Skip to content

bivariate function in gam model

3 messages · Daniel A. Powers, Ben Bolker, Brian Ripley

#
R-users --

I would be interested in tools in R to fit the following gam model:

logit(p) = a + f(x1) + f(x2) + f(x1,x2),

where f(x1,x2) defines a surface.

I have looked into the mgcv library, but it seems only to fit models of
the form:

logit(p) = a + f(x1) + f(x2)

Any ideas?

Cheers,
Dan

=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Dan Powers
Associate Professor, Sociology
University of Texas at Austin


-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
I don't know, but would the thin-plate splines in the funfit library do
what you need?

  Ben Bolker
On Wed, 16 May 2001, Daniel A. Powers wrote:

            

  
    
#
On Wed, 16 May 2001 ben at zoo.ufl.edu wrote:

            
I had a lot of problems with using those in funfit (and its legal status is
unclear).  I think gss is more promising: its gssanova includes bivariate
terms in additive predictors for a GLM, including thin-plate spline terms.
[...]