The Virtue and Vice of Complexity in Equity Risk Premium Prediction

Abstract

When forecasting the equity risk premium, simple techniques generate results that are easier to interpret than results from more complex techniques. If complex techniques have better performance, does the virtue of superior performance trump the vice of lack of interpretability? This presumes simpler techniques underperform. Complex does not equate to superior performance. Old and simple techniques like discriminant analysis combine the virtue of performance with the virtue of intelligibility. This article performs a horse race among stepwise quadratic discriminant analysis, classification trees, regression trees, and ridgeless regression. Sometimes, accuracy can be sacrificed in favor of better out-of-sample Sharpe ratios. This article also shows that preprocessing data using rolling percentage ranks can be better than using either an expanding window or Z-scores.