Credible Granger-causality analysis appears to require post-sample inference, as it is well-known that in-sample fit can be a poor guide to actual forecasting effectiveness. However, post-sample model testing requires an often-consequential <em>a priori</em> partitioning of the data into an...

It is often unclear whether time series displaying substantial persistence should be modelled as a vector autoregression in levels (perhaps with a trend term) or in differences. The impact of this decision on inference is examined here using Monte Carlo simulation. In particular, the size and...

A fundamental statistical test of serial independence is developed and applied to daily stock returns. Let <italic>x</italic> be the deviation of the daily return on a stock from its sample mean after any autocorrelation present has been removed. If <italic>x</italic> is serially independent, then the cumulative sum of <italic>x</italic> over...