Hi everyone,
Hope you are all having wonderful holiday breaks. I have a stats question - two
actually.
I'm having trouble getting the gam function to work (still!)- I get the same
error
everytime I do it ... that one of my elements has fewer unique covariate
combinations than the number of degrees of freedom. I have been using the
following code:
gam.out<-gam(y~s(x1) +s(x2) +...)
I have two dummy variables among my x's - should I take those out? I don't
know
what else to do.. I've made no progress on this for several days now.
Another problem is getting qqplots -
Is this the right code ?
qq.plot(lm.out, simulate=T)
if so, I don't know why it won't plot.
Any advice?! Both of these things just shouldn't be that complicated - so I
must be missing something obvious, or there must be some glitch with my R that
I need to get around. Any help will be appreciated.
Thanks!
Suzanna