Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
.. use "##" , as you are also interested in estimating the non-interacted form
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Antwort: Re: st: Problems with defining varable interactions in ANOVA
From
Justina Fischer <[email protected]>
To
[email protected]
Subject
Antwort: Re: st: Problems with defining varable interactions in ANOVA
Date
Fri, 7 Jan 2011 15:46:20 +0100
in addition
so
xi: reg y c.a##c.b
will estimate the coefficients of a, b and a*b
(assuming a and b are continuous)
JF
[email protected] schrieb: -----
An: [email protected]
Von: Richard Goldstein <[email protected]>
Gesendet von: [email protected]
Datum: 07.01.2011 02:15PM
Thema: Re: st: Problems with defining varable interactions in ANOVA
what Stata manuals are you talking about? the symbol should be "#", not
the asterisk you are using
Rich
On 1/7/11 7:52 AM, Rom Litwin wrote:
> Greetings,
>
> I am super-new to STATA. I am running STATA 11 in Win7 and - contrary to
> what most STATA manuals claim, it seems - I am unable to set up interaction
> variables in ANOVA. Just to use an example from the UCLA manual, when I run:
>
> . use http://www.ats.ucla.edu/stat/stata/faq/crf24
> . anova y a b a*b
>
> I am getting the following error:
> variable a*b not found
> r(111);
>
> Thank you for your advice.
>
> - Rom Litwin
*
* 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/