Dynamic conditional score (DCS) - or Generalized Autoregressive Score (GAS) - models have developed rapidly over the last ten years and continue to be a fruitful area for research; see the papers listed on this site.
These models offer a united and comprehensive theory for a class of nonlinear time series models in which the dynamics of a changing parameter, such as location or scale, are driven by the score of the conditional distribution. When combined with basic ideas of maximum likelihood estimation, this approach leads to observation-driven models which, in contrast to many in the literature, are relatively simple in their form and yield analytic expressions for their principal features.
The models have been particularly successful at capturing the movements in volatility of nancial time series. However, they have been extended into other areas, including dealing with environmental data. This course will stress the range of applications as well as explaining the basic theory. Participants are expected to have taken an introductory course in econometrics or time series analysis.