The geographical distance between conspecific host populations is no doubt a key determinant of the likelihood that exchanges of parasite species occur between these populations. This variable must therefore be taken into account in studies that compare parasite species richness or similarity among host populations. This paper presents a multivariate approach, based on the permutation of matrices, that allows all pairwise geographical distances between host populations to be included as independent variables. The method is illustrated with 3 separate data sets on parasite communities of conspecific fish from different lakes. In 2 of 3 cases, geographical distances among lakes had a significant influence on the similarity of their parasite communities. The effect of geographical distance on species richness of parasite communities also proved important in 2 of the 3 case studies. These examples demonstrate the pervasive influence of distances among host populations on their parasite communities, and the need to properly control for them in statistical analyses.