A periodic and seasonal statistical model for non-negative integer-valued time series with an application to dispensed medications in respiratory diseases

This paper introduces a new class of models for non-negative integer-valued time series with periodic and seasonal autoregressive structure. Some properties the model are discussed conditional quasi-maximum likelihood method is used to estimate parameters. The consistency asymptotic normality estimators established. Their performances investigated finite sample sizes empirical results indicate that gives accurate estimates. proposed applied analyse daily number antibiotic dispensing medication treatment respiratory diseases, registered in health center Vitória, Brazil.