Linear regression analysis for comparing two measurers or methods of measurement: But which regression?
Tóm tắt
1. There are two reasons for wanting to compare measurers or methods of measurement. One is to calibrate one method or measurer against another; the other is to detect bias. Fixed bias is present when one method gives higher (or lower) values across the whole range of measurement. Proportional bias is present when one method gives values that diverge progressively from those of the other.
2. Linear regression analysis is a popular method for comparing methods of measurement, but the familiar ordinary least squares (OLS) method is rarely acceptable. The OLS method requires that the
3. Clinical chemists favour techniques such as major axis regression (‘Deming’s method’), the Passing–Bablok method or the bivariate least median squares method. Other disciplines, such as allometry, astronomy, biology, econometrics, fisheries research, genetics, geology, physics and sports science, have their own preferences.
4. Many Monte Carlo simulations have been performed to try to decide which technique is best, but the results are almost uninterpretable.
5. I suggest that pharmacologists and physiologists should use ordinary least products regression analysis (geometric mean regression, reduced major axis regression): it is versatile, can be used for calibration or to detect bias and can be executed by hand‐held calculator or by using the loss function in popular, general‐purpose, statistical software.
Từ khóa
Tài liệu tham khảo
Brace RA, 1977, Fitting straight lines to experimental data, Am. J. Physiol., 233, R94
Feldmann U, 1981, A multivariate approach for the biometric comparison of analytical methods in clinical chemistry, J. Clin. Chem. Clin. Biochem., 19, 121
Sokal RR, 1995, Biometry
Hopkins WG, 2004, Bias in Bland–Altman but not regression validity analysis, Sportscience, 8, 42
Deming WE, 1938, Statistical Adjustment of Data
Draper NR, 1992, Proceedings of the Conference on Applied Statistics in Agriculture, 1
Passing H, 1983, A new biometrical method for testing the equality of measurements from two different analytical methods. Part I, J. Clin. Chem. Clin. Biochem., 21, 709
Passing H, 1984, Comparison of several regression procedures for method comparison studies and determination of sample sizes. Part II, J. Clin. Chem. Clin. Biochem., 22, 431
Bablok W, 1988, A general regression procedure for method transformation. Part III, J. Clin. Chem. Clin. Biochem., 26, 783
Manly BFJ, 1997, Randomization, Bootstrap and Monte Carlo Methods in Biology
Frisch R, 1929, Correlation and scatter in statistical variables, Nord. Stat. J., 1, 36
Linnet K, 1993, Evaluation of regression procedures from methods comparison studies, Clin. Chem., 39, 424, 10.1093/clinchem/39.3.424
Rousseeuw PJ, 2003, Robust Regression and Outlier Detection
Altman DG, 2000, Statistics with Confidence, 73
BlandJM.How do I estimate limits of agreement when the mean and SD of differences is not constant?2006. Available from:http://www.users.york.ac.uk/~mb55/meas/glucose.htm(accessed 18 March 2010).