[R] p-level in packages mgcv and gam

[Denis Chabot]

Thank you very much Henric, now I see!

Denis
Le 05-10-02 à 11:47, Henric Nilsson a écrit :

> This test concerns only the non-linear part of the term s(Number,  
> 3). In order to simultaneously test both the linear and non-linear  
> part, as mgcv::summary.gam does, you'd
>
> > kyp1.1 <- gam(Kyphosis ~ 1, family=binomial, data=kyphosis)
> > anova(kyp1.1, kyp1, test = "Chisq")
> Analysis of Deviance Table
>
> Model 1: Kyphosis ~ 1
> Model 2: Kyphosis ~ s(Number, 3)
>   Resid. Df Resid. Dev      Df Deviance P(>|Chi|)
> 1   80.0000     83.234
> 2   76.9999     71.997  3.0001   11.237     0.011
>
>
> HTH,
> Henric
>
>