En estimation bayésienne, lorsque le calcul explicite de la loi a posteriori du vecteur des paramètres à estimer est impossible, les méthodes de Monte-Carlo par chaînes de Markov (MCMC) [Robert and Casella, 1999] permettent théoriquement de fournir un échantillon approximativement...

In this paper, we introduce a new approach for volatility modeling in discrete and continuous time. We follow the stochastic volatility literature by assuming that the variance is a function of a state variable. However, instead of assuming that the loading function is ad hoc (e.g., exponential...

Markets makers quote many option categories in terms of implicit volatility. In doing so, they can reactivate the Black and Scholes model which assumes that the volatility of an option underlying is constant while it is highly variable. First of all, this article, whose purpose is very...

The Wishart Autoregressive (WAR) process is a multivariate process of stochastic positive definite matrices. The WAR is proposed in this paper as a dynamic model for stochastic volatility matrices. It yields simple nonlinear forecasts at any horizon and has factor representation, which separates...

We study the problem of a leveraged investor that is forced to unwind a significant fraction of its portfolio in a collection of illiquid markets. It is shown that markets may become disrupted in response to a relatively small liquidity shock. As a consequence, the probability of default can be...