Loglinear model for analysis of cross-tabulated coal mine injury data
Abstract:Mine accidents/injuries can be cross-classified against the variables of interest in a contingency table and their associations can be assessed through aggregate statistics. However, there is a need to develop a coherent and structured procedure for analysis of accident data, which will allow one to identify associations between two or more variables multivariately. In this study, the loglinear model, which has been proposed as a mathematical representation of the contingency table, was applied to accident data from a group of coal mines to assess the associations/interactions between two or more variables multivariately through their main and interaction effects. The case study results revealed that the variables ‘occupation' and ‘workplace location' were highly associated with degree of injury. It was also clearly indicated that the workers with more than 20 years of experience exhibited high injury rate patterns. While designing training programs for miners, focused attention should be given to specific categories of workers to reduce accident/injuries at the case study mines.
Document Type: Research Article
Publication date: 2001-12-01