Parallel computation has a long history in econometric computing, but is not at all wide spread. We believe that a major impediment is the labour cost of coding for parallel architectures. Moreover, programs for specific hardware often become obsolete quite quickly. Our approach is to take a...

The availability of intra-day data on the prices of speculative assets means that we can use quadratic variation like measures of activity in financial markets, called realised volatility, to study the stochastic properties of returns. Here we provide a statistical basis for realised volatility...

Given the increasing use of panel data in testing hypotheses about labour market behaviour, it is essential that economists have a cound grasp of the problems involved in the collection of this type of data. This paper investigates the biases generated by recall errors and panel attrition, using...

This paper shows that the behaviour of inventories is not symmetrical and that their modelling requires more than just a linear regression. Models of inventory behaviour are described and symmetric and non-symmetric-error-correction models are formulated which divide the changes in production...