Abstract
This paper examines the decision to refer a sexual assault case for prosecution using a sample of 730 reported sexual assaults in which the victim received a medical/forensic examination. The decision to refer a case for prosecution was modeled using an algorithmic modeling technique, Random Forests. The key advantages of this modeling approach include its superiority in predicting case outcomes and its ability to easily uncover nonlinear relationships. Key results indicate that the likelihood of referral increased when sperm was found and documented, when the victim could identify the suspect, and as the severity of nongenital injury increased. Neither the presence nor the severity of genital injury impacted the decision to refer a case for prosecution. On the whole, suspect and report characteristics had the largest impact on referring cases for prosecution, with victim characteristics having little influence.
Similar content being viewed by others
Notes
Additional factors examined in the case processing literature include strength of the evidence (Albonetti, 1987), use of a weapon (Alderden & Ullman, 2012; Beichner & Spohn, 2005; Kerstetter, 1990; Spohn et al., 2001), multiple offenders (McGregor et al. 1999, 2002), victim resistance (Alderden & Ullman, 2012; Du Mont & Myhr, 2000; Kerstetter, 1990; Spohn & Horney, 1993; Spohn & Spears, 1996) timing of reporting (Beichner & Spohn, 2005; Kingsnorth et al., 1999; Spears & Spohn, 1997), and the availability of witnesses (Beichner & Spohn, 2005; Kingsnorth et al., 1999).
For brevity’s sake, other results are not presented but are available from the authors upon request. This cost ratio was chosen arbitrarily but it does represent the middle ground among the six estimated cost ratios and provides a representative picture of the effects seen at other cost ratios (although rank order varied slightly, the same six variables provided the largest change in average prediction success for all cases across all cost ratios).
As with variable importance measures, analyses were conducted at all six cost ratios. Across all cost ratios, the shape and direction of the effects were very similar. Partial dependence plots for all independent variables, at all cost ratios, are available from the authors upon request.
Rather than relying solely on the linear interpolation used in R, we also overlay a smoothed version of the partial dependence represented by the dotted curve. Smoothing is done using Friedman’s (1984) Super Smoother, with optimal smoothing chosen by cross-validation.
The rug plot is simply the observed covariate value for each case plus some random disturbance, where the disturbance is a drawn from a Uniform (−0.4,0.4) distribution.
References
Albonetti, C. (1987). Prosecutorial discretion: the effects of uncertainty. Law & Society Review, 21, 291–313.
Alderden, M. A., & Ullman, S. E. (2012). Creating a more complete and current picture: examining police and prosecutor decision-making when processing sexual assault cases. Violence Against Women, 18, 525–551.
Beichner, D., & Spohn, C. (2005). Prosecutorial charging decisions in sexual assault cases: examining the impact of a specialized prosecution unit. Criminal Justice Policy Review, 16, 461–498.
Berk, R. A. (2006). An introduction to ensemble methods for data analysis. Sociological Method & Research, 34, 263–295.
Berk, R. A. (2008a). Statistical learning from a regression perspective. New York: Springer.
Berk, R. A. (2008b). An introduction to statistical learning from a regression perspective. Working paper (Available at: http://www.crim.upenn.edu/faculty/papers/berk/StatisticalLearning.pdf).
Berk, R. A. (2011). Asymmetric loss functions for forecasting in criminal justice settings. Journal of Quantitative Criminology, 27, 107–123.
Berk, R. A., Azuse, L., & Hickman, L. J. (2005). Statistical difficulties in determining the role of race in capital cases: a re-analysis of data from the state of Maryland. Journal of Quantitative Criminology, 21, 365–390.
Berk, R. A., He, Y., & Sorenson, S. (2005). Developing a practical screener for domestic violence incidents. Evaluation Review, 29, 358–383.
Berk, R. A., Kriegler, B., & Baek, J. (2006). Forecasting dangerous inmate misconduct: an application of ensemble statistical procedures. Journal of Quantitative Criminology, 22, 131–145.
Berk, R. A., Sherman, L., Barnes, G., Kurtz, E., & Ahlman, L. (2009). Forecasting murder within a population of probationers and parolees: a high stakes application of statistical learning. Journal of the Royal Statistical Society, 172, 191–211.
Berk, R., Barnes, G., Ahlman, L., & Kurtz, E. (2010). When second best is good enough: a comparison between a true experiment and a regression discontinuity quasi-experiment. Journal of Experimental Criminology, 6, 191–208.
Biau, G., Devroye, L., Lugosi, G. (2007, Oct). Consistency of random forests and other averaging classifiers. (Available at: http://www.econ.upf.edu/~lugosi/randomforest.pdf).
Black, M. C., Basile, K. C., Breiding, M. J., Smith, S. G., Walters, M. L., Merrick, M. T., et al. (2011). The National Intimate Partner and Sexual Violence Survey (NISVS): 2010 summary report. Atlanta: National Center for Injury Prevention and Control, Centers for Disease Control and Prevention.
Bouffard, J. (2000). Predicting type of sexual assault case closure from victim, suspect, and case characteristics. Journal of Criminal Justice, 28, 527–542.
Bradmiller, L., & Walters, W. (1985). Seriousness of sexual assault charges: influencing factors. Criminal Justice and Behavior, 12, 463–484.
Breiman, L. (2001a). Random forest. Machine Learning, 45, 5–32.
Breiman, L. (2001b). Statistical modeling: two cultures. Statistical Science, 16, 199–231.
Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984). Classification and regressiontrees. Monterey: Wadsworth.
Bureau of Justice Statistics (2008). Sourcebook of criminal justice statistics online. Washington, DC: U.S. Department of Justice, Office of Justice Programs. Retrieved from http://www.albany.edu/sourcebook.
Campbell, R. (2008). The psychological impact of rape victims’ experiences with the legal, medical, and mental health systems. American Psychologist, 68, 702–717.
Campbell, R., Patterson, D., & Bybee, D. (2012). Prosecution of adult sexual assault cases: a longitudinal analysis of the impact of a Sexual Assault Nurse Examiner Program. Violence Against Women, 18, 223–244.
Campbell, R., Patterson, D., Bybee, D., & Dworkin, E. (2009). Predicting sexual assault prosecution outcomes: the role of medical forensic evidence collected by Sexual Assault Nurse Examiners (SANEs). Criminal Justice & Behavior, 36, 712–727.
Ciancone, A., Wilson, C., Collette, R., & Gerson, L. (2000). Sexual assault nurse examiner programs in the United States. Annals of Emergency Medicine, 35, 353–357.
Du Mont, J., & Myhr, T. L. (2000). So few convictions: the role of client-related characteristics in the legal processing of sexual assaults. Violence Against Women, 6, 1109–1136.
Frazier, P. A., & Haney, B. (1996). Sexual assault cases in the legal system: police, prosecutor, and victim perspectives. Law and Human Behavior, 20, 607–628.
Friedman, J. H. (1984). A variable span smoother. (Tech. Rep. LCS5) Stanford University.
Friedman, J. H. (1999). Greedy function approximation: A gradient boosting machine. (Tech. Rep.) Stanford University.
Frohmann, L. (1997). Convictability and discordant locales: reproducing race, class, and gender ideologies in prosecutorial decision making. Law & Society Review, 31, 531–556.
Gray-Eurom, K., Seaberg, D. C., & Wears, R. L. (2002). The prosecution of sexual assault cases: correlation with forensic evidence. Annals of Emergency Medicine, 39, 39–46.
Hastie, T., Tibshirani, R., & Friedman, J. (2001). The elements of statistical learning: data mining, inference, and prediction. New York: Springer.
Johnson, D., Peterson, J., Sommers, I., & Baskin, D. (2012). Use of forensic science in investigating crimes of sexual violence: contrasting its theoretical potential with empirical realities. Violence Against Women, 18, 193–222.
Kelley, K. D., & Campbell, R. (2013). Moving on or dropping out: police processing of adult sexual assault cases. Women and Criminal Justice, 23, 1–18.
Kerstetter, W. A. (1990). Gateway to justice: police and prosecutorial response to sexual assaults against women. The Journal of Criminal Law and Criminology, 81, 267–313.
Kilpatrick, D. G., Resnick, H. S., Ruggiero, K. J., Conoscenti, M. A., & McCauley, J. (2007). Drug-facilitated, incapacitated, and forcible rape: A national study. Washington: National Institute of Justice.
Kingsnorth, R., Lopez, J., Wentworth, J., & Cummings, D. (1998). Adult sexual assault: the role of race/ethnic composition in prosecution and sentencing. Journal of Criminal Justice, 26, 359–371.
Kingsnorth, R., MacIntosh, R., & Wentworth, J. (1999). Sexual assault: the role of prior relationship and victim characteristics in case processing. Justice Quarterly, 16, 275–302.
Littel, K. (2001). Sexual Assault Nurse Examiner (SANE) programs: Improving the community response to sexual assault victims. Washington: Office for Victims of Crime, U.S. Department of Justice.
Lonsway, K. A., & Archambault, J. (2009). The “Justice Gap” for sexual assault cases: future directions for research and reform. Violence Against Women, 18, 145–168.
McGregor, M. J., Du Mont, J., & Myhr, T. L. (2002). Sexual assault forensic medical examination: is evidence related to successful prosecution? Annals of Emergency Medicine, 39, 639–647.
McGregor, M. J., Le, G., Marion, S. A., & Wiebe, E. (1999). Examination for sexual assault: is the documentation of physical injury associated with the laying of charges? A retrospective cohort study. Canadian Medical Association Journal, 160, 1565–1569.
McLaren, J. A., Henson, V., & Stone, W. E. (2009). The sexual assault nurse examiner and the successful sexual assault prosecution. Women & Criminal Justice, 19, 137–152.
Postle, G., Rosay, A. B., Wood, D., TePas, K. (2007). Descriptive analysis of sexual assault incidents reported to Alaska State Troopers: 2003–2004. Alaska State Troopers, Department of Public Safety, and Department of Law, State of Alaska.
Rambow, B., Adkinson, C., Frost, T. H., & Peterson, G. F. (1992). Female sexual assault: medical and legal implications. Annals of Emergency Medicine, 21, 727–731.
Rand, M. R. (2009). National crime victimization survey: Criminal victimization, 2008. Washington: Bureau of Justice Statistics.
Rosay, A. B., & Henry, T. (2008). Alaska sexual assault nurse examiner study: Final report. Report prepared for the National Institute of Justice, Office of Justice Programs, U.S. Department of Justice. Anchorage: Justice Center, University of Alaska Anchorage.
Scott, H. S., & Beaman, R. (2004). Demographic and situational factors affecting injury, resistance, completion, and charges brought in sexual assault cases: what is best for arrest? Violence and Victims, 18, 479–494.
Snodgrass, G. M. (2006). Sexual assault case processing: a descriptive model of attrition and decision-making. Alaska Justice Forum, 23, 1–8.
Spears, J. W., & Spohn, C. (1997). The effect of evidence factors and victim characteristics on prosecutors’ charging decisions in sexual assault cases. Justice Quarterly, 14, 501–524.
Spohn, C., Beichner, D., & Davis-Frenzel, E. (2001). Prosecutorial justifications for sexual assault case rejection: guarding the “Gateway to Justice”. Social Problems, 48, 206–235.
Spohn, C., & Holleran, D. (2001). Prosecuting sexual assault: a comparison of charging decisions in sexual assault cases involving strangers, acquaintances, and intimate partners. Justice Quarterly, 18, 651–688.
Spohn, C., & Horney, J. (1993). Rape law reform and the effect of victim characteristics on case processing. Journal of Quantitative Criminology, 9, 383–410.
Spohn, C., & Horney, J. (1996). The impact of rape law reform on the processing of simple and aggravated rape cases. The Journal of Criminal Law and Criminology, 86, 861–886.
Spohn, C., & Spears, J. (1996). The effect of offender and victim characteristics on sexual assault case processing decisions. Justice Quarterly, 13, 649–680.
Tintinalli, F. E., & Hoelzer, M. (1985). Clinical findings and legal resolution in sexual assault. Annals of Emergency Medicine, 14, 447–453.
Tjaden, P., & Thoennes, N. (2006). Extent, nature, and consequences of rape victimization: Findings from the national violence against women survey. Washington: National Institute of Justice.
Traskin, M. (2008). The role of the bootstrap sample size in the consistency of the Random Forest algorithm (Tech. Rep.). University of Pennsylvania.
Wiley, J., Sugar, N., Fine, D., & Eckert, L. O. (2003). Legal outcomes of sexual assault. American Journal of Obstetrics and Gynecology, 188, 1638–1641.
Wood, D. S., Rosay, A. B., Postle, G., & TePas, K. (2011). Police presence, isolation, and sexual assault prosecution. Criminal Justice Policy Review, 22, 330–349.
Acknowledgments
This project is supported by Grants No. 2004-WB-GX-0003 and 2005-WB-GX-0011 awarded by the National Institute of Justice, Office of Justice Programs, U.S. Department of Justice. Points of view in this document are those of the authors and do not represent the views, beliefs, official position, or policies of the U.S. Department of Justice. Additionally, the viewpoints expressed here do not reflect the views or beliefs of the State of Alaska. We thank Tara Henry, MSN, RN, SANEA, SANE-P, for collecting all medical/forensic data.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Snodgrass, G.M., Rosay, A.B. & Gover, A.R. Modeling the Referral Decision in Sexual Assault Cases: An Application of Random Forests. Am J Crim Just 39, 267–291 (2014). https://doi.org/10.1007/s12103-013-9210-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12103-013-9210-x