Philosophy:Dominating decision rule

From HandWiki
Revision as of 13:18, 24 September 2021 by imported>TextAI (over-write)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Short description: Rule that is never worse and sometimes better

In decision theory, a decision rule is said to dominate another if the performance of the former is sometimes better, and never worse, than that of the latter. Formally, let [math]\displaystyle{ \delta_1 }[/math] and [math]\displaystyle{ \delta_2 }[/math] be two decision rules, and let [math]\displaystyle{ R(\theta, \delta) }[/math] be the risk of rule [math]\displaystyle{ \delta }[/math] for parameter [math]\displaystyle{ \theta }[/math]. The decision rule [math]\displaystyle{ \delta_1 }[/math] is said to dominate the rule [math]\displaystyle{ \delta_2 }[/math] if [math]\displaystyle{ R(\theta,\delta_1)\le R(\theta,\delta_2) }[/math] for all [math]\displaystyle{ \theta }[/math], and the inequality is strict for some [math]\displaystyle{ \theta }[/math].[1]

This defines a partial order on decision rules; the maximal elements with respect to this order are called admissible decision rules.[1]

References

  1. 1.0 1.1 Abadi, Mongi; Gonzalez, Rafael C. (1992), Data Fusion in Robotics & Machine Intelligence, Academic Press, p. 227, ISBN 9780323138352, https://books.google.com/books?id=47kOwU1xvMMC&pg=PA227 .