Testing the impact of group offending on behavioural similarity in serial robbery

Abstract

Behavioural case linkage assumes that offenders behave in a similar way across their crimes. However, group offending could impact on behavioural similarity. This study uses robbery data from two police forces to test this by comparing the behavioural similarity of pairs of lone offences (LL), pairs of group offences (GG) and pairs of offences where one crime was committed alone and the other in a group (GL). Behavioural similarity was measured using Jaccard's coefficients. Kruskal-Wallis tests were used to examine differences between the three categories within the linked samples. No statistically significant differences were found for linked GG compared to linked LL pairs. However, differences emerged between GL and the other categories for some behaviours (especially control) suggesting caution should be applied when linking group and lone offences committed by the same perpetrator. Differences between linked and unlinked pairs were assessed using receiver operating characteristic. The results suggest it is possible to distinguish between linked and unlinked pairs based on behaviour especially within the GG and LL categories. There were, however, fewer significant findings for the GL sample, suggesting there may be issues linking crimes where the offender commits one crime as part of a group and the other alone.

Closer to reality? The application of sequence analysis in crime linkage

“…Whereas CCA is concerned with structured queries within large databases such as ViCLAS to find similar cases [1], CLA is a process where a behavioural investigative advisor (BIA) examines a smaller number of two or more offences with regard to their linkage potential. The empirical crime linkage literature has rather focussed on CCA scenarios and amassed a substantial body of research (Burrell et al, 2012;Davies et al, 2012;Ellingwood et al, 2013;Tonkin et al, 2011a;Tonkin et al, 2011b;Salo et al, 2012;Santtila et al, 2005;Santtila et al, 2008;Woodhams and Labuschagne, 2011;Woodhams and Toye, 2007) that has demonstrated two main findings: First, crime linkage is a worthwhile endeavour as large scale studies such as Woodhams et al (2019b) have proved that the theoretical assumptions of consistency and distinctiveness do hold up in international samples of serial sexual assaults. Second, various statistical algorithms do perform objectively well in linking crimes committed by the same offender.…”

Serial theft case linkage based on a two‐step cumulative probability model

“…Serial cases have always been the focus of research by the public security organs of various countries, and the research dimensions are diverse. Burrell, Bull, Bond, and Herrington (2015) measured behavioural similarity using Jaccard's coefficients and used Kruskal-Wallis tests to examine the differences between the linked samples. Campobasso et al (2009) discussed the suspect's motivation, mental health, childhood experiences and other issues in an in-depth study of 15 murder cases of older women over the age of 70.…”

Using Classification Trees to Link Serial Crimes

“…Crime linkage researchers typically control for the impact of prolific offenders by selecting a constant number of crimes per offender (e.g., Bennell & Canter, 2002;Burrell, Bull, Bond, & Harrington, 2015;Markson et al, 2010;Tonkin, Woodhams, et al, 2012).…”

“…As shown earlier in Table 4, the median number of days between unlinked crime pairs was 1,527 days. Most linking studies examining temporal proximity as a predictor have sampled crimes over a shorter timeframe, ranging from 1 to 5 years (e.g., Burrell et al, 2012Burrell et al, , 2015Davies, Tonkin, Bull, & Bond, 2012;Markson et al, 2010;Tonkin, Woodhams, Bull, Bond, & Palmer, 2011;Tonkin & Woodhams, 2015). 39 The median number of days between unlinked crime pairs in these studies is 39 The exception to this is Tonkin, Santtila, et al (2012), where the sample was comprised of Finnish residential burglaries committed between 1990 and 2001; however, the median number of days between crimes for linked pairs and unlinked pairs was not reported in this study.…”

“…On a final note, recall that the domains used in the current study were defined in a relatively atheoretical manner. That is, behaviours that police could identify at the time of the crime were split into domains based on their presumed function (as mentioned, this is a standard approach to forming domains in many linking studies; e.g., Bennell & Canter, 2002;Burrell et al, 2012Burrell et al, , 2015Davies et al, 2012;Woodham & Toye, 2007;Tonkin, Santtila et al, 2012;Tonkin, Woodhams, et al, 2012). This may make it difficult to infer any sort of underlying psychological meaning from the pathways.…”