Complete Test Bank – Explanatory Models 2. Time-Series | Ch6 - Forecasting with Forecast X 7e Complete Test Bank by Barry Keating. DOCX document preview.
Forecasting and Predictive Analytics with Forecast X, 7e (Keating)
Chapter 6 Explanatory Models 2. Time-Series Decomposition
1) The time-series decomposition model is best described as a
A) ratio-to-exponential smoothing technique.
B) ratio-to-moving average technique.
C) multiplicative moving average technique.
D) moving average factorization technique.
E) None of the options are correct.
2) Which of the following is not a reason why time-series decomposition has gained favor with forecasters and their managers?
A) Forecast accuracy
B) Ease in understanding
C) Very little computation is required.
D) Time-series decomposition resembles the way many managers analyze the future.
E) None of the options are correct.
3) Which of the following is not a technique used to generate forecasts with time series decomposition?
A) Moving averages
B) Trend projection
C) Multiplicative seasonality
D) Dummy variables
E) All of the options are correct.
4) In time-series decomposition analysis, “decomposition” refers to
A) converting an annual trend line into a monthly trend line.
B) deseasonalizing the data.
C) separating a time series into component parts.
D) isolating the cyclical component of a time series.
E) None of the options are correct.
5) Which of the following is not a component in the time series decomposition model?
A) Trend
B) Seasonal variation
C) Irregular variation
D) Business indicators
E) Cyclical variation
6) Which forecasting model identifies and forecasts component factors that influence the level of a time series?
A) Event model
B) Time series decomposition
C) Moving average smoothing
D) Exponential smoothing
E) Winter's smoothing
7) Which of the following best describes the general approach to forecasting when actually applying time-series decomposition?
A) Y = T + S + C + I
B) Y = T × S × C × I
C) Y = T × S × C
D) Y = (T + C) × S
E) None of the options are correct.
8) Time series decomposition models seasonality
A) using dummy variables.
B) in an additive fashion.
C) in an exponential manner.
D) similar to Winter's smoothing.
E) None of the options are correct.
9) Which of the following is not correct about using moving averages to deseasonalize a time series?
A) The number of periods in the average should reflect the number of seasons.
B) The number of periods for annual data should be 12.
C) The number of periods for quarterly data should be 4.
D) The moving average is interpreted as the typical level of a variable in a given year.
E) All of the options are correct.
10) Deseasonalizing the data using moving averages
A) removes the seasonal component of a time series.
B) removes the irregular component of a time series.
C) preserves the cyclical component of a time series.
D) preserves the trend component of a time series.
E) All of the options are correct.
11) When calculating centered moving averages, how many data points are lost for a given time series when a n-period moving average is used?
A) n points at the beginning
B) n points at the end
C) n points on both ends
D) sample size − n points at the beginning
E) None of the options are correct.
12) When calculating centered moving-averages using a 4-period moving average, how many data points are lost at the beginning of the original series?
A) 1
B) 2
C) 3
D) 4
E) None of the options are correct.
13) When calculating centered moving-averages using a 4-period moving average, how many data points are lost at both ends of the original series?
A) 1
B) 2
C) 3
D) 4
E) None of the options are correct.
14) In time-series decomposition, seasonal factors are calculated by
A) SFt = (Yt) × (CMAt).
B) SFt = Yt/CMAt.
C) (CMAt) × (SFt) = Yt.
D) SFt = Yt − CMAt.
E) None of the options are correct.
15) A seasonal index number of .80 for quarter one in a time series decomposition model of an automobile parts manufacturer suggests
A) quarter one sales are 80% above the norm.
B) quarter one sales are 1.80% below the norm.
C) quarter one sales are 20% below the norm.
D) quarter one sales are 80% below the norm.
E) None of the options are correct.
16) The sum of seasonal index numbers should equal
A) one.
B) sample size/2.
C) number of seasons.
D) 12.
E) None of the options are correct.
17) The sum of seasonal index numbers for monthly data should equal
A) one.
B) sample size/2.
C) 4.
D) 12.
E) None of the options are correct.
18) Quarter one sales for a tire manufacturer were $120,000,000. If the quarter one seasonal index was 1.20 in a time series decomposition model, what is an estimate of annual sales for this firm?
A) $100,000,000
B) $144,000,000
C) $400,000,000
D) $576,000,000
E) None of the options are correct.
19) Suppose Nike sales are expected to be 1.2 billion dollars for the year 2005. If the January seasonal index for Nike is 0.98, what is a reasonable estimate for January 2005 sales revenue?
A) 0.098 billion
B) 0.1 billion
C) 1.176 billion
D) 2.18 billion
20) People's Bank
Seasonal Indexes of sales revenue of People's Bank are:
|
| |||
January |
| 1.20 |
| |
February |
| 0.90 |
| |
March |
| 1.00 |
| |
April |
| 1.08 |
| |
May |
| 1.02 |
| |
June |
| 1.10 |
| |
July |
| 1.05 |
| |
August |
| 0.90 |
| |
September |
| 0.85 |
| |
October |
| 1.00 |
| |
November |
| 1.10 |
| |
December |
| 0.80 |
| |
Total revenue for People's Bank in 1999 is forecasted to be $60,000. Based on the seasonal indexes above, sales in the first three months of 1999 should be
A) $4,800.
B) $15,500.
C) $14,723.
D) $13,500.
E) None of the options are correct.
21) People's Bank
Seasonal Indexes of sales revenue of People's Bank are:
|
| |||
January |
| 1.20 |
| |
February |
| 0.90 |
| |
March |
| 1.00 |
| |
April |
| 1.08 |
| |
May |
| 1.02 |
| |
June |
| 1.10 |
| |
July |
| 1.05 |
| |
August |
| 0.90 |
| |
September |
| 0.85 |
| |
October |
| 1.00 |
| |
November |
| 1.10 |
| |
December |
| 0.80 |
| |
If December 1999 revenue for People's Bank amounted to $5,000, a reasonable estimate of revenue for January 2000, based on the seasonal indexes given above, would be
A) $3,000.
B) $4,500.
C) $4,800.
D) $7,500.
E) None of the options are correct.
22) People's Bank
Seasonal Indexes of sales revenue of People's Bank are:
|
| |||
January |
| 1.20 |
| |
February |
| 0.90 |
| |
March |
| 1.00 |
| |
April |
| 1.08 |
| |
May |
| 1.02 |
| |
June |
| 1.10 |
| |
July |
| 1.05 |
| |
August |
| 0.90 |
| |
September |
| 0.85 |
| |
October |
| 1.00 |
| |
November |
| 1.10 |
| |
December |
| 0.80 |
| |
If revenue of People's Bank amounted to $5,500 in November 1999, the November 1999 sales revenue, after adjustment for seasonal variation using the indexes given above, would be
A) $6,500.
B) $6,050.
C) $5,500.
D) $4,500.
E) None of the options are correct.
23) A company has computed a seasonal index for its quarterly sales. Which of the following statements is not correct?
A) The sum of the four quarterly seasonal index numbers is 4.
B) An index of 0.75 for quarter-one sales indicates that sales were 25 percent lower than average sales.
C) An index of 1.10 indicates sales 10% above the norm.
D) The index for any quarter must be between 0 and 2.
E) The average index is 1.
24) In computing a seasonal index, specific seasonals were tabulated for each month. The averages over time for the twelve months were obtained and summed. If the mean seasonal factor for June was 96.9, and the sum for all twelve months is 1195, the adjusted seasonal index for June is
A) 97.7.
B) 96.9.
C) 96.4.
D) 102.7.
E) None of the options are correct.
25) Assume the following specific seasonal factors for January are based on the ratio-to-moving average method:
88.2 | 85.9 | 64.3 | 92.4 | 80.1 | 82.4 |
What is the seasonal index for January using the modified mean method?
A) 84.15
B) 79.50
C) 83.34
D) 82.21
E) Not enough information is provided.
26) The following specific seasonal factors were estimated for the month of October:
65.4 | 76.8 | 66.9 | 72.6 | 70.0 |
If the adjustment is 0.98 and the modified mean is used, and if the expected trend for October is $800, what is the seasonally adjusted forecast?
A) $570.00
B) $561.00
C) $551.20
D) $1,168.8
E) None of the options are correct.
27) The long-term trend of a time series in the decomposition model is estimated using
A) a nonlinear time trend.
B) the actual unsmoothed data.
C) the centered moving average data.
D) the series of seasonal factors.
E) All of the options are correct.
28) Consider the following data:
Year | Sales Revenue | Coded Time |
1996 | 800 | 0 |
1997 | 840 | 1 |
1998 | 900 | 2 |
Which linear trend model best fits this data?
A) Y = 846.67 + 100X
B) Y = 840 + 100X
C) Y = 846.67 + 50X
D) Y = 796.67 + 50X
E) None of the options are correct.
29) Which trend model would you choose if the variable you are seeking to forecast were increasing at a constant percentage rate?
A) Y = a + bX
B) Y = abX
C) Y = b + b1X + b2X2
D) Y = b(1/X)
E) None of the options are correct.
30) The cyclical component of a time series is measured by
A) Yt/CMAt.
B) CMA/CMAT.
C) Yt/SIt.
D) CMAt/CMAt−1.
E) None of the options are correct.
31) The difference between cyclical and seasonal factors is best described as
A) they are both calculated as ratios.
B) amplitude.
C) periodicity.
D) wavelike random patterns.
E) None of the options are correct.
32) Which data series is not used in the calculation of cycle factors?
A) CMAT
B) CMA
C) TIME
D) SF
E) All of the options are correct.
33) A researcher mistakenly uses deseasonalized data in calculating the seasonal factors. If she found apparent seasonal behavior, this is best attributed to
A) the business cycle.
B) trend.
C) random noise.
D) seasonality.
E) None of the options are correct.
34) The Sky-Is-Falling forecasting firm is predicting a deep recession next year. What would be the average forecasted cycle factor for next year if you believe such a forecast?
A) Less than zero
B) Close to zero, but negative
C) Close to one, but greater than one
D) Substantially greater than one
E) None of the options are correct.
35) Which of the following is not a similarity between seasonal and cycle factors?
A) They are both calculated as ratios.
B) They both sum to the number of data points in the averaging process.
C) They both model variability in the dependent variable.
D) They both use the actual data series in their calculation.
E) All of the options are correct.
36) Which of the following is not helpful in generating forecasts of cycle factors?
A) A time-series plot of the data
B) Length of previous cycles
C) Amplitude of previous cycles
D) The prime rate of interest
E) All the above are helpful.
37) The range of economic activity from the beginning trough of an expansion to the peak of the expansion is called
A) the recession phase.
B) the contraction phase.
C) the expansion phase.
D) the periodicity.
E) None of the options are correct.
38) If business cycles were pure cycles, they
A) would have constant amplitude.
B) would have constant periodicity.
C) would be easy to forecast.
D) would have predictable trend reversals.
E) All of the options are correct.
39) Over a long period of time, if measured correctly, cycle factors should average
A) zero.
B) one.
C) two.
D) four.
E) twelve.
40) Which of the following is not part of the index of leading economic indicators?
A) Index of stock prices
B) Index of industrial production
C) M2 Money Supply
D) Index of new private housing starts
E) All of the options are correct.
41) Which of the following is not a part of the index of lagging economic indicators?
A) Average prime rate of interest
B) Index of unit labor costs
C) Outstanding commercial loans
D) Ratio of consumer installment credit to personal income
E) None of the options are correct.
42) What is the major problem when using time-series smoothing techniques to forecast the cyclical component of a time series?
A) It takes too much data.
B) It takes too much computer time and effort.
C) Trend reversals cannot be forecasted.
D) Holt's smoothing estimates a linear trend.
E) All of the options are correct.
43) When using moving-average smoothing to generate forecasts of cycle factors, the researcher should be wary of
A) spurious cycles caused by heteroscedasticity.
B) bias caused by heteroscedasticity.
C) spurious cycles caused by serial correlation.
D) bias in trend estimates caused by serial correlation.
E) All of the options are correct.
44) Which of the following advice is not particularly useful in forecasting the cyclical component of a time series?
A) Review the past behavior of the cyclical factor series.
B) Use time-series smoothing when you expect a trend to continue into the forecast horizon.
C) Avoid subjective forecasts of cycle factors.
D) Review the results of several forecasting methods.
E) All of the options are correct.
45) Which statement is not correct?
A) Time series decomposition tends to fit the data very well.
B) Time series decomposition accuracy is usually overstated by model fit statistics.
C) The better the forecast of the cycle factors, the better the out-of-sample fit of time-series decomposition.
D) Time series decomposition tends to be well understood by forecast consumers.
E) All of the options are correct.
46) Which of the following statements regarding time series decomposition is not correct?
A) The fluctuating components of a time series are cyclical, seasonal, and irregular.
B) Short-term forecasts are more accurate than long term.
C) If the original data are valued in dollars, the values of the cycle factors must also be in dollars.
D) Seasonal index numbers for monthly data average 1 and total 12.
E) All of the options are correct.
47) Jewelry Sales
Audit Trail
Series Description | ($Millions) |
Jewelry Sales | 1.00 |
Audit Trail - Statistics
Accuracy Measures | Value |
| Forecast Statistics | Value |
AIC | 1,680.55 |
| Durbin Watson(1) | 1.54 |
BIC | 1,686.49 |
| Mean | 1,781.55 |
Mean Absolute Percentage Error (MAPE) | 3.15 | % | Standard Deviation | 1,070.01 |
R-Square | 99.41 | % | Skewness | 2.85 |
Adjusted R-Square | 99.41 | % | Kurtosis | 10.83 |
Mean Absolute Error | 54.82 |
| Max | 6,554.00 |
Mean Error | 3.01 |
| Min | 802.00 |
Mean Square Error | 6,666.16 |
| Mean Absolute Deviation | 618.70 |
Root Mean Square Error | 81.65 |
| Sum Squared Deviation | 163,723,589.66 |
Standard Deviation of Error | 81.93 |
| Mean Square Deviation | 1,136,969.37 |
Theil | 0.10 |
| Mode | 1,043.00 |
|
|
| Range | 5,752.00 |
|
|
| Root Mean Square | 1,066.29 |
|
|
| Ljng-Box | 69.63 |
Method Statistics | Value |
Method Selected | Decomposition |
Basic Method | Trend (Linear) Regression |
Decomposition Type | Multiplicative |
Components of Decomposition
Date | Original Data | Forecasted Data | Centered Moving Average | CMA Trend | Seasonal Indices | Cycle Factors |
Jan-1992 | 803.00 | 803.00 |
|
| 0.63 |
|
Feb-1992 | 1,030.00 | 1,030.00 |
|
| 0.89 |
|
Mar-1992 | 922.00 | 922.00 |
|
| 0.74 |
|
Apr-1992 | 977.00 | 977.00 |
|
| 0.78 |
|
May-1992 | 1,182.00 | 1,182.00 |
|
| 1.00 |
|
Jun-1992 | 1,104.00 | 1,104.00 |
|
| 0.85 |
|
Jul-1992 | 1,046.00 | 1,020.05 | 1,265.29 | 1,307.72 | 0.81 | 0.97 |
Aug-1992 | 1,100.00 | 1,076.55 | 1,264.08 | 1,314.85 | 0.85 | 0.96 |
Sep-1992 | 1,043.00 | 993.64 | 1,262.08 | 1,321.99 | 0.79 | 0.95 |
Oct-1992 | 1,132.00 | 1,057.19 | 1,262.50 | 1,329.12 | 0.84 | 0.95 |
Nov-1992 | 1,376.00 | 1,371.67 | 1,266.42 | 1,336.26 | 1.08 | 0.95 |
Dec-1992 | 3,469.00 | 3,512.70 | 1,276.00 | 1,343.40 | 2.75 | 0.95 |
Jan-1993 | 802.00 | 816.80 | 1,292.58 | 1,350.53 | 0.63 | 0.96 |
Feb-1993 | 1,002.00 | 1,163.70 | 1,309.33 | 1,357.67 | 0.89 | 0.96 |
Mar-1993 | 902.00 | 978.15 | 1,322.58 | 1,364.80 | 0.74 | 0.97 |
Apr-1993 | 1,007.00 | 1,038.98 | 1,332.13 | 1,371.94 | 0.78 | 0.97 |
May-1993 | 1,246.00 | 1,337.59 | 1,343.21 | 1,379.07 | 1.00 | 0.97 |
Jun-1993 | 1,270.00 | 1,154.83 | 1,365.92 | 1,386.21 | 0.85 | 0.99 |
Jul-1993 | 1,278.00 | 1,116.70 | 1,385.17 | 1,393.34 | 0.81 | 0.99 |
Aug-1993 | 1,270.00 | 1,189.99 | 1,397.29 | 1,400.48 | 0.85 | 1.00 |
Sep-1993 | 1,191.00 | 1,111.41 | 1,411.67 | 1,407.61 | 0.79 | 1.00 |
Oct-1993 | 1,213.00 | 1,193.26 | 1,425.00 | 1,414.75 | 0.84 | 1.01 |
Nov-1993 | 1,561.00 | 1,556.29 | 1,436.88 | 1,421.88 | 1.08 | 1.01 |
Dec-1993 | 3,829.00 | 3,967.96 | 1,441.38 | 1,429.02 | 2.75 | 1.01 |
Jan-1994 | 904.00 | 909.06 | 1,438.58 | 1,436.15 | 0.63 | 1.00 |
Feb-1994 | 1,191.00 | 1,278.43 | 1,438.42 | 1,443.29 | 0.89 | 1.00 |
Mar-1994 | 1,058.00 | 1,067.05 | 1,442.79 | 1,450.42 | 0.74 | 0.99 |
Apr-1994 | 1,171.00 | 1,130.66 | 1,449.67 | 1,457.56 | 0.78 | 0.99 |
May-1994 | 1,367.00 | 1,455.22 | 1,461.33 | 1,464.69 | 1.00 | 1.00 |
Note that this "Components" table is truncated.
Consider the Time Series Decomposition result above. The variable being forecasted is jewelry sales in the United States monthly. After the application of the time series decomposition model,
A) there appears to be no first-order serial correlation.
B) there appears to be first-order serial correlation.
C) there appears to be a problem with the underlying model as evidenced by the Theil's-U.
D) there appears to be a problem with stationarity.
48) Jewelry Sales
Audit Trail — Correlation Coefficient Table
Series Description | ($Millions) |
Jewelry Sales | 1.00 |
Audit Trail - Statistics
Accuracy Measures | Value |
| Forecast Statistics | Value |
AIC | 1,680.55 |
| Durbin Watson(1) | 1.54 |
BIC | 1,686.49 |
| Mean | 1,781.55 |
Mean Absolute Percentage Error (MAPE) | 3.15 | % | Standard Deviation | 1,070.01 |
R-Square | 99.41 | % | Skewness | 2.85 |
Adjusted R-Square | 99.41 | % | Kurtosis | 10.83 |
Mean Absolute Error | 54.82 |
| Max | 6,554.00 |
Mean Error | 3.01 |
| Min | 802.00 |
Mean Square Error | 6,666.16 |
| Mean Absolute Deviation | 618.70 |
Root Mean Square Error | 81.65 |
| Sum Squared Deviation | 163,723,589.66 |
Standard Deviation of Error | 81.93 |
| Mean Square Deviation | 1,136,969.37 |
Theil | 0.10 |
| Mode | 1,043.00 |
|
|
| Range | 5,752.00 |
|
|
| Root Mean Square | 1,066.29 |
|
|
| Ljng-Box | 69.63 |
Method Statistics | Value |
Method Selected | Decomposition |
Basic Method | Trend (Linear) Regression |
Decomposition Type | Multiplicative |
Components of Decomposition
Date | Original Data | Forecasted Data | Centered Moving Average | CMA Trend | Seasonal Indices | Cycle Factors |
Jan-1992 | 803.00 | 803.00 |
|
| 0.63 |
|
Feb-1992 | 1,030.00 | 1,030.00 |
|
| 0.89 |
|
Mar-1992 | 922.00 | 922.00 |
|
| 0.74 |
|
Apr-1992 | 977.00 | 977.00 |
|
| 0.78 |
|
May-1992 | 1,182.00 | 1,182.00 |
|
| 1.00 |
|
Jun-1992 | 1,104.00 | 1,104.00 |
|
| 0.85 |
|
Jul-1992 | 1,046.00 | 1,020.05 | 1,265.29 | 1,307.72 | 0.81 | 0.97 |
Aug-1992 | 1,100.00 | 1,076.55 | 1,264.08 | 1,314.85 | 0.85 | 0.96 |
Sep-1992 | 1,043.00 | 993.64 | 1,262.08 | 1,321.99 | 0.79 | 0.95 |
Oct-1992 | 1,132.00 | 1,057.19 | 1,262.50 | 1,329.12 | 0.84 | 0.95 |
Nov-1992 | 1,376.00 | 1,371.67 | 1,266.42 | 1,336.26 | 1.08 | 0.95 |
Dec-1992 | 3,469.00 | 3,512.70 | 1,276.00 | 1,343.40 | 2.75 | 0.95 |
Jan-1993 | 802.00 | 816.80 | 1,292.58 | 1,350.53 | 0.63 | 0.96 |
Feb-1993 | 1,002.00 | 1,163.70 | 1,309.33 | 1,357.67 | 0.89 | 0.96 |
Mar-1993 | 902.00 | 978.15 | 1,322.58 | 1,364.80 | 0.74 | 0.97 |
Apr-1993 | 1,007.00 | 1,038.98 | 1,332.13 | 1,371.94 | 0.78 | 0.97 |
May-1993 | 1,246.00 | 1,337.59 | 1,343.21 | 1,379.07 | 1.00 | 0.97 |
Jun-1993 | 1,270.00 | 1,154.83 | 1,365.92 | 1,386.21 | 0.85 | 0.99 |
Jul-1993 | 1,278.00 | 1,116.70 | 1,385.17 | 1,393.34 | 0.81 | 0.99 |
Aug-1993 | 1,270.00 | 1,189.99 | 1,397.29 | 1,400.48 | 0.85 | 1.00 |
Sep-1993 | 1,191.00 | 1,111.41 | 1,411.67 | 1,407.61 | 0.79 | 1.00 |
Oct-1993 | 1,213.00 | 1,193.26 | 1,425.00 | 1,414.75 | 0.84 | 1.01 |
Nov-1993 | 1,561.00 | 1,556.29 | 1,436.88 | 1,421.88 | 1.08 | 1.01 |
Dec-1993 | 3,829.00 | 3,967.96 | 1,441.38 | 1,429.02 | 2.75 | 1.01 |
Jan-1994 | 904.00 | 909.06 | 1,438.58 | 1,436.15 | 0.63 | 1.00 |
Feb-1994 | 1,191.00 | 1,278.43 | 1,438.42 | 1,443.29 | 0.89 | 1.00 |
Mar-1994 | 1,058.00 | 1,067.05 | 1,442.79 | 1,450.42 | 0.74 | 0.99 |
Apr-1994 | 1,171.00 | 1,130.66 | 1,449.67 | 1,457.56 | 0.78 | 0.99 |
May-1994 | 1,367.00 | 1,455.22 | 1,461.33 | 1,464.69 | 1.00 | 1.00 |
Note that this "Components" table is truncated.
In the "Jewelry Sales" decomposition model shown above,
A) the cyclicality of the data seems to outweigh the seasonality in the size of the effect.
B) there is no trend in the original data.
C) there appears to be a problem with the seasonal indices as evidenced by the value of 2.75 for the month of December.
D) None of the options are correct.
49) In the classical time-series decomposition model, up-and-down swings of a variable around the trend (typically lasting from one to several years each and differing in length and amplitude from one occurrence to the next) are known as
A) the trend component.
B) the cyclical component.
C) the seasonal component.
D) the irregular component.
50) Which of the following statements about the cyclical component of a classical time series decomposition model is false?
A) The cyclical component of a time series, denoted by C, is a relatively smooth, progressively upward or downward movement of a variable, Y, over an extended period of time.
B) The cyclical component is viewed as the consequence of long-range gradual changes in such factors as population size or composition, technology, or consumer preferences.
C) The cyclical component is typically computed from data that cover a minimum of 2 years.
D) All of the options are correct.
51) Audit Trail - Statistics
Accuracy Measures | Value |
| Forecast Statistics | Value |
AIC | 309.51 |
| Durbin Watson(4) | 1.01 |
BIC | 313.82 |
| Mean | 61.54 |
Mean Absolute Percentage Error (MAPE) | 3.11 | % | Standard Deviation | 12.70 |
R-Square | 95.64 | % | Variance | 161.41 |
Adjusted R-Square | 95.57 | % | Ljung-Box | 58.17 |
Root Mean Square Error | 2.63 |
|
|
|
Theil | 0.29 |
|
|
|
Method Statistics | Value |
Method Selected | Decomposition |
Basic Method | Trend (Linear) Regression |
Decomposition Type | Multiplicative |
Components of Decomposition
Date | Original Data | Forecasted Data | Centered Moving Average | CMA Trend | Seasonal Indices | Cycle Factors |
Sep-1998 | 56.60 |
|
|
| 0.90 |
|
Oct-1998 | 49.10 |
|
|
| 1.09 |
|
Nov-1998 | 58.50 | 58.93 | 55.21 | 62.51 | 1.07 | 0.88 |
Dec-1998 | 57.50 | 54.10 | 57.63 | 62.45 | 0.94 | 0.92 |
Jan-1999 | 54.90 | 55.26 | 61.16 | 62.40 | 0.90 | 0.98 |
Feb-1999 | 70.10 | 66.69 | 61.16 | 62.35 | 1.09 | 0.98 |
Mar-1999 | 65.80 | 64.10 | 60.05 | 62.29 | 1.07 | 0.96 |
Apr-1999 | 50.20 | 55.93 | 59.58 | 62.24 | 0.94 | 0.96 |
May-1999 | 53.30 | 53.27 | 58.96 | 62.19 | 0.90 | 0.95 |
Jun-1999 | 67.90 | 64.62 | 59.26 | 62.13 | 1.09 | 0.95 |
Jul-1999 | 63.10 | 65.27 | 61.15 | 62.08 | 1.07 | 0.99 |
Aug-1999 | 55.30 | 60.18 | 64.10 | 62.03 | 0.94 | 1.03 |
Sep-1999 | 63.30 | 61.55 | 68.13 | 61.97 | 0.90 | 1.10 |
Oct-1999 | 81.50 | 78.71 | 72.19 | 61.92 | 1.09 | 1.17 |
Nov-1999 | 81.70 | 79.51 | 74.49 | 61.87 | 1.07 | 1.20 |
Dec-1999 | 69.20 | 70.60 | 75.20 | 61.82 | 0.94 | 1.22 |
Jan-2000 | 67.80 | 67.77 | 75.01 | 61.76 | 0.90 | 1.21 |
Feb-2000 | 82.70 | 81.01 | 74.30 | 61.71 | 1.09 | 1.20 |
Mar-2000 | 79.00 | 78.17 | 73.24 | 61.66 | 1.07 | 1.19 |
Apr-2000 | 66.20 | 67.71 | 72.13 | 61.60 | 0.94 | 1.17 |
May-2000 | 62.30 | 64.50 | 71.39 | 61.55 | 0.90 | 1.16 |
Jun-2000 | 79.30 | 77.40 | 70.99 | 61.50 | 1.09 | 1.15 |
Jul-2000 | 76.50 | 75.12 | 70.38 | 61.44 | 1.07 | 1.15 |
Aug-2000 | 65.50 | 64.11 | 68.29 | 61.39 | 0.94 | 1.11 |
Sep-2000 | 58.10 | 58.80 | 65.09 | 61.34 | 0.90 | 1.06 |
Oct-2000 | 66.80 | 67.90 | 62.28 | 61.28 | 1.09 | 1.02 |
Nov-2000 | 63.40 | 64.39 | 60.33 | 61.23 | 1.07 | 0.99 |
Dec-2000 | 56.10 | 56.10 | 59.05 | 61.18 | 0.94 | 0.97 |
Consider the time series decomposition output for Mobile Home Sales above. This decomposition model
A) explained about 3% of the variation in mobile home shipments.
B) explained about 96% of the variation in mobile home shipments.
C) explained about 0.27% of the variation in mobile home shipments.
D) None of the options are correct.
52) Audit Trail - Statistics
Accuracy Measures | Value |
| Forecast Statistics | Value |
AIC | 309.51 |
| Durbin Watson(4) | 1.01 |
BIC | 313.82 |
| Mean | 61.54 |
Mean Absolute Percentage Error (MAPE) | 3.11 | % | Standard Deviation | 12.70 |
R-Square | 95.64 | % | Variance | 161.41 |
Adjusted R-Square | 95.57 | % | Ljung-Box | 58.17 |
Root Mean Square Error | 2.63 |
|
|
|
Theil | 0.29 |
|
|
|
Method Statistics | Value |
Method Selected | Decomposition |
Basic Method | Trend (Linear) Regression |
Decomposition Type | Multiplicative |
Components of Decomposition
Date | Original Data | Forecasted Data | Centered Moving Average | CMA Trend | Seasonal Indices | Cycle Factors |
Sep-1998 | 56.60 |
|
|
| 0.90 |
|
Oct-1998 | 49.10 |
|
|
| 1.09 |
|
Nov-1998 | 58.50 | 58.93 | 55.21 | 62.51 | 1.07 | 0.88 |
Dec-1998 | 57.50 | 54.10 | 57.63 | 62.45 | 0.94 | 0.92 |
Jan-1999 | 54.90 | 55.26 | 61.16 | 62.40 | 0.90 | 0.98 |
Feb-1999 | 70.10 | 66.69 | 61.16 | 62.35 | 1.09 | 0.98 |
Mar-1999 | 65.80 | 64.10 | 60.05 | 62.29 | 1.07 | 0.96 |
Apr-1999 | 50.20 | 55.93 | 59.58 | 62.24 | 0.94 | 0.96 |
May-1999 | 53.30 | 53.27 | 58.96 | 62.19 | 0.90 | 0.95 |
Jun-1999 | 67.90 | 64.62 | 59.26 | 62.13 | 1.09 | 0.95 |
Jul-1999 | 63.10 | 65.27 | 61.15 | 62.08 | 1.07 | 0.99 |
Aug-1999 | 55.30 | 60.18 | 64.10 | 62.03 | 0.94 | 1.03 |
Sep-1999 | 63.30 | 61.55 | 68.13 | 61.97 | 0.90 | 1.10 |
Oct-1999 | 81.50 | 78.71 | 72.19 | 61.92 | 1.09 | 1.17 |
Nov-1999 | 81.70 | 79.51 | 74.49 | 61.87 | 1.07 | 1.20 |
Dec-1999 | 69.20 | 70.60 | 75.20 | 61.82 | 0.94 | 1.22 |
Jan-2000 | 67.80 | 67.77 | 75.01 | 61.76 | 0.90 | 1.21 |
Feb-2000 | 82.70 | 81.01 | 74.30 | 61.71 | 1.09 | 1.20 |
Mar-2000 | 79.00 | 78.17 | 73.24 | 61.66 | 1.07 | 1.19 |
Apr-2000 | 66.20 | 67.71 | 72.13 | 61.60 | 0.94 | 1.17 |
May-2000 | 62.30 | 64.50 | 71.39 | 61.55 | 0.90 | 1.16 |
Jun-2000 | 79.30 | 77.40 | 70.99 | 61.50 | 1.09 | 1.15 |
Jul-2000 | 76.50 | 75.12 | 70.38 | 61.44 | 1.07 | 1.15 |
Aug-2000 | 65.50 | 64.11 | 68.29 | 61.39 | 0.94 | 1.11 |
Sep-2000 | 58.10 | 58.80 | 65.09 | 61.34 | 0.90 | 1.06 |
Oct-2000 | 66.80 | 67.90 | 62.28 | 61.28 | 1.09 | 1.02 |
Nov-2000 | 63.40 | 64.39 | 60.33 | 61.23 | 1.07 | 0.99 |
Dec-2000 | 56.10 | 56.10 | 59.05 | 61.18 | 0.94 | 0.97 |
Consider the time series decomposition output for Mobile Home Sales above.
A) There is the possibility of 4th order serial correlation of the error terms (i.e., residuals).
B) There is no evidence of serial correlation of the error terms (i.e., residuals).
C) This model can be expected to forecast no better than a naїve model.
D) None of the options are correct.
53) Audit Trail — Statistics
Accuracy Measures | Value |
| Forecast Statistics | Value |
AIC | 309.51 |
| Durbin Watson(4) | 1.01 |
BIC | 313.82 |
| Mean | 61.54 |
Mean Absolute Percentage Error (MAPE) | 3.11 | % | Standard Deviation | 12.70 |
R-Square | 95.64 | % | Variance | 161.41 |
Adjusted R-Square | 95.57 | % | Ljung-Box | 58.17 |
Root Mean Square Error | 2.63 |
|
|
|
Theil | 0.29 |
|
|
|
Method Statistics | Value |
Method Selected | Decomposition |
Basic Method | Trend (Linear) Regression |
Decomposition Type | Multiplicative |
Components of Decomposition
Date | Original Data | Forecasted Data | Centered Moving Average | CMA Trend | Seasonal Indices | Cycle Factors |
Sep-1998 | 56.60 |
|
|
| 0.90 |
|
Oct-1998 | 49.10 |
|
|
| 1.09 |
|
Nov-1998 | 58.50 | 58.93 | 55.21 | 62.51 | 1.07 | 0.88 |
Dec-1998 | 57.50 | 54.10 | 57.63 | 62.45 | 0.94 | 0.92 |
Jan-1999 | 54.90 | 55.26 | 61.16 | 62.40 | 0.90 | 0.98 |
Feb-1999 | 70.10 | 66.69 | 61.16 | 62.35 | 1.09 | 0.98 |
Mar-1999 | 65.80 | 64.10 | 60.05 | 62.29 | 1.07 | 0.96 |
Apr-1999 | 50.20 | 55.93 | 59.58 | 62.24 | 0.94 | 0.96 |
May-1999 | 53.30 | 53.27 | 58.96 | 62.19 | 0.90 | 0.95 |
Jun-1999 | 67.90 | 64.62 | 59.26 | 62.13 | 1.09 | 0.95 |
Jul-1999 | 63.10 | 65.27 | 61.15 | 62.08 | 1.07 | 0.99 |
Aug-1999 | 55.30 | 60.18 | 64.10 | 62.03 | 0.94 | 1.03 |
Sep-1999 | 63.30 | 61.55 | 68.13 | 61.97 | 0.90 | 1.10 |
Oct-1999 | 81.50 | 78.71 | 72.19 | 61.92 | 1.09 | 1.17 |
Nov-1999 | 81.70 | 79.51 | 74.49 | 61.87 | 1.07 | 1.20 |
Dec-1999 | 69.20 | 70.60 | 75.20 | 61.82 | 0.94 | 1.22 |
Jan-2000 | 67.80 | 67.77 | 75.01 | 61.76 | 0.90 | 1.21 |
Feb-2000 | 82.70 | 81.01 | 74.30 | 61.71 | 1.09 | 1.20 |
Mar-2000 | 79.00 | 78.17 | 73.24 | 61.66 | 1.07 | 1.19 |
Apr-2000 | 66.20 | 67.71 | 72.13 | 61.60 | 0.94 | 1.17 |
May-2000 | 62.30 | 64.50 | 71.39 | 61.55 | 0.90 | 1.16 |
Jun-2000 | 79.30 | 77.40 | 70.99 | 61.50 | 1.09 | 1.15 |
Jul-2000 | 76.50 | 75.12 | 70.38 | 61.44 | 1.07 | 1.15 |
Aug-2000 | 65.50 | 64.11 | 68.29 | 61.39 | 0.94 | 1.11 |
Sep-2000 | 58.10 | 58.80 | 65.09 | 61.34 | 0.90 | 1.06 |
Oct-2000 | 66.80 | 67.90 | 62.28 | 61.28 | 1.09 | 1.02 |
Nov-2000 | 63.40 | 64.39 | 60.33 | 61.23 | 1.07 | 0.99 |
Dec-2000 | 56.10 | 56.10 | 59.05 | 61.18 | 0.94 | 0.97 |
Consider the time series decomposition output for Mobile Home Sales above. Mobile home shipments are modeled here
A) as exhibiting a flat trend.
B) as exhibiting a downward trend.
C) as exhibiting an upward trend.
D) None of the options are true.
54) Audit Trail — Statistics
Accuracy Measures | Value |
| Forecast Statistics | Value |
AIC | 309.51 |
| Durbin Watson(4) | 1.01 |
BIC | 313.82 |
| Mean | 61.54 |
Mean Absolute Percentage Error (MAPE) | 3.11 | % | Standard Deviation | 12.70 |
R-Square | 95.64 | % | Variance | 161.41 |
Adjusted R-Square | 95.57 | % | Ljung-Box | 58.17 |
Root Mean Square Error | 2.63 |
|
|
|
Theil | 0.29 |
|
|
|
Method Statistics | Value |
Method Selected | Decomposition |
Basic Method | Trend (Linear) Regression |
Decomposition Type | Multiplicative |
Components of Decomposition
Date | Original Data | Forecasted Data | Centered Moving Average | CMA Trend | Seasonal Indices | Cycle Factors |
Sep-1998 | 56.60 |
|
|
| 0.90 |
|
Oct-1998 | 49.10 |
|
|
| 1.09 |
|
Nov-1998 | 58.50 | 58.93 | 55.21 | 62.51 | 1.07 | 0.88 |
Dec-1998 | 57.50 | 54.10 | 57.63 | 62.45 | 0.94 | 0.92 |
Jan-1999 | 54.90 | 55.26 | 61.16 | 62.40 | 0.90 | 0.98 |
Feb-1999 | 70.10 | 66.69 | 61.16 | 62.35 | 1.09 | 0.98 |
Mar-1999 | 65.80 | 64.10 | 60.05 | 62.29 | 1.07 | 0.96 |
Apr-1999 | 50.20 | 55.93 | 59.58 | 62.24 | 0.94 | 0.96 |
May-1999 | 53.30 | 53.27 | 58.96 | 62.19 | 0.90 | 0.95 |
Jun-1999 | 67.90 | 64.62 | 59.26 | 62.13 | 1.09 | 0.95 |
Jul-1999 | 63.10 | 65.27 | 61.15 | 62.08 | 1.07 | 0.99 |
Aug-1999 | 55.30 | 60.18 | 64.10 | 62.03 | 0.94 | 1.03 |
Sep-1999 | 63.30 | 61.55 | 68.13 | 61.97 | 0.90 | 1.10 |
Oct-1999 | 81.50 | 78.71 | 72.19 | 61.92 | 1.09 | 1.17 |
Nov-1999 | 81.70 | 79.51 | 74.49 | 61.87 | 1.07 | 1.20 |
Dec-1999 | 69.20 | 70.60 | 75.20 | 61.82 | 0.94 | 1.22 |
Jan-2000 | 67.80 | 67.77 | 75.01 | 61.76 | 0.90 | 1.21 |
Feb-2000 | 82.70 | 81.01 | 74.30 | 61.71 | 1.09 | 1.20 |
Mar-2000 | 79.00 | 78.17 | 73.24 | 61.66 | 1.07 | 1.19 |
Apr-2000 | 66.20 | 67.71 | 72.13 | 61.60 | 0.94 | 1.17 |
May-2000 | 62.30 | 64.50 | 71.39 | 61.55 | 0.90 | 1.16 |
Jun-2000 | 79.30 | 77.40 | 70.99 | 61.50 | 1.09 | 1.15 |
Jul-2000 | 76.50 | 75.12 | 70.38 | 61.44 | 1.07 | 1.15 |
Aug-2000 | 65.50 | 64.11 | 68.29 | 61.39 | 0.94 | 1.11 |
Sep-2000 | 58.10 | 58.80 | 65.09 | 61.34 | 0.90 | 1.06 |
Oct-2000 | 66.80 | 67.90 | 62.28 | 61.28 | 1.09 | 1.02 |
Nov-2000 | 63.40 | 64.39 | 60.33 | 61.23 | 1.07 | 0.99 |
Dec-2000 | 56.10 | 56.10 | 59.05 | 61.18 | 0.94 | 0.97 |
Consider the time series decomposition output for Mobile Home Sales above. The seasonality of mobile home shipments
A) varies 3.11% from the average.
B) varies from 9% below average to 10% above the average.
C) varies from 10% below average to 9% above the average.
D) is negligible in this model.
55) Audit Trail — Statistics
Accuracy Measures | Value |
| Forecast Statistics | Value |
AIC | 309.51 |
| Durbin Watson(4) | 1.01 |
BIC | 313.82 |
| Mean | 61.54 |
Mean Absolute Percentage Error (MAPE) | 3.11 | % | Standard Deviation | 12.70 |
R-Square | 95.64 | % | Variance | 161.41 |
Adjusted R-Square | 95.57 | % | Ljung-Box | 58.17 |
Root Mean Square Error | 2.63 |
|
|
|
Theil | 0.29 |
|
|
|
Method Statistics | Value |
Method Selected | Decomposition |
Basic Method | Trend (Linear) Regression |
Decomposition Type | Multiplicative |
Components of Decomposition
Date | Original Data | Forecasted Data | Centered Moving Average | CMA Trend | Seasonal Indices | Cycle Factors |
Sep-1998 | 56.60 |
|
|
| 0.90 |
|
Oct-1998 | 49.10 |
|
|
| 1.09 |
|
Nov-1998 | 58.50 | 58.93 | 55.21 | 62.51 | 1.07 | 0.88 |
Dec-1998 | 57.50 | 54.10 | 57.63 | 62.45 | 0.94 | 0.92 |
Jan-1999 | 54.90 | 55.26 | 61.16 | 62.40 | 0.90 | 0.98 |
Feb-1999 | 70.10 | 66.69 | 61.16 | 62.35 | 1.09 | 0.98 |
Mar-1999 | 65.80 | 64.10 | 60.05 | 62.29 | 1.07 | 0.96 |
Apr-1999 | 50.20 | 55.93 | 59.58 | 62.24 | 0.94 | 0.96 |
May-1999 | 53.30 | 53.27 | 58.96 | 62.19 | 0.90 | 0.95 |
Jun-1999 | 67.90 | 64.62 | 59.26 | 62.13 | 1.09 | 0.95 |
Jul-1999 | 63.10 | 65.27 | 61.15 | 62.08 | 1.07 | 0.99 |
Aug-1999 | 55.30 | 60.18 | 64.10 | 62.03 | 0.94 | 1.03 |
Sep-1999 | 63.30 | 61.55 | 68.13 | 61.97 | 0.90 | 1.10 |
Oct-1999 | 81.50 | 78.71 | 72.19 | 61.92 | 1.09 | 1.17 |
Nov-1999 | 81.70 | 79.51 | 74.49 | 61.87 | 1.07 | 1.20 |
Dec-1999 | 69.20 | 70.60 | 75.20 | 61.82 | 0.94 | 1.22 |
Jan-2000 | 67.80 | 67.77 | 75.01 | 61.76 | 0.90 | 1.21 |
Feb-2000 | 82.70 | 81.01 | 74.30 | 61.71 | 1.09 | 1.20 |
Mar-2000 | 79.00 | 78.17 | 73.24 | 61.66 | 1.07 | 1.19 |
Apr-2000 | 66.20 | 67.71 | 72.13 | 61.60 | 0.94 | 1.17 |
May-2000 | 62.30 | 64.50 | 71.39 | 61.55 | 0.90 | 1.16 |
Jun-2000 | 79.30 | 77.40 | 70.99 | 61.50 | 1.09 | 1.15 |
Jul-2000 | 76.50 | 75.12 | 70.38 | 61.44 | 1.07 | 1.15 |
Aug-2000 | 65.50 | 64.11 | 68.29 | 61.39 | 0.94 | 1.11 |
Sep-2000 | 58.10 | 58.80 | 65.09 | 61.34 | 0.90 | 1.06 |
Oct-2000 | 66.80 | 67.90 | 62.28 | 61.28 | 1.09 | 1.02 |
Nov-2000 | 63.40 | 64.39 | 60.33 | 61.23 | 1.07 | 0.99 |
Dec-2000 | 56.10 | 56.10 | 59.05 | 61.18 | 0.94 | 0.97 |
Consider the time series decomposition output for Mobile Home Sales above.
A) There is no effect of cycle in this model.
B) The effect of cycle is dramatic in this model.
C) The effect of cycle is not accounted for in time series decomposition.
D) There is no way to determine the effect of cycle from the data displayed.
Document Information
Connected Book
Explore recommendations drawn directly from what you're reading
Chapter 5 Appendix - Combination Models
DOCX Ch. 5
Chapter 5 Regression Forecasting – Causal
DOCX Ch. 5
Chapter 6 Explanatory Models 2. Time-Series Decomposition
DOCX Ch. 6 Current
Chapter 7 ARIMA Forecasting Models
DOCX Ch. 7
Chapter 8 Predictive Analytics Helping To Make Sense Of Big Data
DOCX Ch. 8