Online Program Home
  My Program

Abstract Details

Activity Number: 520 - Contributed Poster Presentations: Business and Economic Statistics Section
Type: Contributed
Date/Time: Wednesday, August 2, 2017 : 10:30 AM to 12:20 PM
Sponsor: Business and Economic Statistics Section
Abstract #323545
Title: A GARCH Type Poisson Model for Time Series of Counts with Cyclically Varying Zero Inflation
Author(s): Isuru Ratnayake* and V A Samaranayake
Companies: Missouri University of Science and Technology and Missouri University of Science and Technology
Keywords: Integer-valued ; Discrete Time Series ; Generalized Conditional Heterskedasticity ; Periodicity

In this study, we introduce a generalization of the zero inflated Poisson process to model time series of count data that exhibit both generalized conditional heteroskedastic volatility and cyclical behavior in the zero inflation factor. This is a generalization of the zero-inflated Poisson-GARCH model proposed by Fukang Zhu in 2012, which in turn can be considered a generalization of the Autoregressive Conditional Poisson model proposed by Andreas Heinen in 2003. While Heinen's Autoregressive Conditional Poisson model accommodates GARCH type behavior, Zhu introduces zero inflation. Our proposed model goes one step further by incorporating the flexibility to allow the zero inflation parameter to vary cyclically or be driven by an exogenous variable. A method for estimating the proposed model is introduced and its performance studied using Monte-Carlo methods.

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

Back to the full JSM 2017 program

Copyright © American Statistical Association