Statistical Computing and Graphics A Diamond-Shaped Equiponderant Graphical Display of the Effects of Two Categorical Predictors on Continuous Outcomes
Xiuhong Li, Jennifer M. Buechner, Patrick M. Tarwater, Alvaro Mu · 2003
Three-dimensional (3-D) bar graphs and their current 2-D alter-natives have certain limitations when the primary objective is to provide an equal representation of the effects of two predictors on an outcome. This article proposes a graphing methodology (in the shape of a diamond) that projects 3-D bar graphs into 2-D whereby the third dimension is replaced with a polygon whose area and middle vertical and horizontal lengths represent the outcome. The proposed graphical representation is invariant to rotations and avoids outcomes in categories being concealed by others. This article shows several applications of our proposal to a variety of data types (e.g., proportions, incidence rates, relative risks), which can be easily implemented with available software. KEY WORDS: Epidemiology; Graphical methods; Statis-tics; Three-dimensional bar graphs; Two-dimensional projec-tions. 1.