Newcomb Fraternity (data)

The Newcomb Fraternity Data (see Newcomb T. (1961). The acquaintance process. New York: Holt, Reinhard & Winston.) consits of 15 matrices recording weekly sociometric preference rankings from 17 men attending the University of Michigan in the fall of 1956. Each participant ranks all 16 others from best friend down to least friend. The image below shows a status layout dependent on the top 3 nominations (see the trail on advanced attribute management for further explanation).

The data are represented in 15 adjacency matrices of order 17x17 in files newfrat01.csv to newfrat15.csv. The entry in row i and colum j gives the rank of j in the ordered list of is friends (ordered from the best friend to the least). Row labels and column labels (actor names) are not included in the files, but the ordering is the same in all files.

The data that we provide for download below are taken from the Pajek data Website [1] (see UCINET IV datasets). For convenience, the file newfrat.dat has been split into 15 separate CSV files each recording the preference rankings for one week. When importing these files in visone, note that the cell delimiter is the space character, that row and column labels are not included, and that repeated cell delimiters should be treated as one (check option merge empty cells). Import, preprocessing, and analysis of these files is illustrated in the trail on advanced attribute management.

Available files (right-click and choose save link as to download):

• Newfrat.zip ZIP file containing all 15 matrices newfrat01.csv to newfrat15.csv
• Newfrat_top3.zip ZIP file containing 15 graphml files obtained from the respective matrices by deleting the links to all but the top 3 friends (see the trail on advanced attribute management for further explanation).