Chapter 4 - Study Module
Given an actual demand of 103, a previous forecast value of 99, and an alpha of .4, the exponential smoothing forecast for the next period would be: A) 101.6 B) 100.6 C) 97.4
A) 100.6
Demand for a certain product is forecast to be 800 units per month, averaged over all 12 months of the year. The product follows a seasonal pattern, for which the January monthly index is 1.25. What is the seasonally-adjusted sales forecast for January? A) 1000 units B) 640 units C) 798.75 units
A) 1000 units The seasonally-adjusted sales forecast for January is 1000 units. To calculate a seasonally-adjusted sales forecast you take the product forecast (in this case 800) and multiply that by the monthly index (in this case 1.25). Thus, 800 * 1.25 = 1000.
If demand is 106 during January, 120 in February, 134 in March, and 142 in April, what is the 3-month simple moving average for May? A) 132 B) 138 C) 126
A) 132 The 3-month moving average for May is 132. The moving average is calculated by summing the relevant monthly demand reports and dividing by the months included in the model. In this case, we are calculating a three month moving average for May so we will use the months of February (120), March (134), and April (142) in our calculation. Therefore: 120+134+142 = 396 396/3 = 132 Moving Average = 132
Quantitative methods of forecasting include A) Exponential smoothing B) Consumer market survey C) Sales force composite
A) Exponential smoothing Quantitative methods of forecasting include exponential smoothing. Consumer market surveys and sales force composites are both considered qualitative methods.
Which time-series model assumes that demand in the next period will be equal to the most recent period's demand? A) Naïve approach B) Exponential smoothing approach C) Moving average approach
A) Naïve approach The time-series model that assumes demand in the next period will be equal to the most recent period's demand is the Naïve approach. The Naïve approach is the simplest forecasting method because it assumes that future demand will equal the last period's demand. The moving average approach, on the other hand, uses the average demand across the most recent periods of data (e.g. quarterly, annually, etc.) to forecast future demand. The exponential smoothing approach is a complicated forecasting approach that uses statistical weights for individual data points.
Forecasts are usually classified into three categories including: A) Short-range, medium-range, and long-range B) Departmental, organizational, and industrial C) Strategic, tactical, and operational
A) Short-range, medium-range, and long-range
Forecasts used for new product planning, capital expenditures, facility location or expansion, and R&D typically utilize a__________ A) long-range time horizon B) medium-range time horizon C) short-range time horizon
A) long-range time horizon Forecasts used for new product planning, capital expenditures, facility location or expansion, and R&D typically utilize a long-range time horizon. Long-range forecasts have a time span that is longer than 3 years. Long range forecasts are used in planning for new products, capital expenditures, and facility planning. Short-range forecasts have a time span of up to 1 year, but are generally less than 3 months. Short-range forecasts are used to schedule jobs, determine workforce levels, and planning purchases. Medium-range forecasts have a time span that ranges from 3 months to 3 years. Medium-range forecasts are used to plan production cycles, determine budgets, and make operation level decisions.
A seasonal index for a monthly series is about to be calculated on the basis of three years' accumulation of data. The three previous July values were 110, 150, and 130. The average over all months is 190. The approximate seasonal index for July is: A) 1.462 B) 0.684 C) 0.487
B) 0.684 The approximate seasonal index for July is 0.684. The seasonal index is calculated by dividing a month's actual average demand by the average demand over all months. Thus, in this case: Step 1 - Calculate average historical demand. To do this, we must first obtain the actual demand during July (in this case 110, 150, 130) and divide by the number of months on record (in this case 3). Thus, average July demand is calculated as 110 + 150 + 130 = 390/3 = 130 Step 2 - Calculate seasonal index by taking monthly average (130) and dividing by average demand over all months (190). Seasonal index for July is 130/190 = 0.684
The last four months of sales were 8, 10, 15, and 9 units. The last four forecasts were 5, 6, 11, and 12 units. The Mean Absolute Deviation (MAD) is: A) 9 B) 3.5 C) 10.5
B) 3.5 The Mean Absolute Deviation (MAD) is 3.5. The mean absolute deviation is designed to provide a measure of overall forecast error for the model. It does this by taking the sum of the absolute values of the individual forecast errors and dividing by the number of data periods. The last four months sales were 8, 10, 15, and 9 units. The forecasts for these same months were 5, 6, 11, and 12 units. Forecast errors are calculated using the equation demand - forecast. In this case, that would be 8 - 5 = 3; 10 - 6 = 4; 15 - 11 = 4; 9 - 12 = -3. Therefore: 3+4+4+3 = 14 14/4 = 3.5
A time-series trend equation is 25.3 + 2.1X. What is your forecast for period 7? A) 27.4 B) 40.0 C) 25.3
B) 40.0 The forecast for period 7 is 40. This is determined by solving the equation 25.3 + 2.1X, where X = time period. In this case we are interested in period 7. Therefore: 25.3 + 2.1(7) =40 25.3 + 14.7 = 40
Given an actual demand of 61, a previous forecast value of 58, and an alpha of .3, the exponential smoothing forecast for the next period would be: A) 65.5 B) 58.9 C) 57.1
B) 58.9 The forecast for the next period would be 58.9. The simple exponential smoothing forecast model uses the following equation: Last period's forecast + α(Last period's demand - last period's forecast), where α = the smoothing constant. Therefore, in this case: Last period's forecast = 58 α = .3 Last period's demand = 61 58 + .3(61 - 58) = 58.9
Given last periods forecast of 65, and last periods demand of 62, what is the simple exponential smoothing forecast with an alpha of .4 for the next period? A) 63.2 B) 65 C) 63.8
C) 63.8 The forecast for the next period would be 63.8. The simple exponential smoothing forecast model uses the following equation: Last periods forecast + α(Last periods demand - last periods forecast), where α = the smoothing constant. Therefore, in this case: Last periods forecast = 65 α = .4 Last periods demand = 62 65 + .4 (62 - 65) = 63.8
Which of the following statements about time-series forecasting is true? A) Because it accounts for trends, cycles, and seasonal patterns, it is always more powerful than associative forecasting. B) It is based on the assumption that the analysis of past demand helps predict future demand. C) It is based on the assumption that future demand will be the same as past demand.
B) It is based on the assumption that the analysis of past demand helps predict future demand. The statement indicating that time-series forecasts are based on the assumption that the analysis of past demand helps predict future demand is true. While time-series forecasts do utilize past demand in the predictive model, the approach does not make the assumption that future demand will be the same as past demand. Time-series forecasts include trends, seasonality, cycles, and random variation so forecasts can increase, decrease, or stay the same as past demand. The quantitative method known as the naïve method makes the assumption that future demand will be the same as past demand. Associative models, such as regression models, are considered more powerful than time-series models because they do not rely solely on historical values for forecasted variables.
Which of the following uses three types of participants: decision makers, staff personnel, and respondents? A) Sales force composites B) The Delphi method C) Executive opinions
B) The Delphi Method The Delphi method uses three types of participants: decision makers, staff personnel, and respondents to make forecasts. Sales force composites are a forecasting technique based on salespersons' estimates of expected sales. Executive opinions are a forecasting technique that uses the opinion of a small group of high-level managers to form a group estimate of demand.
A regression model is used to forecast sales based on advertising dollars spent. The regression line is y=500+35x and the coefficient of determination is .90. Which is the best statement about this forecasting model? A) For every $35 spent on advertising, sales increase by $1. B) The correlation between sales and advertising is positive. C) Even if no money is spent on advertising, the company realizes $35 of sales.
B) The correlation between sales and advertising is positive. The best statement about this forecasting model is that the correlation between sales and advertising is positive. In this example the relationship between coefficients is expressed as a positive (+), which indicates a positive correlation between sales and advertising. The equation does not give us enough information to predict an exact relationship between dollars spent on advertising and ultimate sales.
For a given product demand, the time-series trend equation is 53 - 4X. The negative sign on the slope of the equation: A) is a mathematical impossibility B) is an indication that product demand is declining C) is an indication that the cumulative error will be negative
B) is an indication that product demand is declining The negative sign on the slope of the equation is an indication that product demand is declining. A negative slope indicates a downward trend for the regression line, which would indicate that demand is declining across time periods. While the regression equation, like other quantitative methods, includes statistical error, this is not indicated in the negative slope. Furthermore, a negative slope is mathematically possible.
The tracking signal is the__________ A) mean absolute deviation B) ratio of cumulative error/MAD C) standard error of the estimate
B) ratio of cumulative error/MAD The tracking signal is the ratio of the cumulative error/MAD. A tracking signal is a measure of how well a forecast is predicting actual demand values. The standard formula used to provide a tracking signal is dividing the cumulative error by the mean absolute deviation. This is represented as Tracking signal = cumulative forecast error/mean absolute deviation The mean absolute deviation (MAD) is designed to provide a measure of overall forecast error for the forecast model. It does this by taking the sum of the absolute values of the individual forecast errors and dividing by the number of data periods. The standard error of the estimate is designed to provide a measure of variability around the regression line.
Which of the following smoothing constants would make an exponential smoothing forecast equivalent to a naïve forecast? A) .5 B) 0 C) 1.0
C) 1.0 The smoothing constant that would make an exponential smoothing forecast equivalent to a naïve forecast is 1.0. A smoothing constant value of 1.0 suggests that the forecast for the next period is exactly the same as the forecast for this period's demand, which is the same as the naïve forecast model. A smoothing constant is a weighting factor applied in an exponential smoothing forecast to improve accuracy. The smoothing constant can range from 0 to 1, but most frequently the forecaster chooses a value between .1 and .5.
Given forecast errors of -1, 4, 8, and -3, what is the mean absolute deviation? A) 16 B) 8 C) 4
C) 4 The mean absolute deviation is 4. The mean absolute deviation is designed to provide a measure of overall forecast error for the model. It does this by taking the sum of the absolute values of the individual forecast errors and dividing by the number of data periods. In this case, 1+4+8+3 = 16 16/4 = 4
Given the following data about monthly demand, what is the approximate forecast for May using a four month moving average? November = 39 December = 36 January = 40 February = 42 March = 48 April = 46 A) 39 B) 42 C) 44
C) 44 The four-month moving average is 44. The moving average is calculated by summing the relevant monthly demand reports and dividing by the months included in the model. In this case, we are calculating a four month moving average for May so we will use the months of January (40), February (42), March (48), and April (46) in our calculation. Therefore: 40+42+48+46 = 176 176/4 = 44 Moving Average = 44
The last four weekly values of sales were 80, 100, 105, and 90 units. The last four forecasts were 60, 80, 95, and 75 units. These forecasts illustrate: A) Qualitative methods B) Trend projections C) Bias
C) Bias These forecasts illustrate bias. Bias is a form of measurement error that occurs when forecasts are consistently greater or less than actual values. Trend projections fit a trend line to a series of historical data points and then projects the line into the future to help forecast future demand. While we were given prior demand, we were not given data to make future projections. Qualitative methods of forecasting rely on experience and intuition rather than historical data.
A forecast that projects a company's sales is a(n): A) Economic forecast B) Technological forecast C) Demand forecast
C) Demand forecast A forecast that projects a company's sales is a demand forecast. Demand forecasts (also called sales forecasts) are projections of demand for a company's products or services. Demand forecasts impact a company's production, capacity, and scheduling systems. Economic forecasts utilize indicators like inflation rates, money supplies, and housing starts to understand business cycles. Technological forecasts are concerned with rates of technological progress, which can result in the birth of new products and opportunities.
The primary purpose of the mean absolute deviation (MAD) in forecasting is to: A) Eliminate forecast errors B) Seasonally adjust the forecast C) Measure forecast accuracy
C) Measure forecast accuracy The primary purpose of the mean absolute deviation in forecasting is to measure forecast accuracy. The mean absolute deviation is designed to provide a measure of overall forecast error for the model. It does this by taking the sum of the absolute values of the individual forecast errors and dividing by the number of data periods. While the mean absolute deviation does provide a measure of forecast errors and forecast accuracy, it does not eliminate forecast errors or seasonally adjust forecasts.
The degree or strength of a relationship between two variables is shown by the__________ A) alpha B) mean absolute deviation C) correlation coefficient
C) correlation coefficient
Time-series patterns that repeat themselves after a period of days or weeks are called __________ A) cycles B) trends C) seasonality
C) seasonality Time-series patterns that repeat themselves after a period of days or weeks are called seasonality. Seasonality is a data pattern that repeats itself after a period of time (days, weeks, months, quarters, etc.). Trend is a gradual upward or downward movement of the data over time. Cycles are patterns in data that occur over longer time horizons such as multiple years.