We see what we want to see

From Homophily and Contagion Are Generically Confounded in Observational Social Network Studies by Cosma Rohilla Shalizi and Andrew C. Thomas. The abstract.

We consider processes on social networks that can potentially involve three factors: homophily, or the formation of social ties due to matching individual traits; social contagion, also known as social influence; and the causal effect of an individual's covariates on their behavior or other measurable responses. We show that, generically, all of these are confounded with each other. Distinguishing them from one another requires strong assumptions on the parametrization of the social process or on the adequacy of the covariates used (or both). In particular we demonstrate, with simple examples, that asymmetries in regression coe fficients cannot identify causal effects, and that very simple models of imitation (a form of social contagion) can produce substantial correlations between an individual's enduring traits and their choices, even when there is no intrinsic affi nity between them. We also suggest some possible constructive responses to these results.

I think what this is saying is that the effect of homophily, social influence, and personal choices are hard to isolate from one another in causal terms and that it is too easy to impose an assumed causal relationship when one does not actually exist. And in fact, the act of imposing such a relationship is really just a function of one's preexisting assumptions.