Answers are grounded in this paper and cite their sources.
The empirical frequency distributions of continuously-compounded monthly share returns on the Melbourne Stock Exchange over 1958-73 are studied for individual securities and portfolios. The typical distributional shape is observed and the stable Paretian and Student t distributions are fitted to the returns. The latter clearly is superior and even normality is a reasonable approximation for medium sized portfolios. The most likely explanation seems to be non-stationarity in the generating process for returns, rather than infinite-variance distributions or data errors. The implications for future empirical work and the theory of asset pricing are discussed.
No takes yet. Share an insight, caveat, or question.
Praetz et al. (1978) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: