Figure 1.

Key pathways of analytic model for parallel-process growth modeling; see Cheong et al. (2003) for further details. The independent variable (treatment group) is modeled as affecting linear change (slope) in the mediator, which in turn affects linear change (slope) in the outcome. Intercept factors represent starting points in order to anchor change from a particular baseline. Each intercept and slope factor is a latent variable specified by fixed factor loadings representing time lags for each observed data point.

a = effect of IV on mediator; b = effect of mediator on outcome; c’ = direct effect of IV on outcome; IV = independent variable.