Table 4—
Probability that never married by age 25 are married at age 30–40 |
Probability that married at age 25 are divorced at age 30–40 |
|||||
---|---|---|---|---|---|---|
Types defined from: | Fixed effects | System GMM | Grouped Fixed Eff. | Fixed effects | System GMM | Grouped Fixed Eff. |
Low-type probability | 0.413 | 0.540 | 0.429 | 0.333 | 0.388 | 0.331 |
(0.041) | (0.062) | (0.042) | (0.017) | (0.022) | (0.018) | |
High-type/Low-type prob. gap | 0.194 | 0.046 | 0.175 | −0.105 | −0.159 | −0.101 |
(0.044) | (0.064) | (0.044) | (0.018) | (0.023) | (0.019) |
Note: The left panel presents the coefficients of three regressions of a dummy variable that takes the value of one if the individual is married at some point between ages 30 and 40 on a constant and a dummy variable that equals one if the individual is of high type based on the fixed effects recovered from the estimation of Equations (1), (3), and (2) —for the first two, a high type is defined as an individual at a percentile above the fraction of high types recovered in the third— fitted on the sub-sample of individuals who had never been married by age 25. The right panels present analogous coefficients for a dependent variable that equals one if the individual gets divorced at some point between ages 30 and 40 and it is estimated on the sub-sample of individuals that are married by age 25. These regressions are fitted to the PSID. Robust standard errors in parenthesis.