Hi all,
is there any package in R capable of smooth approximation of CDF
basing on given sample?
(Thus, I am not speaking about ecdf)
In particular, I expect very much that the approximation should
subject to the property:
f(x0)<=f(x1) for x0<x1, where x0 and x1 belong to range of
the sample given.
Polynomial approximation could be OK for me as well.
P.S. whould you please to make Cc on me answering this mail?
kind regards,
Valery A.Khamenya
---------------------------------------------------------------------------
Bioinformatics Department
BioVisioN AG, Hannover
approximation of CDF
2 messages · Khamenia, Valery, Brian Ripley
Almost any method of fitting a density estimate would work on integrating (numerically) the result. In particular, look at package polspline, where p(old)logspline does the integration for you.
On Thu, 8 May 2003, Khamenia, Valery wrote:
is there any package in R capable of smooth approximation of CDF basing on given sample? (Thus, I am not speaking about ecdf)
I think it _is_ an ECDF you want to approximate, since you mention `sample' below.
In particular, I expect very much that the approximation should
subject to the property:
f(x0)<=f(x1) for x0<x1, where x0 and x1 belong to range of
the sample given.
Polynomial approximation could be OK for me as well.
Brian D. Ripley, ripley at stats.ox.ac.uk Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UK Fax: +44 1865 272595