Analysis of local influence in geostatistics using Student's <italic>t</italic>-distribution

This article aims to estimate parameters of spatial variability with Student's <italic>t</italic>-distribution by the EM algorithm and present the study of local influence by means of two methods known as likelihood displacement and <italic>Q</italic>-displacement of likelihood, both using Student's <italic>t</italic>-distribution with fixed degrees of freedom (ν). The results showed that both methods are effective in the identification of influential points.