Every person who sends email, text messages, tweets, or simply surfs the Web leaves a digital trace. Researchers are just starting to comprehend the possibilities of "big data" for creating a new picture of social behavior. The potential for innovative work on social and cultural topics far outstrips current data collection and analysis techniques for a variety of reasons, including researchers' lack of access to corporate data sets, technical skills, and analytical lenses. This article draws a distinction between "horizontal" trace data sets that aggregate a specific type of trace, such as all tweets with a certain hashtag, and "vertical" trace data sets, which are organized around research participants. Although both types of data are observations of real-world digital behavior, they each have distinct advantages and disadvantages for the researcher. Combining these two forms of data provides a richer picture of online activity, and adding other types of data such as interviews, surveys, and experiments can contextualize online activity within broader social processes.