A Bayesian sampling algorithm for parameter estimation in a discrete-response model is presented, where the dependent variables contain two layers of binary choices and one ordered response. The investigation is motivated by an empirical study using such a double-selection rule for three...

Forecasting large numbers of time series is a costly and time-consuming exercise. Before forecasting a large number of series that are logically connected in some way, the authors can first cluster them into groups of similar series. In this paper they investigate forecasting the series in each...

This article explores tests for absolute convergence in economic activity among a set of countries. It proposes a new test procedure that allows the researcher to identify particular countries within the group, which might not be converging. It also proposes that convergence among a set of...

This study proposes a new approach to estimation of the time series properties of daily volatility in financial markets.