Robust GAM that covers Gaussian Distributions

Ilaria Prosdocimi <ilapro <at> ceh.ac.uk> writes:

Christos Giannoulis <cgiannoul <at> gmail.com> writes:

Dear All,

I was looking the r-archives and crantastic...for a package that has

a

robust approach to generalized additive models. I found two packages
"robustgam" and "rgam" but their implemented functions
cover only binomial and poisson distributions (pls correct me if I

am

wrong).

I would greatly appreciate if anyone could share with us other

packages or

robust approaches of general additive modeling that might have a

better

performance with small data sets (n = 50 -100 records).

Thank you very much all for reading this message. I am hoping and

looking

forward to receiving your reply.

Sincerely,

Christos Giannoulis

	[[alternative HTML version deleted]]

Indeed, it seems that both the libraries do not allow normal data. I

think

you could try to use the code in this page
(http://www.stat.ubc.ca/~matias/penalised/) for S-estimation.
If you want the code for the Croux et al paper
(http://onlinelibrary.wiley.com/doi/10.1111/j.1541-

0420.2011.01630.x/full)

just email me (ilapro + ceh.ac.uk) - it seems to be not available

online

anymore. This also allow normal data.

Best

Ilaria

For information - in case somebody finds this post again in the future,
the original files have now been restored in the KULeuven website at
this address
http://wis.kuleuven.be/stat/stat-inferen/codes

I have also packaged the code in a R package which can be accessed on
GitHub (and installed with devtools::install_github) at

https://github.com/ilapros/DoubleRobGam

Best

Ilaria