3
$\begingroup$

Generalized linear models (GLM's) are apparently widely used, but I'm having some trouble to find comprehensive but still simple resources to explain it to someone who is not a statistician but has a basic background on statistics.

Currently I have found the following references:

  1. Wikipedia GLM article
  2. This book (I didn't have access to it yet):MCCULLAGH, Patrick; NELDER, John A. Generalized linear models. 2nd ed. London: Chapman & Hall/CRC, 1995. 511 p.
  3. This paper (very hermetical): McCullagh, Peter. "Generalized linear models." European Journal of Operational Research 16.3 (1984): 285-292.

Looking for websites, books or research papers.

Improve this question
$\endgroup$
5
  • $\begingroup$ This post might be helpful stats.stackexchange.com/questions/94371/… $\endgroup$
    – JohnK
    Commented May 15, 2015 at 13:37
  • $\begingroup$ For non-statisticians I would start with the Gelman-Hill reference from the above comment. $\endgroup$
    – kjetil b halvorsen ♦
    Commented May 15, 2015 at 13:38
  • $\begingroup$ I've found this good. Not knowing much about soil science is not a barrier to finding it useful. Lane, P. W. 2002. Generalized linear models in soil science. European Journal of Soil Science 53: 241-251 DO - 10.1046/j.1365-2389.2002.00440.x $\endgroup$
    – Nick Cox
    Commented May 15, 2015 at 15:08
  • $\begingroup$ This borrows heavily from McCullagh and Nelder and I've found it to be a convenient reference. Also Faraway's book on GLMs is popular (if you google it I believe you can find a free pdf). $\endgroup$
    – jld
    Commented May 15, 2015 at 15:11
  • $\begingroup$ In the duplicate post check in particular the Dobson book & Rodriguez lecture notes (which I just added) for introductory accounts. $\endgroup$
    – Scortchi ♦
    Commented May 15, 2015 at 15:30

1 Answer 1

Reset to default
5
$\begingroup$

To the references of the above comment, I would like to add "Introduction to Categorical Data Analysis" by Alan Agresti.

The book is precisely intended for non-statisticians and I believe it is commonly used as a first couse in the theory of GLM. Its main focus is logistic regression but you also see the Poisson, Negative Binomial and Gamma models in worked out examples. The book uses SAS but not to worry. There is an R-manual that also accompanies it]2, one important difference between SAS and R being of course that the latter is freely available.

I believe there is a free pdf version available somewhere on the internet, so take a look. If you are finding it too easy, you might also want to try its twin, which is intended for more advanced students.

Improve this answer
$\endgroup$
0

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