Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: calculating SMRs, examples?


From   Seb Buechte <sfbuechte@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: calculating SMRs, examples?
Date   Thu, 15 Sep 2005 12:53:18 +0200

Raoul,

to calculate the expected number of deaths you may want to do the following:

AFTER -stset- and -stplit-

gen _e=(_t-_t0)/1000000 * mrate

The "1,000,000" works for rates that are scaled to 1,000,000
person-years which is the case in most of my data. If your reference
rates are per 100,000 person-years than enter this number into the
command. Obviously, other persontime units like person-days etc. also
work - as long as you get the scale right.

Make sure, that before you do the poisson regression you collapse your
date appropiately otherwise the log likelihood is biassed as as you
have an articially increased number of observation eventhough your
reference data is only available in a grouped way.

Kind regards,
sebastian

On 9/14/05, Raoul Reulen <raoulreulen@hotmail.com> wrote:
> Yes, very helpful, thanks. I am still struggling with getting the external
> data right. After I've used stset and stsplit I need to calculated the
> expected number of deaths in each strata. I find it difficult to do that.
> 
> Raoul
> 
> 
> >From: "Svend Juul" <SJ@SOCI.AU.DK>
> >Reply-To: statalist@hsphsun2.harvard.edu
> >To: <statalist@hsphsun2.harvard.edu>
> >Subject: Re: st: calculating SMRs, examples?
> >Date: Wed, 14 Sep 2005 14:27:39 +0200
> >
> >Raoul asked:
> >Are there any good websites or books out there that explain in detail
> >how to calculate a standardized mortality ratio (SMR) with poisson
> >regression using external rates? I find that the STATA manuals do not
> >contain a lot of information regarding this topic, any suggestions?
> >----
> >
> >I wrote, among other things:
> >
> >You may proceed from here to -poisson-; it requires the expected number
> >of deaths:
> >     . gen edeaths = pyrs*mrate
> >     . poisson _d exposure(edeaths) , irr
> >----
> >
> >- and that was wrong. The -poisson- command should be:
> >     . poisson _d , exposure(edeaths)
> >
> >To obtain the SMR, use -lincom- after -poisson-:
> >     . lincom _cons , irr
> >
> >I hope this was not too confusing.
> >
> >Svend
> >
> >__________________________________________
> >
> >Svend Juul
> >Institut for Folkesundhed, Afdeling for Epidemiologi
> >(Institute of Public Health, Department of Epidemiology)
> >Vennelyst Boulevard 6
> >DK-8000  Aarhus C, Denmark
> >Phone: +45 8942 6090
> >Home:  +45 8693 7796
> >Email: sj@soci.au.dk
> >__________________________________________
> >
> >*
> >*   For searches and help try:
> >*   http://www.stata.com/support/faqs/res/findit.html
> >*   http://www.stata.com/support/statalist/faq
> >*   http://www.ats.ucla.edu/stat/stata/
> 
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
> 


-- 
- Seb F Buechte
-
- Stay tuned!

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index