Applying a probabilistic causal approach, we define a class of time series causal models (TSCM) based on stationary Bayesian networks. A TSCM can be seen as a structural VAR identified by the causal relations among the variables. We classify TSCMs into observationally equivalent classes by...

In this note the author discusses the problem of updating forecasts in a time-discrete forecasting model when information arrives between the current period and the next period. To use the information that arrives between two periods, he assumes that the process between two periods can be...

In this paper, we investigate the instability in a self-exciting regime-switchingautoregressive model that is locally stable in each of its regimes respectively. It turnsout that the stability locally in each of the regimes is not sufficient to guarantee thestability of the model. The mechanism...