This sets of three graphs compare tie weight distribution in the three one-mode networks of co-attendance at the meetings of the Shanghai Rotary Club under President Petit's (1919-20), Fitch's (1930-1) and Harkson's (1938-9) terms. In this network, nodes represent participants (persons who attended meetings), whereas edges represents events. Any edge links two persons who participate in the same events. Tie weight measures how frequently two persons co-participate in meetings. This series of graphs is based on the “sum” method. 1 means that persons met only once, 2 that they attend twice the same meeting, 3 three times, and so on. Unsurprisingly, there is a reversely proportional relation between tie weight (number of events co-attended) and number of dyads (co-attending pairs). Those who met regularly are the least frequent. Conversely, pairs who met only once are the most frequent. The first graph refers to Petit's network, the second to Fitch's and the last one to Harkson's. 

The original datasets and the resulting graphs are available in the "Tables" and "Trees" section, respectively. We used the R package "dplyr" to make these graphs.