Does Marriage Reduce Male Earnings Inequality?
Distribution
Outcome
Conditional
Statistics
10
th
-90
th
Percentiles
+ Means & Crosshairs
− Significance Tests
Covariates
0 = Age, Education, Skill, Wave, Area
00 = 0 + Person
1 = 00 + Cohabitation, Separation, Remarriage
3 = 1 + Time At Work
4 = 1 + Children
1x = 1 without age interactions
Person-Years
A ∧ B ∧ C ∧ D
A ∧ B ∧ C ∧ D ∧ E
A = Black & White Men
B = Who Eventually Marry
C = Who the BLS Does Not Drop
D = While Not In School
E = Through 1996
Marriage
Years
−YearBefore
−Cohab
+Kids
Dichotomous
Response
Earnings
Wages
Difference Between Married Men & Non-Married Men
Quantiles
Gradient
.1
.2
.3
.4
.5
.6
.7
.8
.9
.9−.1
.8−.2
.7−.3
.6−.4
***
p
< .001
**
p
< .01
*
p
< .05
^
p
< .1
This model estimates wages as a function of marriage, age, educational attainment, skill, wave, area, age × educational attainment, and age × skill. Their significance tests correspond to 1000 clustered design matrix bootstraps.
Married
White
0.14***
0.13***
0.13***
0.12***
0.12***
0.10***
0.09***
0.08***
0.07***
**
*
**
*
**
*
^
**
Black
0.16***
0.17***
0.17***
0.16***
0.16***
0.15***
0.12***
0.10***
0.08**
*
**
*
**
*
*
**
n.s.
Difference
n.s.
n.s.
n.s.
^
**
^
**
^
**
n.s.
n.s.
n.s.
n.s.
n.s.
n.s.
n.s.