A standardized mean difference effect size for multiple baseline designs across individuals.

Area of Science:

• Psychology
• Behavior Analysis
• Medicine

Background:

• Single-case designs evaluate treatment effects through repeated outcome measures within individuals.
• Existing research focuses on summarizing findings and developing comparable effect size indices.
• Previous work defined effect sizes for treatment reversal (AB)(k) designs.

Purpose of the Study:

• To extend effect size estimation to multiple baseline single-case designs.
• To propose methods for estimating effect size and its variance.
• To demonstrate the applicability of the proposed methods.

Main Methods:

• Proposed novel estimation methods for effect size and variance in multiple baseline designs.
• Conducted simulation studies to evaluate the proposed estimators.
• Applied the methods to two real-world case study applications.

Main Results:

• The proposed estimation methods provide a comparable effect size measure for multiple baseline designs.
• Simulation studies support the validity and utility of the estimators.
• Applications demonstrate the practical use of the effect size measure.

Conclusions:

• The developed effect size measure facilitates standardized comparison of findings across single-case and between-subjects studies.
• This contributes to more robust meta-analysis and evidence synthesis in fields utilizing single-case designs.
• The approach enhances the interpretability and comparability of treatment effect evaluations.