We consider the problem of selecting the auxiliary distribution to implement the wild bootstrap for regressions featuring heteroscedasticity of unknown form. Asymptotic refinements are nominally obtained by choosing a distribution with second and third moments equal to 1. We show that this stipulation may fail in practice, due to the distortion imposed on higher moments. We propose a new class of two-point distributions and suggest using the Kolmogorov-Smirnov statistic as a selection criterion. The results are illustrated by a Monte Carlo experiment.
Monticini, A., Davidson, J., Peel, D., Implementing the wild bootstrap using a two point distribution, <<ECONOMICS LETTERS>>, 2007; 2007/Volume 96, Issue 3 (Settembre): 309-315. [doi:10.1016/j.econlet.2007.01.020] [http://hdl.handle.net/10807/1871]
Implementing the wild bootstrap using a two point distribution
Monticini, Andrea;
2007
Abstract
We consider the problem of selecting the auxiliary distribution to implement the wild bootstrap for regressions featuring heteroscedasticity of unknown form. Asymptotic refinements are nominally obtained by choosing a distribution with second and third moments equal to 1. We show that this stipulation may fail in practice, due to the distortion imposed on higher moments. We propose a new class of two-point distributions and suggest using the Kolmogorov-Smirnov statistic as a selection criterion. The results are illustrated by a Monte Carlo experiment.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
