WEBVTT

1
00:00:00.000 --> 00:00:11.912
Here is the problem: Find the least-squares regression line for x equals 1, 2, 3, 4, 5 and y equals 2, 4, 5, 4, 5.

2
00:00:12.362 --> 00:00:22.358
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
00:00:23.158 --> 00:00:24.656
Means of x and y.

4
00:00:25.106 --> 00:00:28.392
Sums of squares and cross-products about the means.

5
00:00:28.842 --> 00:00:29.388
Slope.

6
00:00:29.838 --> 00:00:33.321
Intercept: the line passes through the point of means.

7
00:00:34.121 --> 00:00:35.259
Regression line.

8
00:00:35.709 --> 00:00:45.276
Correlation and coefficient of determination. Moderate positive linear association; about 60 percent of the variation in y is explained by the line.

9
00:00:46.076 --> 00:00:59.729
So the answer is ŷ equals 11 over 5 plus (3 over 5)x; r approximately 0.774597, r squared approximately 0.6.

10
00:01:00.179 --> 00:01:09.746
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
00:01:10.546 --> 00:01:14.900
The residuals sum to 0, as they must for a least-squares line.