midterm_fall07_solutions

midterm_fall07_solutions - ECO 120, Fall 2007 Midterm...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
ECO 120, Fall 2007 Midterm Solutions November 2, 2007 Professor Jon Robinson 1. (a) The Indonesian government allocated schools based on primary school enrollment: schools were allocated in proportion to the number of children of primary school age not enrolled in school in 1972. This means that districts that received the most schools (the high-intensity districts) had, by de&nition, lower primary school enroll- ment than the districts that received the fewest schools (the low-intensity districts). This is re±ected in the fact that the average child that was aged 2-6 in 1974 in a high- intensity district ended up with fewer years of schooling than the average child that was aged 2-6 in 1974 in a low-intensity district. 1 This fact means that comparing post-treatment means for the 2 groups would be severely downwards biased. Du±o solves this problem by using a Di/erence-in-Di/erence estimator that uses children aged 12-17 in 1974 as a quasi-control group. Since the schools that were constructed were all primary schools, and since only kids aged 7-12 attend primary school (not counting kids that started late or were held back), kids that were older than 12 in 1974 age 7. 2 1 8.49 years of schooling, compared to 9.76 years in low-intensity districts. 2 This is because the younger kids would have had the new schools for their entire primary school experience, while kids between 7 and 12 would have had the new schools for only part of primary school. 1
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
in high- and low-intensity districts for individuals that were 2-6 in 1974, and then to compare this to the di/erence in years of education between individuals in high- and low-intensity districts for individuals that were 12-17 in 1974 (the idea behind this the high-intensity districts were doing worse than the low intensity districts, so the e/ect of the schools can be seen by checking whether this gap was smaller for younger individuals than for older individuals). 3 di/erence in log wages and then estimates the return to education by taking the ratio of these 2 estimates (which is called the Wald estimator). (b) Udry±s study is about informal credit transactions between villagers in Northern
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 05/04/2008 for the course ECON 120 taught by Professor Robinson during the Spring '08 term at UCSC.

Page1 / 7

midterm_fall07_solutions - ECO 120, Fall 2007 Midterm...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online