The Bland-Altman Method Should Not Be Used in Regression Cross-Validation Studies

The purpose of this study was to demonstrate the bias in the Bland-Altman (BA) limits of agreement method when it is used to validate regression models. Data from 1,158 men were used to develop three regression equations to estimate maximum oxygen uptake (R-2 = .40, .61, and .82, respectively). The equations were evaluated in a cross-validation sample of 581 men. The BA means and differences were correlated (p < .001) in the cross-validation sample for each model (r = .55, .39, and .26, respectively), thus demonstrating bias. The BA method is inappropriate for validation of regression models. Validation of regression equations is properly conducted by plotting the residuals against the estimated values and examining the magnitude of the estimation error