@SAS_Rob wrote: The tests for the parameter estimates are based upon a Wald Chi-Square test and not a t-test.  The ParameterEstimates table should have those values and the corresponding p-values. Thank you, Rob. I am not familiar with Wald test, even though I did see that the parameterestimates table provides LowerWaldCL and UpperWaldCL. Both are so close to the estimates (which means the estimates are good) . I always think that t-Values should not be so close to the estimates.        Thanks, again. Rong   ... View more

Thanks for all of you. Ksharp, the option "dist=bin" produces an error, but SAS DOES accept "link=logit". Your thinking about "retain n  1;" is very suggestive. I haven't don't much reading about it, but you seem to suggest that any proportion problem  can be modeled by the way you indicate. But then it makes me feel a little awkward to write statements like "model k/N = ..." in references. Rick_SAS, your comment on "weight" is essential. Thank you. StatDave_sas, I took your suggestion about "glimmix". Thank you. I am sorry. I wanted accept everybody's comments as solution, but it seems that I am only allowed to choose one. When I picked one, I am completely blocked to choose others. ... View more

Thank you, Cynthia. Those are very good sites and I appreciate your help. My question is very specific.  What is the SAS counterpart of the STATA procedure "glm". Thanks again. Rong ... View more

Thanks Tom and Patrick, for your help. Putting the codes first in a file and then including it in the program I have heard sometime ago but never actually implemented. The reason is that I kept thinking there must be a very simple way, ideally by a macro variable combined with a system control character or variable, to create a "newline". Besides, the other parts of my program are quite complicated and I have been trying to avoid introducing additional complexities, sometimes, by sacrificing some generality.      Patrick, inner join is not going to work in my case without essential complications. I am not looking for exact matches, but partial ones. For instance, those (z=1), (z=2), ... are esstially something like (substr(string, n, m) in 'abcde').        Thanks, again.    ... View more

Thank you, Tom. I haven't worked out the details of your code, but I want to make sure we are on the same page. For SAS programs, there is a requirement on how many characters you can type on one line (I think it is 6000 characters), which is what I want to get around. So, I don't want a program to look like proc sql;      ...      where (z=1) or (z=2) or ... or (z=10000); quit; Instead, I want it to look like      proc sql;      ...      where (z=1)      or (z=2)      or ...      or (z=10000); quit; In my case, z is actually a variable representing very complicated medical codes or drug codes. Here I write 1,2,..., 10000 just for simplicity. Thanks, again. ... View more

Suppose you want to do the sql:      Proc sql;           create table TEST_TABLE as           select x,           y,           z           from DATABASE_TABLE           where (z=1)           or (z=2)           or ....           or (z=10000);      quit;      Notice that I use a macro variable, say, a_variable to replace (z=1) or (z=2) or ....or (z=10000), but then it's too long. Is this clear? ... View more

Thank you very much, both of you, data_null_ and Rick. You are absolutely right! Interesting, 32bit and 64bit (or maybe SAS9.1.3 and SAS9.2) work a slightly differently! ... View more