. Author manuscript; available in PMC: 2014 May 27.

Published in final edited form as: Demography. 2012 May;49(2):629–650. doi: 10.1007/s13524-012-0093-0

Table 2.

Decomposition of the log odds of educational homogamy in prevailing marriages

Sample or Simulation	Odds	Log Odds	Contribution to Log Odds	Percentage Contribution (%)	95% CI for Percentage Contribution (%)^a
Observed Prevailing Marriages	2.737	1.007	—	—	—
First Marriages (S1)	2.882	1.058	1.058	105.10	[95.0, 115.2]
+ First Dissolutions (S2)	2.942	1.079	0.021	2.07	[−3.95, 8.09]
+ Remarriages (S3)	2.773	1.020	−0.059	−5.90	[−10.9, −0.88]
+ Later Dissolutions (S4)	2.761	1.015	−0.004	−0.43	[−3.65, 2.79]
+ Educational Upgrades (S5)	2.737	1.007	−0.009	−0.86	[−7.74, 6.02]
Total			1.007	100.00

Notes: Data are weighted using 1979 sampling weights. Estimates are from log-linear models using data from multistate life tables. Wives are aged 18 to 41.

Source: National Longitudinal Survey of Youth (NLSY79), 1979–2002.

95% confidence intervals (CIs) are estimated using 1,000 bootstrapped samples.