0:00:00.000,0:00:03.000
Y will always be less extreme.
0:00:03.000,0:00:08.000
The key to understanding this simply is this equation.
0:00:08.000,0:00:18.000
This is what tells us that the standard scores have a regression coefficient â¤ 1.
0:00:18.000,0:00:25.000
We said it's 1, and so because it's not 1 it must be less than that.
0:00:25.000,0:00:28.000
That means the standard score shrinks.
0:00:28.000,0:00:35.000
If the standard score shrinks that means if it's negative it moves this way.
0:00:35.000,0:00:37.000
If it's positive it moves this way.
0:00:37.000,0:00:40.000
That means there is more area under here,
0:00:40.000,0:00:45.000
so this has to be a little more area than this.
0:00:45.000,0:00:49.000
Therefore, y will always be less extreme.
0:00:49.000,0:00:51.000
This is the concept of regression.
0:00:51.000,0:00:55.000
That is regression to the mean.
0:00:55.000,0:00:58.000
If someone is exceptional in one thing,
0:00:58.000,0:01:02.000
we will always predict that person to be a bit less exceptional
0:01:02.000,0:01:07.000
in that other thing if there is any error.