Identifying outliers in asset pricing data with a new weighted forward search estimator

In this paper the impact of outliers on the estimation of asset pricing models and in associated statistical tests is assessed. A new estimator based on the Forward Search (Atkinson and Riani, 2000) – which is both efficient and robust to outliers – is applied to the 25 Fama-French portfolios (Fama and French, 1993) in the time-series framework of asset pricing analysis. The new estimator is used to identify outliers and to provide robust estimates of the models’ parameters. Our results indicate that the use of robust methods increases the rejection level of the CAPM and the Fama-French three factor model. It is also shown that the outliers identified are linked to relevant economic events such as stock market crashes and bubbles in asset prices.