BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
keldel
Fluorite | Level 6

I would like to compute a 99% confidence interval for the odds ratio based on the likelihood ratio statistic. Here is what I have so far; the output provides a confidence interval for the odds ratio but is this based on the LR statistic?

 

data vaccine2;
input age reaction count;
cards;
65 5 0
65 1 3752
42 5 4
42 1 11301
;
run;
proc freq;
weight count;
tables age*reaction/ cmh chisq BINOMIAL(CL=LIKELIHOODRATIO) alpha=0.01;
run;

1 ACCEPTED SOLUTION

Accepted Solutions
Ksharp
Super User
proc freq;
weight count;
tables age*reaction/ cmh chisq oddsratio(cl=LIKELIHOODRATIO) alpha=0.01;
run;

View solution in original post

2 REPLIES 2
tarheel13
Rhodochrosite | Level 12

I'm probably not much help but I do know that you can get profile-likelihood odds ratios out of proc logistic. 

Ksharp
Super User
proc freq;
weight count;
tables age*reaction/ cmh chisq oddsratio(cl=LIKELIHOODRATIO) alpha=0.01;
run;