Allan,
Thank you. I tried to adapt your suggestion to my situation and it still
does not work [as an aside, I'm new to R, so I may be overlooking something
simple]. Using your example below, I want my lower model to reflect only
an intercept (i.e., medv ~ 1), I want my upper model to reflect all
Not sure I really like stepwise variable selection, but the function
should work, of course. Compare
data(BostonHousing, package = "mlbench")
lmFit <- train(medv ~ ., data = BostonHousing, "lmStepAIC", scope =
list(lower = ~., upper = ~.^2), direction = "forward")
with
lmFit <- train(medv ~
I'm looking for guidance on how to implement forward stepwise regression
using lmStepAIC in Caret.
The stepwise "direction" appears to default to "backward". When I try to
use "scope" to provide a lower and upper model, Caret still seems to
default to "backward".
Any thoughts on how I can make t
3 matches
Mail list logo
