Question 2: Di'erencein-di'erences (17 marks) Read the introduction and section I of the paper by Esther Dlio5 ='Schooling and Labor Market Consequences of School Construction in Indonesia: Evidence from an Unusual Policy,r Experiment" {2001, American Economic: Review}. The government. of Indonesia carried out a largescale primary school construction program (IN PHES) from 19734 to 19789 with the aim to increase primary school enrollment. This paper studies the effect of this school construction program on the level of education and (subsequent) wages of local children. There are two factors that affect the intensity of the program: a Year of Birth: Only individuals who were of primary school going age should benet from the program. So for instance, individuals who were aged 1217 in 197'4 were unlikely to take advantage of the school construction program to further their schooling. On the other hand children aged 26 in 1974 could take advantage of the school construction program since they were of the right age group to attend primary school postconstruction. II Region of Birth: The Indonesian government targeted the program to regions with initially low primary school enrollment rates. Therefore5 someone horn in a a region with low enrollment rates prior to the program (a region with a =Ehigh" level of the program) would he more likely to be affected by the construction program than a person born in a \"low\"1 intensity region. The author collects information on 150,000 men born between 195072 and whose completed education levels and hourly wages [for employed individuals) are collected in 1995. The author then uses the two factors above to divide her sample into four categories individuals who were too old for primary school in 1974 and lived in a high intensity region (the ='OldHigh\" group): individuals who were primary schoolage during the construction program period and lived in high intensity regions (\"YoungHigh\"): individuals who were too old for primary school in 1974 and lived in a low intensity region (\"OldLow\") and individuals who were primary schoolage during the construction period and lived in low intensity regions ( \"YoungLow\" ). The mean wages and education levels for these four groups are reported in Panel A of Table 3 in the paper (copied below). TABLE 3-MEANS OF EDUCATION AND LOG(WAGE) BY COHORT AND LEVEL OF PROGRAM CELLS Years of education Log(wages) Level of program in region of birth Level of program in region of birth High Low Difference High Low Difference (1) (2) (3) (4) (5) (6) Panel A: Experiment of Interest Aged 2 to 6 in 1974 8.49 9.76 -1.27 6.61 6.73 -0.12 (0.043) (0.037) (0.057) (0.0078) (0.0064) (0.010) Aged 12 to 17 in 1974 8.02 9.40 -1.39 6.87 7.02 -0.15 (0.053) (0.042) (0.067) (0.0085) (0.0069) (0.011) Difference 0.47 0.36 0.12 -0.26 -0.29 0.026 (0.070) (0.038) (0.089) (0.011) (0.0096) (0.015) Panel B: Control Experiment Aged 12 to 17 in 1974 8.02 9.40 -1.39 6.87 7.02 -0.15 (0.053) (0.042) (0.067) (0.0085) (0.0069) (0.011) Aged 18 to 24 in 1974 7.70 9.12 -1.42 6.92 7.08 -0.16 (0.059) (0.044) (0.072) (0.0097) (0.0076) (0.012) Difference 0.32 0.28 0.034 0.056 0.063 0.0070 (0.080) (0.061) (0.098) (0.013) (0.010) (0.016) Notes: The sample is made of the individuals who earn a wage. Standard errors are in parentheses