Journals favor rejection of the null hypothesis. This selection upon tests may distort the behavior of researchers. Using 50,000 tests published between 2005 and 2011 in the AER, JPE, and QJE, we identify a residual in the distribution of tests that cannot be explained by selection. The...

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...

Journals favor rejections of the null hypothesis. This selection upon results may distort the behavior of researchers. Using 50,000 tests published between 2005 and 2011 in the AER, JPE and QJE, we identify a residual in the distribution of tests that cannot be explained by selection. The...

Journals favor rejection of the null hypothesis. This selection upon tests may distort the behavior of researchers. Using 50,000 tests published between 2005 and 2011 in the AER, JPE, and QJE, we identify a residual in the distribution of tests that cannot be explained by selection. The...

We propose a new way to conduct multiple hypothesis testing in economics research. Our framework allows for correlation among tests and incomplete data, both of which are prevalent in economic meta-analysis. Our simulations show that that our method is able to produce the correct p-value cutoff...

There is growing interest in the use of subjective well-being data, such as survey questions about happiness and life satisfaction. The existing validation tests determine whether these subjective measures have a positive correlation with objective measures of well-being, such as suicide rates...

When evaluating a trading strategy, it is routine to discount the Sharpe ratio from a historical backtest. The reason is simple: there is inevitable data mining by both the researcher and by other researchers in the past. Our paper provides a statistical framework that systematically accounts...

Hundreds of papers and hundreds of factors attempt to explain the cross-section of expected returns. Given this extensive data mining, it does not make any economic or statistical sense to use the usual significance criteria for a newly discovered factor, e.g., a t-ratio greater than 2.0....

The paper is a keynote lecture from the Tilburg-Madrid Conference on Hypothesis Tests: Foundations and Applications at the Universidad Nacional de Educación a Distancia (UNED) Madrid, Spain, 15-16 December 2011. It addresses the role of tests of statistical hypotheses (specification tests) in...

We argue that frequentist hypothesis testing - the dominant statistical evaluation paradigm in empirical research - is fundamentally unsuited for analysis of the nonexperimental data prevalent in economics and other social sciences. Frequentist tests comprise incompatible repeated sampling...