WEBVTT

1
00:00:00.000 --> 00:00:09.694
Here is the problem: Find the least-squares regression line for x equals 2, 4, 6, 8 and y equals 3, 7, 8, 12.

2
00:00:10.144 --> 00:00:20.349
Fit the straight line ŷ equals a plus bx that minimises the sum of squared vertical distances to the data, and measure how well it fits with r and r squared.

3
00:00:21.149 --> 00:00:22.623
Means of x and y.

4
00:00:23.073 --> 00:00:26.277
Sums of squares and cross-products about the means.

5
00:00:26.727 --> 00:00:27.191
Slope.

6
00:00:27.641 --> 00:00:31.391
Intercept: the line passes through the point of means.

7
00:00:32.191 --> 00:00:33.317
Regression line.

8
00:00:33.767 --> 00:00:44.448
Correlation and coefficient of determination. Strong positive linear association; about 95.61 percent of the variation in y is explained by the line.

9
00:00:45.248 --> 00:01:00.062
So the answer is ŷ equals 1 over 2 plus (7 over 5)x; r approximately 0.977802, r squared approximately 0.956098.

10
00:01:00.512 --> 00:01:09.951
The slope is the predicted change in y for each one-unit increase in x. Correlation measures the strength of the linear pattern, not whether x causes y.

11
00:01:10.751 --> 00:01:14.907
The residuals sum to 0, as they must for a least-squares line.