Bootstrap J tests of nonnested linear regression models

72 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.

Bootstrap Methods in Econometrics (2006, unknown): “For example, Davidson and MacKinnon (2002) apply residual bootstrap methods to the J test of non-nested hypotheses and find that they generally work very well.”
Bootstrap Tests for Regression Models (2009, background): “Given that the alternative hypothesis is H+ 1 : E(y) > 0, the rule (2.4) is appropriate since large values of τ̂ imply small values of PVMC. Under regularity conditions provided in Dufour et al. (2004), this rule provides an exact test when α (B+ 1) is an integer.”
Bootstrap Inference in Econometrics (2002, unknown): “In extreme cases, even for sample sizes as large as 50, an asymptotic J test at the .05 level can reject a true null hypothesis more than 80 per cent of the time; see Davidson and MacKinnon (2002a).”
Bootstrap Hypothesis Testing (2007, methodology): “Davidson and MacKinnon (2002a) provides a detailed analysis for the case in which H0 and H1 are both linear models.”
FAST DOUBLE BOOTSTRAP TESTS OF NONNESTED LINEAR REGRESSION MODELS (2002, background): “In Davidson and MacKinnon,([5]) we developed a theoretical approach which enabled us to show precisely what determines the finite-sample distribution of the”