00:01
Part 1.
00:04
This is the equation estimated by ols.
00:13
Look at the estimate on education.
00:17
Another year of education, holding age fixed, results in about 0 .091 fewer children.
00:29
In other words, for a group of 100 women, if each gets another year of education, they collectively are predicted to have about nine fewer children.
00:53
Part 2.
00:55
This is a reduced form for education.
01:04
We need 5 .3 to be non -zero.
01:15
When we run the regression, we obtain pi 3 hat to be minus 0 .852, with a standard error of 0 .113.
01:41
Therefore, women born in the first half of the year are predicted to have almost one year less education, holding age fixed.
01:54
The t statistic on first half is over 7 .5.
02:06
So we reject the null hypothesis that by 3 equals 0 .0.
02:13
And that means the identification assumption whole.
02:32
Part 3.
02:33
This is the structural equation estimated by instrumental variable.
02:47
The estimated effect of education on fertility is now much larger...