Jason ex-offender data comparing three conditions

Published: 08-03-2021| Version 3 | DOI: 10.17632/3pr3cpx6cg.3
Lenny Jason


This aftercare study involved a sample of 270 criminally-justice involved individuals with substance use disorders, who were randomized either to self-help recovery homes, professionally led therapeutic communities, or a control condition. Subsequently, participants were then followed over two years providing multiple waves of data. The authors of this article concluded that those who had been assigned to the recovery home condition received more money from employment, worked more days, achieved higher continuous alcohol sobriety rates, and had more favorable cost–benefit ratios. Jason, L.A., Olson, B.D., & Harvey, R. (2015). Evaluating alternative aftercare models for ex- offenders. Journal of Drug Issues, 45(1), 53–68. Regarding the Doleac et al. (2020) replication of parts of the Jason et al. (2015) study, for their findings on days incarcerated, the replicators finding of increased days incarcerated for those in the recovery home condition compared to controls was not significant at the p < .05 level. In addition, the replicators’ findings were inflated by selecting those with 30 or more days of participation. In addition, baseline days incarcerated would not have been significant if the replicators had used non-parametric parametric testing. Other measures of criminal involvement indicated no significant baseline differences over time. If a more appropriate criminal justice baseline variable had been used, no differences in the outcomes would have been found. Often, converging evidence from multiple sources is the best way to understand complex phenomena such as that within this study, whereas focusing just on one individual variable that has considerable psychometric flaws is more likely to produce inaccurate results. More extensive information on this replication is in a paper that is being reviewed at a journal: Jason, L.A., Cotler, J., Islam, M.F., & Harvey, R. (2021). Replications can be compromised with policy implications. Submitted for publication. The replication can be found here: Doleac, J.L., Temple, C., & Roberts, D.P.A (2020). Which prisoner reentry programs work? Replicating and extending analyses of three RCTs. International Review of Law and Economics, Published online Feb. 19, 2020.