The study findings indicate that offending was predominantly done alone; however, overall estimates of co-offending varied significantly, depending on the unit of measurement examined. The key conclusion drawn from this study is that each estimate provides valid and distinctive information about co-offending, but they must be distinguished from one another if the results of different studies are to be compared and interpreted correctly. Significant variations in the prevalence of co-offending and the average number of offenders per offense were observed across age, gender, and crime type. Consistent with previous research, there was a negative association between age and co-offending. Individuals implicated in co-offending were significantly younger than solo offenders. Females were slightly more likely than males to participate in joint offending. Property offenses were less likely than violent or other offenses to be committed by lone offenders. Robbery, arson, burglary, and theft of/from motor vehicles were the crime types most likely to involve multiple offenders. Co-offending was rare for sex offenses and fraud. This study is based on an analysis of the universe of notifiable offenses that were cleared by a large metropolitan police force located in the North of England between March 1, 2002, and February 28, 2005. Information was obtained on 105,348 offenses. 6 tables, 2 figures, 54 references, and 1 appendix