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

MathGroup Archive 2011

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

Search the Archive

Maximum likelihood estimatior

  • To: mathgroup at smc.vnet.net
  • Subject: [mg121249] Maximum likelihood estimatior
  • From: "jeanni laus" <jeanni.laus at gmx.de>
  • Date: Tue, 6 Sep 2011 03:56:39 -0400 (EDT)
  • Delivered-to: l-mathgroup@mail-archive0.wolfram.com

Hi
I have some trouble calculating the maximum likelihood estimators for some distribution functions e.g. Gumbel, Log-Normal Distribution.
I tried to use the SMLE package. Everything worked fine for the examples given in the Symbolic maximum likelihood estimation with Mathematica paper. But for my distribution functions I can't calculate the estimators.

SuperLog[On]
func=PDF[GumbelDistribution[\[Alpha], \[Beta]], Subscript[x, i]]
L= \!\(\*UnderoverscriptBox[\(\[Product]\), \(i = 1\), \(n\)]func\)
LogL=Log[L]
scorea = \!\(\*SubscriptBox[\(\[PartialD]\), \(\[Alpha]\)]LogL\)
scoreb = \!\(\*SubscriptBox[\(\[PartialD]\), \(\[Beta]\)]LogL\)
Assuming[\[Beta] > 0, Solve[scorea == 0, \[Alpha]]]
Assuming[\[Beta] > 0, Solve[scoreb == 0, \[Beta]]]

Can someone help, please?
Jeanni 

-- 
NEU: FreePhone - 0ct/min Handyspartarif mit Geld-zurück-Garantie!		
Jetzt informieren: http://www.gmx.net/de/go/freephone




  • Prev by Date: Re: Quit versus Clear["Global`*"]
  • Next by Date: Re: Print bug with -script? (quotes display)
  • Previous by thread: Re: Problem loading 3d models
  • Next by thread: Re: Running notebook from command line