Table 2Standardized mean difference (SMD) ES estimations (and their components) for two independent groups

No.SourceEquationComponents
6.Hedges (1981)25 dhb=c(N-2)Y¯PostE-Y¯PostCSPooled c(N-2)=1-34(N-2)-1SPooled=(nE-1)SE2+(nC-1)SC2nE+nC-2
N = nE + nC
SE = post-test standard deviation of the experimental group
SC = post-test standard deviation of the control group
Y¯PostE= post-test mean of the experimental group
Y¯PostC= post-test mean of the control group
7.Becker (1988)19 db=c(N-2)[Y¯PostE-Y¯PreESPreE-Y¯PostC-Y¯PreCSPreC]
8.Gibbons et al. (1993)23 dg=c(N-2)[Y¯DiffESDiffE-Y¯DiffCSDiffC]
9.Huedo-Medina and Johnson (2011)24 dhw=c(N-2)[Y¯PostE-Y¯PreESwithin-poolE-Y¯PostC-Y¯PreCSwithin-poolC]
10.Shadish et al. (1999)26 ds1=Y¯PostE-Y¯PostCSPooled SPooled=(nE-1)SE2+(nC-1)SC2nE+nC-2SE=Y¯PreE-Y¯PostEnltdE2(1-rPre,PostE)SC=Y¯PreC-Y¯PostCnltdC2(1-rPre,PostC)
11.Shadish et al. (1999)26 ds2=Y¯PostE-Y¯PostCSANOVA SANOVA=MSEb+(tp-1)MSEwtp
MSEb = between-subjects mean square error
MSEw = within-subjects mean square error
tp = number of measured time points
12.Shadish et al. (1999)26 ds3=Y¯PostE-Y¯PostCSANCOVA SANCOVA=MSEa(N-h-1)(1-rw-class2)(N-h)rw-class=FcovFcov+(N-h-1)
MSEa = adjusted mean square error from the covariance analysis

From: Introduction

Cover of Meta-Analytic Statistical Inferences for Continuous Measure Outcomes as a Function of Effect Size Metric and Other Assumptions
Meta-Analytic Statistical Inferences for Continuous Measure Outcomes as a Function of Effect Size Metric and Other Assumptions [Internet].
Johnson BT, Huedo-Medina TB.

NCBI Bookshelf. A service of the National Library of Medicine, National Institutes of Health.