|
Activity Number:
|
426
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Risk Analysis
|
|
Abstract #319115
|
|
|
Title:
|
A Two-Dimensional Poisson Autoregression with Application to Association Study of Two Financial Markets
|
|
Author(s):
|
Ke Wang* and Haipeng Xing
|
|
Companies:
|
and SUNY Stony Brook
|
|
Keywords:
|
2-dimentional ;
log-linear possion autoregresstion ;
time series of counts ;
exceedance returns ;
cross term association
|
|
Abstract:
|
Recent studies have shown that a log-linear model for time series of counts provides a framework that both negative and positive association can be taken into account. We develop a two-dimensional log-linear possion autoregression model for time series of counts to analyze the association between two stocks/financial markets simultaneously. Maximum likelihood method is used for the estimation of the parameters and the property of geometrically ergodic is demonstrated by the perturbed version of the process. This theory can be applied to the number of transactions of financial time series of counts for two stocks and the number of exceedance returns for two stocks/ financial markets. We provide theoretical discussion and extensive simulations study to analyze the association between the number of counts, especially the cross term of the model. We further use this model to estimate the exceedance returns association between SP500 and NASDAQ monthly counts record from 1996 to 2015.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2016 program
|
