Dynamic Generalized Linear Models and Bayesian Forecasting

From MaRDI portal





Dynamic Bayesian models are developed for application in nonlinear non- normal time series and regression problems. The models can be considered as dynamic extensions of standard generalized linear models. On the other hand, algorithms provided in the article can be considered as generalizations of the Kalman filter algorithm. The method is useful when the time series involves distributions of the exponential family. Important special cases are the bionomial and Poisson distributions. This leads to the calculation of closed, standard-form predictive distributions for forecasting. Data analytic aspects of the models are discussed. Some applications are considered.




Cited in
(only showing first 100 items - show all)








This page was built for publication: Dynamic Generalized Linear Models and Bayesian Forecasting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3684997)