Houghton Mifflin Harcourt Algebra 1, 2015
HM
Houghton Mifflin Harcourt Algebra 1, 2015 View details
2. Fitting a Linear Model to Data
Continue to next subchapter

Exercise 9 Page 370

Make a table of values to determine the residuals.

Sum for y=x+3: 88
Sum for y=x+2.6: 75.84
Better Line of Fit: y=x+2.6

Practice makes perfect

We have been given the following table.

x 2 4 6 8
y 1 5 7 3
We have also been given two possible lines of fit.
Lines of Fit
y=x+3 y=x+2.6

In order to determine which line of fit is better, let's calculate the residuals for both lines.

x y (Actual) y Predicted by y=x+3 Residual for y=x+3 y Predicted by y=x+2.6 Residual for y=x+2.6
2 1 y= 2+3= 5 1- 5= -4 y= 2+2.6= 4.6 1- 4.6= -3.6
4 5 y= 4+3= 7 5- 7= -2 y= 4+2.6= 6.6 5- 6.6= -1.6
6 7 y= 6+3= 9 7- 9= -2 y= 6+2.6= 8.6 7- 8.6= -1.6
8 3 y= 8+3= 11 3- 11= -8 y= 8+2.6= 10.6 3- 10.6= -7.6
Now, we will square the residuals and find their sum s for each line so that we can compare which line is a better fit. Let's start with the line y=x+3.
s=( -4)^2+( -2)^2+( -2)^2+( -8)^2
s=16+4+4+64
s=88
Thus, the sum of the squared residuals for y=x+3 is 88. Next, we will continue with the line y=x+2.6.
s=( -3.6)^2+( -1.6)^2+( -1.6)^2+( -7.6)^2
s=12.96+2.56+2.56+57.76
s=75.84
The sum of the squared residuals for y=x+2.6 is 75.84. As a result, we can say that y=x+2.6 is the better line of fit because it has a lesser sum.