AbstractThe stochastic behavior of agricultural commodity prices is investigated using observations of the term structures of futures prices over time. The continuous time dynamics of (log‐) commodity prices are modeled as a sum of a deterministic seasonal component, a non‐stationary state‐variable, and a stationary state‐variable. Futures prices are established by standard no‐arbitrage arguments and the Kalman filter methodology is used to estimate the model parameters for corn futures, soybean futures, and wheat futures based on weekly data from the Chicago Board of Trade for the period 1972–1997. Furthermore, in a discussion of the estimated seasonal patterns in agricultural commodity prices, the paper provides empirical evidence on the theory of storage that predicts a negative relationship between stocks of inventory and convenience yields; in particular, convenience yields used in this analysis are extracted using the Kalman filter. © 2002 Wiley Periodicals, Inc. Jrl Fut Mark 22:393–426, 2002