https://bugs.freedesktop.org/show_bug.cgi?id=87790

            Bug ID: 87790
           Summary: Unexpected values in evaluating R2 using regr.lin
                    (linear fit)
           Product: LibreOffice
           Version: unspecified
          Hardware: x86-64 (AMD64)
                OS: Linux (All)
            Status: UNCONFIRMED
          Severity: minor
          Priority: medium
         Component: Spreadsheet
          Assignee: libreoffice-bugs@lists.freedesktop.org
          Reporter: f.mencarag...@gmail.com

When fitting a series of (x,y) data with a function a * x + b, everything
(slope, intercept, correlation) seems ok   (check done by comparison with excel
and by evaluaton using the standatd formulas in any book). Changing axis so
that the first (x,y) is in the origin and fitting with  a * x' the slope is ok,
but the correlation is wrong, It is neither the Pearson correlation nor the
explained variance vs the total variance.  The result is in disagreement with
what found in excel or by evlautaion with standard formula

I do not understand if there is a bug in the function or if the meaning of r2
is nn clearly eplaine in the on line manual

-- 
You are receiving this mail because:
You are the assignee for the bug.
_______________________________________________
Libreoffice-bugs mailing list
Libreoffice-bugs@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/libreoffice-bugs

Reply via email to