Effect Size Estimation for Mixed Single-Case Experimental Designs

• In Event: 28.030 - Analysis in Experimental Designs and Quasi-Experimental Designs With Propensity Score Matching

Abstract

Single-case experimental designs (SCED) are rigorous (quasi-)experimental designs used to address a variety of research questions examining the effectiveness of interventions. Effect sizes have been suggested and intensively studied for relatively simple SCEDs (i.e., “pure SCEDs”), for example, ABAB reversal designs. To address more sophisticated research questions, various types of SCEDs have been combined (i.e., “mixed SCEDs”). The two most common mixed SCEDs are combinations of (1) a multiple-baseline design (MBD) across participants and an ABAB reversal design and (2) a MBD across participants and alternating treatment design. While these mixed SCED designs can address complex research questions, techniques for effect size estimation lag behind. This study focuses on the quantitative analysis of mixed SCEDs using regression-based effect sizes estimates.

Authors

• Diana Akhmedjanova, University at Albany - SUNY

• Mariola Moeyaert, University at Albany