On statistical methods for comparison of intrasample morphometric variability: Zalavar revisited

In studies of morphology, methods for comparing amounts of variability are often important. Three different ways of utilizing determinants of covarian ce matrices for testing for surplus variability in a hypothesis sample comp ared to a reference sample are presented: an F-test based on standardized g eneralized variances, a parametric bootstrap based on draws on Wishart; mat rices, and a nonparametric bootstrap. The F-test leased on standardized gen eralized variances and the Wishart-based bootstrap are applicable when mult ivariate normality can be assumed. These methods can be applied with only s ummary data available. However, the nonparametric bootstrap can be applied with multivariate nonnormally distributed data as well as multivariate norm ally distributed data, and small sample sizes. Therefore, this method is pr eferable when raw data are available. Three craniometric samples are used t o present the methods. A Hungarian Zalavar sample and an Austrian Berg samp le are compared to a Norwegian Oslo sample, the latter employed as referenc e sample. In agreement with a previous study, it is shown that the Zalavar sample does not represent surplus variability, whereas the Berg sample does represent such a surplus variability. (C) 2000 Wiley-Liss, Inc.