Comparer des méthodes

	Régression linéaire multiple robuste	Régression quantile
Domaine	Statistique	Économétrie
Famille	Regression model	Regression model
Année d'origine	1964–1980s	1978
Auteur d'origine	Peter J. Huber (M-estimators, 1964); extended by Rousseeuw, Yohai, and Maronna	Koenker & Bassett
Type	Robust linear regression	Conditional quantile regression
Source fondatrice	Huber, P. J. (1964). Robust estimation of a location parameter. Annals of Mathematical Statistics, 35(1), 73–101.	Koenker, R. & Bassett, G., Jr. (1978). Regression Quantiles. Econometrica, 46(1), 33-50.
Alias	robust MLR, M-estimator regression, resistant multiple regression, robust OLS	conditional quantile regression, regression quantiles, Kantil Regresyon
Apparentées	6	5
Résumé	Robust multiple linear regression estimates the linear relationship between a continuous outcome and several predictors while being resistant to outliers and violations of the normality assumption. Instead of minimising the sum of squared residuals, it uses a bounded loss function — most commonly Huber's or Tukey's bisquare — so that extreme observations receive limited influence on the estimated coefficients.	Quantile regression models conditional quantiles of an outcome - the median, the 25th or 75th percentile, and so on - rather than the conditional mean that OLS targets. Introduced by Koenker and Bassett in 1978, it reveals how predictors act across the whole distribution, including its tails.