Is chisquare_inv broken?

[Joe Koski]

I'm trying to calculate the probability that the probability density
function of fire temperatures generated with computational fluid dynamics is
consistent with some experimentally determined pdfs of fire temperatures.

All goes well while constructing the chisquare distribution value and the
number of degrees-of-freedom, until I attempt to find the probability of
occurrence related to the chisquare value and the degrees-of-freedom. At
that point, the octave-forge routine chisquare_inv consistently gives me a
NaN instead of an answer.

For example, for chisquare = 10, and 10 degrees-of-freedom, I should get a
probability value somewhat less than 0.5. With chisquare_inv, I get

octave:5> prob = chisquare_inv(10,10)
prob = NaN

I'm doing this with octave-2.1.64 and octave-forge-2004.11.16 on my Mac
running OS X 10.3.7.

Is chisquare_inv broken, or am I doing something wrong?

Joe




 




-------------------------------------------------------------
Octave is freely available under the terms of the GNU GPL.

Octave's home on the web:  http://www.octave.org
How to fund new projects:  http://www.octave.org/funding.html
Subscription information:  http://www.octave.org/archive.html
-------------------------------------------------------------