For a normally distributed variable, the index of atypicality associated with a measurement of that variable is defined as the probability of finding a result closer to the mean of the reference population than the one actually observed. The method extends straight forwardly to multivariate situations, thus providing a joint interpretation of multiple observations recorded on the same subject. In human palaeontology, atypicality indices allow to analyze and to compare the results obtained from variables closely associated with specific traits of the morphology. We briefly outline the principle of the method and give a computer program to carry out the calculations. Finally, we apply the use of univariate and multivariate atypicality indices to data recorded on 53 Upper Palaeolithic skulls.