Dear allstats,
I fitted a logistic regression model on the demographic and health survey
data.
But I would like to compute the Population Attributable Fractions (PAFs).
For the estimates it is straight forward, I can use the below formula.
p(OR-1)/1+(OR-1),
p = disease prevalence, OR = Odds ratio.
My problem is the confidence intervals, the above formula cannot work.
Can some help and provide the theory I can read to compute the confidence
intervals?.
Thank you
Betty
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|