This paper uses the Markov switching approach to account for instabilities in the long-run money demand function and compute the welfare cost of inflation in the United States. In doing so, it circumvents the problem of data-mining of some earlier seminal contributions on these issues, allowing...

We introduce a new class of stochastic volatility models with autoregressive moving average (ARMA) innovations. The conditional mean process has a flexible form that can accommodate both a state space representation and a conventional dynamic regression. The ARMA component introduces serial...

We introduce a new class of stochastic volatility models with autoregressive moving average (ARMA) innovations. The conditional mean process has a flexible form that can accommodate both a state space representation and a conventional dynamic regression. The ARMA component introduces serial...