Using DHS data for six Latin American countries, we estimate the relation between a mother’s teenage childbearing status and that of her daughter. Restricting the estimating sample to mother-daughter matches in the data leads to a large negative selection bias in the estimated effect because missing matches are non-random and affected by the teen childbearing status of mothers and daughters. We deal with this selection bias by developing a Maximum Likelihood estimation using all available data, including incomplete mother-daughter pairs, and allowing missing observations to be endogenous. Our results show that being the daughter of a teen mother increases the chances of being a teen mother between 8.7 and 26.2 percentage points (between 61 and 172%). We conclude that the prevalence of such high intergenerational transmission is at the core of persistent high teenage childbearing rates in Latin America and suggests alternative public policy fixes.