ABSTRACT

On-farm research is a set of procedures for adaptive research aimed at developing recommendations for representative groups of farmers. These groups of farmers’ plots are used as the research site, thereby allowing for appropriate site specific technology, valid results and faster adoption. The move towards on-farm research means that researchers, such as plant breeders and agronomists, who have been trained in techniques of on-station research, are now under pressure to move on-farm. As a result of variations between farms and variations between plots within farm, many variables are encountered during data collections; the task of analyzing such enormous variables becomes a problem. One of such key steps in data analysis is finding ways to reduce dimension without sacrificing accuracy. Principal component analysis is a statistical technique in data analysis. It is used to compress higher dimensional dataset to lower dimensional ones. PCA allows the use of variables which are not measured in the same units for example elevation, concentration of nutrient, temperature and pH, making it an ideal tool for on-farm research data analysis.