Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: Producing graphs post multinomial logistic regression models
From
Amal Khanolkar <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: Producing graphs post multinomial logistic regression models
Date
Tue, 26 Mar 2013 11:02:48 +0000
Hi,
I've run a set of multinomial logistic regression models where I obtain RRR for preterm birth (very early, early and late preterm term birth with the base being term births). I have four set of models with adjustment for various confounders:
eststo clear
eststo: mlogit birth i.exposure sex byear if magecat!=. & parity!=. & smoke1!=. & multibirth==1, base(3) rrr
eststo: mlogit birth i.exposure sex byear ib3.magecat i.parity if smoke1!=. & multibirth==1, base(3) rrr
eststo: mlogit birth i.exposure sex byear ib3.magecat i.parity i.smoke1 if multibirth==1, base(3) rrr
esttab, eform ci
I would like to show the results from the third model using a graph - something simple with bars representing the different risks for very early, early and late preterm births by the different categories of the exposure variable along with 95% confidence intervals.
Is it possible to do this directly after running the third mlogit model above using a post-estimation command or do I have to create a graph manually in Stata?
Thanks,
Amal Khanolkar
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/