We utilize the implementation of the 1986 Compulsory Education Law in China as a natural experiment to examine the relationship between educational attainment and migrant entrepreneurship. Using data from the 2017 China Migrants Dynamics Survey, results from our preferred two-stage least square model, which uses instrumental variable and difference-in-differences estimators to correct for endogeneity, suggest that having one additional year of education generates a 3.5 percentage points increase in the probability of being an employer entrepreneur vis-à-vis an employee, and a 4.7 percentage points increase in the probability of being an employer entrepreneur vis-à-vis a solo entrepreneur. Having better education, however, does not affect the propensity to become an entrepreneur in general vis-à-vis an employee or a solo entrepreneur vis-à-vis an employee. These results are robust to various checks including alternative estimation methods and ways of defining entrepreneurship. We also explore the channels through which educational attainment influences whether one chooses to become an employer entrepreneur. Our findings suggest that assortative mating, difficulties experienced in the host location, permanent settlement intention and social capital mediate the relationship between better education and the choice of both becoming an employer entrepreneur vis-à-vis a solo entrepreneur and an employer entrepreneur vis-à-vis an employee, while risk preferences are a mechanism through which education affects the probability of becoming an employer entrepreneur as opposed to a solo entrepreneur.