Data-driven calibration of linear estimators with minimal penalties

, 430 where price is the price paid in auction (in million $ ), area is the area of the painting (height times width, both measured in inches), ratio is the aspect ratio (height

Keywords: linear regression, Bayesian inference, generalized least-squares, ridge regression, LASSO, model selection criterion,

Indeed, it generalizes the results of Birg´e and Massart (2007) on the existence of minimal penalties to heteroscedastic regression with a random design, even if we have to restrict

In the general statistical experiment model we propose a procedure for selecting an estimator from a given family of linear estimators.. We derive an upper bound on the risk of

This paper tackles the problem of selecting among several linear estimators in non-parametric regression; this includes model selection for linear regression, the choice of

The purpose of this paper is twofold: stating a more general heuristics for designing a data- driven penalty (the slope heuristics) and proving that it works for penalized

The objective of this lecture is to realize some linear regressions and the associated confidence intervals and tests1. 1

The existence of the best linear unbiased estimators (BLUE) for parametric es- timable functions in linear models is treated in a coordinate-free approach, and some relations