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 #322532 View Presentation
Title: In-Curve Updating of Predictions for Functional Time Series
Author(s): Shuhao Jiao* and Alexander Aue
Companies: Department of Statistics, UC Davis and University of California, Davis
Keywords: Functional data ; Prediction ; Principal components ; Time series

Functional time series have become an important tool when dealing with a data that may conveniently be viewed as a curves exhibiting a temporal dependence structure. Such examples are found in variety of application areas. Here we focus on an environmental data set on daily pollution concentration curves. It is discussed how existing functional prediction methodology can be updated in an automatic way using in-curve updates that improve predictions obtained from time series and linear model formulations of the problem. Simulation results and real data examples highlight the performance of the proposed procedure.

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

Back to the full JSM 2017 program

Copyright © American Statistical Association