The availability of many variables with predictive power makes their selection in a regression context difficult. This study considers robust and understandable low-dimensional estimators as building blocks to improve overall predictive power by optimally combining these building blocks. Our new...

We introduce a novel multiple hypothesis testing framework for selecting outperforming mutual funds with control of luck, the functional False Discovery Rate “plus”. We show that our method, which incorporates informative covariates to estimate the false discovery rate, gains considerable...

Stock return predictability by investor sentiment has been subject to constant updating, but reaching a decisive conclusion seems rather challenging as academic research relies heavily on US data. We provide fresh evidence on stock return predictability in an international setting and show that...