Abstract
In deciding which instrument to use in making a prediction or classification, forensic psychologists strive to use the most accurate test possible for their purpose. But accuracy in prediction or classification can be measured in many different ways. Choosing the right approach to measuring accuracy requires a basic understanding of various test accuracy statistics including, most fundamentally, sensitivity, specificity, positive predictive power, and negative predictive power. These statistics and their purposes are reviewed, along with related concepts such as base rates, cut scores, and the application of Bayes’ theorem to the use of tests in particular circumstances. The advantages of using ROC (receiver operating characteristics) curves and AUC (area under the curve) statistics in choosing tests are also briefly reviewed.
This is a preview of subscription content, log in via an institution to check access.
Notes
It would be exactly equal to sensitivity when BR = 0.50 if sensitivity and specificity were the same.
This figure is in line with data from Finkelhor, Hotaling, Lewis, & Smith, 1990, based on a 1985 Los Angeles Times national telephone poll that asked 1145 adult males about their experience of sexual abuse as children.
A statistically sophisticated defense expert may further challenge this figure by calculating that the confidence interval in making predictions for a group of children who exhibit a particular behavior is much narrower than for an individual who exhibits this behavior, but this technical problem is beyond the scope of this primer. Also, of course, the figures tell us nothing about whether the perpetrator, if there was one, was employed at the school.
References
Blake, D., Weathers, F., Nagy, L., Kaloupek, D., Klauminzer, G., Charney, D., & Buckley, T. C. (2000). Clinician-Administered PTSD scale (CAPS): Instruction manual. Boston, MA: National Center for PTSD.
Bossuyt, P., Reistsma, J. B., Bruns, D. E., Gatsonis, C. A. Glasziou, P. P., Irwig, L. M., … de Vet, H. C. (2003). Towards complete and accurate reporting of studies of diagnostic accuracy: The STARD initiative. Annals of Internal Medicine, 138, 40–44.
Finkelhor, D., Hotaling, G., Lewis, I. A., & Smith, C. (1990). Sexual abuse in a national survey of adult men and women: Prevalence, characteristics, and risk factors. Child Abuse and Neglect, 14, 19–28.
Friedrich, W. N. (1993). Sexual behavior in sexually abused children. Violence Update, 3(5), 1, 4, 8–11.
Gradus, J. L. (2014). Epidemiology of PTSD. Retrieved from http://www.ptsd.va.gov/professional/PTSD-overview/epidemiological-facts-ptsd.asp
Kendall-Tackett, K., Williams, L. M., & Finkelhor, D. (1993). Impact of sexual abuse on children: A review and synthesis of recent empirical studies. Psychological Bulletin, 113, 164–180.
Pintea, S., & Moldovan, R. (2009). The Receiver-Operating Characteristic (ROC) analysis: Fundamentals and applications in clinical psychology. Journal of Cognitive and Behavioral Psychotherapies, 9(1), 49–66.
Streiner, D. L. (2003). Diagnosing tests: Using and misusing diagnostic and screening tests. Journal of Personality Assessment, 8(3), 209–219.
Streiner, D. L., & Cairney, J. (2007). What’s under the ROC? An introduction to Receiver Operating Characteristics curves. The Canadian Journal of Psychiatry, 52, 121–128.
Acknowledgments
I would like to thank David L. Streiner for his helpful comments on an earlier draft of this article.
Author information
Authors and Affiliations
Corresponding author
Additional information
Gerald Young served as Action Editor for this paper
Rights and permissions
About this article
Cite this article
Erard, R.E. A Brief Primer on Test Accuracy Statistics and Related Matters. Psychol. Inj. and Law 8, 40–45 (2015). https://doi.org/10.1007/s12207-015-9217-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12207-015-9217-3