A rigorous test is a special statistical test in test theory , a branch of mathematical statistics . Strict tests, like Maximin tests , gain their importance from the fact that, in contrast to consistently best tests, they already exist under weak conditions.
definition
A (not necessarily parametric) statistical model and a disjoint decomposition of the index set into the null hypothesis and alternative are given .
(
X
,
A.
,
(
P
ϑ
)
θ
∈
Θ
)
{\ displaystyle (X, {\ mathcal {A}}, (P _ {\ vartheta}) _ {\ theta \ in \ Theta})}
Θ
{\ displaystyle \ Theta}
Θ
0
{\ displaystyle \ Theta _ {0}}
Θ
1
{\ displaystyle \ Theta _ {1}}
Let be the set of all statistical tests on the level . Let be the quality function of the test and
T
α
{\ displaystyle {\ mathcal {T}} _ {\ alpha}}
α
{\ displaystyle \ alpha}
G
Φ
{\ displaystyle G _ {\ Phi}}
Φ
{\ displaystyle \ Phi}
β
T
α
+
(
ϑ
)
: =
sup
Φ
∈
T
α
G
Φ
(
ϑ
)
{\ displaystyle \ beta _ {{\ mathcal {T}} _ {\ alpha}} ^ {+} (\ vartheta): = \ sup _ {\ Phi \ in {\ mathcal {T}} _ {\ alpha} } G _ {\ Phi} (\ vartheta)}
the envelope power function ( English envelope power function ) of .
T
α
{\ displaystyle {\ mathcal {T}} _ {\ alpha}}
One is called a rigorous test to the level , if
Ψ
∈
T
α
{\ displaystyle \ Psi \ in {\ mathcal {T}} _ {\ alpha}}
α
{\ displaystyle \ alpha}
sup
ϑ
∈
Θ
1
(
β
T
α
+
(
ϑ
)
-
G
Ψ
(
ϑ
)
)
=
inf
Φ
∈
T
α
sup
ϑ
∈
Θ
1
(
β
T
α
+
(
ϑ
)
-
G
Φ
(
ϑ
)
)
{\ displaystyle \ sup _ {\ vartheta \ in \ Theta _ {1}} \ left (\ beta _ {{\ mathcal {T}} _ {\ alpha}} ^ {+} (\ vartheta) -G _ {\ Psi} (\ vartheta) \ right) = \ inf _ {\ Phi \ in {\ mathcal {T}} _ {\ alpha}} \ sup _ {\ vartheta \ in \ Theta _ {1}} \ left (\ beta _ {{\ mathcal {T}} _ {\ alpha}} ^ {+} (\ vartheta) -G _ {\ Phi} (\ vartheta) \ right)}
Explanation
The envelope power function provides for each parameter , the maximum selectivity of the tests in , if present. Thus the expression is
ϑ
∈
Θ
1
{\ displaystyle \ vartheta \ in \ Theta _ {1}}
T
α
{\ displaystyle {\ mathcal {T}} _ {\ alpha}}
ϑ
{\ displaystyle \ vartheta}
β
T
α
+
(
ϑ
)
-
G
Ψ
(
ϑ
)
{\ displaystyle \ beta _ {{\ mathcal {T}} _ {\ alpha}} ^ {+} (\ vartheta) -G _ {\ Psi} (\ vartheta)}
the deficit of the selectivity in relation to the maximum possible selectivity at the point . Hence is
Ψ
{\ displaystyle \ Psi}
ϑ
{\ displaystyle \ vartheta}
sup
ϑ
∈
Θ
1
(
β
T
α
+
(
ϑ
)
-
G
Ψ
(
ϑ
)
)
{\ displaystyle \ sup _ {\ vartheta \ in \ Theta _ {1}} \ left (\ beta _ {{\ mathcal {T}} _ {\ alpha}} ^ {+} (\ vartheta) -G _ {\ Psi} (\ vartheta) \ right)}
the maximum deficit of the selectivity of the test .
Ψ
{\ displaystyle \ Psi}
A strict test is therefore a test in which the maximum deviation from the maximum possible selectivity (and thus the enveloping quality function) is smaller than in any other test at a given level.
existence
The existence of strict tests can be shown under rather weak conditions. The central aid for this is the weak convergence and the weak - * - convergence in and .
L.
1
{\ displaystyle L ^ {1}}
L.
∞
{\ displaystyle L ^ {\ infty}}
The central statement is that if a σ-finite measure exists such that or is dominated by this measure , there is a strict test of the level .
μ
{\ displaystyle \ mu}
(
P
ϑ
)
ϑ
∈
Θ
0
{\ displaystyle (P _ {\ vartheta}) _ {\ vartheta \ in \ Theta _ {0}}}
(
P
ϑ
)
ϑ
∈
Θ
1
{\ displaystyle (P _ {\ vartheta}) _ {\ vartheta \ in \ Theta _ {1}}}
α
{\ displaystyle \ alpha}
literature
<img src="https://de.wikipedia.org/wiki/Special:CentralAutoLogin/start?type=1x1" alt="" title="" width="1" height="1" style="border: none; position: absolute;">