Residual Analysis with Bivariate INAR(1) Models

Authors

  • Predrag M. Popović University of Niš
  • Aleksandar S. Nastić University of Niš
  • Miroslav M. Ristić University of Niš

DOI:

https://doi.org/10.57805/revstat.v16i3.246

Keywords:

bivariate INAR(1) model, residual analysis, predictive distribution, binomial thinning, negative binomial thinning, geometric marginal distribution

Abstract

In this paper we analyze forecasting errors made by random coefficients bivariate integer-valued autoregressive models of order one. These models are based on the thinning operator to support discreteness of data. In order to achieve a comprehensive analysis, we introduce a model that implements a binomial as well as a negative binomial thinning operator. There are two components of the model: survival and innovation. Forecasting errors made by each of these two sources of uncertainty are unobservable in the classic way. Thus, we derive predictive distributions from which we obtain the expected value of each component of the model. We provide an example of residual analysis on real data.

Published

2018-07-09

How to Cite

M. Popović , P., S. Nastić , A., & M. Ristić , M. (2018). Residual Analysis with Bivariate INAR(1) Models. REVSTAT-Statistical Journal, 16(3), 349–363. https://doi.org/10.57805/revstat.v16i3.246

Most read articles by the same author(s)