Missing values and centrality measures

Post date: Jun 17, 2014 2:32:20 PM

No centrality measure in UCINET distinguishes between missing values and zeros. For example, if your adjacency matrix has a row of missing values indicating that the node did not fill out the survey, the centrality measures will treat that as a row of zeros, like an isolate. In general, this is not a problem as long as you remember to do one very important thing: after calculating centrality, you must recode the centrality scores for all nodes with missing values to missing. For example, the missing nodes will probably have centrality scores of zero. This is incorrect -- in reality we don't know what their centrality is, so we should recode it to missing before doing any correlations or other statistical work with the centrality scores.