On the use of receiver operating characteristic area under the curve in eyewitness memory research
On the use of receiver operating characteristic area under the curve in eyewitness memory research
Abstract
Purpose
Eyewitness memory research has reformed police practices and policy and is sometimes relied upon in legal proceedings. Due to the practical implications derived from this research, it is imperative to evaluate how practical recommendations are postulated. To assess the practical relevance of research, effect sizes and their interpretation play a pivotal role.
Methods
We examined how the frequently used effect size Area Under the Curve (AUC) obtained via Receiver Operating Characteristic (ROC) curves are used and interpreted in eyewitness memory research. We identified 157 eyewitness memory related articles that conducted ROC curve analyses resulting in 1580 AUCs.
Results
Approximately 90% of the AUCs were only interpreted via statistical significance. The majority of studies did not report 95%CIs for their AUCs. Finally, power analyses were frequently not conducted or not reproducible.
Conclusions
To improve the practical inferences of eyewitness memory research, we recommend establishing a smallest effect size of interest, focusing on 95%CIs, and conducting reproducible power analyses.