It is well known that activity analysis is inwardlooking into a firm in contrast to production function analysis, which looks outward into the market even when it deals with a single firm. But activity analysis has not been applied to the empirical analysis of farm households. The reason is that it is very difficult to estimate the unknown utility function in the activity model of the farm household, which is formulated as a utility maximization problem with linear inequality constraints.
In this paper, we present a nonparametric estimation method of a unique, unknown utility function using observation data on constraint conditions and the corresponding optimal level of activity. We also present a method of maximizing the estimated utility function under any linear inequality constraints. By applying the two methods mentioned above, we can conduct some analyses, test observation data for consistency with the activity model of the farm household, estimate the marginal valuation of endowed resources and make a comparative static analysis. A case study of simple experimental problems proves the usefulness of our methods. Finally, implications of this paper and problems to be solved in the future are summarized.
View full abstract