This paper tests for the presence of habit formation using household data. A simple model of habit formation implies a condition relating the strength of habits to the evolution of consumption over time. When the condition is estimated with food consumption data from the Panel Study on Income Dynamics (PSID), the results yield no evidence of habit formation at the annual frequency. This finding is robust to a number of changes in the specification. It also holds for several proxies for nondurables and services consumption created by combining PSID variables with weights estimated from Consumer Expenditure Survey data.