Implementing the wild bootstrap using a two-point distribution☆

By James Davidson, A. Monticini, David Peel. 2007

53 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

VARIANCE-RATIO TESTS OF RANDOM WALK: AN OVERVIEW (2009, unknown): “Note that there are other possible choices of two-point distributions for the wild bootstrap, which potentially outperform the standard normal distribution when the sample size is small (Davidson et al., 2007).”
Robust Spectral Analysis (2011, background): “…other than the Rademacher distribution can be used for η, in particular if V̂t(τ)V̂t−j(τ) has a skewed distribution, but there is no evidence that they would lead to better inference; see Davidson, Monticini, and Peel (2007) for a discussion of this point for the standard wild bootstrap.”
Modelling volatility by variance decomposition (2013, methodology): “This drawback could in principle be remedied by a wild bootstrap, but our experiments with two-point distributions along the lines in Davidson, Monticini, and Peel (2007) did not bring satisfactory results.”
Fast and wild: Bootstrap inference in Stata using boottest (2018, methodology): “Simulation studies suggest that wild bootstrap tests based on the Rademacher distribution perform better than ones based on other auxiliary distributions; see Davidson, Monticini, and Peel (2007), Davidson and Flachaire (2008), and Finlay and Magnusson (2016), among others.”