Under what conditions would you prefer a simple exponential smoothing model to the moving averages method for forecasting a time series?
Submit a Word document with your responses and be sure to also attach any relevant Excel files with your submission.
Chapter 12 Exercises
Under what conditions would you prefer a simple exponential smoothing model to the moving averages method for forecasting a time series?
Suppose that monthly data on some time series vari-able exhibit obvious seasonality. Can you use moving averages, with any appropriate span, to track the sea-sonality well? Explain why or why not.
Suppose that quarterly data on some time series variable exhbit obvious seasonality, although the seasonal pattern varies somewhat from year to year. Which method will work best: Winters’ method or regression with dummy variables for quarters (and possibly a time variable for trend)? Why?
The file P12_60.xlsx lists annual revenues (in millions of dollars) for Nike. Create a time series graph of these data. Then superimpose a trend line with Excel’s Trend-line option. Which of the possible Trendline options seems to provide the best fit? Using this option, what are your forecasts for the next two years?
The file P12_61.xlsx contains annual data on carbon dioxide (CO2) levels since 1959, measured at the Mauna Loa Observatory in Hawaii. Fit linear, exponential, and quadratic (polynomial of order 2) trends to these data. In terms of MAD, which fit is best? Using the best fit, forecast CO2 levels for the next 10 years