In: Statistics and Probability
12.21 In Problem 12.9 on page 424, an agent for a real estate company wanted to predict the monthly rent for one bedroom apartments, based on the size of the apartment (stored in ). Using the results of that problem, Rent-SilverSpring r2, a. determine the coefficient of determination, and interpret its meaning. b. determine the standard error of the estimate. c. How useful do you think this regression model is for predicting the monthly rent? d. Can you think of other variables that might explain the varia tion in monthly rent?
Size (Square feet) | Rent ($) |
524 | 1110 |
616 | 1175 |
666 | 1190 |
830 | 1410 |
450 | 1210 |
550 | 1225 |
780 | 1480 |
815 | 1490 |
1070 | 1495 |
610 | 1680 |
835 | 1810 |
660 | 1625 |
590 | 1469 |
675 | 1395 |
744 | 1150 |
820 | 1140 |
912 | 1220 |
628 | 1434 |
645 | 1519 |
840 | 1105 |
800 | 1130 |
804 | 1250 |
950 | 1449 |
800 | 1168 |
787 | 1224 |
960 | 1391 |
750 | 1145 |
690 | 1093 |
840 | 1353 |
850 | 1530 |
965 | 1650 |
1060 | 1740 |
665 | 1235 |
775 | 1550 |
960 | 1545 |
827 | 1583 |
655 | 1575 |
535 | 1310 |
625 | 1195 |
749 | 1200 |
634 | 1185 |
641 | 1444 |
860 | 1385 |
740 | 1275 |
593 | 1050 |
880 | 1650 |
895 | 1340 |
692 | 1560 |
Solution:
Here, we have to construct the regression model for the prediction of the dependent variable Rent in $ based on the size (square feet) of the one bedroom apartment. Required regression model by using excel is given as below:
Regression Statistics |
||||||
Multiple R |
0.354314232 |
|||||
R Square |
0.125538575 |
|||||
Adjusted R Square |
0.106528544 |
|||||
Standard Error |
186.0406563 |
|||||
Observations |
48 |
|||||
ANOVA |
||||||
df |
SS |
MS |
F |
Significance F |
||
Regression |
1 |
228565.1932 |
228565.1932 |
6.603806955 |
0.013481438 |
|
Residual |
46 |
1592111.786 |
34611.12578 |
|||
Total |
47 |
1820676.979 |
||||
Coefficients |
Standard Error |
t Stat |
P-value |
Lower 95% |
Upper 95% |
|
Intercept |
992.9926979 |
147.3668699 |
6.73823566 |
2.25238E-08 |
696.3585787 |
1289.626817 |
Size (Square feet) |
0.493166782 |
0.19190957 |
2.569787336 |
0.013481438 |
0.10687286 |
0.879460704 |
For this regression model, the regression equation is given as below:
Rent ($) = 992.99 + 0.4932*Size (sq.ft.)
The correlation coefficient between two variables rent and size is given as 0.3543, which means there is a low positive linear relationship or association exists between the given two variables rent and size of an apartment.
Questions:
a. determine the coefficient of determination, and interpret its meaning.
The coefficient of determination or the value for R square for this regression model is given as 0.1255, which means only 12.55% of the variation in the dependent variable rent is explained by the independent variable size of the apartment.
b. determine the standard error of the estimate.
The standard error of the estimate is given as 186.0406563.
c. How useful do you think this regression model is for predicting the monthly rent?
The P-value for overall regression model is given as 0.013481438 which is less than 5% level of significance or alpha value 0.05, so we reject the null hypothesis that given regression model is not statistically significant. This means this regression model is useful for prediction of the monthly rent at 5% level of significance. (Please note that, P-value = 0.013481438 > α = 0.01, so this regression model is not useful at 1% level of significance.)
d. Can you think of other variables that might explain the variation in monthly rent?
Yes, there are several other variables that might explain the variation in monthly rent. The variables such as a location of the apartment, facilities available near the apartment, infrastructure of an apartment, etc. may cause the variation in the dependent variable monthly rent.