Objectives: Taxometric analysis employs multiple, nonoverlapping statistical procedures to estimate parameters that characterize latent categories (e.g., base rates). Consistency among these estimates can inform substantive inferences about latent variables and facilitate idiographic classification. We provide a sketch of a taxometric research program to estimate guilty-suspect base rates in criminal justice and legal systems and use this sketch to explore the possible benefits of taxometric investigations for science and public policy. Hypotheses: We investigated whether taxometric analysis can accurately estimate base rates and facilitate idiographic classifications under conditions psycholegal researchers might face. Method: We demonstrate taxometric analysis on simulated data to detect latent categories, estimate their base rates, and classify individual cases. Results: Our simulations show that taxometric analysis can accurately estimate taxon base rates. Specifically, estimated base rates differed from simulated base rates by less than 3%. Further, idiographic classification rules derived from taxometric analysis accurately classified individual cases in additional data sets, with positive predictive values and negative predictive values exceeding .85. Conclusions: If legal categories of interest represent nonarbitrary classes, taxometric methods afford an analytic approach by which researchers can use fallible indicator variables to estimate their base rates and develop algorithms for legal classification. We discuss potential objections to the taxometric approach and identify important avenues for future research and development in psycholegal applications of taxometric methods. Public Significance StatementLegal classification often involves using fallible sources of evidence to sort individual cases into different categories. Depending on the base rates of these categories, however, even highly valid sources of evidence can yield unacceptably high classification error rates. Researchers can use taxometric analyses to estimate some base rates, a process that may help law enforcement and legal systems develop accurate classification procedures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.