Comparer des méthodes

	Régression par Moindres Médianes des Carrés (LMS)	Régression par Moindres Carrés Ordinaires (MCO)
Domaine	Statistique	Économétrie
Famille	Regression model	Regression model
Année d'origine	1984	2019
Auteur d'origine	Peter J. Rousseeuw	Wooldridge (textbook treatment); classical least squares
Type	Robust linear regression	Linear regression
Source fondatrice	Rousseeuw, P. J. (1984). Least Median of Squares Regression. Journal of the American Statistical Association, 79(388), 871-880.	Wooldridge, J. M. (2019). Introductory Econometrics: A Modern Approach (7th ed.). Cengage Learning. ISBN: 978-1337558860
Alias	LMS, least median of squares regression, en küçük medyan kareler (LMS)	ordinary least squares, classical linear regression, linear regression, en küçük kareler regresyonu
Apparentées	5	5
Résumé	Least Median of Squares is a robust linear regression method introduced by Peter J. Rousseeuw in 1984. Instead of minimising the sum of squared residuals like ordinary least squares, it minimises the median of the squared residuals, which lets the fit resist contamination by up to roughly 50% outliers.	Ordinary Least Squares is the classical linear regression method that explains a continuous outcome as a linear combination of predictors. It estimates the coefficients by minimising the sum of squared residuals, and under the Gauss-Markov assumptions these estimates are the best linear unbiased estimator (BLUE).