[Octave-bug-tracker] [bug #58651] [octave-forge](statistics) logistic_regression: what is actually done with >2 categories?

[Muhali]

URL:
  <https://savannah.gnu.org/bugs/?58651>

                 Summary: [octave-forge](statistics) logistic_regression: what
is actually done with >2 categories?
                 Project: GNU Octave
            Submitted by: muhali
            Submitted on: Wed 24 Jun 2020 06:02:45 AM PDT
                Category: None
                Severity: 3 - Normal
                Priority: 5 - Normal
              Item Group: None
                  Status: None
             Assigned to: None
         Originator Name: 
        Originator Email: 
             Open/Closed: Open
                 Release: 5.2.0
         Discussion Lock: Any
        Operating System: GNU/Linux

    _______________________________________________________

Details:

according to the help text, the logistic_regression function fits the model

logit (gamma_i (x)) = theta_i - beta' * x,   i = 1 ... k-1

that is, a unique beta across all categories. This is in contrast to the
multinomial regressions that I know of, such as the Matlab function mnrfit, or
as described here
<https://en.wikipedia.org/wiki/Multinomial_logistic_regression>.

I think this needs to be clarified or corrected.




    _______________________________________________________

Reply to this item at:

  <https://savannah.gnu.org/bugs/?58651>

_______________________________________________
  Message sent via Savannah
  https://savannah.gnu.org/