Theorethical Statistics:
I have two primary interests here:

1. Many physical systems which are chaotic in nature can be modelled succesfully using statistical methods, yet chaotic systems are in fact deterministic. On the other hand when random variables are to be simulated on computer this is achieved by creating chaotic sequences of numbers, which of course are anything but random. I'm interested in the relationships between these two types of modelling uncertainity.
2. I'm also interested in the problems of detecting and remedying mis-specifications in multiple regression models. In particular, testing for autocorrelation and multicollinearity in such models.

Applied Statistics
Under this heading I have a range of interests (which I hope is always expanding). It is my belief that work in Applied Statistics is not only useful in itself but is often the source of inspiration for new theorethical ideas. Recently I've worked in:

1. Educational Science (the efficacy of computer delivery of course material)
2. Information Retrieval (search engine evaluation)
3. Econophysics (analysis of stock market volatility)
4. Scientometrics (evolution of a conference over 25 years)