Online Program Home
My Program

Abstract Details

Activity Number: 492 - Recent Advances in Modeling Complex Dependent Data
Type: Invited
Date/Time: Wednesday, August 1, 2018 : 10:30 AM to 12:20 PM
Sponsor: Business and Economic Statistics Section
Abstract #326716 Presentation
Title: Count Time Series Models Based on Expectation Thinning Operators
Author(s): Harry Joe*
Companies: University of British Columbia
Keywords: count time series; thinning operator

Expectation thinning operators for count time series are compounding operators that include the binomial thinning operator as a special case. Some new results are given for the relationship of the stationary marginal distribution, the innovation distribution and the family of compounding operators that satisfy a self-generalized closure property. It will be shown how to build integer-autoregressive time series models that can accommodate covariates. A data example will be presented as well as the numerical methods required for parameter estimation.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program