Ferrero formula and triangle misclosures revisited
Finding an ε-optimal regression subset
Fitting a linear regression model by combining least squares and least absolute value estimation.
Robust estimation of the multiple regression is modeled by using a convex combination of Least Squares and Least Absolute Value criterions. A Bicriterion Parametric algorithm is developed for computing the corresponding estimates. The proposed procedure should be specially useful when outliers are expected. Its behavior is analyzed using some examples.
Fixed precision estimation of the parameters of a linear regression model with unknown covariance structure
From equivalent linear equations to Gauss-Markov theorem.