Re: Needed: medical example of a continuous-variable interaction in a linerar regression model

Bruce Weaver <bweaver@xxxxxxxxxxxx> wrote in
news:ek6n9s02an@xxxxxxxxxxxxxxxxx:

Can anyone suggest a good medical or health-related example of a
linear regression model that has two continuous predictor variables
and their interaction? A public-domain data set would be useful too,
if available.

Most predictors of atherosclerosis will have interactions between the
independent vars when analyzed with linear regression, The predominance of
logistic and other exponential models is due to the "fact" that most of the
relationships are not linear when only main effects are considered, but
generally have more simple functional forms when examined in a
multiplicative model.

Stulong longitudinal study:
headers and entry data: http://euromise.vse.cz/challenge/data/Entry.zip
Follow-up exams: http://euromise.vse.cz/challenge/data/Entry.zip

Frank Harrell's datasets:
http://biostat.mc.vanderbilt.edu/twiki/bin/view/Main/DataSets

That last page also has links to a boatload of other datasets including the
Ur-Archive (or is that the Urchive?) Statlib at CMU.

--
David Winsemius
.

Relevant Pages