NotesFAQContact Us
Collection
Advanced
Search Tips
Back to results
Peer reviewed Peer reviewed
Direct linkDirect link
ERIC Number: EJ967164
Record Type: Journal
Publication Date: 2011-Dec
Pages: 7
Abstractor: As Provided
ISBN: N/A
ISSN: ISSN-0270-1367
The Bland-Altman Method Should Not Be Used in Regression Cross-Validation Studies
O'Connor, Daniel P.; Mahar, Matthew T.; Laughlin, Mitzi S.; Jackson, Andrew S.
Research Quarterly for Exercise and Sport, v82 n4 p610-616 Dec 2011
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[superscript 2] = 0.40, 0.61, and 0.82, respectively). The equations were evaluated in a cross-validation sample of 581 men. The BA means and differences were correlated (p less than 0.001) in the cross-validation sample for each model (r = 0.55, 0.39, and 0.26, 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. (Contains 2 figures and 3 tables.)
American Alliance for Health, Physical Education, Recreation and Dance. 1900 Association Drive, Reston, VA 20191. Tel: 800-213-7193; Fax: 703-476-9527; e-mail: info@aahperd.org; Web site: http://www.aahperd.org
Publication Type: Journal Articles; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A