Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Recreating Confidence Intervals after Poisson Regression

From   Garret Christensen <>
To   Stata List <>
Subject   st: Recreating Confidence Intervals after Poisson Regression
Date   Fri, 12 Jul 2013 20:44:10 -0700 (PDT)

Thanks Maarten and Richard for the suggestions. I had seen the Stata delta-rule FAQ page, but the delta rule math has always been a challenge for me. I don't quite get the "g()" function in the FAQ or the exponentiation in Maarten's Tip #3, but in my case at least, 
_b[treatment] - invnormal(0.025)*_se[treatment]
_b[treatment] + invnormal(0.025)*_se[treatment]
serve to reproduce the CIs output by the Poisson regression itself.


>>On Thu, Jul 11, 2013 at 1:35 AM, Garret Christensen wrote:
>> I'm interested in working with (read: using as scalars) the confidence intervals created by a Poisson regression.
>> If I were doing a linear regression, I'd just do what they say here
>>, which is:
>I have submitted a new Stata tip that, as an aside, also covers that:
> . It is an aside in that
>tip because it is already discused in the Stata FAQ that Richard
>pointed to :
>The complete reference to the article you are referring to is:
>M.L. Buis (2007), "Stata tip 54: Where did my p-values go?", The Stata
>Journal, 7(4), pp.584-586.
>The best place to download it is:
>- -- Maarten
>- ---------------------------------
>Maarten L. Buis
>Reichpietschufer 50
>10785 Berlin
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index