[Octave-bug-tracker] [bug #47369] [octave forge] (statistics) gevfit malfunctioning (because of fminunc failure)

[Nicholas Jankowski]

Update of bug #47369 (project octave):

                  Status:                    None => Need Info              

    _______________________________________________________

Follow-up Comment #7:

looking at the status of this report:

with octave 7.2, statistics 1.4.3, 
that the comment #0 supplied tests in both matlab and octave produce:


x =
[549,664,382,540,856,1190,432,542,383,251,967,876,1190,302,740,981,620,423,753,801,1100,457,763,572,526,430,459,597,1310,612,896]';

[PARAMHAT, PARAMCI] = gevfit (x)

Octave:
PARAMHAT =
  -6.9804e-03   2.1645e+02   5.5777e+02

PARAMCI =
    -0.3402   151.3145   467.3575
     0.3262   281.5900   648.1833

Matlab 2022a:

PARAMHAT =
   -0.0092  219.5077  556.1071
PARAMCI =
   -0.3542  160.9012  465.2270
    0.3359  299.4610  646.9872


testing the Octave function example in the gevfit help:


data = 1:50;
[pfit, pci] = gevfit (data)

Octave:
pfit =
   -0.4407   15.1923   21.5309

pci =
   -0.7532   11.0777   16.5688
   -0.1282   19.3070   26.4930


Matlab 2022a:
pfit =
   -0.4407   15.1924   21.5306
pci =
   -0.7532   11.5878   16.5686
   -0.1282   19.9183   26.4926



there is discrepancy between octave and matlab in both examples, although in
the second example it is much less. 

is this a gevfit issue or a fminunc issue? algorithm or convergence detection?
perhaps someone more familiar with the underlying deficiency can improve the
title/summary?  


    _______________________________________________________

Reply to this item at:

  <https://savannah.gnu.org/bugs/?47369>

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