A Model for Daily Global Stock Market Returns

Most stock markets are open for 6-8 hours per trading day. The Asian, European and North American stock markets are separated in time by time-zone differences. We propose a statistical factor model for daily returns across multiple time zones. Our model has a common global factor as well as a continent factor. We demonstrate that our model has a structural interpretation. We propose estimation routines by both the Frequentist (the Expectation-Maximisation (EM) algorithm) and Bayesian (the Markov Chain Monte Carlo (MCMC)) methods. Monte Carlo simulations are conducted to assess the validity of our estimation routines. Last, we apply our model to daily portfolio returns from Japan, UK and US.