00:01
For this problem, to begin, we have that the f -statistic for testing the significance of the regression model, the f -statistic is going to be equal to the mean squares for regression divided by the mean squares error.
00:18
So msr over mse.
00:21
Or equivalently, we can say that as, and now i'm just going to double check that i'm using the same terminology here.
00:26
So yeah, you have ssr and sse.
00:28
The one second, i'm fighting with something off screen, excuse me.
00:34
So when we have ssr and sse, we have that the msr mean squares for regression is going to be the regression sum of squares or ssr divided by the number of predictor variables.
00:52
So ssr over k, then the mean squares for error, the mse is going to be equal to the sum of squares for error, the sse, divided by the number of observations minus the number of predictors minus one...