parameters with the Lasso and the adaptive Lasso. The parsimonious random walk allows the parameters to be modelled non … randomly. We characterize the finite sample properties of the Lasso by deriving upper bounds on the estimation and prediction … probability tending to one. We also provide conditions under which the adaptive Lasso is able to achieve perfectmodel selection …

autoregressive models. We propose using Lasso-type estimators to reduce the dimensionality to a manageable one and provide strong …