Online Program Home
  My Program

Abstract Details

Activity Number: 580 - Time Series and Factor Models
Type: Contributed
Date/Time: Wednesday, August 2, 2017 : 2:00 PM to 3:50 PM
Sponsor: Business and Economic Statistics Section
Abstract #323923 View Presentation
Title: Dynamic Factor Model for Functional Time Series
Author(s): Israel Martínez Hernández* and Jesús Gonzalo and Graciela González Farías
Companies: and Universidad Carlos III de Madrid and Centro de Investigación en Matemáticas, CIMAT
Keywords: Functional Time Series ; Dynamic Factor Model ; Non-Stationarity

In econometrics, identify the factors that drives the behavior of observed time series is important, even more when the data is functional. In this study we propose a new approach the Dynamic Factor Model for Functional Time Series. Our model will characterize the dynamic of the data through the factors and the functional behavior of the data via the factor loadings. Via simulation studies, we show that the factors capture the dynamic of the process and share the same properties of the functional data, such as stationarity. We propose a methodology to estimate the factors that produces a consistent estimator and we investigate finite sample performance using Monte Carlo studies.

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

Back to the full JSM 2017 program

Copyright © American Statistical Association