English

Asymptotic behavior of CLS estimators for unstable INAR(2) models

Statistics Theory 2016-07-25 v2 Probability Statistics Theory

Abstract

In this paper the asymptotic behavior of the conditional least squares estimators of the autoregressive parameters (α,β)(\alpha,\beta), of the stability parameter ϱ:=α+β\varrho := \alpha + \beta, and of the mean μ\mu of the innovation \varek\vare_k, k\NNk \in \NN, for an unstable integer-valued autoregressive process Xk=αXk1+βXk2+\varekX_k = \alpha \circ X_{k-1} + \beta \circ X_{k-2} + \vare_k, k\NNk \in \NN, is described. The limit distributions and the scaling factors are different according to the following three cases: (i) decomposable, (ii) indecomposable but not positively regular, and (iii) positively regular models.

Keywords

Cite

@article{arxiv.1202.1617,
  title  = {Asymptotic behavior of CLS estimators for unstable INAR(2) models},
  author = {Matyas Barczy and Marton Ispany and Gyula Pap},
  journal= {arXiv preprint arXiv:1202.1617},
  year   = {2016}
}

Comments

67 pages; the CLS estimator of the mean of the innovation has been added