Publication: Seasonal modulation mixed models for time series forecasting
Loading...
Identifiers
Publication date
2012-11
Defense date
Authors
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
We propose an extension of a seasonal modulation smooth model with P-splines for
times series data using a mixed model formulation. A smooth trend with seasonality
decomposition can be estimated simultaneously. We extend the model to consider the
forecasting of new future observations in the mixed model framework. Two different
approaches are used for forecasting in the context of mixed models, and the equivalence
of both methods is shown. The methodology is illustrated with monthly sulphur dioxide
(SO2) levels in a selection of monitoring sites in Europe from January 1990 to
December 2001.
Description
Keywords
P-splines, Mixed models, Times series forecasting, Varying-coefficient models, Harmonic regression