New testing approaches for mean–variance predictability

We propose parametric tests for serial correlation in levels and squares that exploit the non-normality of financial returns. Our are robust to distributional misspecification. Furthermore, our mean predictability can be robustified against time-varying volatility. Local power analyses confirm their gains over existing methods, while Monte Carlo exercises assess finite sample reliability. apply quarterly returns on five Fama–French factors international stocks, whose distributions mostly symmetric but fat-tailed. results highlight noticeable differences across regions numerical sensitivity usual influential observations.