Much appreciated, this helped me solve my problem.  Thanks. ... View more

I suggest looking at Procs PHREG and LIFEREG as a couple of places to start. ... View more

Thanks to both of you for the response and explanation ... View more

Thank you for the suggestion. That was very helpful ... View more

It seems strange that the hazardratio should be that extreme. Can you attach the dataset? I would like to take a look on it. ... View more

Thanks, Steve, for the ideas. When I did Loess on the individual variables, the inflection points on the Loess curves were noted and used to create cutoffs for these individual variables, also attempting to make them linear and then the scores were multiplied to use as a score that would predict the binary response. I was worried that this method would lose some valuable information and hence wanted to try using these in their original form. You have a good point about the additivity and I will try to see if I can use only clearly additive variables in GAM. I haven't used Glimmix, so I will also try that and Transreg if time permits. Thanks again for your suggestions ... View more

I would like to see some example data.  What you have, and example of what you want. ... View more

One way would be to use the 'offset' option in an axis statement, to add some offset to the left & right... data foo; input y $1 x z; datalines; A 3.6 1 B 2.8 2 ; run; axis1 offset=(30,30); proc gplot; plot x*y=z / haxis=axis1; run; ... View more

no problem. i am just having a hard time visualizing your data structure. hopefully some of the other users on here can chime in. can you show some made up dummy data (something that shows your data structure)? ... View more

I am skeptical about your model. The model should depend on your experimental (or survey) design (layout). Just based on the variable names, I suspect that some effects should be nested within others. ... View more

Hi Cynthia, Thank you very much for the detailed response with the code! Putting the dataset with the longest variable length first in the list of datasets in the "set" statement worked for me this time, but I am sure I will use the length statement the next time. Thanks for showing the difference with the code! ... View more

I finally got around to trying the code and it worked really well for my requirement. Thanks to both of you for the suggestions. the code that I used was the first one that Steve suggested - proc glm modeling the difference. Thanks for the help! ... View more

Check out Chapter 12 in SAS for Mixed Models, 2nd ed. Also a google search on Stroup "mixed models" power will be helpful. SteveDenham ... View more

The experiment was done on two days and although there is difference in mean measurements on the two days, the bimodality is not due to days. And, I tried putting in sample as a random effect and the residual plot is normal! Thanks Dale! I think I ran way too many models and forgot to try the one I really wanted. This random effects model (no fixed effects) will help answer all the questions. And the results are what was expected out of this experiement ... View more

Variance estimates are scale dependent. You don't say what your topic is, or what your variables are, but suppose you are (say) looking at the effect of salary on life expectancy. Measure salary in dollars per year, variance will be huge. Measure it in tens of thousands of dollars per year, variance will be small. Does this apply in your case? ... View more