Orthogonal Regressionoverview how to example data see also
Orthogonal RegressionStat > Regression > Orthogonal Regression
Use orthogonal regression (Deming regression) to test whether two instruments or methods provide comparable measurements. This analysis is commonly used to test the equivalence of instruments used in clinical chemistry or measurements made by two different laboratories. Use orthogonal regression instead of ordinary least squares regression when both the response and predictor contain measurement error.
To determine if two methods are equivalent, the confidence interval for the slope should contain 1 and the confidence interval for the intercept should contain 0.
The hypotheses for the slope are:
H0: b1 = 0 versus H1: b1 ≠ 0
The hypotheses for the intercept are:
H0: b0 = 0 versus H1: b0 ≠ 0
For more information on orthogonal regression, see [15] and [28].
Response (X): Select the column containing Y, or response variable.
Predictor (Y): Select the column containing X, or predictor variable.
Error variance ratio (Y/X): Enter the ratio of the measurement error variances in Y and X. One way to obtain estimates of the error variances is to perform separate Gage R&R studies for X and Y.