[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Help-gsl] Re: Log-Logistic Distribution
From: |
John D Lamb |
Subject: |
[Help-gsl] Re: Log-Logistic Distribution |
Date: |
Thu, 17 Nov 2005 11:30:04 +0000 |
User-agent: |
Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.12) Gecko/20050921 |
Luis Cardenas wrote:
> Hi
>
> My name is Guillermo Cardenas and I'm a Phd candidate in the Polytechnic
> University of Valencia in Spain.
> I've been using GSL to fit data to some distributions provided by the
> library.
> The issue is that Log-Logistic distribution is not included in the
> library. I have found the Density and Cummulative Functions, but I
> require the function to generate Log-logistic numbers.
>
> Any help will be appreciated
I am guessing that you want a random variate generator that generates
log-logistic random variates. GSL provides a random variate generator
that generates logistic random variates. One method that should work
well is to generate a logistic random variate X and then the
log-logistic random variate is exp( X ). This is the method that GSL
uses to generate lognormal variates starting from normal (Gaussian)
variates.
You will need to know how to translate from log-logistic parameters to
logistic parameters.
If this is not enough you might look at the books of Devroye or Kleijnen
and van Groenendaal or Law and Kelton.
--
JDL