Haber, Matthew H. (2025) Positively Misleading Errors. [Preprint]
![]() |
Text
PME-manuscript.pdf Download (952kB) |
Abstract
Positively misleading errors are errors of statistical reasoning in which adding data to an analysis will systematically and reliably strengthen support for an erroneous hypothesis over a correct one. This pattern distinguishes them from other errors of statistical inference and pattern recognition. Here I provide a general account of positively misleading errors by describing an exemplar case from biology along with a candidate case from clinical medicine. Though well known in biology (phylogenetic systematics, to be precise), positively misleading errors are likely more widespread and deserve to be brought to the attention of the wider research community. This will facilitate a better understanding of them and sharpen our ability to assess statistical and probabilistic methods, providing resources for researchers to more effectively identify, diagnose, and dislodge these errors of statistical inference. This reflects the way we have gained a better understanding of scientific reasoning from studying other errors of statistical and probabilistic reasoning.
Export/Citation: | EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL |
Social Networking: |
Monthly Views for the past 3 years
Monthly Downloads for the past 3 years
Plum Analytics
Actions (login required)
![]() |
View Item |