Skip to main content
. Author manuscript; available in PMC: 2013 May 29.
Published in final edited form as: J Am Stat Assoc. 2012 Jan 1;105(489):59–70. doi: 10.1198/jasa.2009.ap08518

Figure 4.

Figure 4

Non-random mixing by age and gender in an example ego’s network. In the latent non-random mixing model m(e, a) allows the propensity of ties to vary based on characteristics of both the alters and the egos. Here, by ego, we refer to a survey respondent and by alter, we refer to a member of subgroup a with whom the respondent could potentially form ties.