Question 1

Which of the following methods tells whether the forecast tends to be too high or too low?
A)MAD
B)MSE
C)MAPE
D)bias

Accepted Answer

The bias method tells us whether the forecast tends to be too high or too low by providing a measure of the forecast's tendency to overestimate or underestimate the actual values. A negative bias indicates that the forecast tends to underestimate the actual values, while a positive bias indicates that the forecast tends to overestimate the actual values. The MAD, MSE, and MAPE methods provide measures of the forecast's accuracy, but do not directly indicate if the forecast tends to be too high or too low.

Question 2

Which of the following methods gives an indication of the percentage of forecast error?
A)MAD
B)MSE
C)MAPE
D)decomposition

Accepted Answer

MAPE (Mean Absolute Percentage Error) calculates the percentage of forecast error by taking the absolute value of the difference between actual and forecasted values, dividing that by the actual value, and then averaging those values. This results in a percentage value that is easy to interpret and compare across different data sets. MAD (Mean Absolute Deviation) and MSE (Mean Squared Error) both give a measure of the overall magnitude of the forecast error, but they do not provide a percentage value that can be easily interpreted or compared. Decomposition is a method for separating a time series into its component parts (e.g. trend, seasonality, etc.), but it does not provide a measure of the accuracy of a forecast.

Question 3

A TIME SERIES forecasting model in which the forecast for the next period is the actual value for the current period is the
A)Delphi model.
B)Holt's model.
C)naïve model.
D)exponential smoothing model.

Accepted Answer

The naïve model assumes that the future value of a time series is equal to the current value. It is often used as a baseline model for comparison with more complex forecasting models.

Question 4

Sales for boxes of Girl Scout cookies over a 4-month period were forecasted as follows: 100, 120, 115, and 123.The actual results over the 4-month period were as follows: 110, 114, 119, 115.What was the MAD of the 4-month forecast?
A)0
B)5
C)7
D)108

Accepted Answer

MAD (Mean Absolute Deviation) is calculated by finding the absolute difference between the forecasted value and the actual value, summing those differences, and dividing by the number of periods.

Month 1: Absolute Difference = |100-110| = 10
Month 2: Absolute Difference = |120-114| = 6
Month 3: Absolute Difference = |115-119| = 4
Month 4: Absolute Difference = |123-115| = 8

MAD = (10+6+4+8)/4 = 7.

Therefore, the MAD of the 4-month forecast was 7. The best choice is C.

Question 5

As one increases the number of periods used in the calculation of a moving average
A)greater emphasis is placed on more recent data.
B)less emphasis is placed on more recent data.
C)the emphasis placed on more recent data remains the same.
D)it requires a computer to automate the calculations.

Accepted Answer

Increasing the number of periods in a moving average calculation spreads the emphasis over a larger set of data points, thereby reducing the impact of any single recent data point. This means less emphasis is placed on more recent data.

Question 6

Which of the following statements about the decomposition method is false?
A)The process of "deseasonalizing" involves multiplying by a seasonal index.
B)Dummy variables are used in a regression model as part of an additive approach to seasonality.
C)Computing seasonal indices is the first step of the decomposition method.
D)Data is "deseasonalized" after the trend line is found.

Accepted Answer

The answer of Which of the following statements about the...

Question 7

Enrollment in a particular class for the last four semesters has been 122, 128, 100, and 155 (listed from oldest to most recent).The best forecast of enrollment next semester, based on a three-semester moving average, would be
A)116.7.
B)168.3.
C)135.0.
D)127.7.

Accepted Answer

A three-semester moving average forecast is calculated by averaging the enrollments of the most recent three semesters: (128 + 100 + 155) / 3 = 127.7.

Question 8

The process of isolating linear trend and seasonal factors to develop more accurate forecasts is called
A)regression.
B)decomposition.
C)smoothing.
D)monitoring.

Accepted Answer

The process of isolating linear trend and seasonal factors is known as decomposition, which involves breaking down a time series into its component parts in order to develop more accurate forecasts. Regression, smoothing, and monitoring are all related concepts, but they do not specifically refer to the process of decomposing a time series.

Question 9

Daily demand for newspapers for the last 10 days has been as follows: 12, 13, 16, 15, 12, 18, 14, 12, 13, 15 (listed from oldest to most recent).Forecast sales for the next day using a two-day weighted moving average where the weights are 3 and 1.
A)14.5
B)13.5
C)14
D)12.25

Accepted Answer

To calculate the two-day weighted moving average, we use the formula:

Forecast = (w1 x Dn-1) + (w2 x Dn-2) / (w1 + w2)

Where:
- Dn-1 is the demand for the previous day
- Dn-2 is the demand for two days ago
- w1 is the weight for the most recent day
- w2 is the weight for the day before that

In this case, the weights are 3 and 1, meaning that we give more importance to the data from yesterday than from two days ago.

Plugging in the numbers, we get:

Forecast = (3 x 15) + (1 x 13) / (3 + 1) = 14.5

Therefore, the best choice is A) 14.5, which is the forecast demand for the next day.

Question 10

Daily demand for newspapers for the last 10 days has been as follows: 12, 13, 16, 15, 12, 18, 14, 12, 13, 15 (listed from oldest to most recent).Forecast sales for the next day using a three-day weighted moving average where the weights are 3, 1, and 1 (the highest weight is for the most recent number).
A)12.8
B)13.0
C)70.0
D)14.0

Accepted Answer

The three most recent days' sales are 13, 15, and 12. Using the weights 3, 1, and 1, the forecast is calculated as follows: [(3*12) + (1*15) + (1*13)] / (3+1+1) = (36 + 15 + 13) / 5 = 64 / 5 = 12.8. However, the correct calculation should be [(3*12) + (1*15) + (1*13)] / 5 = 64 / 5 = 12.8, which seems to be a mistake in the explanation. Correctly applying the weights to the most recent days (giving the highest weight to the most recent number) should actually be [(3*15) + (1*13) + (1*12)] / 5 = (45 + 13 + 12) / 5 = 70 / 5 = 14.

Question 11

Assume that you have tried three different forecasting models.For the first, the MAD = 2.5, for the second, the MSE = 10.5, and for the third, the MAPE = 2.7.We can then say
A)the third method is the best.
B)the second method is the best.
C)method two is the least preferred.
D)We cannot make a determination as to which method is best.

Accepted Answer

The comparison of forecasting models using MAD (Mean Absolute Deviation), MSE (Mean Squared Error), and MAPE (Mean Absolute Percentage Error) directly is not valid because these metrics measure different aspects of forecast errors and are on different scales. Therefore, without converting them into comparable metrics or knowing the context of their application, we cannot determine which method is best.

Question 12

Which of the following methods produces a particularly stiff penalty in periods with large forecast errors?
A)MAD
B)MSE
C)MAPE
D)decomposition

Accepted Answer

MSE (Mean Squared Error) produces a particularly stiff penalty for large forecast errors because it squares the errors before averaging them, thus giving more weight to larger errors compared to smaller ones.

Question 13

Which of the following is not considered one of the steps to developing the decomposition method?
A)compute seasonal indices using CMAs
B)find the equation of the trend line using the deseasonalized data
C)forecast for future periods using the trend line
D)add the seasonal index to the trend forecast

Accepted Answer

In decomposition, the seasonal index is multiplied, not added, to the trend forecast to adjust for seasonality.

Question 14

Demand for soccer balls at a new sporting goods store is forecasted using the following regression equation: Y = 98 + 2.2X where X is the number of months that the store has been in existence.
Let April be represented by X = 4.April is assumed to have a seasonality index of 1.15.What is the forecast for soccer ball demand for the month of April (rounded to the nearest integer)?
A)123
B)107
C)100
D)115

Accepted Answer

The answer of Demand for soccer balls at a new...

Question 15

Daily demand for newspapers for the last 10 days has been as follows: 12, 13, 16, 15, 12, 18, 14, 12, 13, 15 (listed from oldest to most recent).Forecast sales for the next day using a two-day moving average.
A)14
B)13
C)15
D)28

Accepted Answer

The two-day moving average is calculated by adding the demand for the current day and the previous day, and then dividing by 2. For example, the two-day moving average for day 10 is (15 + 13) / 2 = 14. The two-day moving average for day 11 is (14 + 12) / 2 = 13. Therefore, the forecast sales for the next day is 13.

Question 16

Enrollment in a particular class for the last four semesters has been 120, 126, 110, and 130 (listed from oldest to most recent).Develop a forecast of enrollment next semester using exponential smoothing with an alpha = 0.2.Assume that an initial forecast for the first semester was 120 (so the forecast and the actual were the same).
A)118.96
B)121.17
C)130
D)120

Accepted Answer

Exponential smoothing with alpha = 0.2 involves using the formula:
Forecast for next period = (1-alpha) * Actual value + alpha * Previous forecast

Using the given information, we can calculate the forecast for the second semester:
Forecast = (1-0.2) * 126 + 0.2 * 120 = 124.8

For the third semester:
Forecast = (1-0.2) * 110 + 0.2 * 124.8 = 114.24

For the fourth semester:
Forecast = (1-0.2) * 130 + 0.2 * 114.24 = 125.792

Therefore, the forecast for the next semester would be:
Forecast = (1-0.2) * Actual value + 0.2 * Previous forecast
         = (1-0.2) * 130 + 0.2 * 125.792
         = 121.17

So, the best choice is B, which is the closest option to the calculated forecast using exponential smoothing.

Question 17

Which of the following is not considered to be one of the components of a time series?
A)trend
B)seasonality
C)variance
D)cycles

Accepted Answer

The components of a time series are trend, seasonality, cycles, and random fluctuations/residuals. Variance is a measure of the variability or spread of the values in a time series, but it is not considered a component of the series itself.

Question 18

In picking the smoothing constant for an exponential smoothing model, we should look for a value that
A)produces a nice-looking curve.
B)equals the utility level that matches with our degree of risk aversion.
C)produces values which compare well with actual values based on a standard measure of error.
D)causes the least computational effort.

Accepted Answer

The best choice for picking the smoothing constant for an exponential smoothing model is the value that produces values which compare well with actual values based on a standard measure of error. This ensures that the model is accurately forecasting future values based on past trends. Option A is subjective and does not necessarily indicate accuracy. Option B might not apply to all situations and is not a standard method of selecting the smoothing constant. Option D is not a relevant concern when selecting the smoothing constant.

Question 19

A method to measure how well predictions fit actual data is
A)decomposition
B)smoothing
C)tracking signal
D)regression

Accepted Answer

The tracking signal measures the cumulative deviation between actual and predicted values over time. A tracking signal of zero indicates that the forecasting method is accurate, while a non-zero tracking signal suggests that the forecast has consistently over- or under-predicted sales. Decomposition, smoothing, and regression are techniques used to generate forecasts and do not directly measure how well those forecasts fit actual data.

Question 20

Sales for boxes of Girl Scout cookies over a 4-month period were forecasted as follows: 100, 120, 115, and 123.The actual results over the 4-month period were as follows: 110, 114, 119, 115.What was the MSE of the 4-month forecast?
A)0
B)5
C)7
D)54

Accepted Answer

To find the MSE, we need to follow these steps:

1. Calculate the error for each month by subtracting the actual value from the forecasted value:

Month 1 Error = 100 - 110 = -10
Month 2 Error = 120 - 114 = 6
Month 3 Error = 115 - 119 = -4
Month 4 Error = 123 - 115 = 8

2. Square each error:

Month 1 Error^2 = (-10)^2 = 100
Month 2 Error^2 = 6^2 = 36
Month 3 Error^2 = (-4)^2 = 16
Month 4 Error^2 = 8^2 = 64

3. Average the squared errors:

MSE = (100 + 36 + 16 + 64) / 4 = 54

So, the MSE of the 4-month forecast was 54. Therefore, the best choice is D.

Quiz 5: Forecasting

Which of the following methods tells whether the forecast tends to be too high or too low?

Which of the following methods gives an indication of the percentage of forecast error?

A TIME SERIES forecasting model in which the forecast for the next period is the actual value for the current period is the

Sales for boxes of Girl Scout cookies over a 4-month period were forecasted as follows: 100, 120, 115, and 123.The actual results over the 4-month period were as follows: 110, 114, 119, 115.What was the MAD of the 4-month forecast?

As one increases the number of periods used in the calculation of a moving average

Which of the following statements about the decomposition method is false?

Enrollment in a particular class for the last four semesters has been 122, 128, 100, and 155 (listed from oldest to most recent) .The best forecast of enrollment next semester, based on a three-semester moving average, would be

The process of isolating linear trend and seasonal factors to develop more accurate forecasts is called

Daily demand for newspapers for the last 10 days has been as follows: 12, 13, 16, 15, 12, 18, 14, 12, 13, 15 (listed from oldest to most recent) .Forecast sales for the next day using a two-day weighted moving average where the weights are 3 and 1.

Assume that you have tried three different forecasting models.For the first, the MAD = 2.5, for the second, the MSE = 10.5, and for the third, the MAPE = 2.7.We can then say

Which of the following methods produces a particularly stiff penalty in periods with large forecast errors?

Which of the following is not considered one of the steps to developing the decomposition method?

Daily demand for newspapers for the last 10 days has been as follows: 12, 13, 16, 15, 12, 18, 14, 12, 13, 15 (listed from oldest to most recent) .Forecast sales for the next day using a two-day moving average.

Which of the following is not considered to be one of the components of a time series?

In picking the smoothing constant for an exponential smoothing model, we should look for a value that

A method to measure how well predictions fit actual data is

Sales for boxes of Girl Scout cookies over a 4-month period were forecasted as follows: 100, 120, 115, and 123.The actual results over the 4-month period were as follows: 110, 114, 119, 115.What was the MSE of the 4-month forecast?