Services & Resources / Wolfram Forums / MathGroup Archive
-----

MathGroup Archive 2008

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: Re: distribution fitting

  • To: mathgroup at smc.vnet.net
  • Subject: [mg90455] Re: [mg90428] Re: distribution fitting
  • From: mante <claude.mante at univmed.fr>
  • Date: Thu, 10 Jul 2008 06:33:08 -0400 (EDT)
  • References: <g4q9qf$ebq$1@smc.vnet.net> <200807090853.EAA07005@smc.vnet.net>

dennis wrote:
> On occasion I have had data that I need the distribution for but
> clearly does not correspond to any standard distribution.  What I have
> done if use Histogram to estimate the density function and extract a
> list from the histogram that can be used with Interpolation to
> defining a workable density function.
>
> Dennis
>
>   
You should better download the Gress density estimatin package:

http://library.wolfram.com/infocenter/Conferences/5361/

Thre is also somewhere an Histospline package, if you data are grouped.

        Claude



  • Prev by Date: Almost symbolic computations (?)
  • Next by Date: Re: How to show tick labels w/o showi the tick marks?
  • Previous by thread: Re: distribution fitting
  • Next by thread: Re: distribution fitting