This is the first attempt to estimate social returns, by which is meant pre-tax wage gains, to education in the Republic of Mauritius. Social returns are estimated for both sexes, by gender, by private and public sectors, and by rural and urban areas. This study uses cross sectional data from a sample of the 2000 Population Census. Although Psacharopoulos along with other researchers have estimated returns to education for many countries, the Republic of Mauritius had not so far been included due to lack of data prior to 2000. The Mincerian approach is used to estimate social returns for the Republic of Mauritius, using the Ordinary Least Squares (OLS) method. All wage equations are adjusted for selectivity bias. Findings are similar to those reported in the literature. First, there is evidence of diminishing marginal returns to education when the social return to a year of education is estimated. Second, when highest academic qualifications are considered, tertiary education yields the highest social return relative to no schooling at all or to primary schooling only. Third, social returns to academic and vocational qualifications are higher for women than for men, a finding consistent with those reported for other countries and attributed to women's lower foregone earnings. Fourth, social returns to high level academic qualifications (' A' level and above) and vocational qualifications are higher in the private sector than in the public sector. Fifth, social returns are higher for those who reside in urban areas. Sixth, selectivity bias is minimal in most cases. This study also uses the instrumental variable (IV) approach to deal with the omitted variable bias, endogeneity of schooling and measurement error. The 1976 free secondary education law is used as an instrument. This instrument only predicts the schooling of women for the Republic of Mauritius. IV estimates are consistently higher than OLS estimates. Implications of these results are discussed.