A Tutorial on Computing Bayes Factors for Single-Subject Designs.

When researchers are interested in the effect of certain interventions on certain individuals, single-subject studies are often performed. In their most simple form, such single-subject studies require that a subject is measured on relevant criterion variables several times before an intervention and several times during or after the intervention. Scores from the two phases are then compared in order to investigate the intervention effect. Since observed scores typically consist of a mixture of true scores and random measurement error, simply looking at the difference in scores can be misleading. Hence, de Vries & Morey (2013) developed models and hypothesis tests for single-subject data, quantifying the evidence in data for the size and presence of an intervention effect. In this paper we give a non-technical overview of the models and hypothesis tests and show how they can be applied on real data using the BayesSingleSub R package, with the aid of an empirical data set.