Essays on the twins approach in empirical labor economics

Sammanfattning: Estimates of the Return to Schooling in Sweden from a Large Sample of Twins: A large sample of twins was used to examine whether conventional estimates of the return to schooling in Sweden are biased because ability is omitted from the earnings-schooling relationship. Ignoring measurement error, the results indicate that omitting ability from the earnings-schooling relationship leads to estimates that are positively biased. However, reasonable estimates of the measurement-error-adjusted returns are both above and below the unadjusted estimates, showing that the results depend crucially on a parameter not known at this time. However, an estimate of the reliability ratio was obtained using two measures on educational attainment. With this estimate of the reliability ratio the measurement-error-adjusted estimate of the return to schooling in the sample of identical twins indicates that there is at most a slight ability bias in the conventional estimates of the return to schooling. The fundamental assumption of this kind of study is that within-pair differences in educational attainment are randomly determined. This assumption was also tested, but no strong evidence to reject it was found.Estimating the Economic Return to Educational Levels from Data on Twins: This paper relaxes some restrictions of previous twins-based estimates of the effects of education on earnings. First, it estimates a piece-wise linear relationship between the natural logarithm of annual earnings and years of schooling. Second, the measurement error corrections are based on a less restrictive, "non-classical", measurement error model. The estimation strategy implies that the issue of ability bias can be investigated separately in different parts of the educational distribution. The results indicated that the linear relationship between the logarithm of annual earnings and years of schooling is rejected. Furthermore, the results in the sample of identical (MZ) twins indicated both that the ability bias could be of different sign and of different magnitude in different parts of the educational distribution. The twins-based estimates in the sample of fraternal (DZ) twins did not display any marked differences compared to the cross-sectional estimates. Finally, the paper presents results indicating that previous error-corrected within-pair estimates of the average return to years of schooling are not specifically sensitive to the choice of measurement error model.Twin Data vs. Longitudinal Data to Control for Unobserved Variables in Earnings Functions - Which Are the Differences?: An empirical comparison was made of two different methods to control for unobserved variables in earnings functions, the longitudinal and the twins approach. The application concerns the estimation of the marriage premium. The purpose of this comparison is to illustrate advantages and disadvantages of the two approaches. The estimates were obtained by exploiting the longitudinal dimension of a large sample of male Swedish twins, so that within-individual (longitudinal) and within-pair (twins-based) estimates could be obtained in the same sample. Both types of estimates were below the corresponding cross-sectional (OLS) estimates. However, there were substantial differences between the within-individual and the within-pair estimates. It was demonstrated that the differences between the within-individual and within-pair estimates could not be explained by classification error in marital status. An alternative explanation to the difference was investigated, namely that the within-individual estimates tend to capture short run premiums whereas the within-pair estimates tend to capture long-run premiums. Finally, the within-individual estimates have higher standard errors than the within-pair estimates. This result is likely due to the larger amount of within-variation in the twin dimension of the data.