Online Program Home
My Program

Abstract Details

Activity Number: 109 - Time Series and Forecasting
Type: Topic Contributed
Date/Time: Monday, July 30, 2018 : 8:30 AM to 10:20 AM
Sponsor: Business and Economic Statistics Section
Abstract #330100 Presentation
Title: New Methods for Threshold Variable Identification and Estimation in Threshold Dynamic Factor Models
Author(s): Xialu Liu* and Rong Chen
Companies: San Diego State University and Rutgers University
Keywords: Factor model; high-dimensional time series ; nonstationary process; threshold variable

We consider a threshold factor model for high-dimensional time series in which the dynamics of the time series is assumed to switch between different regimes according to the value of a threshold variable. This is an extension of the general threshold modeling approach to a high-dimensional time series setting under a factor structure. Specifically, within each regime, the time series follows a factor model with a noise process that is white. The factor loading matrices are different in different regimes. The model can also be viewed as an extension of the traditional factor models for time series. It provides flexibility in dealing with situations that the underlying states may be changing over time, as often observed in economic time series and other applications. Procedures are developed for the estimation of the loading spaces, the number of factors and the threshold value, as well as the identification of the threshold variable. Theoretical properties of the estimators are investigated. Simulated and real data examples are presented.

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

Back to the full JSM 2018 program