In: Statistics and Probability
Use the following data to answer the questions below | |||
SAT | Income | GPA | |
1651 | 47000 | 2.79 | |
1581 | 34000 | 2.97 | |
1790 | 90000 | 3.48 | |
1626 | 60000 | 2.5 | |
1754 | 113000 | 2.92 | |
1754 | 71000 | 3.76 | |
1706 | 105000 | 2.8 | |
1765 | 59000 | 3.26 | |
1786 | 50000 | 3.89 | |
1686 | 27000 | 3.67 | |
1790 | 107000 | 3.31 | |
1707 | 109000 | 3.16 | |
1804 | 81000 | 3.73 | |
1712 | 62000 | 3.21 | |
1607 | 72000 | 2.8 | |
1738 | 63000 | 3.7 | |
1790 | 55000 | 3.86 | |
1796 | 64000 | 3.91 | |
1547 | 47000 | 2.63 | |
1692 | 89000 | 2.98 | |
1711 | 42000 | 3.45 | |
1689 | 70000 | 3.06 | |
1740 | 118000 | 2.88 | |
1940 | 113000 | 3.96 |
a | What is the model for income to predict GPA | ||||
b | What is the estimated GPA for someone with an income of $100,000? | ||||
c | For each additional $1,000 in income, how much does their GPA increase? | ||||
d | How much variation in GPA is explained by Income? |
a.
X - Mx | Y - My | (X - Mx)2 | (X - Mx)(Y - My) |
-25833.3333 | -0.4883 | 667361111.1 | 12615.2778 |
-38833.3333 | -0.3083 | 1508027778 | 11973.6111 |
17166.6667 | 0.2017 | 294694444.4 | 3461.9444 |
-12833.3333 | -0.7783 | 164694444.4 | 9988.6111 |
40166.6667 | -0.3583 | 1613361111 | -14393.0556 |
-1833.3333 | 0.4817 | 3361111.111 | -883.0556 |
32166.6667 | -0.4783 | 1034694444 | -15386.3889 |
-13833.3333 | -0.0183 | 191361111.1 | 253.6111 |
-22833.3333 | 0.6117 | 521361111.1 | -13966.3889 |
-45833.3333 | 0.3917 | 2100694444 | -17951.3889 |
34166.6667 | 0.0317 | 1167361111 | 1081.9444 |
36166.6667 | -0.1183 | 1308027778 | -4279.7222 |
8166.6667 | 0.4517 | 66694444.44 | 3688.6111 |
-10833.3333 | -0.0683 | 117361111.1 | 740.2778 |
-833.3333 | -0.4783 | 694444.4444 | 398.6111 |
-9833.3333 | 0.4217 | 96694444.44 | -4146.3889 |
-17833.3333 | 0.5817 | 318027777.8 | -10373.0556 |
-8833.3333 | 0.6317 | 78027777.78 | -5579.7222 |
-25833.3333 | -0.6483 | 667361111.1 | 16748.6111 |
16166.6667 | -0.2983 | 261361111.1 | -4823.0556 |
-30833.3333 | 0.1717 | 950694444.4 | -5293.0556 |
-2833.3333 | -0.2183 | 8027777.778 | 618.6111 |
45166.6667 | -0.3983 | 2040027778 | -17991.3889 |
40166.6667 | 0.6817 | 1613361111 | 27380.2778 |
SS: 16793333333.3333 | SP: -26116.6667 |
Sum of X = 1748000
Sum of Y = 78.68
Mean X = 72833.3333
Mean Y = 3.2783
Sum of squares (SSX) = 16793333333.3333
Sum of products (SP) = -26116.6667
Regression Equation = ŷ = bX + a
b = SP/SSX =
-26116.67/16793333333.33 = 0
a = MY - bMX = 3.28 -
(0*72833.33) = 3.3916
ŷ = 0X + 3.3916
b. For income of $100,000, ŷ = 3.3916
c. As here slope is 0, so value here is 0
d. To find this we will first need to find r
X - Mx | Y - My | (X - Mx)2 | (Y - My)2 | (X - Mx)(Y - My) |
-25833.333 | -0.488 | 667361111.1 | 0.238 | 12615.278 |
-38833.333 | -0.308 | 1508027778 | 0.095 | 11973.611 |
17166.667 | 0.202 | 294694444.4 | 0.041 | 3461.944 |
-12833.333 | -0.778 | 164694444.4 | 0.606 | 9988.611 |
40166.667 | -0.358 | 1613361111 | 0.128 | -14393.056 |
-1833.333 | 0.482 | 3361111.111 | 0.232 | -883.056 |
32166.667 | -0.478 | 1034694444 | 0.229 | -15386.389 |
-13833.333 | -0.018 | 191361111.1 | 0 | 253.611 |
-22833.333 | 0.612 | 521361111.1 | 0.374 | -13966.389 |
-45833.333 | 0.392 | 2100694444 | 0.153 | -17951.389 |
34166.667 | 0.032 | 1167361111 | 0.001 | 1081.944 |
36166.667 | -0.118 | 1308027778 | 0.014 | -4279.722 |
8166.667 | 0.452 | 66694444.44 | 0.204 | 3688.611 |
-10833.333 | -0.068 | 117361111.1 | 0.005 | 740.278 |
-833.333 | -0.478 | 694444.444 | 0.229 | 398.611 |
-9833.333 | 0.422 | 96694444.44 | 0.178 | -4146.389 |
-17833.333 | 0.582 | 318027777.8 | 0.338 | -10373.056 |
-8833.333 | 0.632 | 78027777.78 | 0.399 | -5579.722 |
-25833.333 | -0.648 | 667361111.1 | 0.42 | 16748.611 |
16166.667 | -0.298 | 261361111.1 | 0.089 | -4823.056 |
-30833.333 | 0.172 | 950694444.4 | 0.029 | -5293.056 |
-2833.333 | -0.218 | 8027777.778 | 0.048 | 618.611 |
45166.667 | -0.398 | 2040027778 | 0.159 | -17991.389 |
40166.667 | 0.682 | 1613361111 | 0.465 | 27380.278 |
Mx: 72833.333 | My: 3.278 | Sum: 16793333333.333 | Sum: 4.675 | Sum: -26116.667 |
X Values
∑ = 1748000
Mean = 72833.333
∑(X - Mx)2 = SSx =
16793333333.333
Y Values
∑ = 78.68
Mean = 3.278
∑(Y - My)2 = SSy = 4.675
X and Y Combined
N = 24
∑(X - Mx)(Y - My) = -26116.667
R Calculation
r = ∑((X - My)(Y - Mx)) /
√((SSx)(SSy))
r = -26116.667 / √((16793333333.333)(4.675)) = -0.0932
Now r^2=-0.0932^2=0.0087
So 8.7% of variation in GPA is explained by Income