This paper provides important background information on the Fragile Families and Child Wellbeing Study, and is the first and only paper to provide detailed information on the research methodology and sampling strategies employed. The bulk of the paper is devoted to a detailed description of the three-stage sampling process that was used to obtain a nationally representative sample of non-marital births in large US cities. First, it was necessary to sample cities that, collectively, were nationally representative and had maximum variation in policy regimes. Next, it was necessary to sample hospitals so as to be representative of non-marital births in each city. Finally, we sampled births in order to be representative of those at each hospital. The paper concludes with some general information about the study and a simple description of the baseline non-marital sample from the first seven cities.