1. 1. Forecasting techniques generally assume an existing causal system that will continue to exist in the future. True False 1. Forecasting techniques generally assume an existing causal system that will continue to exist in the future. TRUE Forecasts depend on the rules of the game remaining reasonably constant. 2. 2. For new products in a strong growth mode, a low alpha will minimize forecast errors when using exponential smoothing techniques. True False 2. For new products in a strong growth mode, a low alpha will minimize forecast errors when using exponential smoothing techniques. FALSE 3. 3. Once accepted by managers, forecasts should be held firm regardless of new input since many plans have been made using the original forecast. True False 3. Once accepted by managers, forecasts should be held firm regardless of new input since many plans have been made using the original forecast. FALSE 4. Flexibility to accommodate major changes is important to good forecasting. 4. Forecasts for groups of items tend to be less accurate than forecasts for individual items because forecasts for individual items don't include as many influencing factors. True False 4. Forecasts for groups of items tend to be less accurate than forecasts for individual items because forecasts for individual items don't include as many influencing factors. FALSE 5. Forecasting for an individual item is more difficult than forecasting for a number of items. 5. Forecasts help managers plan both the system itself and provide valuable information for using the system. True False 5. Forecasts help managers plan both the system itself and provide valuable information for using the system. TRUE 6. Both planning and use are shaped by forecasts. 6. Organizations that are capable of responding quickly to changing requirements can use a shorter forecast horizon and therefore benefit from more accurate forecasts. True False 6. Organizations that are capable of responding quickly to changing requirements can use a shorter forecast horizon and therefore benefit from more accurate forecasts. TRUE 7. If an organization can react quicker, its forecasts need not be so long term. 7. When new products or services are introduced, focus forecasting models are an attractive option. True False 7. When new products or services are introduced, focus forecasting models are an attractive option. FALSE Because focus forecasting models depend on historical data, they're not so attractive for newly introduced products or services. 8. 8. The purpose of the forecast should be established first so that the level of detail, amount of resources, and accuracy level can be understood. True False 8. The purpose of the forecast should be established first so that the level of detail, amount of resources, and accuracy level can be understood. TRUE All of these considerations are shaped by what the forecast will be used for. 9. 9. Forecasts based on time series (historical) data are referred to as associative forecasts. True False 9. Forecasts based on time series (historical) data are referred to as associative forecasts. FALSE 10. Forecasts based on time series data are referred to as time-series forecasts. 10. Time series techniques involve identification of explanatory variables that can be used to predict future demand. True False 10. Time series techniques involve identification of explanatory variables that can be used to predict future demand. FALSE 11. Associate forecasts involve identifying explanatory variables. 11. A consumer survey is an easy and sure way to obtain accurate input from future customers since most people enjoy participating in surveys. True False 11. A consumer survey is an easy and sure way to obtain accurate input from future customers since most people enjoy participating in surveys. FALSE 12. Most people do not enjoy participating in surveys. 12. The Delphi approach involves the use of a series of questionnaires to achieve a consensus forecast. True False 12. The Delphi approach involves the use of a series of questionnaires to achieve a consensus forecast. TRUE A consensus among divergent perspectives is developed using questionnaires. 13. 13. Exponential smoothing adds a percentage (called alpha) of last period's forecast to estimate next period's demand. True False 13. Exponential smoothing adds a percentage (called alpha) of last period's forecast to estimate next period's demand. FALSE Exponential smoothing adds a percentage to the last period's forecast error. 14. 14. The shorter the forecast period, the more accurately the forecasts tend to track what actually happens. True False 14. The shorter the forecast period, the more accurately the forecasts tend to track what actually happens. TRUE Long-term forecasting is much more difficult to do accurately. 15. 15. Forecasting techniques that are based on time series data assume that future values of the series will duplicate past values. True False 15. Forecasting techniques that are based on time series data assume that future values of the series will duplicate past values. FALSE Time-series forecast assume that future patterns in the series will mimic past patterns in the series. 16. 16. Trend adjusted exponential smoothing uses double smoothing to add twice the forecast error to last period's actual demand. True False 16. Trend adjusted exponential smoothing uses double smoothing to add twice the forecast error to last period's actual demand. FALSE Trend adjusted smoothing smoothes both random and trend-related variation. 17. 17. Forecasts based on an average tend to exhibit less variability than the original data. True False 17. Forecasts based on an average tend to exhibit less variability than the original data. TRUE Averaging is a way of smoothing out random variability. 18. 18. The naive approach to forecasting requires a linear trend line. True False 18. The naive approach to forecasting requires a linear trend line. FALSE The naïve approach is useful in a wider variety of settings. 19. 19. The naive forecast is limited in its application to series that reflect no trend or seasonality. True False 19. The naive forecast is limited in its application to series that reflect no trend or seasonality. FALSE 20. When a trend or seasonality is present, the naïve forecast is more limited in its application. 20. The naive forecast can serve as a quick and easy standard of comparison against which to judge the cost and accuracy of other techniques. True False 20. The naive forecast can serve as a quick and easy standard of comparison against which to judge the cost and accuracy of other techniques. TRUE Often the naïve forecast performs reasonably well when compared to more complex techniques. 21. 21. A moving average forecast tends to be more responsive to changes in the data series when more data points are included in the average. True False 21. A moving average forecast tends to be more responsive to changes in the data series when more data points are included in the average. FALSE More data points reduce a moving average forecast's responsiveness. 22. 22. In order to update a moving average forecast, the values of each data point in the average must be known. True False 22. In order to update a moving average forecast, the values of each data point in the average must be known. TRUE The moving average cannot be updated until the most recent value is known. 23. 23. Forecasts of future demand are used by operations people to plan capacity. True False 23. Forecasts of future demand are used by operations people to plan capacity. TRUE Capacity decisions are made for the future and therefore depend on forecasts. 24. 24. An advantage of a weighted moving average is that recent actual results can be given more importance than what occurred a while ago. True False 24. An advantage of a weighted moving average is that recent actual results can be given more importance than what occurred a while ago. TRUE Weighted moving averages can be adjusted to make more recent data more important in setting the 25. forecast. 25. Exponential smoothing is a form of weighted averaging. True False 25. Exponential smoothing is a form of weighted averaging. TRUE 26. The most recent period is given the most weight, but prior periods also factor in. 26. A smoothing constant of .1 will cause an exponential smoothing forecast to react more quickly to a sudden change than a smoothing constant value of .3. True False 26. A smoothing constant of .1 will cause an exponential smoothing forecast to react more quickly to a sudden change than a smoothing constant value of .3. FALSE Smaller smoothing constants result in less reactive forecast models. 27. 27. The T in the model TAF = S+T represents the time dimension (which is usually expressed in weeks or months). True False 27. The T in the model TAF = S+T represents the time dimension (which is usually expressed in weeks or months). FALSE The T represents the trend dimension. 28. 28. Trend adjusted exponential smoothing requires selection of two smoothing constants. True False 28. Trend adjusted exponential smoothing requires selection of two smoothing constants. TRUE 29. One is for the trend and one is for the random error. 29. An advantage of "trend adjusted exponential smoothing" over the "linear trend equation" is its ability to adjust over time to changes in the trend. True False 29. An advantage of "trend adjusted exponential smoothing" over the "linear trend equation" is its ability to adjust over time to changes in the trend. TRUE A linear trend equation assumes a constant trend; trend adjusted smoothing allows for changes in the underlying trend. 30. 30. A seasonal relative (or seasonal indexes) is expressed as a percentage of average or trend. True False 30. A seasonal relative (or seasonal indexes) is expressed as a percentage of average or trend. TRUE Seasonal relatives are used when the seasonal effect is multiplicative rather than additive. 31. 31. In order to compute seasonal relatives, the trend of past data must be computed or known which means that for brand new products this approach can't be used. True False 31. In order to compute seasonal relatives, the trend of past data must be computed or known which means that for brand new products this approach can't be used. TRUE Computing seasonal relatives depends on past data being available. 32. 32. Removing the seasonal component from a data series (de-seasonalizing) can be accomplished by dividing each data point by its appropriate seasonal relative. True False 32. Removing the seasonal component from a data series (de-seasonalizing) can be accomplished by dividing each data point by its appropriate seasonal relative. TRUE Deseasonalized data points have been adjusted for seasonal influences. 33. 33. If a pattern appears when a dependent variable is plotted against time, one should use time series analysis instead of regression analysis. True False 33. If a pattern appears when a dependent variable is plotted against time, one should use time series analysis instead of regression analysis. TRUE Patterns reflect influences such as trends or seasonality that go against regression analysis assumptions. 34. 34. Curvilinear and multiple regression procedures permit us to extend associative models to relationships that are non-linear or involve more than one predictor variable. True False 34. Curvilinear and multiple regression procedures permit us to extend associative models to relationships that are non-linear or involve more than one predictor variable. TRUE Regression analysis can be used in a variety of settings. 35. 35. The sample standard deviation of forecast error is equal to the square root of MSE. True False 35. The sample standard deviation of forecast error is equal to the square root of MSE. TRUE The MSE is equal to the sample variance of the forecast error. 36. 36. Correlation measures the strength and direction of a relationship between variables. True False 36. Correlation measures the strength and direction of a relationship between variables. TRUE The association between two variations is summarized in the correlation coefficient. 37. 37. MAD is equal to the square root of MSE which is why we calculate the easier MSE and then calculate the more difficult MAD. True False 37. MAD is equal to the square root of MSE which is why we calculate the easier MSE and then calculate the more difficult MAD. FALSE MAD is the mean absolute deviation. 38. 38. In exponential smoothing, an alpha of 1.0 will generate the same forecast that a naïve forecast would yield. True False 38. In exponential smoothing, an alpha of 1.0 will generate the same forecast that a naïve forecast would yield. TRUE With alpha equal to 1 we are using a naïve forecasting method. 39. 39. A forecast method is generally deemed to perform adequately when the errors exhibit an identifiable pattern. True False 39. A forecast method is generally deemed to perform adequately when the errors exhibit an identifiable pattern. FALSE Forecast methods are generally considered to be performing adequately when the errors appear to be randomly distributed. 40. 40. A control chart involves setting action limits for cumulative forecast error. True False 40. A control chart involves setting action limits for cumulative forecast error. FALSE Control charts set action limits for the tracking signal. 41. 41. A tracking signal focuses on the ratio of cumulative forecast error to the corresponding value of MAD. True False 41. A tracking signal focuses on the ratio of cumulative forecast error to the corresponding value of MAD. TRUE Large absolute values of the tracking signal suggest a fundamental change in the forecast model's performance. 42. 42. The use of a control chart assumes that errors are normally distributed about a mean of zero. True False 42. The use of a control chart assumes that errors are normally distributed about a mean of zero. TRUE 43. Over time, a forecast model's tracking signal should fluctuate randomly about a mean of zero. 43. Bias exists when forecasts tend to be greater or less than the actual values of time series. True False 43. Bias exists when forecasts tend to be greater or less than the actual values of time series. TRUE A tendency in one direction is defined as bias. 44. 44. Bias is measured by the cumulative sum of forecast errors. True False 44. Bias is measured by the cumulative sum of forecast errors. TRUE Bias would result in the cumulative sum of forecast errors being large in absolute value. 45. 45. Seasonal relatives can be used to de-seasonalize data or incorporate seasonality in a forecast. True False 45. Seasonal relatives can be used to de-seasonalize data or incorporate seasonality in a forecast. TRUE Seasonal relatives are used to de-seasonalize data to forecast future values of the underlying trend, and they are also used to re-seasonalize de-seasonalized forecasts. 46. 46. The best forecast is not necessarily the most accurate. True False 46. The best forecast is not necessarily the most accurate. TRUE More accuracy often comes at too high a cost to be worthwhile. 47. 47. A proactive approach to forecasting views forecasts as probable descriptions of future demand, and requires action to be taken to meet that demand. True False 47. A proactive approach to forecasting views forecasts as probable descriptions of future demand, and requires action to be taken to meet that demand. FALSE Proactive approaches involve taking action to influence demand. 48. 48. Simple linear regression applies to linear relationships with no more than three independent variables. True False 48. Simple linear regression applies to linear relationships with no more than three independent variables. FALSE 49. Simple linear regression involves only one independent variable. 49. An important goal of forecasting is to minimize the average forecast error. True False 49. An important goal of forecasting is to minimize the average forecast error. FALSE Regardless of the model chosen, so long as there is no fundamental bias average forecast error will be zero. 50. 50. Forecasting techniques such as moving averages, exponential smoothing, and the naive approach all represent smoothed (averaged) values of time series data. True False 50. Forecasting techniques such as moving averages, exponential smoothing, and the naive approach all represent smoothed (averaged) values of time series data. FALSE The naïve approach involves no smoothing. 51. 51. In exponential smoothing, an alpha of .30 will cause a forecast to react more quickly to a large error than will an alpha of .20. True False 51. In exponential smoothing, an alpha of .30 will cause a forecast to react more quickly to a large error than will an alpha of .20. TRUE Larger values for alpha result in more responsive models. 52. 52. Forecasts based on judgment and opinion don't include A. executive opinion B. salesperson opinion C. second opinions D. customer surveys E. Delphi methods C 53. 53. In business, forecasts are the basis for: A. capacity planning B. budgeting C. sales planning D. production planning E. all of the above E 54. 54. Which of the following features would not generally be considered common to all forecasts? A. Assumption of a stable underlying causal system. B. Actual results will differ somewhat from predicted values. C. Historical data is available on which to base the forecast. D. Forecasts for groups of items tend to be more accurate than forecasts for individual items. E. Accuracy decreases as the time horizon increases. C 55. 55. Which of the following is not a step in the forecasting process? A. determine the purpose and level of detail required B. eliminate all assumptions C. establish a time horizon D. select a forecasting model E. monitor the forecast B 56. 56. Minimizing the sum of the squared deviations around the line is called: A. mean squared error technique B. mean absolute deviation C. double smoothing D. least squares estimation E. predictor regression D 57. 57. The two general approaches to forecasting are: A. mathematical and statistical B. qualitative and quantitative C. judgmental and qualitative D. historical and associative E. precise and approximation B 58. 58. Which of the following is not a type of judgmental forecasting? A. executive opinions B. sales force opinions C. consumer surveys D. the Delphi method E. time series analysis E 59. 59. Accuracy in forecasting can be measured by: A. MSE B. MRP C. MAPE D. MTM E. A & C E 60. 60. Which of the following would be an advantage of using a sales force composite to develop a demand forecast? A. The sales staff is least affected by changing customer needs. B. The sales force can easily distinguish between customer desires and probable actions. C. The sales staff is often aware of customers' future plans. D. Salespeople are least likely to be influenced by recent events. E. Salespeople are least likely to be biased by sales quotas. C 61. 61. Which phrase most closely describes the Delphi technique? A. associative forecast B. consumer survey C. series of questionnaires D. developed in India E. historical data C 62. 62. The forecasting method which uses anonymous questionnaires to achieve a consensus forecast is: A. sales force opinions B. consumer surveys C. the Delphi method D. time series analysis E. executive opinions C 63. 63. One reason for using the Delphi method in forecasting is to: A. avoid premature consensus (bandwagon effect) B. achieve a high degree of accuracy C. maintain accountability and responsibility D. be able to replicate results E. prevent hurt feelings A 64. 64. Detecting non-randomness in errors can be done using: A. MSEs B. MAPs C. Control Charts D. Correlation Coefficients E. Strategies C 65. 65. Gradual, long-term movement in time series data is called: A. seasonal variation B. cycles C. irregular variation D. trend E. random variation D 66. 66. The primary difference between seasonality and cycles is: A. the duration of the repeating patterns B. the magnitude of the variation C. the ability to attribute the pattern to a cause D. the direction of the movement E. there are only 4 seasons but 30 cycles A 67. 67. Averaging techniques are useful for: A. distinguishing between random and non-random variations B. smoothing out fluctuations in time series C. eliminating historical data D. providing accuracy in forecasts E. average people B 68. 68. Putting forecast errors into perspective is best done using A. Exponential smoothing B. MAPE C. Linear decision rules D. MAD E. Hindsight B 69. 69. Using the latest observation in a sequence of data to forecast the next period is: A. a moving average forecast B. a naive forecast C. an exponentially smoothed forecast D. an associative forecast E. regression analysis B 70. 70. For the data given below, what would the naive forecast be for the next period (period #5)? A. 58 B. 62 C. 59.5 D. 61 E. cannot tell from the data given D 71. 71. Moving average forecasting techniques do the following: A. immediately reflect changing patterns in the data B. lead changes in the data C. smooth variations in the data D. operate independently of recent data E. assist when organizations are relocating C 72. 72. Which is not a characteristic of simple moving averages applied to time series data? A. smoothes random variations in the data B. weights each historical value equally C. lags changes in the data D. requires only last period's forecast and actual data E. smoothes real variations in the data D 73. 73. In order to increase the responsiveness of a forecast made using the moving average technique, the number of data points in the average should be: A. decreased B. increased C. multiplied by a larger alpha D. multiplied by a smaller alpha E. eliminated if the MAD is greater than the MSE A 74. 74. A forecast based on the previous forecast plus a percentage of the forecast error is: A. a naive forecast B. a simple moving average forecast C. a centered moving average forecast D. an exponentially smoothed forecast E. an associative forecast D 75. 75. Which is not a characteristic of exponential smoothing? A. smoothes random variations in the data B. weights each historical value equally C. has an easily altered weighting scheme D. has minimal data storage requirements E. smoothes real variations in the data B 76. 76. Which of the following smoothing constants would make an exponential smoothing forecast equivalent to a naive forecast? A. 0 B. .01 C. .1 D. .5 E. 1.0 E 77. 77. Simple exponential smoothing is being used to forecast demand. The previous forecast of 66 turned out to be four units less than actual demand. The next forecast is 66.6, implying a smoothing constant, alpha, equal to: A. .01 B. .10 C. .15 D. .20 E. .60 C 78. 78. Given an actual demand of 59, a previous forecast of 64, and an alpha of .3, what would the forecast for the next period be using simple exponential smoothing? A. 36.9 B. 57.5 C. 60.5 D. 62.5 E. 65.5 D 79. 79. Given an actual demand of 105, a forecasted value of 97, and an alpha of .4, the simple exponential smoothing forecast for the next period would be: A. 80.8 B. 93.8 C. 100.2 D. 101.8 E. 108.2 C 80. 80. Which of the following possible values of alpha would cause exponential smoothing to respond the most quickly to forecast errors? A. 0 B. .01 C. .05 D. .10 E. .15 E 81. 81. A manager uses the following equation to predict monthly receipts: Yt = 40,000 + 150t. What is the forecast for July if t = 0 in April of this year? A. 40,450 B. 40,600 C. 42,100 D. 42,250 E. 42,400 A 82. 82. In trend-adjusted exponential smoothing, the trend adjusted forecast (TAF) consists of: A. an exponentially smoothed forecast and a smoothed trend factor B. an exponentially smoothed forecast and an estimated trend value C. the old forecast adjusted by a trend factor D. the old forecast and a smoothed trend factor E. a moving average and a trend factor A 83. 83. In the "additive" model for seasonality, seasonality is expressed as a ______________ adjustment to the average; in the multiplicative model, seasonality is expressed as a __________ adjustment to the average. A. quantity, percentage B. percentage, quantity C. quantity, quantity D. percentage, percentage E. qualitative, quantitative A 84. 84. Which technique is used in computing seasonal relatives? A. double smoothing B. Delphi C. Mean Squared Error (MSE) D. centered moving average E. exponential smoothing D 85. 85. A persistent tendency for forecasts to be greater than or less than the actual values is called: A. bias B. tracking C. control charting D. positive correlation E. linear regression A 86. 86. Which of the following might be used to indicate the cyclical component of a forecast? A. leading variable B. Mean Squared Error (MSE) C. Delphi technique D. exponential smoothing E. Mean Absolute Deviation (MAD) A 87. 87. The primary method for associative forecasting is: A. sensitivity analysis B. regression analysis C. simple moving averages D. centered moving averages E. exponential smoothing B 88. 88. Which term most closely relates to associative forecasting techniques? A. time series data B. expert opinions C. Delphi technique D. consumer survey E. predictor variables E 89. 89. Which of the following corresponds to the predictor variable in simple linear regression? A. regression coefficient B. dependent variable C. independent variable D. predicted variable E. demand coefficient C 90. 90. The mean absolute deviation (MAD) is used to: A. estimate the trend line B. eliminate forecast errors C. measure forecast accuracy D. seasonally adjust the forecast E. all of the above C 91. 91. Given forecast errors of 4, 8, and - 3, what is the mean absolute deviation? A. 4 B. 3 C. 5 D. 6 E. 12 C 92. 92. Given forecast errors of 5, 0, - 4, and 3, what is the mean absolute deviation? A. 4 B. 3 C. 2.5 D. 2 E. 1 B 93. 93. Given forecast errors of 5, 0, - 4, and 3, what is the bias? A. - 4 B. 4 C. 5 D. 12 E. 6 B 94. 94. Which of the following is used for constructing a control chart? A. mean absolute deviation (MAD) B. mean squared error (MSE) C. tracking signal (TS) D. bias E. none of the above B 95. 95. The two most important factors in choosing a forecasting technique are: A. cost and time horizon B. accuracy and time horizon C. cost and accuracy D. quantity and quality E. objective and subjective components C 96. 96. The degree of management involvement in short range forecasts is: A. none B. low C. moderate D. high E. total B 97. 97. Which of the following is not necessarily an element of a good forecast? A. estimate of accuracy B. timeliness C. meaningful units D. low cost E. written D 98. 98. Current information on _________ can have a significant impact on forecast accuracy: A. prices B. promotion C. inventory D. competition E. all of the above E 99. 99. A managerial approach toward forecasting which seeks to actively influence demand is: A. reactive B. proactive C. influential D. protracted E. retroactive B 100. 100. Customer service levels can be improved by better: A. mission statements B. control charting C. short term forecast accuracy D. exponential smoothing E. customer selection C 101. 101. Given the following historical data, what is the simple three-period moving average forecast for period 6? A. 67 B. 115 C. 69 D. 68 E. 68.67 D 102. 102. Given the following historical data and weights of .5, .3, and .2, what is the three-period moving average forecast for period 5? A. 144.20 B. 144.80 C. 144.67 D. 143.00 E. 144.00 B 103. 103. Use of simple linear regression analysis assumes that: A. Variations around the line are random. B. Deviations around the line are normally distributed. C. Predictions are to be made only within the range of observed values of the predictor variable. D. all of the above E. none of the above D 104. 104. Given forecast errors of - 5, - 10, and +15, the MAD is: A. 0 B. 10 C. 30 D. 175 E. none of these B 105. 105. Develop a forecast for the next period, given the data below, using a 3-period moving average. F₆ = (18 + 19 + 17)/3 = 18 106. 106. Consider the data below: Using exponential smoothing with alpha = .2, and assuming the forecast for period 11 was 80, what would the forecast for period 14 be? Using exponential smoothing with alpha = .2, and assuming the forecast for period 11 was 80, what would the forecast for period 14 be? (SEE IMAGE FOR THIS PART) Feedback: The forecast error in period 13 (2.84) is multiplied by the smoothing constant. This is then added to the period 13 forecast to get the period 14 forecast. 107. 107. A manager is using exponential smoothing to predict merchandise returns at a suburban branch of a department store chain. Given a previous forecast of 140 items, an actual number of returns of 148 items, and a smoothing constant equal to .15, what is the forecast for the next period? Feedb ack: The forecast error in the previous period is multiplied by the smoothing constant. This is then added to the previous period's forecast to get the upcoming period's forecast. 108. 108. A manager is using the equation below to forecast quarterly demand for a product: Yt = 6,000 + 80t where t = 0 at Q2 of last year Quarter relatives are Q1 = .6, Q2 = .9, Q3 = 1.3, and Q4 = 1.2. What forecasts are appropriate for the last quarter of this year and the first quarter of next year? For Q4 of this year t = 6 For Q1 of next year t = 7 (SEE IMAGE FOR THIS PART) Feedback: Adjust de-seasonalized forecasts by the quarterly seasonal relatives. 109. 109. Over the past five years, a firm's sales have averaged 250 units in the first quarter of each year, 100 units in the second quarter, 150 units in the third quarter, and 300 units in the fourth quarter. What are appropriate quarter relatives for this firm's sales? Hint: Only minimal computations are necessary. (SE E IMAGE FOR THIS PART) Feedback: Since a trend is not present, quarter relatives are simply a percentage of average, which is 200 units. 110. 110. A manager has been using a certain technique to forecast demand for gallons of ice cream for the past six periods. Actual and predicted amounts are shown below. Would a naive forecast have produced better results? (SEE IMAGE FOR THIS PART) Summary: Current method: MAD = 3.67; MSE = 16.8; 2s Control limits  8.2 (OK) Naïve method: MAD = 4.40; MSE = 30.0; 2s Control limits  11.0 (OK) Feedback: Either MSE or MAD should be computed for both forecasts and compared. The demand data are stable. Therefore, the most recent value of the series is a reasonable forecast for the next period of time, justifying the naïve approach. The current method is slightly superior both in terms of MAD and MSE. Either method would be considered in control. 111. 111. A new car dealer has been using exponential smoothing with an alpha of .2 to forecast weekly new car sales. Given the data below, would a naive forecast have provided greater accuracy? Explain. Assume an initial exponential forecast of 60 units in period 2 (i.e., no forecast for period 1). (SEE IMAGE) Summary: Exponential method: MAD = 1.70; MSE = 6.34 Naïve method: MAD = 3.00; MSE = 15.25 Feedback: The exponential forecast method appears to be superior because both MAD and MSE are lower when it is used. 112. 1 12. A CPA firm has been using the following equation to predict annual demand for tax audits: Yt = 55 + 4t Demand for the past few years is shown below. Is the forecast performing as well as it might? Explain. (SEE IMAGE FOR THIS PART) all values are within the limits. It seems, then, that only random variation is present, so one might say that the forecast is working. One might also observe that the first three errors are negative and the last three are positive. Although six observations constitute a relatively small sample, it may be that the errors are cycling, and this would be a matter to investigate with additional data. Feedback: Either a tracking signal or a control chart is called for. To conduct these assessments, it is necessary to generate the forecasts so that errors can be determined. 113. 113. Given the data below, develop a forecast for period 6 using a four-period weighted moving average and weights of .4, .3, .2 and .1 .4(17) + .3(19) + .2(18) + .1(20) = 18.1 Feedback: Multiply demand observed in periods 2 through 5 by the appropriate weight, then sum these products. 114. 114. Use linear regression to develop a predictive model for demand for burial vaults based on sales of caskets. A) Develop the regression equation. A) Develop the regression equation. (SEE IMAGE) Feedback: Least-squares estimation leads to this regression equation. 115. model for y as a function of x. 115. Given the following data, develop a linear regression (SEE IMAGE) Feedback: Least-squares estimation leads to this regression equation. 116. model for y as a function of x. (SEE IMAGE) 116. Given the following data, develop a linear regression Feedback: Least-squares estimation leads to this regression equation. 117. 117. Develop a linear trend equation for the data on bread deliveries shown below. Forecast deliveries for period 11 through 14. See Image 118. 118. The president of State University wants to forecast student enrollments for this academic year based on the following historical data: What is the forecast for this year using the naive approach? A. 18,750 B. 19,500 C. 21,000 D. 22,000 E. 22,800 C 119. 119. Demand for the last four months was: (SEE IMAGE) A) Predict demand for July using each of these methods: 1) a 3-period moving average 2) exponential smoothing with alpha equal to .20 (use a naive forecast for April for your first forecast) B) If the naive approach had been used to predict demand for April through June, what would MAD have been for those months? See Image 120. 120. A manager wants to choose one of two forecasting alternatives. Each alternative was tested using historical data. The resulting forecast errors for the two are shown in the table. Analyze the data and recommend a course of action to the manager. See Image Feedback: Although Alternative #1 has the smaller MSE, it appears to be cycling and steady; Alternative #2 errors after the first three periods are small or zero. For the last six periods, Alternative #2 was much better, suggesting that approach would be better. 121. 121. A manager uses this equation to predict demand: Yt = 20 + 4t. (t in problem are subscripted) Over the past 8 periods, demand has been as follows. Are the results acceptable? Explain. The president of State University wants to forecast student enrollments for this academic year based on the following historical data: See Part two of Image. Feedback: s = 2.10; 2s control limits are +/- 4.20. Although all values are within control limits, the errors may be exhibiting cyclical patterns, which would suggest nonrandomness. 122. 122. What is the forecast for this year using a four-year simple moving average? A. 18,750 B. 19,500 C. 21,000 D. 22,650 E. 22,800 123. What is the forecast for this year using exponential smoothing with alpha = 0.5, if the forecast for two years ago was 16,000? A. 18,750 B. 19,500 C. 21,000 D. 22,650 E. 22,800 124. What is the forecast for this year using the least squares trend line for these data? A. 18,750 B. 19,500 C. 21,000 D. 22,650 E. 22,800 125. What is the forecast for this year using trend adjusted (double) smoothing with alpha = . 05 and beta = 0.3, if the forecast for last year was 21,000, the forecast for two years ago was 19,000, and the trend estimate for last year's forecast was 1,500? A. 18,750 B. 19,500 C. 21,000 D. 22,650 E. 22,800 A 123. 123. What is the forecast for this year using exponential smoothing with alpha = 0.5, if the forecast for two years ago was 16,000? A. 18,750 B. 19,500 C. 21,000 D. 22,650 E. 22,800 B 124. 124. What is the forecast for this year using the least squares trend line for these data? A. 18,750 B. 19,500 C. 21,000 D. 22,650 E. 22,800 E 125. 125. What is the forecast for this year using trend adjusted (double) smoothing with alpha = .05 and beta = 0.3, if the forecast for last year was 21,000, the forecast for two years ago was 19,000, and the trend estimate for last year's forecast was 1,500? A. 18,750 B. 19,500 C. 21,000 D. 22,650 E. 22,800 D 126. The business analyst for Video Sales, Inc. wants to forecast this year's demand for DVD decoders based on the following historical data: (See Image) 126. What is the forecast for this year using the naive approach? A. 163 B. 180 C. 300 D. 420 E. 510 C 127. 127. What is the forecast for this year using a three-year weighted moving average with weights of .5, .3, and .2? A. 163 B. 180 C. 300 D. 420 E. 510 D 128. 128. What is the forecast for this year using exponential smoothing with alpha = .4, if the forecast for two years ago was 750? A. 163 B. 180 C. 300 D. 420 E. 510 E 129. 129. What is the forecast for this year using the least squares trend line for these data? A. 163 B. 180 C. 300 D. 420 E. 510 B 130. 130. What is the forecast for this year using trend adjusted (double) smoothing with alpha = 0.3 and beta = 0.2, if the forecast for last year was 310, the forecast for two years ago was 430, and the trend estimate for last year's forecast was -150? A. 162.4 B. 180.3 C. 301.4 D. 403.2 E. 510.0 A 131. Professor Very Busy needs to allocate time next week to include time for office hours. He needs to forecast the number of students who will seek appointments. He has gathered the following data: (See Image) 131. What is this week's forecast using the naive approach? A. 45 B. 50 C. 52 D. 65 E. 78 B 132. 132. What is this week's forecast using a three-week simple moving average? A. 49 B. 50 C. 52 D. 65 E. 78 D 133. 133. What is this week's forecast using exponential smoothing with alpha = .2, if the forecast for two weeks ago was 90? A. 49 B. 50 C. 52 D. 65 E. 77 E 134. 134. What is this week's forecast using the least squares trend line for these data? A. 49 B. 50 C. 52 D. 65 E. 78 A 135. 135. What is this week's forecast using trend adjusted (double) smoothing with alpha = 0.5 and beta = 0.1, if the forecast for last week was 65, the forecast for two weeks ago was 75, and the trend estimate for last week's forecast was -5? A. 49.3 B. 50.6 C. 51.3 D. 65.4 E. 78.7 C 136. A concert promoter is forecasting this year's attendance for one of his concerts based on the following historical data: (See Image) 136. What is this year's forecast using the naive approach? A. 22,000 B. 20,000 C. 18,000 D. 15,000 E. 12,000 B 137. 137. What is this year's forecast using a two-year weighted moving average with weights of .7 and .3? A. 19,400 B. 18,600 C. 19,000 D. 11,400 E. 10,600 A 138. 138. What is this year's forecast using exponential smoothing with alpha = .2, if last year's smoothed forecast was 15,000? A. 20,000 B. 19,000 C. 17,500 D. 16,000 E. 15,000 D 139. 139. What is this year's forecast using the least squares trend line for these data? A. 20,000 B. 21,000 C. 22,000 D. 23,000 E. 24,000 E 140. 140. The previous trend line had predicted 18,500 for two years ago, and 19,700 for last year. What was the mean absolute deviation (MAD) for these forecasts? A. 100 B. 200 C. 400 D. 500 E. 800 C 141. The dean of a school of business is forecasting total student enrollment for this year's summer session classes based on the following historical data: (See Image) 141. What is this year's forecast using the naive approach? A. 2,000 B. 2,200 C. 2,800 D. 3,000 E. none of the above D 142. 142. What is this year's forecast using a three-year simple moving average? A. 2,667 B. 2,600 C. 2,500 D. 2,400 E. 2,333 A 143. 143. What is this year's forecast using exponential smoothing with alpha = .4, if last year's smoothed forecast was 2600? A. 2,600 B. 2,760 C. 2,800 D. 3,840 E. 3,000 B 144. 144. What is the annual rate of change (slope) of the least squares trend line for these data? A. 0 B. 200 C. 400 D. 180 E. 360 E 145. 145. What is this year's forecast using the least squares trend line for these data? A. 3,600 B. 3,500 C. 3,400 D. 3,300 E. 3,200 C 146. The owner of Darkest Tans Unlimited in a local mall is forecasting this month's (October's) demand for the one new tanning booth based on the following historical data: (See Image) 146. What is this month's forecast using the naive approach? A. 100 B. 160 C. 130 D. 140 E. 120 B 147. 147. What is this month's forecast using a four-month weighted moving average with weights of .4, .3, .2, and .1? A. 120 B. 129 C. 141 D. 135 E. 140 C 148. 148. What is this month's forecast using exponential smoothing with alpha = .2, if August's forecast was 145? A. 144 B. 140 C. 142 D. 148 E. 163 A 149. 149. What is the monthly rate of change (slope) of the least squares trend line for these data? A. 320 B. 102 C. 8 D. -0.4 E. -8 C 150. 150. What is this month's forecast using the least squares trend line for these data? A. 1,250 B. 128.6 C. 102 D. 158 E. 164 D 151. 151. Which of the following mechanisms for enhancing profitability is most likely to result from improving short term forecast performance? A. increased inventory B. reduced flexibility C. higher-quality products D. greater customer satisfaction E. greater seasonality D 152. 152. Which of the following changes would tend to shorten the time frame for short term forecasting? A. bringing greater variety into the product mix B. increasing the flexibility of the production system C. ordering fewer weather-sensitive items D. adding more special-purpose equipment E. none of the above B 153. 153. Which of the following helps improve supply chain forecasting performance? A. contracts that require supply chain members to formulate long term forecasts B. penalties for supply chain members that adjust forecasts C. sharing forecasts or demand data across the supply chain D. increasing lead times for critical supply chain members E. increasing the number of suppliers at critical junctures in the supply chain C 154. 154. Inaccuracies in forecasts along the supply chain lead to: A. shortages or excesses of materials B. reduced customer service C. excess capacity D. missed deliveries E. all of the above E 155. 155. Which of the following is the most valuable piece of information the sales force can bring into forecasting situations? A. what customers are most likely to do in the future B. what customers most want to do in the future C. what customers' future plans are D. whether customers are satisfied or dissatisfied with their performance in the past E. what the salesperson's appropriate sales quota should be A 156. 156. What is this year's forecast using the naive approach? (See Image) 49 Feedback: This year's forecast would be last year's demand. 157. 157. What is this year's forecast using a four-year simple moving average? (45.5) Feedback: Average the four most recent periods of demand. 158. 158. What is this year's forecast using exponential smoothing with alpha = .25, if last year's smoothed forecast was 45? (45.8) Feedback: Multiply last year's forecast error by the smoothing constant. Add the resulting product to last year's forecast to get this year's forecast. 159. 159. What are this and next year's forecasts using the least squares trend line for these data? (62; 69) Feedback: Treat the earliest period as period 0 in formulating least squares coefficients, then proceed. 160. 160. What is this year's forecast using trend adjusted (double) smoothing with alpha = 0.2 and beta = 0.1, if the forecast for last year was 56, the forecast for two years ago was 46, and the trend estimate for last year's forecast was 7? (61.76) Feedback: Smooth both the trend and the forecasts using the appropriate smoothing coefficients. 161. 161. What is the centered moving average for spring two years ago? (See Image) 29
Feedback: First average the four periods beginning fall three years ago. Then average the four periods beginning spring two years ago. Then average these two averages. 162. 162. What is the spring's seasonal relative? (Spring 0.91) (Summer 0.63) (Fall 1.03) (Winter 1.43) Feedback: Divide data points by centered moving averages where moving averages are available. Average the resulting values across the seasons to get the seasonal relatives. 163. 163. What is the linear regression trend line for these data (t = 0 for spring, three years ago)? (y=17 + 2.33t) Feedback: Used de-seasonalized data points to formulate least squares coefficients. 164. 164. What is this year's seasonally adjusted forecast for each season? (Spring 40.93) (Summer 29.81) (Fall 51.14) (Winter 74.37) Feedback: First forecast each period's de-seasonalized value (e.g., Spring is period 12). Then multiply the de-seasonalized forecast by the appropriate seasonal relative