Table 7.

Heterogeneity of ITT treatment effects by baseline characteristics.

Dep. Var.: Endline Standardized Math Score	Half and above Material Taught on Blackboard	Math Score below the Average	Household Asset below the Average	Parents Out-Migrated for Work	Not Wearing Eyeglasses at Baseline
	(1)	(2)	(3)	(4)	(5)
Treatment (1 = yes)	−0.029	0.033	−0.009	0.025	0.056
	(0.071)	(0.051)	(0.067)	(0.051)	(0.084)
Treatment × half and above material taught on blackboard	0.125 ***
	(0.093)
Half and above material taught on blackboard (1 = yes)	−0.100 ***
	(0.069)
Treatment × baseline standardized math below the average		0.052 *
		(0.070)
Baseline math score below the average (1 = yes)		0.051
		(0.076)
Treatment × household asset value below the average			0.095 **
			(0.076)
Household asset value below the average (1 = yes)			−0.097 *
			(0.111)
Treatment × one or both parents out-migrated for work				0.070 **
				(0.066)
One or both parents out-migrated for work (1 = yes)				−0.043 *
				(0.046)
Treatment × not wearing eyeglasses at baseline					0.007
					(0.088)
Not wearing eyeglasses at baseline (1 = yes)					−0.019
					(0.069)
Treatment effect for subgroup if dummy equals one	0.098 ***	0.081 ***	0. 090 ***	0.112 ***	0.062 ***
	(0.054)	(0.062)	(0.048)	(0.058)	(0.046)
Treatment effect for subgroup if dummy equals zero	−0.032	0.038	−0.028	0.032	0.050
	(0.071)	(0.051)	(0.067)	(0.051)	(0.084)
Baseline standardized math score controlled	Yes	Yes	Yes	Yes	Yes
Student, family, teacher, characteristics controlled	Yes	Yes	Yes	Yes	Yes
R-square	0.411	0.411	0.411	0.410	0.408
Number of observations	2087	2087	2087	2087	2087

Notes: Full sample is analyzed. Standardized coefficients are reported. Standard errors clustered at the school level are reported in parentheses. * p < 0.10, ** p < 0.05, *** p < 0.01.