No label defined (Q3706311)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3934189
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 3934189 |
Statements
1985
0 references
partial sufficiency of linear forms
0 references
characterization
0 references
normal location family
0 references
gamma scale family
0 references
linear statistic
0 references
0.8436874747276306
0 references
0.802834689617157
0 references
[For the entire collection see Zbl 0564.00015.] A statistic T is sufficient for a family of probability measures P if for all bounded measurable functions f there exists a conditional expectation \(E_ p(f| T)\) which does not depend on P. Partial sufficiency is defined by the existence of \(E_ p(f| T)\) independent of P not for all f but for f lying in a smaller class of functions: f bounded and depending on the data only through the statistics S and T. By the existence of partially sufficient statistics some location and scale parameter families are characterized: Partial sufficiency of \(T=sample\) mean for \(S=different\) linear statistic is possible, a) for a location parameter family iff it is Gaussian, b) for a scale parameter family iff it is gamma (Theorems 1 and 3).
0 references