Methods in Labor Economics

The curved line shows the predictedfit from

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: he curved line shows the predictedfit from regressingaverage log annual earnings on a birth cohort quartic polynomial and an indicatorfor the schoolleaving age faced at age 14. The school leaving age increasedfrom 14 to 15 in 1947, indicated by the vertical line. Earningsare measuredin 1998 U.K. pounds using the U.K. retail price index. ble estimate for Northern Ireland is 13.5 percent,and about20 percentwith the inclusion of age controls (see columns 5 and 6). These estimatedeffects are similarto previous returns to compulsory schooling estimates, in particular those presented in Harmon and Walker's (1996) U.K. analysis. The regression discontinuity approachleads to some imprecision, given that earnings are taperingoff for successively older birthcohorts at the time the discontinuityoccurs. The analysis is strengthened,however, by moving to a difference-in-differences and instrumentalvariablesanalysis by combining the two sets of U.K. data. Doing so lowers the averagefraction affected by compulsory schooling a little, compared to using Britain alone, but the difference is not great. The thirdrow in Table 1 shows the estimated effects of raising the school-leaving age on the average age respondents left fulltime school for the combinedBritishand North- ern Irish samples. Again I regressed average education attainmenton a quartic birth cohort control, an indicator for the minimum schoolleaving age a cohortfaced, and now an indicator for Northern Ireland. The estimated increase in years of schooling from the higher schoolleaving age with the combined data is 0.42 years, comparedto 0.44 using only the British sample. The standarderror,however, falls considerably, to 0.04 (t-statistic = 13.6), and the results are robust to including age controls (shown in columns 2 and 3). Figure 8, which shows the corresponding combined plots of British and Northern Irish education attainmentby cohort, clearly illustrates the differences in attainmentbefore and after the change in the school laws. Bot...
View Full Document

Ask a homework question - tutors are online