Barrameda, Claire Emerson.; Clemente, Jillian C.; Conroy, Jackson D.; Calnan, Mark. – 2020
This paper shares the findings of a study that explored the impacts of different risk factors and service allocation to infants from urban areas of Texas who were placed into foster care as a result of parental substance abuse. Through the use of predictive analytics, the study determined the impact that services and other factors had on a child’s length of stay in foster care. The study found that non-service factors play an important role in predicting how long a child spends in care. Of the 157 coefficients from a regression analysis, every coefficient includes a non-service factor in some form (either by themselves or within an interaction term). The five most common non-service factors were monthly foster care payments, median household income, poverty rate, crime rate, and unemployment rate. These findings were then used to develop a mechanism that reallocates services with the goal of minimizing the total amount of time children spend in care. The paper concludes that there is an opportunity to improve service allocation by examining not only the details within a child’s case, but also the environmental factors surrounding the child’s case. Numerous references. (Author abstract modified)