Page - 218 - in Differential Geometrical Theory of Statistics
Image of the Page - 218 -
Text of the Page - 218 -
Entropy2016,18, 433
AComment.
Themapping
M→ qM
is a global geometrical invariant in the sense of Erlangen. In otherwords it is an invariant of the
Γ-geometry in [E,π,M,D,p].
Ouraimis todemonstrate that
M→ qM
isacharacteristic invariant in thecategoryGM(Ξ,Ω). Inotherwords the isomorphismclassof the
model
M=[E,π,(M,D),p]
isencodedbythe functor
∇→ qM[∇].
Thefirst step is the following lemma.
Lemma7. In the sameobject [E,π,M,D]weconsider twostatisticalmodels
M1=[E,π,M,D,p1],
M2=[E,π,M,D,p2].
The followingassertionsare equivalent
(1) qM1 = qM2,
(2) p1= p2.
Proof. Wework in thedomainofa local trivializationof [E,π,M,D]. By thevirtueofLemma6above
weknowthat
qp1 = qp2
if andonly if
p1(x,ξ)=λ(ξ)p2(x,ξ)
withλ∈RΞ+. Sinceboth p1 and p2 areΓ-equivariant the function
Ξ ξ→λ(ξ)
isΓ-invariant too.Nowwetakeintoaccount that thenaturalactionofΓ inΞ is transitive. Thereforethe
Γ-equivariant functionλ(ξ) isaconstant function. Therefore
p1(x,ξ)=λp2(x,ξ)
Theoperationof integrationalongafiberofπyields
λ=1
Thisends theproof.
Weconsider twom-dimensional statisticalmodels for (Ξ,Ω), namely
Mj=[Ej,πj,Mj,Dj,pj], j :=1,2.
218
Differential Geometrical Theory of Statistics
- Title
- Differential Geometrical Theory of Statistics
- Authors
- Frédéric Barbaresco
- Frank Nielsen
- Editor
- MDPI
- Location
- Basel
- Date
- 2017
- Language
- English
- License
- CC BY-NC-ND 4.0
- ISBN
- 978-3-03842-425-3
- Size
- 17.0 x 24.4 cm
- Pages
- 476
- Keywords
- Entropy, Coding Theory, Maximum entropy, Information geometry, Computational Information Geometry, Hessian Geometry, Divergence Geometry, Information topology, Cohomology, Shape Space, Statistical physics, Thermodynamics
- Categories
- Naturwissenschaften Physik