evaluated using a chi-square distribution. A significant change in fit between the models (p < 0.05) for the difference in degrees of freedom indicates that dropping the parameter caused a significant decrease in fit of the model, indicating that pathway significantly contributes to the outcome trait and should be retained in the model. Model-fitting proceeded in a series of steps. We first tested the significance of the main effect of the moderator (i.e., the neighborhood variable). We then tested the significance of moderation effects by dropping all moderation (3 df test, βX, βY, and βZ dropped). When this test was significant, we conducted further testing to determine what specific variance components showed significant moderation by sequentially dropping and testing the significance of each of the moderating effects one by one.
