CFDP 1454

A Quantilogram Approach to Evaluating Directional Predictability


Publication Date: March 2004

Pages: 23


In this note we propose a simple method of measuring directional predictability and testing for the hypothesis that a given time series has no directional predictability. The test is based on the correlogram of quantile hits. We provide the distribution theory needed to conduct inference, propose some model free upper bound critical values, and apply our methods to stock index return data. The empirical results suggests some directional predictability in returns especially in mid range quantiles like 5%-10%.


Correlogram; Dependence; Efficient Markets; Quantiles

JEL Classification Codes:  C12, C13, C14, C22


Published in Journal of Econometrics (November 2007), 141(1): 250-282 [DOI]