Logistic Regression for Classification in Agricultural Ergonomics

Abstract

Classification and prediction in agricultural systems are quite useful for effective planning. In this paper, logistic regression modeling has been employed for classification purposes on data pertaining to the area of agricultural ergonomics. Presence or absence of discomfort for the farm labourers in operating farm machineries has been considered as the dependent variable and associated quantitative and qualitative variables as regressors. From the different possible subsets of regressors, appropriate logistic regression models that best describe the dependent variable have been selected. Appropriate goodness of fit and predictive ability measures have been utilized for evaluating the performance of the fitted models. A single best regressor i.e., load given to the farm machinery during operation has been identified by employing variable selection based on collinearity diagnostics and stepwise logistic regression. Results of classifications of the test datasets revealed that logistic regression performed better than the conventionally used discriminant function analysis approach. The study revealed that logistic regression modeling can be employed as a viable alternative for classification purposes in the field of agricultural ergonomics