Message-ID: <Pine.SOL.4.44.0304250851320.19695-100000@robotron.gpcc.itd.umich.edu>
Date: 2003-04-25T12:55:49Z
From: Thomas W Blackwell
Subject: numericDeriv and ecdf
In-Reply-To: <D15343265276D31197BC00A024A6C110774008@EXS_BDC>
On only ten points, what did you expect ? Even with 1000
observations, estimating a density is difficult, and has
been the subject of a century of research. Kernel density
estimates are among the most successful. For your immediate
application, try plot(density(rnorm(10)), type="l"), etc.
- tom blackwell - u michigan medical school - ann arbor -
On Fri, 25 Apr 2003, Khamenia, Valery wrote:
> Hi All,
>
> following expression:
>
> x <- sort(rnorm(10)); e <- ecdf(x); d <- numericDeriv(e(x),"x");
>
> makes d far from approximation of one dimensional pdf.
>
> What's wrong then here?
>
> Kind regards.
> ---------------------------------------------------------------------------
> Valery A.Khamenya
> Bioinformatics Department
> BioVisioN AG, Hannover