This chapter discusses a number of issues that arise during the encounter between the econometrician and economic data. Econometricians have an ambivalent attitude toward economic data. It is possible to take an alternative view for economic data issues that there are no data problems only model problems in econometrics. For any set of data, there is the right model. Much of econometrics is devoted to procedures that try to assess whether a particular model is right in this sense and to criteria for deciding when a particular model fits and is correct enough. Theorists and model builders often proceed, however, on the assumption that ideal data will be available and define variables that are unlikely to be observable, at least not in their pure form.