NotesFAQContact Us
Search Tips
ERIC Number: ED543975
Record Type: Non-Journal
Publication Date: 2012-Sep
Pages: 16
Abstractor: As Provided
Reference Count: 25
A Standardized Mean Difference Effect Size for Single Case Designs
Hedges, Larry V.; Pustejovsky, James E.; Shadish, William R.
Online Submission, Research Synthesis Methods v3 n3 p224-239 Sep 2012
Single case designs are a set of research methods for evaluating treatment effects by assigning different treatments to the same individual and measuring outcomes over time and are used across fields such as behavior analysis, clinical psychology, special education, and medicine. Emerging standards for single case designs have focused attention on the need for effect sizes for summarizing and meta-analyzing findings from the designs; although many effect size measures have been proposed, there is little consensus regarding their use. This article proposes a new effect size measure for single case research that is directly comparable with the standardized mean difference (Cohen's "d") often used in between-subjects designs. Techniques are provided for estimating the new effect size, as well as its variance, from balanced or unbalanced treatment reversal designs. The proposed estimation methods are further evaluated using a simulation study and then demonstrated in two applications. The following are appended: (1) Derivation of the exact expectation and variance of ES from the moments of D and the inverse moments of S[superscript 2]; (2) Derivation of the effect size estimator for the general (AB)[superscript k] design; and (3) Formulas for estimators phi and rho in the unbalanced (AB)[superscript k] design. (Contains 1 table and 2 figures.)
Publication Type: Journal Articles; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: Institute of Education Sciences (ED)
Authoring Institution: N/A
IES Funded: Yes
Grant or Contract Numbers: R305D100046