Hola Claudio,
Without the code and concrete problem is very difficult to say
anything about your question.
Cheers,
Juan Pablo
2012/6/17 Claudio Tablada <address@hidden
<mailto:address@hidden>>
Hi,
I am trying to maximize a -log likelihood function of a
Birnbaum-Saunders distribution with two parameters using BFGS and
Monte Carlo. I have the samples generates using
gsl_ran_gaussian_ziggurat and later transforming for the
Birnbaum-Saunders distribution. The problem is that for some
values of the sample the algorithm converges and for other values
it results in NaN. Thanks in advanced.