Precision bias also known as numeracy bias is a form of cognitive bias[1] in which an evaluator of information commits a logical fallacy as the result of confusing accuracy and precision.[2] More particularly, in assessing the merits of an argument, a measurement, or a report, an observer or assessor falls prey to precision bias when they believe that greater precision implies greater accuracy (i.e., that simply because a statement is precise, it is also true); the observer or assessor are said to provide false precision.[3][4]

The clustering illusion[5] and the Texas sharpshooter fallacy[6] may both be treated as relatives of precision bias. In these related fallacies, precision is mistakenly considered evidence of causation, when in fact the clustered information may actually be the result of randomness.

See also


  1. ^ Proceedings of the 33rd Annual Meeting of the Cognitive Science Society (CogSci 2011), held in Boston, USA 20-32 July 2011 / L. Carlson, C. Hoelscher and T. Shipley (eds.): pp.1521-1526
  2. ^ "Practices of Science: Precision vs. Accuracy |". Retrieved 2022-10-22.
  3. ^ Lim, Daniel; DeSteno, David (2020). "Past adversity protects against the numeracy bias in compassion". Emotion. 20 (8): 1344–1356. doi:10.1037/emo0000655. ISSN 1931-1516. PMID 31414833. S2CID 198166331.
  4. ^ Jerez-Fernandez, Alexandra; Angulo, Ashley N.; Oppenheimer, Daniel M. (2014). "Show Me the Numbers: Precision as a Cue to Others' Confidence". Psychological Science. 25 (2): 633–635. doi:10.1177/0956797613504301. ISSN 0956-7976. PMID 24317423. S2CID 43824955.
  5. ^ Howard, Jonathan (2019), "Illusionary Correlation, False Causation, and Clustering Illusion", Cognitive Errors and Diagnostic Mistakes, Cham: Springer International Publishing, pp. 265–283, doi:10.1007/978-3-319-93224-8_15, ISBN 978-3-319-93223-1, S2CID 150016878, retrieved 2022-10-22
  6. ^ Thompson, W. C. (2009-09-01). "Painting the target around the matching profile: the Texas sharpshooter fallacy in forensic DNA interpretation". Law, Probability and Risk. 8 (3): 257–276. doi:10.1093/lpr/mgp013. ISSN 1470-8396.