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

st: RE: logistic regression


From   BISSERY Alvine <Alvine.BISSERY@hop.egp.ap-hop-paris.fr>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: logistic regression
Date   Thu, 03 Oct 2002 11:52:29 +0200

What you have to know is how you want to code your categorical variable ... 

if you have a linear trend between the different categories of these
variables (you have the same risk from 1 to 2, 2 to 3 , ...), you can let
this code, and the syntax is 

logistic prop1 conc inc

But if it's not true, you have to recode them as dummy variables, with the
syntax xi

xi:logistic prop1 i.conc i.inc

Hope this helps

Alvine

> -----Message d'origine-----
> De: Chris.Fergusson@sth.nhs.uk [mailto:Chris.Fergusson@sth.nhs.uk]
> Date: jeudi 3 octobre 2002 11:37
> : statalist@hsphsun2.harvard.edu
> Objet: st: logistic regression
> 
> 
> Hello statalisters,
> 
> Could anybody tell me how I would treat the following problem,
> 
> I am using logistic regression to calculate the relationship between a
> dependent variable (prop1) and two catagorical variables 
> (conc and inc).
> There are no other variables.  Conc takes the values 
> 1,2,...,8 and inc takes
> the values 1,2,3.  Any advice on the syntax would be most 
> appreciated, or
> pointers towards literature.
> 
> Thank you in advance,
> 
> Christopher D Fergusson
> *
> *   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/



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