Tests for Time Series of Counts Based on the Probability Generating Function
Statistics Theory
2014-10-24 v1 Statistics Theory
Abstract
We propose testing procedures for the hypothesis that a given set of discrete observations may be formulated as a particular time series of counts with a specific conditional law. The new test statistics incorporate the empirical probability generating function computed from the observations. Special emphasis is given to the popular models of integer autoregression and Poisson autoregression. The asymptotic properties of the proposed test statistics are studied under the null hypothesis as well as under alternatives. A Monte Carlo power study on bootstrap versions of the new methods is included as well as real-data examples.
Cite
@article{arxiv.1410.6172,
title = {Tests for Time Series of Counts Based on the Probability Generating Function},
author = {Šárka Hudecová and Marie Hušková and Simos G. Meintanis},
journal= {arXiv preprint arXiv:1410.6172},
year = {2014}
}
Comments
24 pages, 16 figures, to be published in Statistics