In order to compare linear dimensions made by traditional anthropometric techniques, and those obtained from three-dimensional coordinates, samples of four indigenous southern African populations were analysed. Linear measurements were obtained using mathematically transformed, three-dimensional landmark data on 207 male crania of Cape Nguni, Natal Nguni, Sotho and Shangaan. Univariate comparisons for accuracy of the transformed linear data were made with those in a traditional linear study by de Villiers (The Skull of the South African Negro: A Biometrical and Morphological Study. Witwatersrand University Press, Johannesburg) on similar samples and equivalent landmarks. Comparisons were not made with her Penrose (Ann Eugenics 18 (1954) 337) analysis as an apparently anomalous 'shape'-'size' statistic was found. The univariate comparisons demonstrated that accurate linear measurements could be derived from three-dimensional data, showing that it is possible to simultaneously obtain data for three-dimensional geometric 'shape' and linear interlandmark analyses. Using Penrose and canonical variates analyses of the transformed three-dimensional interlandmark measurements, similar population distances were found for the four indigenous southern African populations. The inter-population distance relationships took the form of three separated pairs of distances, with the within-pair distances very similar in size. The cranial features of the four populations were found to be overall very similar morphometrically. However the populations were each shown by CVA to have population specific features, and using discriminant analyses 50% or more of the individual crania (with the exception of the Sotho) could be referred to their correct populations.