In: Math
Customer |
Months Since |
Type of Repair Electrical (0) Mechanical (1) (x2) |
Truck (1) (x3) |
Mileage of Vehicle (x4) |
Repair Time |
1 |
2 |
1 |
1 |
98855 |
2.9 |
2 |
6 |
0 |
0 |
86883 |
3 |
3 |
8 |
1 |
1 |
75645 |
4.8 |
4 |
3 |
0 |
0 |
97823 |
1.8 |
5 |
2 |
1 |
1 |
62099 |
2.9 |
6 |
7 |
1 |
0 |
67697 |
4.9 |
7 |
9 |
0 |
1 |
73113 |
4.2 |
8 |
8 |
0 |
0 |
76240 |
4.8 |
9 |
4 |
1 |
1 |
71170 |
4.4 |
10 |
6 |
1 |
1 |
60626 |
4.5 |
An analyst at a local automotive garage wanted to see if there were relationships between repair time in hours (y) and months since last service(x1), type of repair(x2), whether it was a truck or car(x3), or the mileage of the vehicle(x4). Use a level of significance of 0.05.
1:
The dependent variable is:
Repair times in hour
-----------------------------
2:
The independent variables:
Months Since Last Service,
Type of Repair Electrical (0) Mechanical (1),
Truck (1) or Car (0),
Mileage of Vehicle
-------------------------
3:
Following is the output of regression analysis:
SUMMARY OUTPUT | ||||||
Regression Statistics | ||||||
Multiple R | 0.936550158 | |||||
R Square | 0.877126198 | |||||
Adjusted R Square | 0.778827156 | |||||
Standard Error | 0.507390569 | |||||
Observations | 10 | |||||
ANOVA | ||||||
df | SS | MS | F | Significance F | ||
Regression | 4 | 9.18877405 | 2.297193512 | 8.923039162 | 0.016897485 | |
Residual | 5 | 1.28722595 | 0.25744519 | |||
Total | 9 | 10.476 | ||||
Coefficients | Standard Error | t Stat | P-value | Lower 95% | Upper 95% | |
Intercept | 2.284192218 | 1.764451241 | 1.294562391 | 0.252029574 | -2.251474091 | 6.819858526 |
X1 | 0.353129727 | 0.082490263 | 4.280865589 | 0.007857034 | 0.141081756 | 0.565177697 |
X2 | 1.164299608 | 0.478798629 | 2.431710406 | 0.059255638 | -0.06649145 | 2.395090667 |
X3 | -0.171488843 | 0.406240421 | -0.422136338 | 0.690462098 | -1.215763089 | 0.872785402 |
X4 | -1.30116E-05 | 1.6542E-05 | -0.786581632 | 0.467152578 | -5.55342E-05 | 2.95109E-05 |
The prediction equation is
y' = 2.2842 +0.3531*x1+1.1643*x2-0.1715*x3-0.000013*X4
----------------
4:
The p-value of F is 0.0169
Since p-value is less than 0.05 so model is significant at 5% level of significance.
--------------------
5:
The p-value of all variable except X1 is greater than 0.05 so only this variable is significant to the model.
-----------------
6:
Following is the output of regression analysis generated by excel:
SUMMARY OUTPUT | ||||||
Regression Statistics | ||||||
Multiple R | 0.730873795 | |||||
R Square | 0.534176504 | |||||
Adjusted R Square | 0.475948567 | |||||
Standard Error | 0.781022322 | |||||
Observations | 10 | |||||
ANOVA | ||||||
df | SS | MS | F | Significance F | ||
Regression | 1 | 5.596033058 | 5.596033058 | 9.17388683 | 0.016338159 | |
Residual | 8 | 4.879966942 | 0.609995868 | |||
Total | 9 | 10.476 | ||||
Coefficients | Standard Error | t Stat | P-value | Lower 95% | Upper 95% | |
Intercept | 2.147272727 | 0.604977289 | 3.549344356 | 0.007516627 | 0.752192597 | 3.542352857 |
X1 | 0.304132231 | 0.100412033 | 3.02884249 | 0.016338159 | 0.072581669 | 0.535682794 |
The regression equation is:
y'=2.1473 +0.3041*X1
-----------------
7:
Here we have
X1=6, X2=0, X3=0, X4 = 90000
The required predicted value is:
y' = 2.2842 +0.3531*6+1.1643*0-0.1715*0-0.000013*90000=3.2328
Answer: 3.2