We present two models based on Dirichlet process mixtures for Bayesian inference in dynamic linear models with stochastic variances. The proposed models allow to capture variance clustering, outliers and structural breaks in time series analysis. The computations require MCMC algorithms, which we implement by the new R-package "dlm" that we have developed. (pagg. 341-344).
Bayesian inference for dynamic linear models with random variances.
PETRONE, SONIA
2007
Abstract
We present two models based on Dirichlet process mixtures for Bayesian inference in dynamic linear models with stochastic variances. The proposed models allow to capture variance clustering, outliers and structural breaks in time series analysis. The computations require MCMC algorithms, which we implement by the new R-package "dlm" that we have developed. (pagg. 341-344).
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
