Education, Employment and Earnings of Secondary School-Leavers ...

5.4 Estimated Private Rates of Return to Educational QualificationsWe now turn to an examination of the estimated private rates of return for the twoeducational qualifications used here – senior secondary and university. These arecomputed using the differences in the estimated coefficients between adjacentqualifications divided by the difference in years. If we define the interval regressionearnings model parameter for a university qualification as γ U and for senior secondaryas γ S , the rate of return (RoR) to a university qualification is computed as:RoR – University Qualification =UγUYears- γ-SSYears[9]where U Years is total years in education to acquire a university qualification and S Yearsis the corresponding number of years taken to acquire a senior secondaryqualification. The rate of return to senior secondary schooling can then be computedas:RoR – Senior Secondary Qualification =SYearsγS- JYears[10]where J Years is total years in education to acquire a junior certification qualification.The sampling variances for the estimated rates of return are easily computed using theconventional formula.The estimated rates return reported in table 7 are the exponentiated versions of [9] and[10] expressed in percentages and the corresponding sampling variances areconstructed using the delta method. In respect of employees the point estimate for thesenior secondary qualification is just under nine per cent but is situated within a largeconfidence interval and is only significant at the 10 per cent level. The comparablepoint estimate for the self-employed is close to five per cent but is even moreimprecisely estimated.At a conventional level of statistical significance, theproposition that the sample data were generated from an underlying population with azero return for the senior secondary qualification cannot be rejected for the selfemployed.26