Skip to main content

Table 5 RD estimates of test scores by parental education

From: The effect of age at school entry on college admission and earnings: a regression-discontinuity approach

 

Less-educated parents

 

Well-educated parents

Polyn.

CCT procedure

 

IW procedure

 

CCT procedure

 

IW procedure

degree

Ï„

z-stat

Bandwidth

 

Ï„

z-stat

Bandwidth

 

Ï„

z-stat

Bandwidth

 

Ï„

z-stat

Bandwidth

 

Male

0

0.177**

2.447

23.28

 

0.159***

2.639

33.51

 

0.046

1.482

44.83

 

0.035

1.322

60.86

1

0.205**

2.149

48.14

 

0.217***

2.845

76.23

 

0.149**

2.374

37.33

 

0.060

1.429

88.54

2

0.209**

1.962

83.50

 

0.213**

2.085

91.51

 

0.190**

2.518

56.81

 

0.102*

1.853

105.42

 

Female

0

0.09**

2.220

45.63

 

0.082***

2.604

76.65

 

−0.004

−0.160

40.91

 

0.001

0.055

61.08

1

0.107*

1.825

80.29

 

0.110**

2.059

96.40

 

−0.014

−0.354

78.42

 

−0.011

−0.392

134.77

2

0.030

0.282

60.86

 

0.106

1.511

125.08

 

−0.083

−1.207

55.88

 

−0.028

−0.571

105.52

  1. This table shows the RD estimates of test scores using different local-polynomial degrees (per row) and different bandwidth selection procedures (per column). The first panel on the left has the results for candidates whose parents have no college degree and at least one has no high school education. The second panel on the right has the results for candidates whose either both parents have a high school diploma or at least one has a college degree. The CCT procedure is proposed by Calonico et al. (2014). The IW procedure is proposed by Imbens and Kalyanaraman (2012). All functions are estimated using a triangular kernel. Data come from applications for undergraduate programs at UFPE from 2002 to 2005. The sample is restricted to those who graduated from high school in the same year and were under 18.5 years old. Ï„ is the robust RD estimate
  2. ***, **, * represent statistical significance at the 1, 5, and 10 % levels, respectively
Back to article page