Contributions of Decision- Tree Methodology to a Farming Systems Program

Abstract

During the past decade anthropologists in several cultures have used natural process or hierarchical decision-tree models to predict the actual choices of individuals. Decision trees have predicted with a high degree of accuracy selling decisions made by Ghanaian fish sellers, farmers' adoption decisions in Puebla, Mexico, farmers' land use patterns in Costa Rica, and farm families' choice of treatment for illness in Pichatero, Mexico. In each case where the method has been used, the predictability has been as high as 85% to 95% of the actual choice data used to test the model. Unfortunately, the method has not yet been used regularly by national or international agricultural research centers. The reason is that the decision-tree tool presupposes a farming system research and extension program in which the farmer as decision maker is directing the program. This paper, therefore, shows how one decision-tree model was used in a farming systems program at a national agricultural research center to provide ...