MathGroup Archive 2009

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

Search the Archive

Re: random variable

  • To: mathgroup at
  • Subject: [mg102847] Re: random variable
  • From: Bill Rowe <readnews at>
  • Date: Sat, 29 Aug 2009 06:32:27 -0400 (EDT)

On 8/28/09 at 5:43 AM, bdairmb at (omar bdair) wrote:

>I want to ask, how can I generate a random vaiable from some
>probability density functions which are not well-known? I mean, if
>we have some pdf which is not normal, binomial, weibull, ... but the
>only thing I know that it is a log-concave function, then how can I
>generate a number of random variables?

Simply put, without more detail than "log-concave function" it
isn't possible to do what you want.

There are a variety of methods for generating pseudo-random
numbers from arbitrary distribution functions. Knuth in
Seminumerical Algorithms Vol 2 describes the standard
approaches. Any of these can be implemented in Mathematica.

There is also a third party package available for Mathematica,
Mathstatica available to do this and much more. I've been quite
satisfied with version 1.2 in the past. However, I've just
noticed versoin 2.0 is finally available for usage with ver 7 of
Mathematica. I've not yet used this version. I assume it has
more capability to do things like this than version 1.2.

You can get more information about Mathstatica on their web site


  • Prev by Date: Re: ClearAll ?? or what
  • Next by Date: Re: Eigenvalues broken?
  • Previous by thread: Re: random variable
  • Next by thread: Re: random variable