Skip to main content

Table 3 Instrumental-variable models exploiting changes in compulsory schooling laws across US States.

From: Skills, earnings, and employment: exploring causality in the estimation of returns to skills

  All levels of school attainment At most high school More than high school At most high school
Age 35–54 Age 35–65
(1) (2) (3) (4) (5) (6)
Second stage (dependent variable: log gross hourly wage)
 Numeracy .661***
(.305)
.798***
(.246)
.659***
(.182)
  .783***
(.273)
.633***
(.306)
 State fixed effects X X X X X X
 Age quartic X      
 Birth year fixed effects   X X X X X
 State-specific trends       X
First stage (dependent variable: numeracy skills)
 Minimum school-leaving age .027***
(.005)
.029***
(.008)
.061***
(.016)
−.000
(.006)
.047***
(.020)
.057***
(.022)
 Instrument F statistic 25.9 15.1 14.5 0.0 5.7 6.5
 Observations 932 932 369 563 520 520
  1. Two-stage least squares regressions weighted by sampling weights. Sample: full-time employees in the United States. Second-stage coefficient is not displayed if the first-stage coefficient is insignificant. All regressions control for gender. Robust standard errors (adjusted for clustering at state level) in parentheses. Significance levels: * p < 0.10, ** p < 0.05, *** p < 0.01