I was thinking of a more focused search including the terms contour
and either r-help or r-project, but not one restricted to
GoogleGroups, ,,, more along the lines of:
http://www.google.com/search?hl=en&rlz=1B3GGGL_enUS278US278&q=r-help+quantile+contour&start=20&sa=N
or...
http://www.google.com/search?hl=en&rlz=1B3GGGL_enUS278US278&q=r-project+quantile+contour&btnG=Search
One does not always get the same result. This morning when I tested
that strategy, I got these hits:
http://addictedtor.free.fr/graphiques/RGraphGallery.php?graph=104
and also found:
http://addictedtor.free.fr/graphiques/RGraphGallery.php?graph=112
Both of which seemed of use for such a purpose.
--
David Winsemius
On Feb 15, 2009, at 9:48 PM, yuankun shi wrote:
> There is misunderstanding between us.
> I have search the groups with key words quantile and found this
> article
>
http://groups.google.com/group/r-help-archive/browse_thread/thread/9f0d6e72702de11c/e2eb078d0c6f1e5f?hl=en&lnk=gst&q=quantile#e2eb078d0c6f1e5f
> It talked about to use quantile to generate a contour with desired
> proportion, but this probortion stand for how much percent of max
> value of population.
> While my problem is how to get the proportion of particles lies in
> this cycle generated by contour not the proportion of z axis
>
> 2009/2/15 David Winsemius <dwinsemius@comcast.net>
>
> On Feb 15, 2009, at 7:55 AM, yk wrote:
>
> I have searched this forum with keywords contour and percent, it only
> give one irrelevent result.
> My problems is how to plot contour in percent.
> In my figure, I have use kde2d to generate density of an array with
> two dimension point.
> Using image and contour could plot it.
> But the line contour generated represent absolute value of population,
> not how much pecent point within this cycle.
> So, i there any function which could accomplish it?To generate a cycle
> which could tell me how much percent of points lies in this cycle.
> Thank you for your attention
>
> One way to approach it would be to
> -create a function that returns the density for each x and y
> -assign a density score to each case
> -determine the quantiles
> -draw the pseudo-3d or contour plot with colors or levels at the
> desired proportion.
>
> I think I have seen worked examples of this process, so it may be
> that searching on "quantile" instead of "percent" would
be more
> successful.
>
> --
> David Winsemius
>
[[alternative HTML version deleted]]