Prev: Back transform probits
Next: SASAUTOS= Question
From: Jo Sugar on 3 May 2010 21:44
Hi! I have some binomial disease data and have analysed it with probit
and logit link functions. I have been able to back transform the
logits but not the probits. Has anyone got code to back transform the
probits? That would be great if you do. Thanks.
From: shiling99 on 16 May 2010 17:23
On May 3, 9:44 pm, Jo Sugar <jstrin...(a)bses.org.au> wrote:
> Hi! I have some binomial disease data and have analysed it with probit
> and logit link functions. I have been able to back transform the
> logits but not the probits. Has anyone got code to back transform the
> probits? That would be great if you do. Thanks.

I believe you are talking about transforming back to the probability
from scores in a probit model. There is a couple of ways you can do.
Please see attached program below.

data t1;
do i =1 to 50;
x=rannor(567);
y=1+1*x > rannor(567);
output;
end;
run;

proc logistics data=t1;
model y (event='1') = x / link= probit;
output out = t2 xbeta=xbeta p1=p1 ;
run;

data t3;
set t2;
p_1=cdf('normal', xbeta);
run;

proc print data=t3;
run;



 | 
Pages: 1
Prev: Back transform probits
Next: SASAUTOS= Question