Dynamic Discrete Mixtures for High-Frequency Prices

The tick structure of the financial markets entails discreteness of stock price changes. Based on this empirical evidence, we develop a multivariate model for discrete price changes featuring a mechanism to account for the large share of zero returns at high frequency. We assume that the observed price changes are independent conditional on the realization of two hidden Markov chains determining the dynamics and the distribution of the multivariate time series at hand. We study the properties of the model, which is a dynamic mixture of zero-inflated Skellam distributions. We develop an expectation-maximization algorithm with closed-form M-step that allows us to estimate the model by maximum likelihood. In the empirical application, we study the joint distribution of the price changes of a number of assets traded on NYSE. Particular focus is dedicated to the assessment of the quality of univariate and multivariate density forecasts, and of the precision of the predictions of moments like volatility and correlations. Finally, we look at the predictability of price staleness and its determinants in relation to the trading activity on the financial markets.