Title: A compendium of reproducible research about time series analysis
Authors: Wessa, Patrick
Issue Date: 2008
Publisher: Wessa
Series Title: pages:30
Abstract: This document can be used as an introductory, interactive case study about Time Series Analysis based on decomposition, multiple regression and exponential smoothing (including the Holt-Winters model). Section 2 describes the problem and section 3 introduces theoretical concepts that are of importance in applied analysis. Section 4 treats the problem of decomposing a time series into its underlying components (trend, seasonality, and a random component) from an experimental (“try, see, and reflect") perspective. In section 5 emphasis is on “ad hoc" Forecasting of the time series under investigation, based on regression (section 5.1) and exponential smoothing techniques (section 5.2). At the same time this document is an illustrated tutorial about and It illustrates how Reproducible Research can be integrated in Statistics Education based on a Compendium that contains all references to archived information that makes the underlying research reproducible and reusable.
Publication status: published
KU Leuven publication type: DI
Appears in Collections:Department of Marketing Management, Campus Carolus Antwerp

Files in This Item:
File Status SizeFormat
tutorial1.pdf Published 370KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.