6.2 Linear Regressions
A linear regression is the process of mathematically finding the line of best fit. Once you have a linear regression completed, you can interpolate and extrapolate accurately.
We're going to do all the calculations on the graphing calculators, but the process for determining the linear regression involves the use of Least-Squares fit in order to minimize the residuals.
<GSP Demo>
In
order to describe a line, we need a slope and a y-intercept in the
form
![]()
and
![]()
Ex 1 The following table indicates rabbit and wolf population over the course of 8 years
|
Year |
1994 |
1995 |
1996 |
1997 |
1998 |
1999 |
2000 |
2001 |
|
Rabbit |
61 |
72 |
78 |
76 |
65 |
54 |
39 |
43 |
|
Wolf |
26 |
33 |
42 |
49 |
37 |
30 |
24 |
19 |
(a) Determine the line of best fit and correlation coefficient for these data.
(b) Graph the data and predict the populations today.
Ex 2 The table shows the number of hours of instruction in driving versus the score on the driving test.
|
Hours |
10 |
15 |
21 |
6 |
18 |
20 |
12 |
|
Score |
78 |
85 |
96 |
75 |
84 |
45 |
82 |
(a) Graph the scatter plot and the line of best fit for this data.
(b) Comment on any data that seems unusual.
p. 180# 1, 2, 5, 6, 7