[prev in list] [next in list] [prev in thread] [next in thread]
List: gnuplot-info
Subject: Re: [Gnuplot-info] Integration of kdensity plots
From: Ethan Merritt <eamerritt () gmail ! com>
Date: 2015-01-30 19:51:28
Message-ID: CAGRdh4vHY=7ckviN0RrFeYKw1j=Oib4+0VH1wPwV4gdgvy0+rg () mail ! gmail ! com
[Download RAW message or body]
On Fri, Jan 30, 2015 at 8:10 AM, <lynx.abraxas@freenet.de> wrote:
>
> It seems approximate integration is possible with gnuplot, as in eg
> bivariat.dem. I'd like to use tha to get integrations of a kdensity plot that
> is based on measurements.
> Fort that, is it possible to get the function that is behind a kdensity plot
> or would I have to construct it by hand for the given data? Or is it possible
> to directly get the integral value of a specified interval?
The kdensity plot produced by gnuplot is a sum of Gaussians.
I.e. it is a plot of the first equation given on the Wikipedia page
for "kernel density estimation" where K(x) = φ(x) = normal density
function.
It sounds like the quantity you want is a trivial variant of that
which substitutes the cumulative normal distribution function norm(x)
for φ(x). It is probably easier to calculate the sum directly from
the data than it is to program an approximate integration based on an
intermediate plot.
Ethan
------------------------------------------------------------------------------
Dive into the World of Parallel Programming. The Go Parallel Website,
sponsored by Intel and developed in partnership with Slashdot Media, is your
hub for all things parallel software development, from weekly thought
leadership blogs to news, videos, case studies, tutorials and more. Take a
look and join the conversation now. http://goparallel.sourceforge.net/
_______________________________________________
gnuplot-info mailing list
gnuplot-info@lists.sourceforge.net
Membership management via: https://lists.sourceforge.net/lists/listinfo/gnuplot-info
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic