R help - Jun 2007 - kernel smooth for tw-dimensional data

Hi all:

I can use the density() function to get the kernel density for given
observed data X with bandwidth.

Is there a function in R that can take in two dimensional data(x, y) and
return a joint density based
on the bandwidth. Do I need to provide bandwith for x and then for y?

Is the GRASS package
kde2d.G(x, y, h, G, reverse=reverse(G))

provide such function?

Thanks
pat

Hi, I found kde2d in the MASS packages return densities for the bivariate
random varaibles.

I donot understand why each element of density Z is a 2*2 matrix.
Why it is not a number.

For example, a bivariate normula distribution given (x, y) will return a
number, the density, not a matrix.

Thanks
Pat

> Hi all:
>
> I can use the density() function to get the kernel density for given
> observed data X with bandwidth.
>
> Is there a function in R that can take in two dimensional data(x, y) and
> return a joint density based
> on the bandwidth. Do I need to provide bandwith for x and then for y?
>
> Is the GRASS package
> kde2d.G(x, y, h, G, reverse=reverse(G))
>
> provide such function?
>
> Thanks
> pat
>
> ______________________________________________
> R-help at stat.math.ethz.ch 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.
>

On Tue, 5 Jun 2007, Patrick Wang wrote:
> Hi, I found kde2d in the MASS packages return densities for the bivariate
> random varaibles.
> 
> I donot understand why each element of density Z is a 2*2 matrix.
> Why it is not a number.
> 
> For example, a bivariate normula distribution given (x, y) will return a
> number, the density, not a matrix.
I think you were asking these questions last week: 

library(mvtnorm) 
?dmvnorm

not 2D kernel *density* (the word is perhaps overloaded).

However, kde2d() *is* a 2D density(), so maybe you need to consider what 
you are looking for.
> 
> Thanks
> Pat
> 
> 
> > Hi all:
> >
> > I can use the density() function to get the kernel density for given
> > observed data X with bandwidth.
> >
> > Is there a function in R that can take in two dimensional data(x, y)
and
> > return a joint density based
> > on the bandwidth. Do I need to provide bandwith for x and then for y?
> >
> > Is the GRASS package
> > kde2d.G(x, y, h, G, reverse=reverse(G))
> >
> > provide such function?
> >
> > Thanks
> > pat
> >
> > ______________________________________________
> > R-help at stat.math.ethz.ch 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.
> >
> 
> ______________________________________________
> R-help at stat.math.ethz.ch 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.
> 
-- 
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: Roger.Bivand at nhh.no