The power of bootstrap and asymptotic tests

By Russell Davidson, James G. MacKinnon. 2006

136 citations recorded by the source corpus.

Subfields: Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/b42691d795128a0b9c29829ca06f2faabec82000

How researchers see this paper

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

In Finance

In Statistics and Probability

Citations in the corpus

Bootstrap inference in a linear equation estimated by instrumental variables (2008, methodology): “For any bootstrapping procedure, the first task, and usually the most important one, is to choose a suitable bootstrap DGP; see Davidson and MacKinnon (2006a).”
Thirty Years of Heteroskedasticity-Robust Inference (2013, background): “Ideally, one would like to adjust both tests to have precisely the correct size, but this is very difficult to do in a way that is unambiguously correct; see Davidson and MacKinnon (2006).”
Bootstrap Methods in Econometrics (2006, unknown): “Other references on Monte Carlo tests include Dwass (1957), in which they were first proposed, Jöckel (1986) and Davidson and MacKinnon (2000), both of which discuss power loss, Dufour and Khalaf (2001), which is a valuable survey, and Dufour, Khalaf, Bernard, and Genest (2004), which discusses Mont”
Bootstrap Hypothesis Testing (2007, methodology): “Comparing the power of tests that do not have the correct size is fraught with difficulty; see Davidson and MacKinnon (2006a).”
Testing for Stochastic Dominance Efficiency (2010, methodology): “Besides, a Monte Carlo investigation of the finite sample properties of subsampling based tests is too time consuming in our context (see Section 5 on how we solve that problem in a bootstrap setting based on a suggestion of Davidson and MacKinnon 2006, 2007).”
Testing for Granger Causality in Large Mixed-Frequency VARs (2016, unknown): “Indeed, as shown by Davidson and MacKinnon (2006), the power of a bootstrap test can only equal the size-corrected power of the original test; as the parameter proliferation causes the original Wald test to be grossly oversized, the amount of size-correcting needed implies the remaining power to be ”
Bootstrap LR tests of stationarity, common trends and cointegration (2012, unknown): “Bootstrap resampling methods are becoming part of the standard toolkit of applied econometricians and practitioners in all contexts of parameter estimation, testing and forecasting (see 7–11 for comprehensive surveys with emphasis on econometrics).”