Hi everyone,    Please bear with me. I'm confused to understand Odds Ratio in Proc Glimmix with interaction. In Proc Logistic, if there is an interaction between factor A(two levels) and B(levels ≥2), Odds ratio of A will be presented in different level of B. In a word, there are different OR of A under different level of B. However, in Proc Glimmix, only one OR is presented even if there is an interaction. Here is my code are result.   proc glimmix data=mas ; where farm ne 'hy'; class season(ref='summer') treatment parity(ref='1') result farm year ; model result(event='pregnant')= season | parity | treatment / dist=binary oddsratio ; random farm year; run; As you can see, there is an interaction between treatment and parity or season. However, OR of treatment is 1.509. Why there is a difference between proc logistic and proc glimmix in the matter of OR? Thanks in advance for the help!  ... View more

How can I add confidence interval and significance like in the first plot below?. I'm using  syntax "series" in PROC SGPLOT Procedure, however can not found any statement about the interval and significance. I want to show the confidence interval and significance between two group in the second plot. Here are the codes:   proc sgplot data=text; series x=season y=Preg/group=co smoothconnect markers; run;   Hope you can help me. Thank you.     ... View more

I encountered quasi-complete separation when I used Logistic Regression. After viewing definition of quasi-complete separation and its solutions. There are still two confusions remained. 1:One of these solutions is FIRTH method. However, there came out "ERROR: Selection methods are not currently available with the FIRTH option" after I tried to use FIRTH method to solve the problem. 2:I can't found out which independent variable or a combination of several independent variables caused the separation.   Here is the program:   proc logistic data=maanshan320; class season(ref='summer') treatment result season parity; model result(event='pregnant')=season | treatment | parity | BCS / firth selection=B sls=0.11 lackfit orpvalue ; oddsratio treatment ; run;   Hope you can help me.   ... View more