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

Area of Science:

• Psychology
• Behavioral Science
• Clinical Research

Background:

• Single-subject studies are crucial for evaluating interventions on individuals.
• Traditional analysis of single-subject data can be misleading due to measurement error.
• Existing methods may not accurately quantify intervention effects.

Purpose of the Study:

• To provide a non-technical overview of de Vries & Morey's (2013) models for single-subject data.
• To explain hypothesis tests for assessing intervention effects in single-subject studies.
• To demonstrate the application of these methods using the BayesSingleSub R package.

Main Methods:

• Utilizing statistical models to differentiate true scores from measurement error.
• Implementing hypothesis tests to quantify evidence for intervention effects.
• Applying the BayesSingleSub R package for data analysis.

Main Results:

• The developed models offer a more accurate quantification of intervention effects.
• Hypothesis tests provide robust evidence for the presence and size of effects.
• The BayesSingleSub package enables practical implementation on empirical data.

Conclusions:

• The presented models and tests enhance the rigor of single-subject research.
• Accurate analysis of intervention effects is achievable by accounting for measurement error.
• The BayesSingleSub R package serves as a valuable tool for researchers in the field.