commons-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From F Norin <>
Subject Re: [math] Questions regarding probability distributions
Date Thu, 14 Oct 2004 18:37:34 GMT

Yes you're right, with the parametrization model you're using it would 
probably be confusing to simply let the exponential and chisquared 
distributions be instances of a gammadistribution. However, this indicates 
that there may be something flawed here. Remember, the chisquared 
distribution *is a* gammadistribution, and this should be reflected in the 
inheritance structure. Basically, you need some means to express 
relationships between probability distributions.

> I agree with all points below.  It occured to me later this AM that
> exposing the right parameters meant that the implementations needed to be
> separate.  I now agree with you and Mark that this would be too tricky to
> implement correctly while presenting the right interface to the user.
> What is you opinion on the DiscreteDistribution int vs. double issue?
> Phil
> -----Original Message-----
> From: Brent Worden []
> Sent: Wed 10/13/2004 2:08 PM
> To: Jakarta Commons Developers List
> Cc:
> Subject: Re: [math] Questions regarding probability distributions
>  Here's my basis for the exponential, chi-squared, and gamma distribution
> design (forgive me for reiterating some points made by others):
>  Exponential is separate because both the CDF and inverse CDF have closed
> form computations.  This provides better performance and higher accuracy
> than the iterative method approximation.
>  Both exponential and chi-squared are separate from gamma to provide access
> only to the parameters specific to each distribution.
>  In chi-squared case, extension could have easily been use but this would
> have exposed the alpha and beta properties in chi-squared.  This would
> allow users to modify the properties in an uncontrolled fashion, possibly
> resulting in a disfunctional distribution.  Thus, encapsulation was used to
> hide the gamma properties and only expose the relavent chi-squared
> properties.
> 	---------------------------------------------------------------------
> 	To unsubscribe, e-mail:
> 	For additional commands, e-mail:

To unsubscribe, e-mail:
For additional commands, e-mail:

View raw message