y,
Ariyo
2007/10/5, Simon Wood <[EMAIL PROTECTED]>:
> Actually the answers to you questions may well be linked
>
> On Thursday 04 October 2007 22:11, Ariyo Kanno wrote:
> > Dear all,
> >
> > I'm trying to fit a pure additive model of the following formula
Dear all,
I'm trying to fit a pure additive model of the following formula :
fit <- gam(y~x1+te(x2, x3, bs="cr"))
,with the smoothing parameter estimation method "magic"(default).
Regarding this, I have two questions :
Question 1 :
In some cases the value of "mgcv.conv$fully.converged" becomes
"
Thank you for your advices.
I will try even increased "gamma" values, and all-out cross-validations.
2007/10/3, Frank E Harrell Jr <[EMAIL PROTECTED]>:
> Ariyo Kanno wrote:
> > Sorry, let me fix 1 sentence.
> >
> > "Here I try to mean by "overfitti
mean square error of prediction of the validation data, which
> was randomly selected and not used for regression.
>
> Best Wishes,
> Ariyo
>
> 2007/10/3, Simon Wood <[EMAIL PROTECTED]>:
> > On Wednesday 03 October 2007 10:49, Ariyo Kanno wrote:
> > > I apprec
e mean square error of prediction of the validation data, which
was randomly selected and not used for regression.
Best Wishes,
Ariyo
2007/10/3, Simon Wood <[EMAIL PROTECTED]>:
> On Wednesday 03 October 2007 10:49, Ariyo Kanno wrote:
> > I appreciate your quick reply.
> > I am using the
at very low values
> > (3 to 5). However, I don't think this is reasonable because knots
> > selection will then be an
> > important issue.
> >
> > Is there any other means to avoid overfitting when alalyzing small
> &
6 matches
Mail list logo
