Statalist


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

Re: st: Panel data and poisson-regression


From   "Martin Weiss" <Martin.Weiss1@gmx.de>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Panel data and poisson-regression
Date   Thu, 31 Dec 2009 23:26:55 +0100

<>





" Instead of fitting individual dummy variables isnt it possible to use
 xtpoisson/xtmepoisson instead ?"

Try 

***
xtpoisson _freq t, i(state) nolog
xtmepoisson _freq t || state:, nolog
***

HTH
Martin
-------- Original-Nachricht --------
> Datum: Thu, 31 Dec 2009 21:38:25 +0100
> Von: moleps <moleps2@gmail.com>
> An: statalist@hsphsun2.harvard.edu
> Betreff: Re: st: Panel data and poisson-regression

> OK.. thanks.. didnt know xtline accepted multiple variables.
> 
> Instead of fitting individual dummy variables isnt it possible to use
> xtpoisson/xtmepoisson instead ?
> 
> Regards,
> M
> 
> 
> On 31. des. 2009, at 19.44, Austin Nichols wrote:
> 
> > Clarify by worked example, or carefully chosen words, not confused
> > pseudocode (note that -xtline- applied to the time variable produces a
> > bunch of y=x function graphs).
> > 
> > webuse psidextract, clear
> > collapse (sum) _freq=union, by(ed t)
> > ren ed state
> > tsset state t
> > qui xi: poisson _freq t i.state
> > predict n
> > xtline n _freq if state>12
> > 
> > On Thu, Dec 31, 2009 at 1:12 PM, moleps <moleps2@gmail.com> wrote:
> >> What I want is to overlay the poisson predicted values (that I´m
> unsure how to get), ie :
> >> 
> >> tsset state _freq
> >> xtline _freq
> >> xtpoisson ...something...
> >> predict pr
> >> 
> >> xtline ***_freq & pr (/overlaid on each other**
> >> 
> >> Happy new year,
> >> 
> >> M
> >> 
> >> On 31. des. 2009, at 19.02, Martin Weiss wrote:
> >> 
> >>> <>
> >>> 
> >>> What exactly do you want to overlay? The predicted number from the
> -poisson- regressions? Please clarify.
> >>> 
> >>> 
> >>> Happy new year
> >>> Martin
> >>> -------- Original-Nachricht --------
> >>>> Datum: Thu, 31 Dec 2009 18:14:59 +0100
> >>>> Von: moleps <moleps2@gmail.com>
> >>>> An: statalist@hsphsun2.harvard.edu
> >>>> Betreff: st: Panel data and poisson-regression
> >>> 
> >>>> Dear listers,
> >>>> I´m looking for an effect over time between different states on the
> >>>> incidence of a rare cancertype. I´ve contracted my data so that I´m
> only left
> >>>> with _freq, state and year.
> >>>> 
> >>>> .tsset state _freq
> >>>> .xtline _freq
> >>>> 
> >>>> and from here on I´m stuck. What I´d like to do is to fit a poisson
> >>>> regression model for each of the states and have it overlaid on the
> -xtline
> >>>> _freq-...
> >>>> 
> >>>> Any ideas on how to do this?
> >>>> 
> >>>> regards,
> >>>> M
> > 
> > *
> > *   For searches and help try:
> > *   http://www.stata.com/help.cgi?search
> > *   http://www.stata.com/support/statalist/faq
> > *   http://www.ats.ucla.edu/stat/stata/
> 
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

-- 
GRATIS für alle GMX-Mitglieder: Die maxdome Movie-FLAT!
Jetzt freischalten unter http://portal.gmx.net/de/go/maxdome01
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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