Seasonal Dynamic Factor Analysis and Bootstrap Inference: Application to Electricity Market Forecasting

• Published in: Technometrics Vol. 53; no. 2; pp. 137 - 151
• Main Authors: Alonso, Andrés M., García-Martos, Carolina, Rodríguez, Julio, Jesús Sánchez, María
• Format: Journal Article
• Language: English
• Published: Alexandria, VA Taylor & Francis 01.05.2011; The American Society for Quality and The American Statistical Association; American Society for Quality and the American Statistical Association; American Society for Quality
• Subjects: Analytical forecasting; Applied sciences; Bootstrap method; Computer science; control theory; systems; Data processing. List processing. Character string processing; Dimensionality reduction; Discriminant analysis; Economic forecasting models; Electrical engineering. Electrical power engineering; Electrical power engineering; Electricity prices; Energy prices; Exact sciences and technology; Factor analysis; Forecasting; Forecasting models; Inference from stochastic processes; time series analysis; Linear inference, regression; Mathematics; Memory organisation. Data processing; Modeling; Nonstationary; Parameter estimation; Power marketers; Power networks and lines; Probability and statistics; Sciences and techniques of general use; Seasonality; Software; Statistical forecasts; Statistics; Time series; Time series forecasting; Time series models; Uncertainty; Unobserved components; VARIMA models; Parameter estimation; Dynamic analysis; Seasonality; Non stationary process; Unobserved components; Modeling; Autoregressive integrated moving average model; Uncertain system; Seasonal variation; Bootstrap; Reduced order systems; System identification; Dimensionality reduction; Data analysis; Factor analysis; Time series; Non stationary condition; Inference; Coverage; Market survey; Energy prices; Vector method; Statistical forecasting; Long term; Stationary condition; Bootstrapping; Dimension reduction; VARIMA models; Electrical network; Remolded sample; Nonstationary; Factorial design

In this work, we propose the Seasonal Dynamic Factor Analysis (SeaDFA), an extension of Nonstationary Dynamic Factor Analysis, through which one can deal with dimensionality reduction in vectors of time series in such a way that both common and specific components are extracted. Furthermore, common...