Dear Tugan,
re: random effects references.
If, like me, you used to think that a t-test was a method for analysing
Darjeeling, I'd recommend the following general treatments:
Searle, S.R (1971) Linear Models - Chapter 9 (pp376-384) gives a good,
non-mathematical overview of the concepts involved, as does the first
chapter of
Searle's later book (Variance Components; Searle, Casella and McCulloch
1992). The following paper is also quite useful, albeit statistically more
complex.
Frisson L & Pocock SJ (1992)
"Repeated measures in clinical trials: Analysis using
mean summary statistics and its implications for design"
Statistics in Medicine 11:1685-1704.
At the moment, the only published reference specifically dealing with random
effects analyses in a neuroimaging context is Andrew's abstract from HBM 98,
which you can get from: http://www.fil.ion.ucl.ac.uk/spm/RFXabstract.pdf for
the abstract, and http://www.fil.ion.ucl.ac.uk/spm/RFXposter.pdf for the
poster.
Best Wishes
Dave McG.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|