Single-Case Experimental Design Meta-Analyses: A Systematic Review of Methodology

• In Event: Advanced Research Methodologies in Educational Data

Abstract

This paper aims to review methodological research conducted in the field of single-case experimental design (SCED) meta-analysis. By using a systematic approach, 27 eligible reports were identified, and data was extracted related to meta-analytic techniques, data generation models, design conditions, statistical properties, and recommendations. The results show that multilevel modeling is the most investigated SCED meta-analytic technique used, and parameter bias is the most prominent statistical property investigated. Further, the researchers in the field recommend bootstrapping or Bayesian approaches to reduce parameter bias. This systematic review contributes significantly as a summary of methodological work done in the field of SCED meta-analysis and informs the need of future methodological research. The recommendations provided informs meta-analysists of SCED studies about best practices.

Authors

• Marzieh Dehghan-Chaleshtori, University at Albany - SUNY
  Presenting Author

• Mariola Moeyaert, University at Albany - SUNY
  Presenting Author

• Xinyun Xu, University at Albany - SUNY
  Non-Presenting Author