No open-access location is known for this record yet.
No open-access location is known for this record yet.
I thank the editor for inviting me to write a comment on this paper. I also thank the authors for this paper, which I think is a most important contribution to the debate on likelihood ratios. I agree in principle with the authors on the message they convey. Notwithstanding, I think that some points in their paper need to be viewed from different perspectives. Here the perspective will be that of a forensic statistician meeting forensic experts in daily casework with their challenging tasks of assigning likelihood ratios. I would like to emphasize that my views are reflexions of my own experience and not the result of any survey among forensic experts. My first point is actually what may be seen as the core of the paper, namely the concept of probability, or rather how the definition of probability we use may be one of the roots to the misconception. Taking personal degree-of-belief in something as the definition of the probability of that something is sound, I certainly agree on that. However, we should keep in mind that such a definition is seldom used in basic academic education. An introductory course in statistics comprising elementary concepts of probability theory would approach probabilities the very classical way. Strictly frequentist probability definitions are not stressed, but the probabilities themselves are often disguised as population proportions, to be used in theoretical descriptions of binomial or hypergeometric experiments. Some courses comprise Bayes’ theorem, but merely expressed and applied as a mathematical tool to compute conditional probabilities, no matter from where these probabilities may have come.
Loading…
Stored only when both papers are in the corpus — 14 citations exist upstream.
Papers that cite the same references — the relational fallback while embeddings are still backfilling.
Imported from OpenAlex (CC0) — nothing here is generated.