Chap0015 - Chapter 15 - Demand Management and Forecasting...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Chapter 15 - Demand Management and Forecasting CHAPTER 15 DEMAND MANAGEMENT AND FORECASTING Review and Discussion Questions 1. What is the difference between dependent and independent demand? Independent demand is forecasted item demand that occurs separately from the demand for other items. Dependent demand is calculated from the demand for another item. The difference lies in the way the two demands are determined. 2. Examine Exhibit 15.4 and suggest which model you might use for (1) bathing suit demand, (2) demand for new houses, (3) electrical power usage, (4) new plant expansion plans. While any of the models in Exhibit 15.4 can potentially be used to forecast any of the items, the following models are generally appropriate: (1) Bathing suit demand could be forecasted using exponential smoothing. The time horizon is short, model complexity and cost is low, model accuracy is fair and data requirements are very low. (2) Demand for new houses can be forecasted using linear regression. The time horizons are long, model complexity is medium high, model accuracy is medium high and data requirements are high. (3) Causal regression models might be used to forecast electrical power usage. The time horizon is long, model complexity is fairly high, model accuracy is high and data requirements are high. (4) New plant expansion plans can be forecast using qualitative forecasting techniques. This takes into account nonquantifible issues when planning plant expansion. 3. What is the logic in the least squares method of linear regression analysis? The least squares method fits a line to the data which minimizes the sum of the squared error between particular points on a regression line and actually observed data lying in the same X plane. If a central point (X-bar, Y-bar) is located in a scatter plot, an infinitely large number of regression lines could be found to represent the data equally well in terms of absolute error. However, there is only one, unique regression line that minimizes the sum of the square errors. Explain the procedure to create a forecast using the decomposition method of least squares regression. The steps are as follows: I. Decompose the time series into the components. a. Find the seasonal component. b. Deseasonalize the demand. c. Find the trend component 174
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Chapter 15 - Demand Management and Forecasting II. Forecast future values of each component. a. Project trend components into the future. b. Multiply trend component by seasonal component. 4. Give some very simple rules you might use to manage demand for a firm’s product. (An example is “limited to stock on hand.”) Demand management can be in terms of: order control—“limited to stock on hand,” lead time —“allow six weeks for delivery,” need—“supply the parts to inoperative units first,” time open—“close up early every day,” or “closed on Saturdays,” plus others as mentioned in the text such as price cuts, incentives, promotions, etc. 5.
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 07/17/2011 for the course MBA 587 taught by Professor None during the Spring '11 term at Missouri (Mizzou).

Page1 / 32

Chap0015 - Chapter 15 - Demand Management and Forecasting...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online