00:01
This question is all about the standard error of regression estimates.
00:06
And for this question, it gave us se, which is standard error of the estimate, as 30 .77.
00:15
And we are asked to explain in the context of breakfast cereals what this actually means.
00:21
So to start with, i've given the formula for se.
00:26
I'm just going to explain a little bit what this means.
00:28
So this bit at the top is the sum of residuals squared.
00:42
And because why is your actual value for any of your serials and why dash is the predicted value? so from previous questions, if you ever take an actual value minus predictive value, that is your residual.
00:59
And if you square that, it's to get rid of any negative positive aspects.
01:05
So when we're doing residuals, something like this, we don't really mind whether they're negative or positive...