The estimation of the rate of return to education in China: an empirical analysis using instrument variable estimation with months of birth and its Issues

Abstract

Any attempt to estimate the rate of return to education using ordinary least squares (OLS) models suffers from omitted variable bias due to unobservable factors that are correlated with both the education variable and the return dependent variable. Instrument Variables, such as the birth months of students, provide an alternative estimation method that can create less biased estimates. The validity of the birth months as instrument variables depends on being uncorrelated with individual personal attributes while having an effect on the education outcome of the individual. However, the exogenous criterion is violated if unobservable factors influences the month of birth and education outcome creating the omitted variable bias problem. We investigate if the birth month is a good instrument for use in estimating the rate of return to education using empirical evidence from the 2000 Chinese Population Census and the 2009 Chinese Urban Household Income and Expenditure Survey. We split the sample into two groups, individuals with rural education and individuals with urban education due to an urban/rural education gap that the literature captures. A Two Stage Least Squares Model (TSLS) is run to estimate the rate of return to education and to determine if the instrument birth month variables are strong instruments. We also run an OLS model to compare the OLS rate of return to education with the TSLS estimates. We use the parent’s education level as a proxy for socioeconomic status and investigate if there is a violation of the exclusion restriction for the birth month instruments. We find students born after August typically achieving a higher education level on average than students born in the August and months before August. In addition, there is a significant and positive rate of return to education using IV estimation which is larger than the OLS estimate of the return to education. We find that parent’s socio economic status either has an insignificant or trivial effect on the timing of births. We conclude there is a significant birth month effect on education and that the birth month variables are independent of parental background variables. We also find the birth month variables to be weak instruments but we argue that the bias present is less than the bias present in the OLS estimation of the rate of return to education.