00:01
All right, so here we have a set of data and our equation kind of, our scatterplot sort of looks like that.
00:13
We got our lee squares regression line going through there.
00:16
So what i did was i typed in my data into l1 and l2.
00:20
So all of my height and then my head circumferences and then created a scatter plot off of that with my x list and my y list.
00:31
And then to do our lee squares regression line, i did linear regression a plus bx.
00:40
So you have to go to your stats menu and then stat calculations and type in the right x and y list.
00:51
And that gets me 12 .4932 plus 0 .182732x.
01:03
So our slope is 0 .182732, which means that as height increases by one inch head circumference is predicted to increase by 0 .185 inches.
01:27
Our y intercept was 12 .4932, which means if the height is zero, the head circumference, is predicted to be 12 .4932 inches, which does not make sense.
01:49
Okay, so it's not really that appropriate to interpret the y intercept.
01:53
To predict the head circumference of 25 centimeters tall, so 12 .4932 plus 0 .182732 times 25, 12 .4932 plus 0 .18273225, 17 .0615.
02:20
The residual is the actual minus predicted.
02:25
The actual height of 25 was 16 .9 minus 17 .0615, negative .1615...