logo Netzschleuder network catalog, repository, and centrifuge

crime — Rosenfeld crime network (1991)

Description

Involvement of individuals in crime events in St. Louis (Missouri, USA), collected from police records by R. Rosenfeld and N. White in the 1990s. Starting from five homicides, they recorded the names of all the individuals involved as victims, suspects or witnesses, then searched the files for all the other crimes in which the same individuals appeared, and continued this snowball process until they had data on 557 crime events, with 870 participants: 569 appearances as victims, 682 as suspects, 195 as witnesses, and 41 as both victim and suspect in the same crime. The sex of each individual was also recorded. The data were distributed by L. C. Freeman on his network data page at the University of California, Irvine (no longer online), from which this version was obtained via the Internet Archive.

The network is bipartite: an undirected edge connects an individual to a crime event in which they were involved. One cell of the source matrix is coded as missing ("?"), and is not represented as an edge. The file contains 40 individuals and 4 crime events without any involvement, which are isolated nodes.

The network has the following properties:

  • (Node) is_crime: whether the node is a crime event (otherwise, it is an individual).
  • (Node) name: the name of the individual (with the family name first, without a space), or the identifier of the crime event (two identifiers, 930011 and 930019, are each used for two different crime events).
  • (Node) sex: the sex of the individual ("F" or "M"; empty for crime events). The coding of sex is not documented in the source (it is given as 0 or 1); it is inferred here from the first names.
  • (Edge) role: the role of the individual in the crime event ("victim", "suspect", "witness", or "victim and suspect").
Tags
Social Offline Unweighted Metadata
Added
2020-08-11
Citation
  • S. Decker, C. W. Kohfeld, R. Rosenfeld, & J. Sprague, "St. Louis Homicide Project: Local Responses to a National Problem." University of Missouri-St. Louis (1991) books.google.com
Upstream URL OK
https://web.archive.org/web/20210115130726/http://moreno.ss.uci.edu/data.html#crime
Networks
Tip: hover over a column header for a description.
Column legend
$\left<k\right>$
Mean degree
$\sigma_k$
Standard deviation of the degrees
$\lambda_h$
Largest eigenvalue of the Hashimoto (non-backtracking) matrix
$\tau$
Random walk mixing time
$r$
Degree assortativity
$c$
Global clustering coefficient
$\oslash$
(Pseudo-) diameter
$S$
Relative size of the largest component
NPs
Node properties
EPs
Edge properties
Name Nodes Edges $\left<k\right>$ $\sigma_k$ $\lambda_h$ $\tau$ $r$ $c$ $\oslash$ $S$ Kind Mode NPs EPs gt GraphML GML csv
crime 1,380 1,476 2.14 2.14 3.28 1385.50 -0.17 0.00 32 0.92 Undirected Bipartite meta 25 KiB 34 KiB 34 KiB 27 KiB
Ridiculograms*
* These are automatically generated force-directed visualizations, and can be quite meaningless for networks both big and small. They should not be taken seriously as sources of scientific insight. See here for a discussion.