Follow

I notice that the R-squared statistical value is different in Excel than in Grapher with a fit curve that goes through the origin. Why?

According to a variety of statistical sources, R-squared (coefficient of determination) cannot be calculated in the same manner when a through origin fit is selected.

  • Excel uses the same equation regardless of whether the fit curve is forced through the origin. This results in a different R-squared value in Excel. This value can occasionally be negative, so using the same equation is not a good idea when forcing a curve through the origin.

  • Grapher uses an equation specifically designed for a through origin fit that takes into account the issues of how the line is centered.

Refer to the Fit Statistics Grapher help page for the R-squared equation used in both cases (through-origin and not through-origin).

 

Updated January 12, 2018

Was this article helpful?
0 out of 0 found this helpful
Have more questions? Submit a request

0 Comments

Please sign in to leave a comment.