Generico has been manufacturing videotapes since 1982. The 3-hour VHS format is by far the largest component of their product mix. Historical demand for these items since 1992 is listed below <data attached>.
Don Wirtz, general managing partner of Generico is concerned about the state of the current market for VHS format tapes. If demand is seen to be falling, Wirtz may need to consider diversification, if demand appears to be strong, Wirtz may need to consider ways to enhance the competitiveness of his manufacturing enterprise.
QUESTION: Please provide Don with monthly forecasts for the years 2004 and 2005, while considering all relevant phenomena present in the historical demand pattern....
We have just started the semester, so the techniques we have discussed are limited to:
1) Time series analysis: SimpleMovingAverage, WMA, Exponential Smoothing
3) Forecast errors: absolute deviation, mean absolute deviation (MAD), and tracking signal
4) Single linear regression
5) Seasonalized time series regression
I'm not sure how to approach this. How do I know what technique is best? do I need to try more than one and measure the error (MAD or tracking) to see which is most accurate? What "phenomena" do I need to consder? HELP....
Yes, you should try each of the techniques you've learned, calculate the MAD for each one, and determine which is the best method (i.e. has lowest MAD). Use the best method to forecast data for 2004-2005 (to be thorough, include an explanation for why you chose that method, including the calculations you made). You also need to consider possible seasonality of the data (a potential ...