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

R: R: st: combine indicator values

From   "Carlo Lazzaro" <>
To   <>
Subject   R: R: st: combine indicator values
Date   Mon, 23 Nov 2009 13:54:36 +0100

Maarten is correct: Nick actually reported that he is using a different
(binary)dependent variable. I wrongly assumed that Nick eventually decided
to consider the child_123 var as the dependent one. 
Hence, following Maarten's suggestion would solve Nick's problem.

Please apologize for my previous misreading.

Kind Regards,

-----Messaggio originale-----
[] Per conto di Maarten buis
Inviato: lunedì 23 novembre 2009 12.44
Oggetto: Re: R: st: combine indicator values

--- On Mon, 23/11/09, Carlo Lazzaro wrote:
> Nick is seemingly drifting away from his original query.
> If Nick plugs in the model the child_123 var as he
> reported, he seems to leave the logistic regression
> framework in favour of the Poisson one (that is, he 
> replaces binary response with count data).

No, he reported that he is using a different (binary)
dependent variable. So his problem seems to be how to
add a categorical variable to a logistic regression 
model (with or without -xi-). He wants to create a
categorical variable from a set of dummy variables,
and than use -xi- to put them (as a set of dummies)
in logistic regression. He is just not sure how
to set the reference category when adding a set
of dummy variables directly rather than through
-xi-, which I explained in the posts befor.

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index