AN 300 FINAL EXAM QUESTIONS & ANSWERS
Which of the following statements about time-series forecasting is TRUE? - Answers :It
is a predictive analytics technique.
It applies to strategic planning by predicting market growth rate.
It predicts the future outcome of the item of interest.
It needs data on observations of an item of interest over time.
Types of data patterns - Answers :Horizontal- constant avg. value over time
Trend- a gradual upward or downward shift in values over time
Seasonality- a recurring pattern that occurs at set periods within a larger time frame
Cycle- an alternating pattern of points lying above and below an underlying pattern (as
opposed to random fluctuation) across multiple years (ex. boom and bust periods in US
economy)
Seasonality - Answers :A recurring pattern that occurs at set periods within a larger time
frame.
Upward trend - Answers :A gradual increase in values over time
downward trend - Answers :A gradual decrease in values over time
Level - Answers :A constant average value over time
Which of the following statements about time-series forecasting methods is TRUE? -
Answers :Linear Regression for Seasonality without Trend method is appropriate for
data with a seasonal pattern only.
The Simple Average method is also known as the Historical Moving Average method.
Linear Regression is the method of choice for data with a trend pattern.
You choose a small value for "k" when using the Simple Moving Average method of
order "k" to track movement in the most recent data.
Forecast error formula - Answers :Forecast error = Actual value - Forecast value
Absolute error formula - Answers :Absolute error = Absolute value of the forecast error,
i.e., the forecast error without the sign.
Cumulative forecast error - Answers :It sums up all the errors available.
Mean forecast error - Answers :It averages all the errors available.
It averages all the absolute errors available.
Sum of squared errors - Answers :It sums up all the squared error available.
You want to emphasize large errors.
, Absolute percentage error - Answers :It divides the absolute error of a period by the
actual value of that period. The resulting quotient is then multiplied by 100
Mean absolute percentage error - Answers :It takes the average of the absolute
percentage error values over a range of time periods.
You want to compare two different applications of the same forecasting method.
Which of the following statements about CFE and MFE is TRUE? - Answers :The
biases are aggregated.
Positive errors may be offset by the negative ones.
The least biased CFE/MFE is preferred.
CFE stands for Cumulative Forecast Error.
MFE stands for Mean Forecast Error.
Which of the following is a business application of time series forecasting? - Answers
:Sales forecasts of swimsuits from past records
Given the following sales data (in $000) for C&A's product:
January 15
February 18
March 14
April 16
May 13
June 16
What is the naive forecast for June?
What is the historical moving average forecast for July?
What is the simple moving average forecast of order 3 for June?
What is the simple moving average forecast of order 1 for June?
What is the exponential smoothing forecast for July if alpha = 0.2 and the forecast for
February is 15?
The simple moving average method of order 1 is the same as the Naive method. -
Answers :13
15.33
14.33
13
15.15
T
Naive - Answers :It requires only one historical data value.
It adapts readily to sudden shifts in data pattern.
Simple moving average - Answers :It requires the data points in the time series as well
as the number of periods used in forecasting.
Which of the following statements about time-series forecasting is TRUE? - Answers :It
is a predictive analytics technique.
It applies to strategic planning by predicting market growth rate.
It predicts the future outcome of the item of interest.
It needs data on observations of an item of interest over time.
Types of data patterns - Answers :Horizontal- constant avg. value over time
Trend- a gradual upward or downward shift in values over time
Seasonality- a recurring pattern that occurs at set periods within a larger time frame
Cycle- an alternating pattern of points lying above and below an underlying pattern (as
opposed to random fluctuation) across multiple years (ex. boom and bust periods in US
economy)
Seasonality - Answers :A recurring pattern that occurs at set periods within a larger time
frame.
Upward trend - Answers :A gradual increase in values over time
downward trend - Answers :A gradual decrease in values over time
Level - Answers :A constant average value over time
Which of the following statements about time-series forecasting methods is TRUE? -
Answers :Linear Regression for Seasonality without Trend method is appropriate for
data with a seasonal pattern only.
The Simple Average method is also known as the Historical Moving Average method.
Linear Regression is the method of choice for data with a trend pattern.
You choose a small value for "k" when using the Simple Moving Average method of
order "k" to track movement in the most recent data.
Forecast error formula - Answers :Forecast error = Actual value - Forecast value
Absolute error formula - Answers :Absolute error = Absolute value of the forecast error,
i.e., the forecast error without the sign.
Cumulative forecast error - Answers :It sums up all the errors available.
Mean forecast error - Answers :It averages all the errors available.
It averages all the absolute errors available.
Sum of squared errors - Answers :It sums up all the squared error available.
You want to emphasize large errors.
, Absolute percentage error - Answers :It divides the absolute error of a period by the
actual value of that period. The resulting quotient is then multiplied by 100
Mean absolute percentage error - Answers :It takes the average of the absolute
percentage error values over a range of time periods.
You want to compare two different applications of the same forecasting method.
Which of the following statements about CFE and MFE is TRUE? - Answers :The
biases are aggregated.
Positive errors may be offset by the negative ones.
The least biased CFE/MFE is preferred.
CFE stands for Cumulative Forecast Error.
MFE stands for Mean Forecast Error.
Which of the following is a business application of time series forecasting? - Answers
:Sales forecasts of swimsuits from past records
Given the following sales data (in $000) for C&A's product:
January 15
February 18
March 14
April 16
May 13
June 16
What is the naive forecast for June?
What is the historical moving average forecast for July?
What is the simple moving average forecast of order 3 for June?
What is the simple moving average forecast of order 1 for June?
What is the exponential smoothing forecast for July if alpha = 0.2 and the forecast for
February is 15?
The simple moving average method of order 1 is the same as the Naive method. -
Answers :13
15.33
14.33
13
15.15
T
Naive - Answers :It requires only one historical data value.
It adapts readily to sudden shifts in data pattern.
Simple moving average - Answers :It requires the data points in the time series as well
as the number of periods used in forecasting.
