Literature shows that the regression of independent and (nearly) nonstationary time series could result in spurious outcomes. In this paper, we conjecture that under some situations, the regression of two independent and nearly non-stationary series does not have any spurious problem at all. To...

Adopting a MS-VAR model (Krolzig, 1997) and a recently developed regime-dependent impulse response analysis technique (Ehrmann, et al., 2003), this paper investigates the dynamic relationships among the stock markets of the US, Australia and New Zealand. Our results reveal the existence of two...

Literature shows that the regression of independent and (nearly) non-stationary time series could result in spurious outcomes. In this paper, we conjecture that under some situations, the regression of two independent and nearly non-stationary series does not have any spurious problem at all. To...

We consider AR(q) models in time series with asymmetric innovations represented by two families of distributions: (i) gamma with support IR : (0 , \infty), and (ii) generalized logistic with support IR : (- \infty, \infty). Since the ML (maximum likelihood) estimators are intractable, we derive...

Three-moment chi-square and four moment F approximations are given which can be used for testing a unit root in AR(1) model when the innovations have one of a very wide family of symmetric distributions (Student's t)