Dear Statlisters
I am analyzing simple data with multiple regression. The dependent (Y)
is not normal, and a transformation (log) seem to partly solve the
problem. However, I have just read that when I trnsform the data the
interpretation of the R2 is not anymore meaningful in terms of the
original data. Now, I understand this in those case where you transform
a predictor (X); in such a case it is clear that R2 is not anymore the %
of variance in Y explained by the X -- it is the % of Y explained by
log(X). But what meaning gets the R2 when I transform the Y?
(I read an aswer to Y. Nagao by [email protected] about using
generalized linear models instead of transforming; which is very
interesting, but I need an aswer now, dont have time to study GLm for
this problem).
Thanks.
Cheers,
--
Luca Bianco Prevot, M.Sc. Candidate
Dept. of Psychology, Neuroscience & Behaviour
McMaster University
1280 Main St. West, Hamilton,ON
L8S-4K1 Canada
Tel: (905)525-9140 x26042
E-mail: [email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
