00:01
For this problem, in part a we begin by stating our hypotheses.
00:05
In this case, our null hypothesis is that the slope of the regression equation is equal to zero.
00:12
The alternate hypothesis will be that the slope is something other than zero, it just does not equal zero.
00:19
To find our f statistic, the first thing that we're going to want to do is to find the regression sum of squares.
00:28
We can find that by taking our total sum of squares, sst, minus the error sum of squares.
00:38
So that is going to be equal to 1600 minus 510.
00:44
So we have 1090 as our regression sum of squares.
00:49
Now that we have that, we want to find the mean squares for regression, which is going to be equal to the ssr divided by the number of degrees of freedom for regression, and the mean squares for error, which would be the sse divided by the degrees of freedom for error.
01:13
Now, since we are only estimating one independent variable, we have that the degrees of freedom for regression will be equal to one.
01:23
We have that the total degrees of freedom, dft, will be equal to the total number of observations minus one.
01:33
So we'll have 26 total degrees of freedom, and the degrees of freedom error, dfe, will be equal to the total degrees of freedom minus the regression degrees of freedom.
01:47
So we'd have 25 error degrees of freedom.
01:52
That then means, one second here, i'll move my stuff around a little bit for a logical order.
02:00
So we calculate the degrees of freedom, then we can plug those into the msr and mse formulas.
02:06
So msr is going to be 1090 divided by one, so just 1090...