PubAg

Main content area

An analysis of ill-posed production problems using maximum entropy

Author:
Paris, Q., Howitt, R.E.
Source:
American journal of agricultural economics 1998 v.80 no.1 pp. 124-138
ISSN:
0002-9092
Subject:
agriculture, production economics, decision making, cost analysis, resource allocation, input output analysis, econometric models, linear programming
Abstract:
Production economics problems are often ill-posed. This means that the number of parameters to be estimated is greater than the number of observations. In this article we show how to recover flexible cost functions from very limited data sets using a maximum entropy approach. We also argue that there exists a continuum of analysis between mathematical programming and traditional econometric techniques which is based solely upon the available information. The limiting case of a multi-output cost function recovered using only a single observation of a farmer's allocation decisions can be easily extended to handle more than one observation.
Agid:
1464875