摘要：Systems of equations comprising cost functions and ￠rst-order derivative equationsare often used to estimate characteristics of production technologies. Unfortunately,many estimated systems violate the regularity conditions implied by economictheory. Sampling theory methods can be used to impose these conditions globally,but these methods destroy the ￡exibility properties of most functional forms. Wedemonstrate how Bayesian methods can be used to maintain ￡exibility by imposingregularity conditions locally. The Bayesian approach is used to estimate a system ofcost and share equations for the merino wool-growing sector. The e.ect of localimposition of monotonicity and concavity on the signs and magnitudes of elasticitiesis examined.
