Let's Put the Seasonality and Trend in Decomposition
Robert L. Nydick
Department of Management and Operations, School of Business, Villanova University, Villanova, Pennsylvania 19085, robert.nydick@villanova.edu
Howard J. Weiss
Department of Marketing and Supply Chain Management, Fox School of Business, Temple University, Philadelphia, Pennsylvania 19122, hweiss@temple.edu
Abstract
When discussing forecasting, most textbooks in management science oroperations management explain that the values in a time series are afunction of seasonality, trend, and random variation. Many textbooks have pictures depicting different patterns of data. We present a workbook thatallows the user to manipulate a dynamic picture of these patterns and, in sodoing, allows the user to examine the relationship between error measuresand forecasting techniques for these different patterns. We also show aresult regarding the relationship between the annual trend and the quarterlytrend that surprises most of our students.
Key words
forecasting; trend; seasonality; decomposition; MAD; MSE; MAPE; excel
History
Received April 2011; accepted August 2011.
Download the PDF
Supplementary Material
Citation Information
Nydick, R. L., H. J. Weiss. 2012. Let's put the seasonality and trend in decomposition. INFORMS Trans. Ed. 12(3) 147–152. Available online at http://ite.pubs.informs.org/.