In this paper, we review several estimators of the average treatment effect (ATE) that belong to three main groups: regression, weighting and doubly robust methods. We unify the exposition of these estimators within an M-estimation framework and we derive the corresponding sandwich form variance estimators. We compare the finite sample properties of the estimators by a Monte Carlo study, where the emphasis lies on the effect of various types of misspecifications and degree of overlap. Additionally, we re-estimate the causal return to higher education on earnings by the reviewed methods using the rich dataset provided by the British National Child Development Study (NCDS) as an empirical illustration.