A statistic taking constant values on orbits generated by a group of one-to-one measurable transformations of the sample space. Thus, if $ ( \mathfrak X , \mathfrak B ) $
is the sample space, $ G = \{ g \} $
is a group of one-to-one $ \mathfrak B $-
measurable transformations of $ \mathfrak X $
onto itself and $ t ( x) $
is an invariant statistic, then $ t ( gx ) = t ( x) $
for all $ x \in \mathfrak X $
and $ g \in G $.
Invariant statistics play an important role in the construction of invariant tests (cf. Invariant test; Invariance of a statistical procedure).
[1] | E.L. Lehmann, "Testing statistical hypotheses" , Wiley (1986) |
[2] | S. Zacks, "The theory of statistical inference" , Wiley (1971) |
[3] | G.P. Klimov, "Invariant inferences in statistics" , Moscow (1973) (In Russian) |