English

Joint temporal and contemporaneous aggregation of random-coefficient AR(1) processes with infinite variance

Statistics Theory 2020-05-01 v2 Statistics Theory

Abstract

We discuss joint temporal and contemporaneous aggregation of NN independent copies of random-coefficient AR(1) process driven by i.i.d. innovations in the domain of normal attraction of an α\alpha-stable distribution, 0<α20< \alpha \le 2, as both NN and the time scale nn tend to infinity, possibly at a different rate. Assuming that the tail distribution function of the random autoregressive coefficient regularly varies at the unit root with exponent β>0\beta > 0, we show that, for β<max(α,1)\beta < \max (\alpha, 1), the joint aggregate displays a variety of stable and non-stable limit behaviors with stability index depending on α\alpha, β\beta and the mutual increase rate of NN and nn. The paper extends the results of Pilipauskait\.e and Surgailis (2014) from α=2\alpha = 2 to 0<α<20 < \alpha < 2.

Keywords

Cite

@article{arxiv.1901.05380,
  title  = {Joint temporal and contemporaneous aggregation of random-coefficient AR(1) processes with infinite variance},
  author = {Vytautė Pilipauskaitė and Viktor Skorniakov and Donatas Surgailis},
  journal= {arXiv preprint arXiv:1901.05380},
  year   = {2020}
}