Recruitment Homophily

Compute a homophily measure for the recruitment process, i.e. do respondents tend to recruit people like themselves? Take as an example homophily by disease status. In this case, it is the ratio of number of recruits that have the same disease status as their recruiter to the number we would expect by chance. The difference with the Population Homophily is that here we calculate for the recruitment chain rather than the whole population of social ties.

  • If the recruitment homophily on disease status is about 1, we see little effect of recruitment homophily.
  • Values larger than one indicate more homophily.

The following shows how to calculate recruitment homophily on disease status for the fauxmadrona data set.