User manual SPSS TRENDS 13.0

[. . . ] SPSS Trends 13. 0 ® For more information about SPSS® software products, please visit our Web site at http://www. spss. com or contact SPSS Inc. 233 South Wacker Drive, 11th Floor Chicago, IL 60606-6412 Tel: (312) 651-3000 Fax: (312) 651-3668 SPSS is a registered trademark and the other product names are the trademarks of SPSS Inc. No material describing such software may be produced or distributed without the written permission of the owners of the trademark and license rights in the software and the copyrights in the published materials. The SOFTWARE and documentation are provided with RESTRICTED RIGHTS. [. . . ] See the SPSS Command Syntax Reference for complete syntax information. Part 2: Examples Chapter Exponential Smoothing 8 Using Exponential Smoothing to Predict Future Sales A catalog company is interested in forecasting monthly sales of its men's clothing line. To this end, the company collected monthly sales of men's clothing for a 10-year period. This information is collected in catalog_seasfac. sav, found in the \tutorial\sample_files\ subdirectory of the directory in which you installed SPSS. Use the Exponential Smoothing procedure to predict monthly sales of men's clothing for the following year. Preliminaries In the examples that follow, it is more convenient to use variable names rather than variable labels. E From the menus choose: Edit Options. . . 49 50 Chapter 8 Figure 8-1 Options dialog box E Select Display names in the Variable Lists group. E Click OK. Understanding Your Data The first step in analyzing a time series is to plot it. Visual inspection of a time series can often be a powerful guide in choosing an appropriate exponential smoothing model. In particular: Does the series have an overall trend?Does the trend appear constant or does it appear to be dying out with time?Do the seasonal fluctuations seem to grow with time or do they appear constant over successive periods? 51 Exponential Smoothing To obtain a plot of men's clothing sales over time: E From the menus choose: Graphs Sequence. . . Figure 8-2 Sequence Charts dialog box E Select men and move it into the Variables list. E Select date and move it into the Time Axis Labels list. E Click Time Lines. 52 Chapter 8 Figure 8-3 Sequence Charts Time Axis Reference Lines dialog box E Select Line at each change of. E Select YEAR_ and move it into the Reference Variable list. These choices result in a vertical reference line at the start of each year, which is useful for identifying annual seasonality. E Click Continue. E Click OK in the Sequence Charts dialog box. 53 Exponential Smoothing Figure 8-4 Sales of men's clothing (in U. S. dollars) The series shows a global upward trend; that is, the series values tend to increase over time. The upward trend is seemingly constant, which indicates a linear trend. The series also has a distinct seasonal pattern with annual highs in December. This is easy to see because of the vertical reference lines positioned at the start of each year. The seasonal variations appear to grow with the upward series trend, which suggests multiplicative rather than additive seasonality. Building and Analyzing Exponential Smoothing Models Building a best-fit exponential smoothing model involves determining the model type--does the model need to include trend and/or seasonality--and then obtaining the best-fit parameters for the chosen model. 54 Chapter 8 The plot of men's clothing sales over time suggested a model with both a linear trend component and a multiplicative seasonality component. First, however, we will explore a simple model (no trend and no seasonality) and then a Holt model (incorporates linear trend but no seasonality). This will give you practice in identifying when a model is not a good fit to the data, which is an essential skill in successful model building. Building and Analyzing a Simple Model To build an exponential smoothing model: E From the menus choose: Analyze Time Series Exponential Smoothing. . . Figure 8-5 Exponential Smoothing dialog box E Select men and move it into the Variables list. [. . . ] You must difference such a series until it is stationary before you can identify the process. Autoregressive processes have an exponentially declining ACF and spikes in the first one or more lags of the PACF. The number of spikes indicates the order of the autoregression. Moving average processes have spikes in the first one or more lags of the ACF and an exponentially declining PACF. [. . . ]