>i have what may be a simple question. i have a two independent class >variables and a continuous dependent variable. i am using glm to compare >the group means of one variable within levels of the other variable. for >example: > > Z 1 2 >X >1 15 17 >2 25 27 >3 10 35 > >i want to compare level 3 to 1 and level 2 to 1 within level 1 of Z and the >same within level 2 of Z. can anyone provide insight as to how to formulate >this using proc glm? after plodding through the manual it appears that a >contrast statement might do the trick. thanks. > >regards. > > >gerald mcgwin, jr, ms > >================================================== >department of epidemiology department of ophthalmology >school of public health school of medicine >tidwell hall eye foundation hospital >u n i v e r s i t y of a l a b a m a at b i r m i n g h a m >720 south 20th street 1720 university blvd. (RM H347) >birmingham, al 35294 birmingham, al 35294 >205-975-7369 205-325-8614 >205-934-8665 (fax) 205-325-8692 (fax) >gmcgwin@epi.soph.uab.edu mcgwin@eyes.uab.edu >================================================== > >

You can analyse the data by a one-way anova with 6 treatments and define the contrasts of interest using the estimate or the contrast statement. This amounts to application of the cell-means model.

Hans-Peter _______________________________________________________________________ Hans-Peter Piepho Institut f. Nutzpflanzenkunde WWW: http://www.wiz.uni-kassel.de/fts/ Universitaet Kassel Mail: piepho@wiz.uni-kassel.de Steinstrasse 19 Fax: +49 5542 98 1230 37213 Witzenhausen, Germany Phone: +49 5542 98 1248