Forecasting time series using principal component analysis with respect to instrumental variables

Authors:
P. -A. Cornillon;W. Imam;E. Matzner-Løber
Affiliations:
íquipe de Statistique, IRMAR UMR 6625, Université Rennes 2, Av. G. Berger CS24307, Haute Bretagne, 35043 Rennes, France;Higher Institute for Demographic Studies and Researches, Damascus, Syria;íquipe de Statistique, IRMAR UMR 6625, Université Rennes 2, Av. G. Berger CS24307, Haute Bretagne, 35043 Rennes, France
Venue:
Computational Statistics & Data Analysis
Year:
2008

Citing 3
Cited 3

Generalized principal component analysis with respect to instrumental variables via univariate spline transformations

Computational Statistics & Data Analysis
Forecast comparison of principal component regression and principal covariate regression

Computational Statistics & Data Analysis
Forecasting daily time series using periodic unobserved components time series models

Computational Statistics & Data Analysis

An artificial neural network (p,d,q) model for timeseries forecasting

Expert Systems with Applications: An International Journal
A novel hybridization of artificial neural networks and ARIMA models for time series forecasting

Applied Soft Computing
A new class of hybrid models for time series forecasting

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.03

Visualization

Abstract

Two new forecasting methods of time series are introduced. They are both based on a factorial analysis method called spline principal component analysis with respect to instrumental variables (spline PCAIV). The first method is a straightforward application of spline PCAIV while the second one is an adaptation of spline PCAIV. In the modified version, the used criteria according to the unknown value that need to be predicted are differentiated. Those two forecasting methods are shown to be well adapted to time series.