A statistical analysis was performed to determine the strength of the association between particular risk factors and the violence incurred. To account for the fact that each study used different methods, this relationship was expressed as a correlation coefficient, which was arrived at using standard meta-analytical procedures (Rosenthal, 1991). The findings from two or more studies were summarized as a weighted mean correlation, which gives more weight to studies with large samples than to studies with small samples.
The strength of the association between a risk factor and subsequent violence can also be expressed as an odds ratio (the odds of violence in the group with a particular risk factor divided by the odds of violence in the group without that risk factor). An odds ratio expresses the degree of increased risk for violence associated with the presence of a risk factor in a population. For example, an odds ratio of 2 indicates a doubling of risk. This Bulletin provides odds ratios for predictors when they were given or could be compiled from the information provided in a study.