Multivariate statistical simulation
Multivariate statistical simulation
Bayesian forecasting and dynamic models (2nd ed.)
Bayesian forecasting and dynamic models (2nd ed.)
| Hi-index | 0.00 |
This paper shows a generalization of the linear dynamic model, which is practical and easy to compute. The generalization is made by assuming a continuous elliptical joint distribution for the parameters and errors. Updated distribution and probabilistic characteristics of the current and future vector of state and observations are given. As a particular simple submodel, the one with a multidimensional exponential power initial distribution is developed. An example showing its use is given.