Our research primarily deals with theory and empirical applications of non-Gaussian econometric time series models. Currently we focus, in particular, on the following models:
- Noninvertible and noncausal time series models
- Vector autoregressive (VAR) models, including nonlinear, non-Gaussian and non-causal VAR models, cointegrated VAR models, as well as structural VAR models
- Univariate and multivariate Gaussian mixture autoregressive (GMAR) models
- Discrete and limited dependent time series models
Our theoretical work involves derivation of the properties of these models, and development of both classical and Bayesian methods of inference and forecasting related to them. Our empirical applications range from pricing financial risks to modelling the effects of monetary policy and forecasting the phases of the business cycle by means of financial information.