This research examines the sentencing outcomes of convicted child sexual offenders from data collected over an eight year period. Multiple regression and nominal log linear regression are used to examine length of prison sentence, length of probation sentence, and whether or not the convicted offender is actually sent to prison or to probation. While many independent variables appear to be related to sentence outcome, they fall into three categories: characteristics of the offender, characteristics of the victim, and characteristics of the crime. Additionally, while many variables appear related at the bivariate level, when multivariate analysis is applied, fewer variables remain significant and these are mostly from the characteristics of the offense.
Patrick, Steven and Marsh, Robert. (2011). "Sentencing Outcomes of Convicted Child Sex Offenders". Journal of Child Sexual Abuse, 20(1), 94-108. http://dx.doi.org/10.1080/10538712.2011.541356