Varying coefficient models in biostatistics
by Professor Richard Huggins
Abstract: In many applications it is not possible to parametrically model all features of a data set. This is particularly true of processes involving humans where their behaviour changes as the process evolves. Here we shall examine an epidemic model, where the interest is in predicting on day n the day n+j when the epidemic falls below a given
level and a model for the monthly numbers of suicides in Hong Kong where the interest is in detecting long term trends.
For More Information: Paul Norbury tel. 8344 5534 http://www.ms.unimelb.edu.au/~pnorbury/colloquium/colloquium-2005.html