Dear jianghua and all R professor:
I use the suggestion that jianghua gives. But the problem is still there.
Use "summary(m1)" or "summary.gam(m1)" is the same result and it doesn't show
the significance results of parametric terms.
Should I choose another smoother to get significance results of parametric
terms ?
I know another "gam way" in the package "mgcv" and they can show me the
significance results of parametric terms in package mgcv.
But the smoother is different between in package "gam" and "mgcv"
Is it possible to find significance results of parametric terms in package
"gam" ?
or maybe I have to try another smoother in package "mgcv" !!
Is it possible that in package "mgcv" do some assunptions which can make the
result is the same in package "gam" ?
Ashely, Yang
in package gam
¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ
> library(gam)
Loading required package: splines
>
>
> m1=gam(y~ost+wst+park10+sch50+comm+build+suite+y95+y96+y97+y98+y99+s(builarea)+s(age)+s(fl)+s(totfl)+s(cbd)+s(redl))
>
> summary.gam(m1)
Call: gam(formula = y ~ ost + wst + park10 + sch50 + comm + build +
suite + y95 + y96 + y97 + y98 + y99 + s(builarea) + s(age) +
s(fl) + s(totfl) + s(cbd) + s(redl))
Deviance Residuals:
Min 1Q Median 3Q Max
-753.51 -118.98 -15.27 99.16 1253.28
(Dispersion Parameter for gaussian family taken to be 41952.11)
Null Deviance: 564111793 on 4714 degrees of freedom
Residual Deviance: 196251969 on 4678 degrees of freedom
AIC: 63607.24
Number of Local Scoring Iterations: 2
DF for Terms and F-values for Nonparametric Effects
Df Npar Df Npar F Pr(F)
(Intercept) 1
ost 1
wst 1
park10 1
sch50 1
comm 1
build 1
suite 1
y95 1
y96 1
y97 1
y98 1
y99 1
s(builarea) 1 3 13.852 5.440e-09 ***
s(age) 1 3 13.410 1.033e-08 ***
s(fl) 1 3 41.732 < 2.2e-16 ***
s(totfl) 1 3 19.146 2.454e-12 ***
s(cbd) 1 3 15.464 5.222e-10 ***
s(redl) 1 3 4.839 0.002300 **
---
Signif. codes: 0 ¡¥***¡¦ 0.001 ¡¥**¡¦ 0.01 ¡¥*¡¦ 0.05 ¡¥.¡¦ 0.1 ¡¥ ¡¦ 1
>
> summary(m1)
Call: gam(formula = y ~ ost + wst + park10 + sch50 + comm + build +
suite + y95 + y96 + y97 + y98 + y99 + s(builarea) + s(age) +
s(fl) + s(totfl) + s(cbd) + s(redl))
Deviance Residuals:
Min 1Q Median 3Q Max
-753.51 -118.98 -15.27 99.16 1253.28
(Dispersion Parameter for gaussian family taken to be 41952.11)
Null Deviance: 564111793 on 4714 degrees of freedom
Residual Deviance: 196251969 on 4678 degrees of freedom
AIC: 63607.24
Number of Local Scoring Iterations: 2
DF for Terms and F-values for Nonparametric Effects
Df Npar Df Npar F Pr(F)
(Intercept) 1
ost 1
wst 1
park10 1
sch50 1
comm 1
build 1
suite 1
y95 1
y96 1
y97 1
y98 1
y99 1
s(builarea) 1 3 13.852 5.440e-09 ***
s(age) 1 3 13.410 1.033e-08 ***
s(fl) 1 3 41.732 < 2.2e-16 ***
s(totfl) 1 3 19.146 2.454e-12 ***
s(cbd) 1 3 15.464 5.222e-10 ***
s(redl) 1 3 4.839 0.002300 **
---
Signif. codes: 0 ¡¥***¡¦ 0.001 ¡¥**¡¦ 0.01 ¡¥*¡¦ 0.05 ¡¥.¡¦ 0.1 ¡¥ ¡¦ 1
>
in package mgcv
¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ¡õ
> library(mgcv)
This is mgcv 1.3-29
Attaching package: 'mgcv'
The following object(s) are masked from package:gam :
anova.gam,
gam,
gam.control,
gam.fit,
plot.gam,
predict.gam,
print.gam,
print.summary.gam,
s,
summary.gam
>
> m1=gam(y~ost+wst+park10+sch50+comm+build+suite+y95+y96+y97+y98+y99+s(builarea)+s(age)+s(fl)+s(totfl)+s(cbd)+s(redl))
>
> summary(m1)
Family: gaussian
Link function: identity
Formula:
y ~ ost + wst + park10 + sch50 + comm + build + suite + y95 +
y96 + y97 + y98 + y99 + s(builarea) + s(age) + s(fl) + s(totfl) +
s(cbd) + s(redl)
Parametric coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 865.501 18.487 46.816 < 2e-16 ***
ost -73.602 11.473 -6.415 1.55e-10 ***
wst -55.797 12.772 -4.369 1.28e-05 ***
park10 18.397 6.210 2.962 0.003067 **
sch50 49.629 12.296 4.036 5.52e-05 ***
comm -33.151 9.127 -3.632 0.000284 ***
build 71.412 24.353 2.932 0.003380 **
suite -72.243 18.651 -3.873 0.000109 ***
y95 -92.786 12.804 -7.247 4.97e-13 ***
y96 -110.059 11.747 -9.369 < 2e-16 ***
y97 -96.286 10.909 -8.827 < 2e-16 ***
y98 -122.834 11.166 -11.001 < 2e-16 ***
y99 -135.183 18.182 -7.435 1.24e-13 ***
---
Signif. codes: 0 ¡¥***¡¦ 0.001 ¡¥**¡¦ 0.01 ¡¥*¡¦ 0.05 ¡¥.¡¦ 0.1 ¡¥ ¡¦ 1
Approximate significance of smooth terms:
edf Est.rank F p-value
s(builarea) 5.728 9 733.118 < 2e-16 ***
s(age) 6.571 9 8.152 4.19e-12 ***
s(fl) 8.758 9 20.564 < 2e-16 ***
s(totfl) 8.196 9 8.401 1.54e-12 ***
s(cbd) 8.915 9 51.787 < 2e-16 ***
s(redl) 7.910 9 4.504 6.45e-06 ***
---
Signif. codes: 0 ¡¥***¡¦ 0.001 ¡¥**¡¦ 0.01 ¡¥*¡¦ 0.05 ¡¥.¡¦ 0.1 ¡¥ ¡¦ 1
R-sq.(adj) = 0.661 Deviance explained = 66.5%
GCV score = 41115 Scale est. = 40600 n = 4715
>
> Date: Tue, 5 May 2009 08:57:34 -0700
> From: jianghua....@shef.ac.uk
> To: r-help@r-project.org
> Subject: Re: [R] smoothing spline in package gam
>
>
> Strangely, summary.gam(m1) should give you significance results of parametric
> terms such as ost, wst, park10, sch50, comm, build and suite. These results
> should be located above the summary results for smooth terms.
> Please using summary.gam(m1) to have a look if there is the information you
> need.
> Good luck!
>
>
> ·¨ ¸ÖÃý wrote:
> >
> >
> > dear all,
> >
> >
> >
> > i have a little question, but it make me torment long time
> >
> >
> >
> > hope you can help me and give some advices , thanks
> >
> >
> >
> >
> >
> > i use smoothing spline in package gam
> >
> >
> >
> > the model
> >
> >
> >
> >> m1=gam(y~ost+wst+park10+sch50+comm+build+suite+y05+y06+y07+y99+y98+s(builarea)+s(age)+s(fl)+s(totfl)+s(cbd)+s(redl))
> >
> >
> > and summary(m1) can show the "s"(smoothing) variables' Signif. codes.
> >
> >
> >
> > but i also want to know the Parametric coefficients and their Signif.
> > codes. like ost, wst...etc.
> >
> >
> >
> > is that possible to get the Parametric coefficients' Signif. codes (in
> > package gam) ?
> >
> >
> >
> >
> >
> > thanks~~
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> >
> > _________________________________________________________________
> >
> >
> > [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > R-help@r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> > http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> >
> >
>
> --
> View this message in context:
> http://www.nabble.com/smoothing-spline-in-package-gam-tp23382805p23390437.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
_________________________________________________________________
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
