Nonparametric tests for profit maximization with incomplete data: application to the pulp and fine paper production in Finland
2005
Kallio, A.M.I. | Hanninen, R.
Forest sector models give relevant information to decision makers only if they are based on correct economic hypotheses. This requires that the data from which the model parameters are estimated are consistent with the a priori assumptions made on market agents' behavior and competition patterns. For static models, rather simple nonparametric tests exist for checking such consistency. Such tests also provide an analyst with insights on possible errors in the data and the suitability of the data for the particular econometric model that the analyst has in mind. This article proposes data tests for the competitive or noncompetitive profit-maximization hypothesis that can also be used with incomplete data. The tests are applied to quarterly data on the production of pulp and fine paper in Finland. It is found that the data may not represent profit-maximizing price takers. Although this can be due to, e.g., integrated production, missing dynamics, or noncompetitive behavior--a hypothesis that was indeed found to be consistent with the fine paper data--it is evident that the modeler should not use these data in estimating a parametric industry model that builds on price-taking profit-maximizing behavior. The results emphasize the importance of testing the data before modeling. FOR. SCI. 51(1):19-28.
Show more [+] Less [-]AGROVOC Keywords
Bibliographic information
This bibliographic record has been provided by National Agricultural Library