You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@commons.apache.org by bu...@apache.org on 2004/06/07 03:56:58 UTC

DO NOT REPLY [Bug 29419] - ChiSquareTest does not return

DO NOT REPLY TO THIS EMAIL, BUT PLEASE POST YOUR BUG 
RELATED COMMENTS THROUGH THE WEB INTERFACE AVAILABLE AT
<http://issues.apache.org/bugzilla/show_bug.cgi?id=29419>.
ANY REPLY MADE TO THIS MESSAGE WILL NOT BE COLLECTED AND 
INSERTED IN THE BUG DATABASE.

http://issues.apache.org/bugzilla/show_bug.cgi?id=29419

ChiSquareTest does not return





------- Additional Comments From brent@worden.org  2004-06-07 01:56 -------
The problem is in the Gamma special functions.  For large x values in 
comparison to a values, the regularizedGammaP function never converges to a 
finite sum because the series terms approach numerical infinity.

IIRC, the algorithm I chose is slow to converge for this particular parameter 
scenario (x >> a).  Long term, I will research a different approach for this 
case and get it integrated into regularizedGammaP.

Short term, I was going to add a infinite term check to short-circut the 
algorithm and either return infinity or throw an exception from 
regularizedGammaP.  Any input on which choice of inifinity handling is 
preferred?

---------------------------------------------------------------------
To unsubscribe, e-mail: commons-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: commons-dev-help@jakarta.apache.org