Autori
Sunecher, Yuvraj
Mamode Khan, Naushad
Ristic, Miroslav M.
Jowaheer, Vandna

Titolo
BINAR(1) negative binomial model for bivariate non-stationary time series with different over-dispersion indices
Periodico
Statistical methods & applications : Journal of the Italian Statistical Society
Anno: 2019 - Volume: 28 - Fascicolo: 4 - Pagina iniziale: 625 - Pagina finale: 653

The existing stationary bivariate integer-valued autoregressive model of order 1(BINAR(1)) with correlated Negative Binomial (NB) innovations is capable of mod-elling stationary count series where the innovation terms of both series have sameover-dispersion index. Such BINAR(1) may not be useful to model real-life series thatare affected by common time-dependent covariates whereby the two series may displaynon-stationarity as well as different over-dispersion indices. In this paper, we proposea novel BINAR(1) model with the pair of innovations following a joint NB distributionthat accommodates different over-dispersion indices. The estimation of parameters isconducted using generalized quasi-likelihood (GQL) approach that operates in twophases. Monte Carlo simulations are implemented to assess the performance of theproposed GQL under the wide range of combinations of the model parameters. ThisBINAR(1) model is also applied to analyze the daily series of day and night accidentdata in some regions of Mauritius.



SICI: 1618-2510(2019)28:4<625:BNBMFB>2.0.ZU;2-X

Esportazione dati in Refworks (solo per utenti abilitati)

Biblioteche ACNP che possiedono il periodico