Chapter 13 - Regression and Forecasting Models 1. Forecasting models can be divided into three groups. They are: a. time series, optimization, and simulation methods b. judgmental, regression, and extrapolation methods c. judgmental, random, and linear methods d. linear, non-linear, and extrapolation methods ANSWER: b POINTS: 1 DIFFICULTY: Easy |Bloom's Knowledge QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.1 Introduction OTHER: BUSPROG - Communication |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 2. In regression analysis, the variable we are trying to explain or predict is called the a. independent variable b. dependent variable c. regression variable d. statistical variable ANSWER: b POINTS: 1 DIFFICULTY: Easy |Bloom's Knowledge QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.2 Overview of Regression Models OTHER: BUSPROG - Communication |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 3. In multiple regression, the regression coefficients reflect the expected change in: a. Y when the associated X value increases by one unit, holding the other variables constant b. X when the associated Y value increases by one unit, holding the other variables constant c. Y when the associated X value decreases by one unit, holding the other variables constant d. X when the associated Y value decreases by one unit, holding the other variables constant ANSWER: a POINTS: 1 DIFFICULTY: Easy |Bloom's Evaluation QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.4 Multiple Regression Models OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM Copyright Cengage Learning. Powered by Cognero. Page 1 Chapter 13 - Regression and Forecasting Models 4. The biggest challenge of regression is: a. differentiating the independent variable(s) from the dependent variable(s) b. determining which independent variable(s) to include c. collecting accurate data d. properly coding the variables ANSWER: b POINTS: 1 DIFFICULTY: Easy |Bloom's Evaluation QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.4 Multiple Regression Models OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 5. The adjusted R2 adjusts R2 for: a. non-linearity b. outliers c. low correlation d. the number of explanatory variables in a multiple regression model ANSWER: d POINTS: 1 DIFFICULTY: Moderate |Bloom's Comprehension QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.4 Multiple Regression Models - Solution OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 6. A "fan" shape in a scatterplot indicates: a. nonconstant error variance b. a nonlinear relationship c. the absence of outliers d. sampling error ANSWER: a POINTS: 1 DIFFICULTY: Moderate |Bloom's Comprehension QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.4 Multiple Regression Models - A Caution about Regression Assumptions OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM Copyright Cengage Learning. Powered by Cognero. Page 2 Chapter 13 - Regression and Forecasting Models DATE MODIFIED: 10/21/2017 10:04 PM 7. The term autocorrelation refers to: a. the analyzed data refers to itself b. the sample is related too closely to the population c. the data are in a loop (values repeat themselves) d. time series variables are usually related to their own past values ANSWER: d POINTS: 1 DIFFICULTY: Easy |Bloom's Comprehension QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.4 Multiple Regression Models - A Caution about Regression Assumptions OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 8. Which of the following is not one of the commonly used summary measures for forecast errors? a. MAE (mean absolute error) b. MFE (mean forecast error) c. RMSE (root mean square error) d. MAPE (mean absolute percentage error) ANSWER: b POINTS: 1 DIFFICULTY: Easy |Bloom's Knowledge QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.5 Overview of Time Series Models - Measures of Forecast Error OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 9. When using the moving average method, you must select ____ which represent(s) the number of terms in the moving average. a. a smoothing constant b. the explanatory variables c. an alpha value d. a span ANSWER: d POINTS: 1 DIFFICULTY: Easy |Bloom's Comprehension QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.6 Moving Average Models Copyright Cengage Learning. Powered by Cognero. Page 3 Chapter 13 - Regression and Forecasting Models OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 10. A model that uses temperature, season of the year (fall, winter, spring, summer), and whether or not it is a weekend, to predict the # of customers for the day would include how many independent variables? a. 3 b. 5 c. 6 d. 7 ANSWER: b POINTS: 1 DIFFICULTY: Easy |Bloom's Comprehension QUESTION TYPE: Multiple Choice HAS VARIABLES: False TOPICS: 13.7 Exponential Smoothing Models - Winter's Method for Seasonality OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 11. The residual is defined as the difference between the actual and predicted, or fitted values of the response variable. a. True b. False ANSWER: True POINTS: 1 DIFFICULTY: Moderate |Bloom's Comprehension QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.2 Overview of Regression Models - The Least Squares Line OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 12. The least squares line is the line that minimizes the sum of the residuals. a. True b. False ANSWER: False POINTS: 1 DIFFICULTY: Moderate |Bloom's Comprehension QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.2 Overview of Regression Models - The Least Squares Line OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM Copyright Cengage Learning. Powered by Cognero. Page 4 Chapter 13 - Regression and Forecasting Models DATE MODIFIED: 10/21/2017 10:04 PM 13. A useful graph in almost any regression analysis is a scatterplot of residuals (on the vertical axis) versus fitted values (on the horizontal axis), where a "good" fit not only has small residuals, but it has residuals scattered randomly around zero with no apparent pattern. a. True b. False ANSWER: True POINTS: 1 DIFFICULTY: Moderate |Bloom's Comprehension QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.3 Simple Regression Models - Discussion of the Results OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 14. In reference to the equation , the value 0.10 is the expected change in Y per unit change in X. a. True b. False ANSWER: True POINTS: 1 DIFFICULTY: Easy |Bloom's Evaluation QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.3 Simple Regression Models OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 15. In regression analysis, we can often use the standard error of estimate se to judge which of several potential regression equations is the most useful. a. True b. False ANSWER: True POINTS: 1 DIFFICULTY: Moderate |Bloom's Comprehension QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.2 Overview of Regression Models - Measures of Goodness of Fit OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM Copyright Cengage Learning. Powered by Cognero. Page 5 Chapter 13 - Regression and Forecasting Models 16. The percentage of variation explained R2 is the square of the correlation between the observed Y values and the fitted Y values. a. True b. False ANSWER: True POINTS: 1 DIFFICULTY: Moderate |Bloom's Comprehension QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.4 Multiple Regression Models - Discussion of the Results OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 17. The adjusted R2 is used primarily to monitor whether extra explanatory variables really belong in a multiple regression model. a. True b. False ANSWER: True POINTS: 1 DIFFICULTY: Moderate |Bloom's Comprehension QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.4 Multiple Regression Models - Discussion of the Results OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 18. A time series can consist of four different components: trend, seasonal, cyclical, and random (or noise). a. True b. False ANSWER: True POINTS: 1 DIFFICULTY: Easy |Bloom's Comprehension QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.5 Overview of Time Series Models OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 19. The smoothing constant used in simple exponential smoothing is analogous to the span in moving averages. a. True b. False Copyright Cengage Learning. Powered by Cognero. Page 6 Chapter 13 - Regression and Forecasting Models ANSWER: POINTS: DIFFICULTY: QUESTION TYPE: HAS VARIABLES: TOPICS: OTHER: DATE CREATED: DATE MODIFIED: True 1 Easy |Bloom's Comprehension True / False False 13.7 Exponential Smoothing Models - Simple Exponential Smoothing BUSPROG - Analytic |DISC - Regression and Forecasting 5/17/2017 3:51 PM 10/21/2017 10:04 PM 20. Winter's method is an exponential smoothing method, which is appropriate for a series with trend but no seasonality. a. True b. False ANSWER: False POINTS: 1 DIFFICULTY: Easy |Bloom's Comprehension QUESTION TYPE: True / False HAS VARIABLES: False TOPICS: 13.7 Exponential Smoothing Models - Winter's Method for Seasonality OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM Exhibit 13-1 An express delivery service company recently conducted a study to investigate the relationship between the cost of shipping a package (Y), the package weight in pounds (X1), and the distance shipped in miles (X2). Twenty packages were randomly selected from among the large number received for shipment, and a detailed analysis of the shipping cost was conducted for each package. The sample information is shown in the table below: Copyright Cengage Learning. Powered by Cognero. Page 7 Chapter 13 - Regression and Forecasting Models 21. Refer to Exhibit 13-1. Estimate a simple linear regression model involving shipping cost and package weight. Interpret the slope coefficient of the least squares line as well as R2. ANSWER: POINTS: DIFFICULTY: QUESTION TYPE: HAS VARIABLES: PREFACE NAME: TOPICS: OTHER: DATE CREATED: DATE MODIFIED: As the package weight increases by one pound, the cost of shipping the package increases by $1.49 on average. This simple linear regression model explains 59.85% of the total variation in the cost of shipment. 1 Moderate |Bloom's Analysis Subjective Short Answer False Exhibit 13-1 13.3 Simple Regression Models - Discussion of the Results BUSPROG - Analytic |DISC - Regression and Forecasting 5/17/2017 3:51 PM 10/21/2017 10:04 PM Copyright Cengage Learning. Powered by Cognero. Page 8 Chapter 13 - Regression and Forecasting Models 22. Refer to Exhibit 13-1. Add the second explanatory variable (distance shipped) to the regression model. Estimate and interpret the slopes of this expanded model. ANSWER: POINTS: DIFFICULTY: QUESTION TYPE: HAS VARIABLES: PREFACE NAME: TOPICS: OTHER: DATE CREATED: DATE MODIFIED: Now, holding all else constant, the cost of shipping a package rises by approximately $1.29 when the package weight increases by one pound. Furthermore, holding all else constant, the cost of shipping a package rises by approximately $0.04 when the distance shipped increases by one mile. 1 Moderate |Bloom's Analysis Subjective Short Answer False Exhibit 13-1 13.4 Multiple Regression Models - Discussion of the Results BUSPROG - Analytic |DISC - Regression and Forecasting 5/17/2017 3:51 PM 10/21/2017 10:04 PM 23. Refer to Exhibit 13-1. How does the R2 value for this multiple regression model compare to that of the simple regression model estimated above? Interpret the adjusted R2 values for the two models. ANSWER: Both the R2 and adjusted R2 values have increased considerably with the addition of the second explanatory variable; the multiple regression model fits the given data better than did the simple linear model. The R2 and adjusted R2 values are quite similar for the multiple regression model. Therefore, both explanatory variables are adding to the explanation of the variation in the cost of shipment. POINTS: 1 DIFFICULTY: Moderate |Bloom's Analysis QUESTION TYPE: Subjective Short Answer HAS VARIABLES: False PREFACE NAME: Exhibit 13-1 TOPICS: 13.4 Multiple Regression Models - Discussion of the Results OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM Exhibit 13-2 Copyright Cengage Learning. Powered by Cognero. Page 9 Chapter 13 - Regression and Forecasting Models The station manager of a local television station is interested in predicting the amount of television (in hours) that people will watch in the viewing area. The explanatory variables are: X1 age (in years), X2 education (highest level obtained, in years) and X3 family size (number of family members in household). The multiple regression output is shown below: Summary measures Multiple R 0.8440 R-Square 0.7123 Adj R-Square 0.6644 StErr of 0.5598 Estimate ANOVA Table Source df Explained 3 Unexplained 18 SS 13.9682 5.6413 MS 4.6561 0.3134 F 14.8564 p-value 0.0000 Regression coefficients Constant Age Education Family Size Coefficient 1.683 −0.0498 0.2135 0.0405 Std Err 1.1696 0.0199 0.0503 0.0784 t-value 1.4389 −2.5018 4.2426 0.5168 p-value 0.1674 0.0222 0.0005 0.6116 24. Refer to Exhibit 13-2. Use the information above to estimate the linear regression model. ANSWER: POINTS: DIFFICULTY: QUESTION TYPE: HAS VARIABLES: PREFACE NAME: TOPICS: OTHER: DATE CREATED: DATE MODIFIED: 1 Easy |Bloom's Analysis Subjective Short Answer False Exhibit 13-2 13.4 Multiple Regression Models - Discussion of the Results BUSPROG - Analytic |DISC - Regression and Forecasting 5/17/2017 3:51 PM 10/21/2017 10:04 PM 25. Refer to Exhibit 13-2. Interpret each of the estimated regression coefficients of the regression model above. ANSWER: This model shows that the number of hours people spend watching television decreases by 0.0498 hours on average with every additional year in age (while holding education level and family size constant); increases by 0.2135 hours on average with a person's education level increasing by one year (while holding age and family size constant), and increases by 0.0405 hours on average as the family size increases by one person (while holding age and education level constant). POINTS: 1 DIFFICULTY: Easy |Bloom's Analysis QUESTION TYPE: Subjective Short Answer HAS VARIABLES: False PREFACE NAME: Exhibit 13-2 TOPICS: 13.4 Multiple Regression Models - Discussion of the Results Copyright Cengage Learning. Powered by Cognero. Page 10 Chapter 13 - Regression and Forecasting Models OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM 26. Refer to Exhibit 13-2. Identify and interpret the percentage of variation explained (R2) for the model. ANSWER: The percentage of variation explained R2 = 0.7123; this represents 71.23% of the variation in the hours spent watching television can be explained by this regression equation. POINTS: 1 DIFFICULTY: Easy |Bloom's Analysis QUESTION TYPE: Subjective Short Answer HAS VARIABLES: False PREFACE NAME: Exhibit 13-2 TOPICS: 13.4 Multiple Regression Models - Discussion of the Results OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:51 PM DATE MODIFIED: 10/21/2017 10:04 PM Exhibit 13-3 The quarterly numbers of applications for home mortgage loans at a branch office of a large bank are recorded in the table below. Quarter-Year 1-13 2-13 3-13 4-13 1-14 2-14 3-14 4-14 1-15 2-15 3-15 4-15 1-16 2-16 3-16 4-16 1-17 2-17 3-17 4-17 1-18 2-18 Applications 96 114 112 81 97 103 120 99 105 110 117 96 74 94 100 96 95 122 113 100 102 96 Copyright Cengage Learning. Powered by Cognero. Page 11 Chapter 13 - Regression and Forecasting Models 3-18 4-18 116 98 27. Refer to Exhibit 13-3. Obtain a time series chart. Which of the forecasting models (one or more) do you think should be used for forecasting based on this chart? Why? ANSWER: There is no apparent trend or seasonality, so a simple smoothing model (moving average or simple exponential smoothing) is a reasonable choice. It appears the data are random, so it may be difficult to find a model that fits well. POINTS: DIFFICULTY: QUESTION TYPE: HAS VARIABLES: PREFACE NAME: TOPICS: OTHER: DATE CREATED: DATE MODIFIED: 1 Moderate |Bloom's Analysis Subjective Short Answer False Exhibit 13-3 13.5 Overview of Time Series Models BUSPROG - Analytic |DISC - Regression and Forecasting 5/17/2017 3:51 PM 10/21/2017 10:04 PM 28. Refer to Exhibit 13-3. Use a moving average model to forecast these data, requesting 4 quarters of future forecasts. Use a span of 4 quarters. Copyright Cengage Learning. Powered by Cognero. Page 12 Chapter 13 - Regression and Forecasting Models ANSWER: POINTS: DIFFICULTY: QUESTION TYPE: HAS VARIABLES: PREFACE NAME: TOPICS: OTHER: DATE CREATED: DATE MODIFIED: 1 Moderate |Bloom's Analysis Subjective Short Answer False Exhibit 13-3 13.6 Moving Average Models BUSPROG - Analytic |DISC - Regression and Forecasting 5/17/2017 3:51 PM 10/21/2017 10:04 PM 29. Refer to Exhibit 13-3. Use simple exponential smoothing to forecast these data, requesting 4 quarters of future forecasts. Use the default smoothing constant of 0.10. Is this better than the moving average model? ANSWER: The MAPE has increased from 9.24% to 9.5%, so this model fits the data worse than the moving average model. POINTS: 1 DIFFICULTY: Moderate |Bloom's Analysis QUESTION TYPE: Subjective Short Answer HAS VARIABLES: False PREFACE NAME: Exhibit 13-3 TOPICS: 13.7 Exponential Smoothing Models - Simple Exponential Smoothing OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:52 PM Copyright Cengage Learning. Powered by Cognero. Page 13 Chapter 13 - Regression and Forecasting Models DATE MODIFIED:10/21/2017 10:04 PM 30. Refer to Exhibit 13-3. Obtain a simple exponential smoothing forecast again, this time optimizing the smoothing constant. Does it make much of an improvement? ANSWER: It doesn't seem to matter much whether we use a smoothing constant of 0.10 or the optimal smoothing constant (which turns out to be 0.079). Neither model fits the data very well, and the MAPE is still higher than the MAPE for the moving average model. POINTS: 1 DIFFICULTY: Easy |Bloom's Analysis QUESTION TYPE: Subjective Short Answer HAS VARIABLES: False PREFACE NAME: Exhibit 13-3 TOPICS: 13.7 Exponential Smoothing Models - Simple Exponential Smoothing OTHER: BUSPROG - Analytic |DISC - Regression and Forecasting DATE CREATED: 5/17/2017 3:52 PM DATE MODIFIED 10/21/2017 10:04 PM : Copyright Cengage Learning. Powered by Cognero. Page 14