Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: dummy interaction
From
"Mol, M.C." <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: dummy interaction
Date
Thu, 2 May 2013 13:37:43 +0000
Dear all,
I seem to be missing something interpreting the interaction between to dummy variables. I always understood that it should not really make any difference whether or not you include a dummy variable as being continuous or factor. This seems confirmed by running reg Y i.dummy1##i.dummy2 which gives me the same results as reg Y c.dummy1##c.dummy2, which again gives me the same results as running reg Y i.dummy1 i.dummy2 i.dummy1#i.dummy2.
However, when I only include the main effect of 1 of the dummies and run reg Y i.dummy1 i.dummy1#i.dummy2 the results differ from reg Y c.dummy1 c.dummy1#c.dummy2
Would anyone care to explain to me what I am missing
Sincerely
Mischa
PS: The reason for running without the main effect of the second dummy is t=
hat I have multiple measurements per respondent and the second dummy only v=
aries between respondents and not in time (and therefore gets omitted).
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/