The t test and beyond: Recommendations for testing the central tendencies of two independent samples in research on speech, language and hearing pathology

PurposeIn this Tutorial we compare current practice of the analysis of data obtained in designs involving two independent samples with new developments in statistics and evidence on the behavior of conventional statistics. We included t tests, non-parametric alternatives, such as the Wilcoxon–Mann–Whitney test, and recently developed approaches, known as bootstrapping and randomization tests. The relative use of the different statistics is illustrated on the basis of counts carried out in three journals on disordered communication in the time interval 2005–2013: Clinical Linguistics & Phonetics, Journal of Communication Disorders and Journal of Speech, Language and Hearing Research. A number of recommendations are given to guide the researcher in the presentation and analysis of her/his data.ConclusionsThe main messages are (a) that researchers should present more relevant features of their data (means, medians, SD, skewness, tailedness, outliers etc.), (b) not routinely use conventional non-parametric tests like Wilcoxon–Mann–Whitney test in case one or more of the assumptions of t tests are not met, and (c) should consider using less conventional, but robust statistics which have been developed and tested in the last decades.