In: Statistics and Probability
Because elderly people may have difficulty standing to have their height measured, a study looked at the relationship between overall height and height to the knee. Here are data (in centimeters) for five elderly men: Knee Height ? 56.5 46.3 41.2 47.7 52.7 Height ? 192.4 151.8 149.7 162.1 174.5 What is the equation of the least-squares regression line for predicting height from knee height? ANSWER: ?̂ =
Solution:
The general regression equation is given as below:
y = a + b*x
Where a is y-intercept and b is the slope.
Formulas for a and b are given as below:
b = (∑XY – n*Xbar*Ybar)/(∑X^2 – n*Xbar^2)
a = Ybar – b*Xbar
The calculation table is given as below:
No. |
Knee Height x |
Height y |
x^2 |
y^2 |
xy |
1 |
56.5 |
192.4 |
3192.25 |
37017.76 |
10870.6 |
2 |
46.3 |
151.8 |
2143.69 |
23043.24 |
7028.34 |
3 |
41.2 |
149.7 |
1697.44 |
22410.09 |
6167.64 |
4 |
47.7 |
162.1 |
2275.29 |
26276.41 |
7732.17 |
5 |
52.7 |
174.5 |
2777.29 |
30450.25 |
9196.15 |
Total |
244.4 |
830.5 |
12085.96 |
139197.8 |
40994.9 |
Mean |
48.88 |
166.1 |
From above table, we have
n = 5
∑x = 244.4
∑y = 830.5
∑x^2 = 12085.96
∑y^2 = 139197.8
∑xy = 40994.9
Xbar = ∑x/n = 244.4/5 = 48.88
Ybar = ∑y/n = 830.5/5 = 166.1
b = (∑XY – n*Xbar*Ybar)/(∑X^2 – n*Xbar^2)
b = (40994.9 – 5*48.88*166.1)/( 12085.96 – 5*48.88^2)
b = 2.863954
a = Ybar – b*Xbar
a = 166.1 – 2.863954*48.88
a = 26.10993
y = a + b*x
y = 26.10993 + 2.863954*x
ANSWER: ?̂ = 26.10993 + 2.863954*x