In: Statistics and Probability
An agent for a residential real estate company in a suburb located outside of Washington, DC, has the business objective of developing more accurate estimates of the monthly rental cost for apartments. Toward that goal, the agent would like to use the size of an apartment, as defined by the square footage to predict the monthly rental cost. The agent selects a sample of one-bedroom apartments and collects and stores the data.
a. Construct a scatter plot.
b. Use the least-squares method to determine the regression coefficients b0 and b1.
c. Interpret the meaning of b0 and b1 in this problem.
d. Predict the mean monthly rent for an apartment that has 800 square feet.
e. Why would it not be appropriate to use the model to predict the monthly rent for apartments that have 1,500 square feet?
f. Your friends Jim and Jennifer are considering signing a lease for a one-bedroom apartment in this residential neighborhood. They are trying to decide between two apartments, one with 800 square feet for a monthly rent of $1,130 and the other with 830 square feet for a monthly rent of $1,410. Based on (a) through (d), which apartment do you think is a better deal?
X (Rent) | Y (Sq Ft) |
950 | 850 |
1600 | 1450 |
1200 | 1085 |
1500 | 1232 |
950 | 718 |
1700 | 1485 |
1650 | 1185 |
935 | 726 |
875 | 700 |
1150 | 956 |
1400 | 1100 |
1650 | 1285 |
2300 | 1985 |
1800 | 1985 |
1400 | 1369 |
1450 | 1175 |
1450 | 1225 |
1100 | 1245 |
1700 | 1259 |
1200 | 1150 |
1150 | 896 |
1600 | 1361 |
1650 | 1040 |
1200 | 755 |
800 | 1000 |
1750 | 1200 |
a)
Following is the scatter plot:
(b)
Following table shows the calculations
X | Y | X^2 | Y^2 | XY | |
950 | 850 | 902500 | 722500 | 807500 | |
1600 | 1450 | 2560000 | 2102500 | 2320000 | |
1200 | 1085 | 1440000 | 1177225 | 1302000 | |
1500 | 1232 | 2250000 | 1517824 | 1848000 | |
950 | 718 | 902500 | 515524 | 682100 | |
1700 | 1485 | 2890000 | 2205225 | 2524500 | |
1650 | 1185 | 2722500 | 1404225 | 1955250 | |
935 | 726 | 874225 | 527076 | 678810 | |
875 | 700 | 765625 | 490000 | 612500 | |
1150 | 956 | 1322500 | 913936 | 1099400 | |
1400 | 1100 | 1960000 | 1210000 | 1540000 | |
1650 | 1285 | 2722500 | 1651225 | 2120250 | |
2300 | 1985 | 5290000 | 3940225 | 4565500 | |
1800 | 1985 | 3240000 | 3940225 | 3573000 | |
1400 | 1369 | 1960000 | 1874161 | 1916600 | |
1450 | 1175 | 2102500 | 1380625 | 1703750 | |
1450 | 1225 | 2102500 | 1500625 | 1776250 | |
1100 | 1245 | 1210000 | 1550025 | 1369500 | |
1700 | 1259 | 2890000 | 1585081 | 2140300 | |
1200 | 1150 | 1440000 | 1322500 | 1380000 | |
1150 | 896 | 1322500 | 802816 | 1030400 | |
1600 | 1361 | 2560000 | 1852321 | 2177600 | |
1650 | 1040 | 2722500 | 1081600 | 1716000 | |
1200 | 755 | 1440000 | 570025 | 906000 | |
800 | 1000 | 640000 | 1000000 | 800000 | |
1750 | 1200 | 3062500 | 1440000 | 2100000 | |
Total | 36110 | 30417 | 53294850 | 38277489 | 44645210 |
(c)
Slope shows that for each additional sq.ft., rent is increased by $0.7637.
Intercept shows that for apartment with 0 sq. ft. rent is $109.2228. It is meaningless in this case.
(d)
(e)
It should be useful to predict he monthly rent for apartments that have 1,500 square feet because 1500 is in the range of X used to make the model.
(f)
Residual for X =800 :
$1,130 - $720.18 = $409.82
----------------------
Residual for X =830 :
$1410 - $743.09 = $666.91
Since residual is small for 800 so 800 square feet apartment seems to be a better deal.