Johnson Filtration, Inc., provides maintenance service for water filtration systems throughout southern Florida. Customers contact Johnson with requests for maintenance service on their water filtration
Johnson Filtration, Inc., provides maintenance service for water filtration systems throughout southern Florida. Customers contact Johnson with requests for maintenance service on their water filtration systems. To estimate the service time and the service cost, Johnson's managers want to predict the repair time necessary for each maintenance request. Hence, repair time in hours is the dependent variable. Repair time is believed to be related to three factors; the number of months since the last maintenance service, the type of repair problem (mechanical or electrical), and the repairperson who performs the repair (Donna Newton or Bob Jones). Data for a sample of 10 service calls are reported in the following table.
Click on the datafile logo to reference the data.
Repair Time inHours
Months Since LastService
Type of Repair
Repairperson
2.9
2
Electrical
Donna Newton
3.0
6
Mechanical
Donna Newton
4.8
8
Electrical
Bob Jones
1.8
3
Mechanical
Donna Newton
2.9
2
Electrical
Donna Newton
4.9
7
Electrical
Bob Jones
4.2
9
Mechanical
Bob Jones
4.8
8
Mechanical
Bob Jones
4.4
4
Electrical
Bob Jones
4.5
6
Electrical
Donna Newton
(a)
Use the data to develop the simple linear regression equation to predict repair time given the number of months since the last maintenance service.
Letxrepresent the number of months since the last maintenance service.
If required, round your answers to four decimal places. For subtractive or negative numbers use a minus sign even if there is a + sign before the blank. (Example: -300).
= + x
Use the results to test the hypothesis that no relationship exists between repair time and the number of months since the last maintenance service at the 0.05 level of significance. What is the interpretation of this relationship?
Because thep-value is - Select your answer -greater thanless thanItem 3 0.05, we - Select your answer -cancannotItem 4 conclude that there is a relationship between repair time and the number of months since the last maintenance service.
What is the coefficient of determination?
If required, round your answers to four decimal places.
Interpret the coefficient of determination. If required, round your answer to one decimal place.
This regression model explains approximately % of the variation in the values of repair time in the sample.
(b)
Using the simple linear regression model developed in part (a), calculate the predicted repair time and residual for each of the 10 repairs in the data. NOTE: The table below is sorted in ascending order by value of the residual. Your output in Excel will not be sorted and therefore will look different. It is recommended that you copy the Excel residual output to a new area of the spreadsheet and then sort the copied output using Excel's sorting tools.
If required, round your answers to four decimal places. For subtractive or negative numbers use a minus sign.
Repair Timein Hours
Months SinceLast Service
Type of Repair
Repairperson
Predicted RepairTime in Hours
Residuals
1.8
3
Mechanical
Donna Newton
3.0
6
Mechanical
Donna Newton
4.2
9
Mechanical
Bob Jones
2.9
2
Electrical
Donna Newton
2.9
2
Electrical
Donna Newton
4.8
8
Electrical
Bob Jones
4.8
8
Mechanical
Bob Jones
4.5
6
Electrical
Donna Newton
4.9
7
Electrical
Bob Jones
4.4
4
Electrical
Bob Jones
Do you see any pattern in the residuals for the two types of repair? Do you see any pattern in the residuals for the two repairpersons? Do these results suggest any potential modifications to your simple linear regression model?
(i)
Mechanical repairs generally have negative residuals and electrical repairs generally have positive residuals. Two of the repairs made by Donna Newton have large negative residuals and repairs made by Bob Jones typically have positive residuals. The results suggest that using dummy variables to represent the type of repair and repairperson may enhance this fit of the regression model.
(ii)
Mechanical repairs generally have positive residuals and electrical repairs generally have negative residuals. Two of the repairs made by Donna Newton have large positive residuals and repairs made by Bob Jones typically have negative residuals. The results suggest that using dummy variables to represent the type of repair and repairperson may enhance this fit of the regression model.
(iii)
Mechanical repairs generally have negative residuals and electrical repairs generally have positive residuals. Two of the repairs made by Donna Newton have large negative residuals and repairs made by Bob Jones typically have positive residuals. The results suggest that using a dummy variable to represent only the type of repair may enhance this fit of the regression model.
(iv)
Mechanical repairs generally have positive residuals and electrical repairs generally have negative residuals. Two of the repairs made by Donna Newton have large positive residuals and repairs made by Bob Jones typically have negative residuals. The results suggest that the use of dummy variables is not needed.
- Select your answer -Option (i)Option (ii)Option (iii)Option (iv)Item 27
Create a scatter chart in Excel with months since last service on thex-axis and repair time in hours on they-axis for which the points representing electrical and mechanical repairs are shown in different shapes and or colors. Choose the correct chart below.
(i)
(ii)
(iii)
(iv)
- Select your answer -Chart (i)Chart (ii)Chart (iii)Chart (iv)Item 28
Create a similar scatter chart in Excel of months since last service and repair time in hours for which the points representing repairs by Bob Jones and Donna Newton are shown in different shapes and or colors. Choose the correct chart below.
(i)
(ii)
(iii)
(iv)
- Select your answer -Chart (i)Chart (ii)Chart (iii)Chart (iv)Item 29
Do these charts and the results of your residual analysis suggest the same potential modifications to your simple linear regression model?
- Select your answer -YesNoItem 30
(c)
Create a new dummy variable that is equal to 0 if the type of repair is mechanical and 1 if the type of repair is electrical. Develop the multiple regression equation in Excel to predict repair time, given the number of months since the last maintenance service and the type of repair.
Letx1represent the number of months since the last maintenance service.
Letx2represent the type of repair (a dummy variable).
If required, round your answers to four decimal places. For subtractive or negative numbers use a minus sign even if there is a + sign before the blank. (Example: -300).
= + x1+ x2
What are the interpretations of the estimated regression parameters?
(i)
b1is the best estimate of the change in repair time if we hold the repairperson constant and the type of repair is electrical, not mechanical.b2the best estimate of the change in repair time if we hold the type of repair constant and have a 1 month increase in the number of months since the last maintenance service.
(ii)
b1the best estimate of the change in repair time if we hold the number of months since the last maintenance service constant and the type of repair is electrical, not mechanical.b2is the best estimate of the change in repair time if we hold the type of repair constant and have a 1 month increase in the number of months since the last maintenance service.
(iii)
b1is the best estimate of the change in repair time if we hold the type of repair constant and have a 1 month increase in the number of months since the last maintenance service.b2the best estimate of the change in repair time if we hold the number of months since the last maintenance service constant and the type of repair is electrical, not mechanical.
(iv)
b1is the best estimate of the change in repair time if we hold the type of repair constant and have a 1 month increase in the number of months since the last maintenance service.b2the best estimate of the change in repair time if we hold the number of months since the last maintenance service constant and the type of repair is mechanical, not electrical.
- Select your answer -Option (i)Option (ii)Option (iii)Option (iv)Item 34
What is the coefficient of determination?
If required, round your answers to four decimal places.
Interpret the coefficient of determination. If required, round your answer to one decimal place.
This regression model explains approximately % of the variation in the values of repair time in the sample.
(d)
Create a new dummy variable that is equal to 0 if the repairperson is Bob Jones and 1 if the repairperson is Donna Newton. Develop the multiple regression equation in Excel to predict repair time, given the number of months since the last maintenance service and the repairperson.
Letx1represent the number of months since the last maintenance service.
Letx2represent the repairperson (a dummy variable).
If required, round your answers to four decimal places. For subtractive or negative numbers use a minus sign even if there is a + sign before the blank. (Example: -300)
= + x1+ x2
What are the interpretations of the estimated regression parameters?
(i)
b1the best estimate of the change in repair time if we hold the number of months since the last maintenance service constant and the repairperson is Donna Newton, not Bob Jones.b2is the best estimate of the change in repair time if we hold repairperson constant and have a 1 month increase in the number of months since the last maintenance service.
(ii)
b1is the best estimate of the change in repair time if we hold the type of repair constant and have a 1 month increase in the number of months since the last maintenance service.b2the best estimate of the change in repair time if we hold the number of months since the last maintenance service constant and the type of repair is electrical, not mechanical.
(iii)
b1the best estimate of the change in repair time if we hold the number of months since the last maintenance service constant and the type of repair is electrical, not mechanical.b2is the best estimate of the change in repair time if we hold the type of repair constant and have a 1 month increase in the number of months since the last maintenance service.
(iv)
b1is the best estimate of the change in repair time if we hold repairperson constant and have a 1 month increase in the number of months since the last maintenance service.b2the best estimate of the change in repair time if we hold the number of months since the last maintenance service constant and the repairperson is Donna Newton, not Bob Jones.
- Select your answer -Option (i)Option (ii)Option (iii)Option (iv)Item 40
What is the coefficient of determination?
If required, round your answers to four decimal places.
Interpret the coefficient of determination. If required, round your answer to one decimal place.
This regression model explains approximately % of the variation in the values of repair time in the sample.
(e)
Develop the multiple regression equation to predict repair time given the number of months since the last maintenance service, the type of repair, and the repairperson.
Letx1represent the number of months since the last maintenance service.
Letx2represent the type of repair (a dummy variable).
Letx3represent the repairperson (a dummy variable).
If required, round your answers to four decimal places. For subtractive or negative numbers use a minus sign even if there is a + sign before the blank. (Example: -300).
= + x1+ x2+ x3
What are the interpretations of the estimated regression parameters?
(i)
b1is the best estimate of the change in repair time if we hold the number of months since the last maintenance service and type of repair constant and the repairperson is Bob Jones.b2is the best estimate of the change in repair time if we hold type of repair and repairperson constant and have a 1 month increase in the number of months since the last maintenance service.b3the best estimate of the change in repair time if we hold the number of months since the last maintenance service and repairperson constant and the type of repair is electrical and not mechanical.
(ii)
b1is the best estimate of the change in repair time if we hold type of repair and repairperson constant and have a 1 month increase in the number of months since the last maintenance service.b2the best estimate of the change in repair time if we hold the number of months since the last maintenance service and repairperson constant and the type of repair is electrical and not mechanical.b3is the best estimate of the change in repair time if we hold the number of months since the last maintenance service and type of repair constant and the repairperson is Donna Newton.
(iii)
b1is the best estimate of the change in repair time if we hold the number of months since the last maintenance and type of repair constant and the type of repair is mechanical and not electrical.b2the best estimate of the change in repair time if we hold the number of months since the last maintenance service and type of repair constant and have a 1 month increase in the number of months since the last maintenance service.b3is the best estimate of the change in repair time if we hold the number of months since the last maintenance service and type of repair constant and the repairperson is Bob Jones.
- Select your answer -Option (i)Option (ii)Option (iii)Item 47
What is the coefficient of determination?
If required, round your answers to four decimal places.
Interpret the coefficient of determination. If required, round your answer to one decimal place.
This regression model explains approximately % of the variation in the values of repair time in the sample.
(f)
Which of these models would you use? Why?
(i)
The preferred model is the one with the lowest coefficient of determination, so the best model to use is in part (c).
(ii)
The preferred model is the one with the lowest coefficient of determination, so the best model to use is in part (d).
(iii)
The preferred model is the simplest that works well, so the best model to use is in part (c).
(iv)
The preferred model is the one with the highest coefficient of determination, so the best model to use is in part (c).
(v)
The preferred model is the one with the highest coefficient of determination, so the best model to use is in part (d).