The development and validation of the Youth Actuarial Care Needs Assessment Tool for Non-Offenders (Y-ACNAT-NO)

Abstract

Background: In The Netherlands, police officers not only come into contact with juvenile offenders, but also with a large number of juveniles who were involved in a criminal offense, but not in the role of a suspect (i.e., juvenile non-offenders). Until now, no valid and reliable instrument was available that can be used by Dutch police officers for estimating the risk for future care needs of juvenile non-offenders. In the present study, the Youth Actuarial Care Needs Assessment Tool for Non-Offenders (Y-ACNAT-NO) was developed for predicting the risk for future care needs that consisted of (1) a future supervision order as imposed by a juvenile court judge and (2) future worrisome incidents involving child abuse, domestic violence/strife, and/or sexual offensive behavior at the juvenile's living address (i.e., problems in the child-rearing environment).

Methods: Police records of 3,200 juveniles were retrieved from the Dutch police registration system after which the sample was randomly split in a construction (n = 1,549) and validation sample (n = 1,651). The Y-ACNAT-NO was developed by performing an Exhaustive CHAID analysis using the construction sample. The predictive validity of the instrument was examined in the validation sample by calculating several performance indicators that assess discrimination and calibration.

Results: The CHAID output yielded an instrument that consisted of six variables and eleven different risk groups. The risk for future care needs ranged from 0.06 in the lowest risk group to 0.83 in the highest risk group. The AUC value in the validation sample was .764 (95% CI [.743, .784]) and Sander's calibration score indicated an average assessment error of 3.74% in risk estimates per risk category.

Conclusions: The Y-ACNAT-NO is the first instrument that can be used by Dutch police officers for estimating the risk for future care needs of juvenile non-offenders. The predictive validity of the Y-ACNAT-NO in terms of discrimination and calibration was sufficient to justify its use as an initial screening instrument when a decision is needed about referring a juvenile for further assessment of care needs.

Figure 1

Classification tree for the validation sample. The grey shaded terminal nodes represent the eleven “risk groups” in which juveniles have similar scores on the variables that comprise the Y-ACNAT-NO and therefore the same risk for future care needs. n (%) = the number and percentage of juveniles that are classified in each tree node. Prop. care needs = proportion of juveniles with care needs.

Figure 2

Receiver operating characteristic curve analysis of the Y-ACNAT-NO and YO-CNAT. Y-ACNAT-NO = Youth Actuarial Care Needs Assessment Tool for Non-Offenders; YO-CNAT = Youth Offender Care Needs Assessment Tool.