Business cycle asymmetries in stock returns: Evidence from higher order moments and conditional densities

Markov switching models with time-varying means, variances and mixing weigh ts are applied to characterize business cycle variation in the probability distribution and higher order moments of stock returns. This allows us to p rovide a comprehensive characterization of risk that goes well beyond the m ean and variance of returns. Several mixture models with different specific ations of the state transition are compared and we propose a new mixture of Gaussian and student-t distributions that captures outliers in returns. Th e models produce very similar expected returns and volatilities but imply v ery different time series for conditional skewness, kurtosis and predictive density. Consistent with economic theory, the gains in predictive accuracy from considering two-state mixture models rather than a single-state speci fication are higher for small fil ms than for large firms. (C) 2001 Publish ed by Elsevier Science S.A.