Bootstrapping non-parametric models is a fairly complicated exercise which is associated with implicit assumptions or requirements that are not always obvious to the non-expert user. Bootstrap DEA is a significant development of the past decade; however, some of its assumptions and properties are...

We develop exact distribution-free test procedures for joint inference about the forward rate unbiasedness hypothesis (FRUH) across multiple currencies. The procedures can be applied with either levels or differences specifications. This unified approach proceeds with sign and signed rank tests...

In a model with endogenous regressors, heteroskedastic and autocorrelated (HAC) errors and weak instruments, tests that depend on the data only through the Anderson-Rubin (AR) and Lagrange Multiplier (LM) statistics ignore important information on the regression coefficients. This is in contrast...

This paper deals with two alternatives to the so-called Hausman test for the exogeneity of instruments, in the context of a model where one or more explanatory variables are possibly correlated with the structural error. These two alternatives are at least as good or better than the Hausman test...

Economists, like other scientists, routinely rely on classical statistical inference to form expectations on whether a claim holds in academic research, with significance levels such as 0.05 being assigned special meaning. We present experimental evidence suggesting that most people are also...

The economics 'credibility revolution' has promoted the identification of causal relationships using difference-in-differences (DID), instrumental variables (IV), randomized control trials (RCT) and regression discontinuity design (RDD) methods. The extent to which a reader should trust claims...

I comment on the controversy between McCloskey & Ziliak and Hoover & Siegler on statistical versus economic significance, in the March 2008 issue of the Journal of Economic Methodology. I argue that while McCloskey & Ziliak are right in emphasizing 'real error', i.e. non-sampling error that...