Integer-valued bilinear time series models
 
 
Description: 

The analysis of count processes has become an important area of research in the last two decades. In this paper we consider the simple non-negative integer-valued bilinear process INBL(1,0,1,1). The parameter estimation is addressed and the problem of forecasting integer-valued time series modelled by the INBL(1,0,1,1) process is considered. Bayesian methodology is used to obtain parameter estimates, point predictions and confidence intervals for future values of the process. The parameters estimates and predictions thus obtained are compared with their classic counterparts. The proposed approaches are illustrated with a simulation study and applied to a real data set.

Date:  2011-11-29
Start Time:   12:00
Speaker:  Isabel Pereira (Univ. Aveiro)
Institution:  Departamento de Matemática da Universidade de Aveiro
Place:  Room 5.5
Research Groups: -Probability and Statistics
See more:   <Main>  
 
© Centre for Mathematics, University of Coimbra, funded by
Science and Technology Foundation
Powered by: rdOnWeb v1.4 | technical support