing there is an older answer here recommending the same book of Casella. This probably, imo, makes the two answers virtually same. $\endgroup$ Aug 3, 2023 at 4:03
  • $\begingroup$ In any case, I prefer yours for at least it provides a glimpse of the theme the author caters to unlike the older answer which only throws a link (perhaps in concordance with older norms here). $\endgroup$ Aug 3, 2023 at 4:05
3
$\begingroup$

If your field is biology/ecology, a nice and well written text is "Experimental Design and Data Analysis for Biologists" of Quinn and Keough (amazon).

the work done by Underwood is also very interesting to read:

Experiments in Ecology: Their Logical Design and Interpretation Using Analysis of Variance (amazon).

$\endgroup$
2
$\begingroup$

The Design of Experiments: Statistical Principles for Practical Applications by Roger Mead. Examples are drawn from agriculture and biology, so probably most appropriate if you're interested in one of those fields. Rather expensive for a 600-page paperback but you can probably find it second-hand.

$\endgroup$
2
$\begingroup$

Experimental Design in Biotechnology by Perry D. Haaland, ed Marcel Dekker.

$\endgroup$
2
$\begingroup$

If you're in the social sciences:

Using Randomization in Development Economics Research: A Toolkit

$\endgroup$
2
$\begingroup$

A contemporary reference that I've found really useful is

"Randomization in Clinical Trials" by Rosenberger and Lachin

While the focus is on randomized trials and in-human studies, it covers many topics not previously covered in a nice, codified reference (group sequential designs, covariate adaptive designs, causality, etc.).

Lachin has been a trusted reference with a great deal of influence on FDA decision making over the years. The book has some very interesting applied examples, particularly the ECMO study, to demonstrate contemporary issues in trials (blinding, bias, crossover, etc.)

$\endgroup$
1
$\begingroup$

Hands on DOE book

John Lawson has written two books.

  1. Design and Analysis of Experiments with SAS

  2. Design and Analysis of Experiments with R

One is for SAS users and another one for R users. Both the version are same in content and context, the only difference is the software used in the book. Second one which is for R users is more useful as R is open source. So this is more of an hands on DOE book. He has in fact developed a library around with name daewr

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.