Enhancing Computational Efficiency in State-Space Models Using Rao-Blackwellization and 2-Step Approximation

Autor:	Kitagawa, Genshiro
Rok vydání:	2024
Předmět:	Statistics - Computation 62M20(Primary) 62M05(Secondary)
Druh dokumentu:	Working Paper
Popis:	This paper explores a Bayesian self-organization method for state-space models, enabling simultaneous state and parameter estimation without repeated likelihood calculations. While efficient for low-dimensional models, high-dimensional cases like seasonal adjustment require many particles. Using Rao-Blackwellization and a 2-step approximation, the method reduces particle use and computation time while maintaining accuracy, as shown in Monte Carlo evaluations. Comment: 23 pages, 6 tables, 12 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.16056 Zobrazit plný text záznamu View this record from Arxiv