Determining Relationships Among the Adoption Parameters of Computers and Internet in Agriculture: An Application of Probit Model

Abstract

The main reason for carrying out this study was to determine possible relationships among several adoption parameters of computer use, internet usage and internet access in agriculture. The key options for determining relationships (apart from non-parametric correlation techniques) are canonical correlation analysis, probit models and logit models. Canonical correlation analysis is generally seen as a weaker statistical technique than probit or logit models. The number of categorical variables in the data set made it difficult to fit logit models. So, the left probit models are the preferred techniques for testing the research question. To address the research question survey data was collected. Producers were asked to rank, in turn, how important computers and internet usage were to their business. These rankings could then be tested against other variables collected in order to determine whether it was the cost reduction or the productivity enhancing activities that were significant in explaining the rankings.