Re: Bug in empirical_pdf?

[Luke15153]

Hello Juan Pablo,

thanks for your reply.

The bug should be located in discrete_pdf, which is used by empirical_pdf. I
submitted a bug to the Octave bugtracker (
http://savannah.gnu.org/bugs/?39280 <http://savannah.gnu.org/bugs/?39280>  )

This workaround works for me:

pdf = histc(data, uniqe(data));
pdf = pdf/length(data);

histc just counts the occurances and thus has to be normalized (
/length(data)).

Regards,

Lutz



--
View this message in context: 
http://octave.1599824.n4.nabble.com/Bug-in-empirical-pdf-tp4654443p4654479.html
Sent from the Octave - General mailing list archive at Nabble.com.