26 Apr
2006
26 Apr
'06
7:13 a.m.
Yes, sorry to be imprecise again, by "all of the multiplicative
interactions of the original 4 variables," I mean the one four-way
interaction and all of the three-way interactions. See Clayton's post.
Best,
Dan
----
Ph.D. Student
Department of Government
Harvard University
Tutor, Currier House
dhopkins(a)fas.harvard.edu
http://www.danhopkins.org
On Wed, 26 Apr 2006, Holger Lutz Kern wrote:
Dan,
I think Juan was referring to three-way interactions and
four-way interactions, i.e. age * household * democrat.
Holger
Dan Hopkins wrote:
A good question. Clearly, you could just keep
going--what about
age^4*voted86^2? When we wrote the problem, we envisioned:
* all the covariates
* all of their squared terms
* all of the multiplicative interactions of the original 4 variables
I hope that clarifies things--obviously, it's OK if people also included
cubic terms.
Best,
Dan
----
Ph.D. Student
Department of Government
Harvard University
Tutor, Currier House
dhopkins(a)fas.harvard.edu
http://www.danhopkins.org
On Wed, 26 Apr 2006, Juan Vargas wrote:
--
Holger Lutz Kern
Graduate Student
Department of Government
Cornell University
Institute for Quantitative Social Science
Harvard University
1737 Cambridge Street N350
Cambridge, MA 02138
www.people.cornell.edu/pages/hlk23
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi,
What does exactly "all their multiplicative interactions" mean? Is is
all the possible interactions of pairs of covariates or are we supposed
to allow for higher order intercations of the type: X1*X2*X3*X4?
Juan
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l