Page - 208 - in Differential Geometrical Theory of Statistics
Image of the Page - 208 -
Text of the Page - 208 -
Entropy2016,18, 433
Deļ¬nition 49. Adatum [U,ΦUĆĻU,PU,γUUā] as in the last deļ¬nition is called a local statistical chart
of [E,Ļ,M,D].
Figure4 is representswhatare crucial steps toward theserachof characteristic invariants, viz
invariants encoding the points of themoduli space of statisticalmodels. At the present Figure 4
describes themoduli spaceof thecategoryFB(Ī,Ī)
Before dealing with morphisms of the category GM(Ī,Ī©)we introduce a relevant global
geometrical invariant.
8.3.2. TheGlobalProbabilityDensityofaStatisticalModel
WeconsideraCOMPLETE(ormaximalstatistical)atlasofanobject [E,Ļ,M,D] (of thecategory
GM(Ī,Ī©)),namely
AΦ=[Uj,Φj,Ļj,Pj,γij].
ThefamilyUj isanopencoveringofM. ThepairEjĆUj is thedomainof the localchart(ΦjĆĻj).
Wehave
Ej=EUj.
IfUiā©Uj =ā
thenonehas
Ļj(x)= γĖji Ā·Ļij(x) āxāUiā©Uj.
InparticularA=(Uj,Ļj) isanafļ¬neatlasof the locallyļ¬atmanifold (M,D).Wehave
Φj(Eyā)=Ļj(yā)ĆĪ āyā āUj.
Thereforeweset
[Eyā,Ī©yā]=Φā1j [[Ļj(yā)ĆĪ],Ī©].
TheatlasAΦ satisļ¬esrequirements(Ļ1.1),(Ļ1.2)and(Ļ1.3). InEUj thelocalfunctionpj isdeļ¬nedby
pj=Pjā¦Ī¦j.
Wesuppose that
Uiā©Uj =ā
.
By thevirtueofof [Ļ1.3]onehas
pi(e)= pj(e)
forall eāEUiā©Uj.
Therebythereexistsauniquefunction
E eā p(e)āR
whoserestrictiontoEj coincideswith pj. TherestrictiontoEx isdenotedby px. The triple
(Ex,Ωx,px)
isaprobabilityspace.
Deļ¬nition50. The function
E eā p(e)āR
is called theprobabilitydensityof themodel [E,Ļ,M,D].
208
Differential Geometrical Theory of Statistics
- Title
- Differential Geometrical Theory of Statistics
- Authors
- FrƩdƩric 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