Please enable JavaScript to view this site.

Standard linear regression assumes that you know the X values perfectly, and all the uncertainty is in Y. It minimizes the sum of squares of the vertical distance of the points from the line.

If both X and Y variables are subject to error, fit linear regression using a method known as Deming, or Model II, regression.

If your goal is to compare two analysis methods, consider using a Bland-Altman plot instead.

© 1995-2019 GraphPad Software, LLC. All rights reserved.