1. (a) What is forecasting? Why is it so important in the management of business firms and other enterprises? (b) What are the different types of forecasting? (c) How can the firm determine the most suitable forecasting method to use?
2. (a) Which type of smoothing technique is generally better? (b) How do we determine which of two smoothing techniques is better? (c) How can we forecast the values of a time series that contains a secular trend as well as strong seasonal and random variations?
3. Explain why it is still useful to pursue forecasting even though it is often off the mark by wide margins.
Problems
4. The following table presents data on three leading indicators for a three- month period. Construct the diffusion index from month 2 to 5. (In this problem, we have three leading indicators. The diffusion index from month 1 to 2 is 66.7 (=2/3) because two indicators move up and move down (see p. 236)
|
Month
|
Leading Indicator A
|
Leading Indicator B
|
Leading Indicator C
|
|
1
|
100
|
200
|
30
|
|
2
|
110
|
230
|
27
|
|
3
|
120
|
240
|
33
|
Appendix Problems
6. The following table reports the Consumer Price Index for the Los Angeles area on a monthly basis from January 1998 to December 2000 (base year = 1982 - 1984). Use Excel to forecast the index for all of 2000 using a three-and six-month average. Which provides a better forecast for 2000 using the data provided?
7. Forecast the data for 2000 again in Problem 1 with exponential smoothing with w = 0.3 and w = 0.7. Is this a better forecast than the moving average? (Compare RMSEs for moving average and exponential forecasts to answer "Is this a better forecast than the moving average" (see also p.234) Use 166.63, the mean of all 36 months, as the initial forecast for Jan. 1998 for both exponential smoothing forecast.