Abstract:

The authors  used quasilikelihood method to estimate the parameter of integervalued AR(p) process with signed binomial thinning to obtain the modifiedquasilikelihood estimator of the model parameters, and the asymptotic distribution of this estimator, thus, we can have some statistical analysis results about the model parameter, such as hypothesis testing. And  we compared the modifiedquasilikelihood estimator with the conditional least squares estimator via simulation. The results show that under some conditions,  the modifiedquasilikelihood estimator is better than conditional least squares estimator.

Key words: models of count data, signed Binomial thinning operator, conditional least squares, asymptotic distribution