AbstractThis paper tests the hypothesis that the small‐firm effect can be explained on the basis of investor preference for positive skewness. Traditional stochastic dominance methodology is extended to consider portfolios including variable weights of investment in a riskless asset. Including a riskless asset provides the result that small‐firm portfolios stochastically dominate all other portfolios. This result, which is derived on the basis of 19 years of monthly returns, indicates that the small‐firm effect cannot be fully attributed to tax effects, benchmark error, or incorrect assumptions of the CAPM about investor risk ave