Re: Random effects when doing linear regression

Thank you both for your help. Unfortunately I have unbalanced data, but
oh well. Maybe I will use STATA instead of MATLAB.

Tony

Anon. wrote:
Antoine Bruguier wrote:
Hi all,

I've been looking into books and on the internet for something that
should be available, but nothing came up so I am resorting to this
newsgroup for references and pointers.

I'm trying to do a random-effects analysis to test the significance of
a parameter found by linear regression (in my field, we call that
GLM=general linear models). I have all the math figured out for the
fixed effect but I can't find a good reference for the random effect.

My next step will be to do this for an F-test (comparing two GLMs), so
if you have a reference for this, that'd be great too.

If your data isn't balanced, then you're in for a lot of fun! Quite
frankly, it's better to use a stats package to do the calculations for
you. OK, it's not as fun but you'll get your results.

Things are easier if it's balanced, for example see Searle (1971) Linear
Models. Hmm, he also has a new book out: Linear Models for Unbalanced Data.

Bob

--
Bob O'Hara

Dept. of Mathematics and Statistics
P.O. Box 68 (Gustaf Hällströmin katu 2b)
FIN-00014 University of Helsinki
Finland

Telephone: +358-9-191 51479
Mobile: +358 50 599 0540
Fax: +358-9-191 51400
WWW: http://www.RNI.Helsinki.FI/~boh/
Journal of Negative Results - EEB: http://www.jnr-eeb.org

.