Richard Nobles and David Schiff revisit the Sally Clark case and consider the presentation by nonstatisticians of statistical evidence in court.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1258/rsmmsl.47.1.7 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Ethical and security challenges in AI for forensic genetics: From bias to adversarial attacks.
Forensic Sci Int Genet
January 2025
Computer Science Department, University of Buenos Aires, Faculty of Exact and Natural Sciences, Buenos Aires, Argentina.
Forensic scientists play a crucial role in assigning probabilities to evidence based on competing hypotheses, which is fundamental in legal contexts where propositions are presented usually by prosecution and defense. The likelihood ratio (LR) is a well-established metric for quantifying the statistical weight of the evidence, facilitating the comparison of probabilities under these hypotheses. Developing accurate LR models is inherently complex, as it relies on cumulative scientific knowledge.
View Article and Find Full Text PDFAvoiding causal fraud in the evaluation of clinical benefits of treatments for Alzheimer's disease.
Alzheimers Dement
January 2025
Division of Psychiatry, University College London, London, UK.
Recent regulatory approvals of three amyloid-lowering monoclonal antibody therapies for the treatment of Alzheimer's disease (AD) have triggered a polarizing debate in the field on the clinical meaningfulness of their reported effects. The question of how to define clinical meaningfulness for any treatment that has a modest effect size is important and will likely be subject to influence from interested stakeholders. We warn of claims of evaluating meaningful within-individual change from randomized parallel-group trials of AD treatments, sometimes purportedly assessed by a commonly recognized "responder" analysis approach, and explain why it is likely to mislead and should simply be avoided.
View Article and Find Full Text PDFRisk of bias assessment tools often addressed items not related to risk of bias and used numerical scores.
J Clin Epidemiol
January 2025
Division of Nephrology and Hypertension, Department of Internal Medicine, University of Kansas Medical Centre, 3901 Rainbow Blvd, MS3002, Kansas City, KS, USA. Electronic address:
Objective: We aimed to determine whether the existing risk of bias assessment tools addressed constructs other than risk of bias or internal validity, and whether they used numerical scores to express quality, which is discouraged and may be a misleading approach.
Methods: We searched Ovid MEDLINE and Embase to identify quality appraisal tools across all disciplines in human health research. Tools designed specifically to evaluate reporting quality were excluded.
Compositional data analysis enables statistical rigor in comparative glycomics.
Nat Commun
January 2025
Department of Chemistry and Molecular Biology, University of Gothenburg, Gothenburg, Sweden.
Comparative glycomics data are compositional data, where measured glycans are parts of a whole, indicated by relative abundances. Applying traditional statistical analyses to these data often results in misleading conclusions, such as spurious "decreases" of glycans when other structures increase in abundance, or high false-positive rates for differential abundance. Our work introduces a compositional data analysis framework, tailored to comparative glycomics, to account for these data dependencies.
View Article and Find Full Text PDFCausal language and inferences in observational rotator cuff database studies published from 2013 to 2022.
J Orthop
July 2025
Department of Orthopaedic Surgery, Virginia Commonwealth University, 1250 E. Marshall Street, Richmond, VA, 23219, USA.
Background: The use of large multi-institutional databases in rotator cuff repair (RCR) research is expanding, but these studies are observational and cannot establish causation. This study examines the prevalence of causal language in clinical RCR database studies published from 2013 to 2022.
Methods: Administrative database and clinical registry studies on RCR published in eight orthopaedic journals from 2013 to 2022 were systematically identified and graded by two reviewers for the presence, absence, or inconsistent use of causal language in both the title/abstract and the full text.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!