I've used the scatterplot3d function to graph some data and had it
graph a "smooth" fit. Is there a way to actualy find out the function
of the surface? I've looked through the help and figured out how to get
it to report the following:
Family: gaussian
Link function: identity
Formula:
y ~ s(x, z)
Parametric coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.20750 0.01223 16.97 <2e-16 ***
---
Signif. codes: 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1
Approximate significance of smooth terms:
edf Est.rank F p-value
s(x,z) 8.403 17 9.729 1.76e-14 ***
---
Signif. codes: 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1
R-sq.(adj) = 0.684 Deviance explained = 70.9%
GCV score = 0.017692 Scale est. = 0.016151 n = 108
But I'm still not really sure what I'm looking at, either that or
"smooth" means something different than I thought. Any help would be
great!
thanks,
-Max
Dear Max, I'm guessing that you're actually using scatter3d() in the Rcmdr package rather than scatterplot3d(), since the latter, I believe, doesn't fit regression surfaces. If I'm right, then as it says in ?scatter3d, the smooth surface is fit by the gam() function in the mgcv package using a smoothing spline and there is no explicit equation to examine. See ?gam for more information. I hope this helps, John -------------------------------- John Fox, Professor Department of Sociology McMaster University Hamilton, Ontario, Canada L8S 4M4 905-525-9140x23604 http://socserv.mcmaster.ca/jfox> -----Original Message----- > From: r-help-bounces at r-project.org [mailto:r-help-bounces at r- > project.org] On Behalf Of Max > Sent: December-18-07 2:02 PM > To: r-help at stat.math.ethz.ch > Subject: [R] Scatterplot3d model reporting question > > I've used the scatterplot3d function to graph some data and had it > graph a "smooth" fit. Is there a way to actualy find out the function > of the surface? I've looked through the help and figured out how to get > it to report the following: > > Family: gaussian > Link function: identity > > Formula: > y ~ s(x, z) > > Parametric coefficients: > Estimate Std. Error t value Pr(>|t|) > (Intercept) 0.20750 0.01223 16.97 <2e-16 *** > --- > Signif. codes: 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1 > > Approximate significance of smooth terms: > edf Est.rank F p-value > s(x,z) 8.403 17 9.729 1.76e-14 *** > --- > Signif. codes: 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1 > > R-sq.(adj) = 0.684 Deviance explained = 70.9% > GCV score = 0.017692 Scale est. = 0.016151 n = 108 > > But I'm still not really sure what I'm looking at, either that or > "smooth" means something different than I thought. Any help would be > great! > > thanks, > > -Max > > ______________________________________________ > R-help at 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.
Dear Max, I'm guessing that you're actually using scatter3d() in the Rcmdr package rather than scatterplot3d(), since the latter, I believe, doesn't fit regression surfaces. If I'm right, then as it says in ?scatter3d, the smooth surface is fit by the gam() function in the mgcv package using a regression spline and there is no explicit equation to examine. I hope this helps, John -------------------------------- John Fox, Professor Department of Sociology McMaster University Hamilton, Ontario, Canada L8S 4M4 905-525-9140x23604 http://socserv.mcmaster.ca/jfox> -----Original Message----- > From: r-help-bounces at r-project.org [mailto:r-help-bounces at r- > project.org] On Behalf Of Max > Sent: December-18-07 2:02 PM > To: r-help at stat.math.ethz.ch > Subject: [R] Scatterplot3d model reporting question > > I've used the scatterplot3d function to graph some data and had it > graph a "smooth" fit. Is there a way to actualy find out the function > of the surface? I've looked through the help and figured out how to get > it to report the following: > > Family: gaussian > Link function: identity > > Formula: > y ~ s(x, z) > > Parametric coefficients: > Estimate Std. Error t value Pr(>|t|) > (Intercept) 0.20750 0.01223 16.97 <2e-16 *** > --- > Signif. codes: 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1 > > Approximate significance of smooth terms: > edf Est.rank F p-value > s(x,z) 8.403 17 9.729 1.76e-14 *** > --- > Signif. codes: 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1 > > R-sq.(adj) = 0.684 Deviance explained = 70.9% > GCV score = 0.017692 Scale est. = 0.016151 n = 108 > > But I'm still not really sure what I'm looking at, either that or > "smooth" means something different than I thought. Any help would be > great! > > thanks, > > -Max > > ______________________________________________ > R-help at 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.