Theses and Dissertations

Date of Award

4-2-2026

Document Type

Dissertation - NSU Access Only

Degree Name

Doctor of Philosophy (PhD)

Department

Abraham S. Fischler College of Education and School of Criminal Justice

Advisor

Steven Hecht

Committee Member

Marcelo Castro

Committee Member

Alexander Toth

Keywords

benchmarks, classification, Cohen’s d, CrimeSolutions, criminal justice research, effect size, effect size benchmarks, effect size classification, empirical benchmarks, intervention effectiveness, meta-analysis, percentile-based methods, policymaking, quasi-meta-analysis, statistical validity, violent crime, violent crime interventions

Abstract

Criminal justice researchers apply Cohen’s (1988) benchmarks to classify effect sizes as small, medium, or large, despite these standards never being meant for broad, decontextualized use (Cohen, 1988; Gies et al., 2024; Goulet-Pelletier & Cousineau, 2018; Lakens, 2013; Milner et al., 2023). Repeatedly doing so may weaken statistical validity, distort findings, and impede effective policymaking. This study introduces the first effect size benchmarks specifically designed for violent crime interventions.

Using a quasi-meta-analysis framework, 1,605 effect sizes from 104 violent crime intervention studies from the CrimeSolutions clearinghouse were converted to Cohen’s d. Three new discrete benchmarking methods were created using a tailored version of Cohen’s benchmarks (Cohen, 1988), tertiles (Gies et al., 2024; Hemphill, 2003; Lipsey & Wilson, 1993; Meyer et al., 2001), and quartiles (Lovakov & Agadullina, 2021; Milner et al., 2023; Panjeh et al., 2023; Tanner-Smith et al., 2018).

Results suggest that Cohen’s (1988) benchmark underestimates effects and overclassifies them as small. Interpretations of effect sizes are affected by benchmarking methodology, the category of violent crime, and size classification. Researchers do not regularly report effect sizes; instead, they usually present statistical test values or raw means and standard deviations. Significant differences in classification proportions were observed between Cohen-based and percentile-based methods.

These findings question the use of Cohen’s (1988) benchmark for violent crime interventions and offer empirically grounded alternatives for interpreting effect sizes that might otherwise be considered insignificant or undervalued. With a better understanding of the magnitude of interventions, policymakers can prioritize more effective programs (Gies et al., 2024; Tanner-Smith et al., 2018).

Available for download on Thursday, August 05, 2027

To access this thesis/dissertation you must have a valid nova.edu OR mynsu.nova.edu email address and create an account for NSUWorks.

Free My Thesis

If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the Free My Thesis button.

  Contact Author

Share

COinS