[Libreoffice-bugs] [Bug 127517] New: Libreoffice Calc Trendline R^2 value calculation goes wrong when trendline is forced through 0

[bugzilla-daemon at bugs.documentfoundation.org]

https://bugs.documentfoundation.org/show_bug.cgi?id=127517

            Bug ID: 127517
           Summary: Libreoffice Calc Trendline R^2 value calculation goes
                    wrong when trendline is forced through 0
           Product: LibreOffice
           Version: 6.3.1.2 release
          Hardware: All
                OS: Linux (All)
            Status: UNCONFIRMED
          Severity: normal
          Priority: medium
         Component: Calc
          Assignee: libreoffice-bugs at lists.freedesktop.org
          Reporter: mohr.christoph at gmail.com

Description:
When plotting a scatter plot and forcing a trendline through zero, the R^2
value is wrong.
I created a screenshot as an example:
In Libreoffice Calc you get those lines and values:
https://i.imgur.com/9ZMpKrV.png
The R^2 value of the forced trendline is 0.95 and a lot better than the R^2
value of the unforced line (0.779) 
I plotted the same thing in Microsoft excel:https://i.imgur.com/tdYMbQL.png
As you can see the equations are the same, the R^2 value for the unforced line
too, but excel calculates R^2 with the forced trendline correctly 

Steps to Reproduce:
1. Create Scatter Plot
2. Fit a trendline and force it through zero
3. Compare to eg Microsoft excel results
4. See that Libreoffice calc has the wrong value

Actual Results:
Results: R^2 is wrong

Expected Results:
Expected: Correct R^2 value


Reproducible: Always


User Profile Reset: Yes



Additional Info:

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/libreoffice-bugs/attachments/20190912/11238247/attachment.html>