Skip to main content
. Author manuscript; available in PMC: 2014 Mar 1.
Published in final edited form as: Rev Gen Psychol. 2012 Oct 29;17(1):111–121. doi: 10.1037/a0030048

Table 2.

Summary of regression equations derived from GLMM framework for calculations of GMA d from different research designs

Equation Design Characteristics
Y = a + bGroup + e (2) 2 groups, 1 time point (no pretest)
Y = a + b1Pretest + b2Group + e (5) 2 groups, 2 time points (pretest and posttest)
Y = a + b1Group1 + b2Group2 + e (7) 3 or more groups, 1 time point, orthogonal a priori contrasts
Y = a + b1Group + b2Time + b3Group*Time + e (8) 2 groups, 3 or more time points, linear model
Y = a + b1Group + b2Linear + b3Linear*Group + b4Quadratic + b5 Quadratic*Group + e (10) 2 groups, 3 or more time points, non-linear model
Y = a + b1Group + b2Sex + b3Group*Sex + e (11) 2 groups, 1 time point, subject moderator (e.g., sex)
Y = a + b1Group + b2Sex + b3Time +b4Group*Sex + b5Group*Time + b6Time*Sex + b7Group*Sex*Time + e (13) 2 groups, 3 or more time points, subject moderator

Note. Equation numbers are in parentheses following equations.