Empirically relevant critical values for hypothesis tests: A bootstrap approach

By Joel L. Horowitz, Nathan Eugene Savin, Art Goldberger, Beth F. Ingram, Tom Rothenberg, Paul. 2000

99 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/c8af92fc1167a7c961508a5112e96b541099ac1d

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

1. James G. MacKinnon
2. Russell Davidson
3. Martin Wagner
4. Marcelo Fernandes
5. Christoph Hanck
6. P. R. Hansen
7. Matei Demetrescu
8. Jaroslava Hlouskova

In Finance

1. James G. MacKinnon
2. Russell Davidson
3. Marcelo Fernandes
4. Christoph Hanck
5. Jaroslava Hlouskova
6. Joel L. Horowitz
7. P. R. Hansen
8. Martin Wagner

In Statistics and Probability

1. James G. MacKinnon
2. Russell Davidson
3. P. R. Hansen
4. Marcelo Fernandes
5. Jaroslava Hlouskova
6. Joel L. Horowitz
7. Christoph Hanck
8. Martin Wagner

Citations in the corpus

• A Conditional Likelihood Ratio Test for Structural Models (2003, background): “5 Rothenberg (1984) and Horowitz and Savin (2000) discuss the problem of size distortions due to”
• A Test for Superior Predictive Ability (2005, background): “(See Horowitz and Savin 2000 for a criticism of reporting “size”-adjusted powers.)”
• Bootstrap inference in a linear equation estimated by instrumental variables (2008, background): “In Horowitz and Savin (2000), it is pointed out that, unless one is working with pivotal statistics, it is not in general possible to define an empirically relevant definition of the power of a test that does not have true level equal to its nominal level.”
• The Performance of Panel Cointegration Methods: Results from a Large Scale Simulation Study (2009, background): “This is not the size as defined by the maximal type I error rate over all feasible DGPs under the null hypothesis, see Horowitz and Savin (2000) for an excellent discussion of this issue.”
• The Performance of Panel Unit Root and Stationarity Tests: Results from a Large Scale Simulation Study (2006, background): “This follows from the fact, discussed in detail in Horowitz and Savin (2000), that size correction based on arbitrary points in the set of feasible DGPs under the null hypothesis in general leads to empirically irrelevant critical values.19 The problem arises because the actual type I errors (of…”
• Nonparametric specification tests for conditional duration models (2005, background): “As singled out by Horowitz and Savin (2000), bootstrapping permits the computation of meaningful size-corrected critical values, putting power figures into perspective.”
• The bootstrap and hypothesis tests in econometrics (2001, background): “See Horowitz and Savin (2000) for a numerical example.”
• Unit Root Testing in Heteroscedastic Panels Using the Cauchy Estimator (2012, background): “Given that sizeadjusted critical values are not available in practice we do not report size-adjusted power (Horowitz and Savin, 2000).”
• Bootstrap Methods in Econometrics (2006, unknown): “Comparing the power of tests that are not exact is fraught with difficulties; see Horowitz and Savin (2000) and Davidson and MacKinnon (2006a).”