Skip to main content
. Author manuscript; available in PMC: 2020 Oct 30.
Published in final edited form as: Eur Econ Rev. 2018 Mar 11;104:138–166. doi: 10.1016/j.euroecorev.2018.02.005

Table 5—

Contingency Tables: Assortative Mating by Innate Health

Innate permanent health — Fixed effects (ηi)
Observed marital sorting %
Random matching %
Wife Wife
1 2 3 4 5 1 2 3 4 5 Marginal

Husband 1 8.1 3.0 2.4 2.4 2.1 3.2 2.5 4.5 4.8 3.0 18.0
2 2.6 3.2 3.1 3.4 1.7 2.5 1.9 3.5 3.8 2.3 14.1
3 2.5 2.5 14.7 5.5 0.7 4.7 3.5 6.5 7.0 4.3 26.0
4 2.6 3.3 4.2 12.8 3.6 4.8 3.6 6.6 7.1 4.4 26.5
5 2.1 1.7 0.5 2.7 8.4 2.8 2.1 3.9 4.1 2.5 15.4
Marginal 18.0 13.6 25.0 26.8 16.5 18.0 13.6 25.0 26.8 16.5 100.0
Innate permanent health — System-GMM (ηi)
Observed marital sorting %
Random matching %
Wife Wife
1 2 3 4 5 1 2 3 4 5 Marginal

Husband 1 8.9 2.7 2.3 2.6 2.7 3.7 4.2 4.5 4.3 2.5 19.2
2 2.6 9.8 4.6 3.3 0.8 4.1 4.6 4.9 4.7 2.7 21.0
3 2.4 4.9 10.0 4.1 0.7 4.3 4.8 5.2 5.0 2.9 22.2
4 2.9 3.6 5.4 10.2 2.4 4.8 5.3 5.8 5.5 3.2 24.6
5 2.7 0.7 1.2 2.1 6.3 2.5 2.8 3.1 2.9 1.7 13.1
Marginal 19.5 21.8 23.5 22.3 12.9 19.5 21.8 23.5 22.3 12.9 100.0
Innate health type (ηg(i))
Observed sorting %
Random matching %
Wife Wife
Husband Low High Low High Marginal

Low 5.7 8.2 2.0 11.9 13.9
High 8.6 77.5 12.3 73.8 86.1
Marginal 14.3 85.7 14.3 85.7 100.0

Note: In the left columns of the two top panels, each cell gives the observed percentage of married households in which husbands and wifes lie in each indicated quintile of innate permanent health (η^i) estimated from Equations (1) and (3) respectively). In the right columns of each panel, each cell gives the predicted percentage from multiplying marginal distributions of husbands and wives, which are reported, respectively, at the last column and row. The bottom panel provides similar statistics computed for the innate health types (ηg(i)^) obtained from the estimation of Equation (2).