Predictability of nodes in network models offer an additional perspective on symptom networks, which relates to the practical relevance of edges, the selection of optimal treatment and the degree to which (parts of) the network are self-determined or determined by factors outside of the networks.
How to interpret interactions between categorical variables in a mixed graphical model? How can we recover the direction of interactions between continuous variables? Have a look at this blog post to find out!
In many situations one is interested in constructing a network from different types of variables, for example age (continuous), type of medication (categorical) and number of diagnoses (count). In this blog post on R-bloggers.com, I describe how to construct such a network using the R-package “mgm”: