J 2015

A Predictive Likelihood Approach to Bayesian Averaging

JEŘÁBEK, Tomáš a Radka ŠPERKOVÁ

Základní údaje

Originální název

A Predictive Likelihood Approach to Bayesian Averaging

Autoři

JEŘÁBEK, Tomáš (203 Česká republika, garant, domácí) a Radka ŠPERKOVÁ (203 Česká republika)

Vydání

Acta Univ Agric Silvic Mendel Brun, Praha, Mendel University Press, 2015, 1211-8516

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

50200 5.2 Economics and Business

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Kód RIV

RIV/04274644:_____/15:#0000041

Organizační jednotka

Vysoká škola finanční a správní

Klíčová slova česky

predictive likelihood; density forecasts; Bayesian averaging; Bayesian VAR model

Klíčová slova anglicky

predictive likelihood; density forecasts; Bayesian averaging; Bayesian VAR model

Příznaky

Recenzováno
Změněno: 8. 6. 2018 10:01, Mgr. Tomáš Jeřábek, Ph.D., MBA

Anotace

V originále

Multivariate time series forecasting is applied in a wide range of economic activities related to regional competitiveness and is the basis of risk management analysis. In this paper we combine multivariate density forecasts. The performance of models is identified using historical dates including domestic economy and foreign economy, which is represented by countries of the Eurozone. Because forecast accuracy of observed models are different, the weighting scheme based on the predictive likelihood, the trace of past MSE matrix, model ranks are used to combine the models. The equal-weight scheme is used as a simple combination scheme. The results show that optimally combined densities are comparable to the best individual models.

Česky

Multivariate time series forecasting is applied in a wide range of economic activities related to regional competitiveness and is the basis of risk management analysis. In this paper we combine multivariate density forecasts. The performance of models is identified using historical dates including domestic economy and foreign economy, which is represented by countries of the Eurozone. Because forecast accuracy of observed models are different, the weighting scheme based on the predictive likelihood, the trace of past MSE matrix, model ranks are used to combine the models. The equal-weight scheme is used as a simple combination scheme. The results show that optimally combined densities are comparable to the best individual models.