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

st: RE: -xi- with multible variables


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: -xi- with multible variables
Date   Fri, 11 Mar 2005 18:07:10 -0000

There is no problem in using -xi- with 
multiple variables. The help file 
gives examples. 

As always, comment on what you tried 
but didn't work for you is much easier if we 
can see exactly what you typed. 

If I wanted to lay down the kind of 
artillery barrage of covariates you have in mind 
here, I think I would resort to 
producing the arguments for -xi- 
with some macro manipulation. 

Some other users have found -xi- 
insufficiently flexible for their 
needs. -xi3- and -desmat- appear
to be the main user-written alternatives. 
A -findit- is recommeneded.

Nick 
n.j.cox@durham.ac.uk 

Prahm, Jeremy
 
> Is there some way to use the -xi- command with multiple 
> variables?  This
> is the context of a three level nested logit model with around 10
> independent variables.  I need to create interactions for all of the
> nests.
> 
> I have a categorical variable that I want to interact with a number of
> continuous variables, is there a Stata command to do this?  Xi only
> seems to work with one variable.
> 
> Let variable categorical_1-categorical_3 have 5 levels each.
> Let var1-var8 be continuous variables that I want to interact 
> them with.
> Is there some way to interact categorical_1*(var1-var8),
> categorical_2*(var1-var8), and categorical_3*(var1-var8) 
> easily?  I know
> I can change the prefix, but this still requires 24 different prefixes
> and creates a number of redundant dummies.  Surely this must 
> be a common task and I'm overlooking something.
 

*
*   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