A Stepwise Spa Test for Data Snooping and its Application on Fund Performance Evaluation

Abstract

In this study, we propose a Stepwise SPA Test which is powerful in searching for predictive models or profitable investment targets with appropriate family-wise error control. Our testing method, built on White's Reality Check (2000), Hansen's SPA test (2005), and Romano and Wolf's stepwise procedure (2005), aims to conduct large-scale joint hypothesis testing in a given data set. Based on the Monte Carlo simulations, we show that the proposed test is more powerful than the other three tests in limited samples. We then apply the test to examine the performance of mutual funds and hedge funds, and obtain some interesting results. We find that only eight mutual funds are found to beat the S&P 500 index, and only few hedge funds outperform the risk-free rate. With these two empirical cases, we substantiate the empirical value of our test in fund performance evaluation.

Keywords: Data Snooping, Reality Check, Stepwise Test, SPA test

JEL Classification: C12, C32