[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Octave-bug-tracker] [bug #65170] [octave forge] (statistics) Failing BI
From: |
Dmitri A. Sergatskov |
Subject: |
[Octave-bug-tracker] [bug #65170] [octave forge] (statistics) Failing BIST in fitcknn |
Date: |
Tue, 16 Jan 2024 18:02:12 -0500 (EST) |
Follow-up Comment #2, bug#65170 (group octave):
I think it is one of those "WTF Matlab?" bugs and Andreas wants to be
bug-for-bug compatible with matlab.
octave:32> c = cov(x)
c =
6.250000000000000e+00 6.750000000000000e+00 7.250000000000000e+00
6.750000000000000e+00 8.250000000000000e+00 9.750000000000000e+00
7.250000000000000e+00 9.750000000000000e+00 1.225000000000000e+01
octave:33> 4*c
ans =
25 27 29
27 33 39
29 39 49
and one can easily calculate with pen and paper (or perhaps with some symbolic
math software) that det(4*c) is exactly 0.
So "c" is NOT positive definite.
Dmitri.
--
_______________________________________________________
Reply to this item at:
<https://savannah.gnu.org/bugs/?65170>
_______________________________________________
Message sent via Savannah
https://savannah.gnu.org/