Bootstrap Inference in Econometrics

By James G. MacKinnon. 2002

326 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/b11c65e36313bebcca2fb9d095520d0991067956

How researchers see this paper

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

In Economics and Econometrics

In Finance

In Statistics and Probability

Citations in the corpus

Climbing atop the Shoulders of Giants: The Impact of Institutions on Cumulative Research (2011, unknown): “We can easily reject 19 All models include block bootstrapped standard errors, clustered either by article pairs or article dummies, depending on the set of fixed effects included in the specification (Marianne Bertrand, Esther Duflo, and Sendhil Mullainathan 2004; James G. MacKinnon 2002).”
Thirty Years of Heteroskedasticity-Robust Inference (2013, methodology): “There is a great deal of evidence that the wild bootstrap outperforms the pairs bootstrap in these contexts; see Horowitz (2001), MacKinnon (2002), Flachaire (2005), and Davidson and Flachaire (2008), among others .”
Rational bubbles or persistent deviations from market fundamentals (2005, unknown): “…the estimators is different in the case of monthly data as evidenced in Table 6; NLS is the least biased estimator of bd, followed by EML and MPL. MacKinnon (2002) argues that, in many cases, using simulated distributions to perform tests and construct confidence intervals yields inferences that…”
Of Mice and Academics: Examining the Effect of Openness on Innovation (2009, background): “As well, all of the models report block bootstrapped standard errors clustered by mouse-article (MacKinnon, 2002).”
The Continuing Puzzle of Short Horizon Exchange Rate Forecasting (2008, background): “…on time series bootstrapping and the increase of computational power have made the bootstrap an increasingly attractive alternative to asymptotic inference (see Berkowitz and Kilian,1996, Kilian, 1999, Mark and Sul, 2001, MacKinnon, 2002, Brownstone and Valletta, 2001, and Politis and White, 2004).”
Bootstrap Methods in Econometrics (2006, unknown): “However, as we will see in the next subsection, percentile t intervals do not always perform well in practice (MacKinnon, 2002).”
Investor Sentiment, Limits to Arbitrage and Private Market Returns (2014, background): “Thus, each residual is multiplied by (n/n − v)1/2, where n is the number of observations and v refers to the degrees of freedom of the VAR (MacKinnon 2002).”
Bootstrap Hypothesis Testing (2007, methodology): “Racine and MacKinnon (2007b) proposes a very simple method for performing Monte Carlo tests that does not require α(B + 1) to be an integer.”
Bootstrap-Based Improvements for Inference with Clustered Errors (2008, unknown): “This correction generalizes the HC3 measure (jackknife) of MacKinnon and White (1985), and so we refer to this correction as the CR3 variance estimator.”
Specification Curve: Descriptive and Inferential Statistics on All Reasonable Specifications (2015, unknown): “Bootstrapping for hypothesis testing purposes involves modifying the dataset so that the null is true, and then computing the test statistic on random samples from that modified dataset (Bickel & Ren, 2001; Boos, 2003; MacKinnon, 2002; Paparoditis & Politis, 2005).”
Asymptotic theory and wild bootstrap inference with clustered errors (2019, methodology): “MacKinnon (2016) provides simulation evidence which illustrates this point.”