This study examines the role of higher-order systematic co-moments in an asset pricing model, when stock returns are non-normally distributed. We test the effect of higher-order systematic co-moments using direct observations and the Fame-MacBeth two-pass regression on a data set comprising of weekly returns of Thai common stocks dating the post-crisis period .By sorting stocks into portfolios based on Fame-French method we find that, in general, the portfolios of small-sized stocks end of value stocks tend to have higher returns . Furthermore, we find that the portfolios with relatively higher returns tend to have Jess, or negative, systematic co-skewness. Results from two-pass regression show that Fame- French three-factor model has a better explanatory power than the traditional CAPM and adding systematic co-moments into both models yields a slight improvement. The slope coefficient of systematic co-skewness is generally negative, implying there is a trade-off between mean returns and systematic co-skewness