00:01
Part 1.
00:03
You can easily show from the model this equation.
00:11
This is similar to the partial derivative of vote a with respect to expand b.
00:20
This ratio equals beta 3 plus beta 4 times expand a.
00:38
Regarding the sign of the coefficient, beta 3 would be less than 0.
00:48
Beta 3 is negative because an increase in the spending by b lowers the share of the vote received by a.
01:03
Let me write that down.
01:19
For beta 4, the sign is ambiguous.
01:24
We are not sure if beta 4 is positive or negative, because we don't know when the spending of b, no, sorry, the spending of a increase, would that lead to a greater or smaller effect of more spending by b? in part two of the question, you will estimate the model, and this is the regression result.
02:36
Look at the interaction term.
02:41
You can see that the standard error of the estimated coefficient, 0 .50 -72, is greater in absolute value, to the absolute value of the estimated coefficient.
03:02
So this number is larger than the number.
03:06
This number.
03:08
And so you can conclude that the interaction term is not statistically significant.
03:21
So the t -statt, which is the ratio of beta head over the standard error of beta.
03:35
This is a more formal way to prove which coefficient is significant.
03:44
The t -start of this interaction term is less than one.
03:48
So this term is not significant.
03:59
There is more information to the estimated equation.
04:06
We have 173 observations.
04:10
The r square is .571 and the adjusted r square is .561.
04:22
Let's move to part 3.
04:25
This is what we get from part 1.
04:29
Now we can quantify the change of vote a given what we know from the regression result.
04:41
So from the regression result, we have the value of beta 3 is, let me write this down.
05:08
This is minus 0317 and beta 4 is minus 0 .017.
05:20
You will have 5 zeros and 66.
05:28
We want to measure the change in vote a when the spending of a is 300 and when the change in the spending of b is 100.
05:50
The unit is 1000 usd.
05:56
We can easily find out that the change in vote a is roughly minus 3 .37.
06:09
This is a quite large effect.
06:19
We will continue with part 4.
06:23
Again, we will calculate the change in vote a.
06:27
Now with different conditions.
06:35
Again, we will plug in the values, the estimated values of beta 2 and beta 4, and the change in expanding of b.
06:53
We will have the value of the bracket as 0 .0376...