A limit theory is developed for mildly explosive autoregression under both weakly and strongly dependent innovation errors. The asymptotic behaviour of the sample moments is affected by the memory of the innovation process both in the form of the limiting distribution and, in the case of long...

A new method for detecting regime switches between different probability distributions in financial time series is shown. In the proposed method, time series observations are divided into several segments, and a Gaussian model or a Cauchy model is fitted to each segment. The goodness of fit of...

A limit theory is developed for mildly explosive autoregression under both weakly and strongly dependent innovation errors. We find that the asymptotic behaviour of the sample moments is affected by the memory of the innovation process both in the in the form of the limiting distribution and, in...

We offer a new and straightforward proof of F.B. Knight's [3] theorem that the Cauchy type is characterized by the fact that it has no atom and is invariant under the involution i : x - -1/x. Our approach uses the representation X = tan theta where theta is uniform on (-pi/2,pi/2) when X is...

In this paper a characterization is presented for Pearson's Type II and VII multivariate distributions by means of the maximum entropy principle. It is shown that within the class of multivariate distributions, that satisfy appropriate constraints expressed by mean values, the Pearson Type II...