The group lasso is an extension of the lasso to do variable selection on (predefined) groups of variables in linear regression models. The estimates have the attractive property of being invariant under groupwise orthogonal reparameterizations. We extend the group lasso to logistic regression...

We propose a flexible generalized auto-regressive conditional heteroscedasticity type of model for the prediction of volatility in financial time series. The approach relies on the idea of using multivariate "B"-splines of lagged observations and volatilities. Estimation of such a "B"-spline...

We study the properties of an MA([infinity])-representation of an autoregressive approximation for a stationary, real-valued process. In doing so we give an extension of Wiener's theorem in the deterministic approximation setup. When dealing with data, we can use this new key result to obtain...

We apply the blockwise bootstrap for stationary observations, proposed by Künsch (1989), to empirical processes indexed by function classes which satisfy some bracketing conditions. We prove a bootstrap central limit theorem for empirical processes of stationary [beta]-mixing variables, which...

Ensemble methods aim at improving the predictive performance of a given statistical learning or model fitting technique. The general principleof ensemble methods is to construct a linear combinationof some model fitting methods, instead of using a single fit of the method.

Estimation of structure, such as in variable selection, graphical modelling or cluster analysis, is notoriously difficult, especially for high dimensional data. We introduce stability selection. It is based on subsampling in combination with (high dimensional) selection algorithms. As such, the...