An Infinite-Dimensional Geometric Structure on the Space of all the Probability Measures Equivalent to a Given One
Pistone, Giovanni ; Sempi, Carlo
Ann. Statist., Tome 23 (1995) no. 6, p. 1543-1561 / Harvested from Project Euclid
Let $\mathscr{M}_\mu$ be the set of all probability densities equivalent to a given reference probability measure $\mu$. This set is thought of as the maximal regular (i.e., with strictly positive densities) $\mu$-dominated statistical model. For each $f \in \mathscr{M}_\mu$ we define (1) a Banach space $L_f$ with unit ball $\mathscr{V}_f$ and (2) a mapping $s_f$ from a subset $\mathscr{U}_f$ of $\mathscr{M}_\mu$ onto $\mathscr{V}_f$, in such a way that the system $(s_f, \mathscr{U}_f, f \in \mathscr{M}_\mu)$ is an affine atlas on $\mathscr{M}_\mu$. Moreover each parametric exponential model dominated by $\mu$ is a finite-dimensional affine submanifold and each parametric statistical model dominated by $\mu$ with a suitable regularity is a submanifold. The global geometric framework given by the manifold structure adds some insight to the so-called geometric theory of statistical models. In particular, the present paper gives some of the developments connected with the Fisher information metrics (Rao) and the Hilbert bundle introduced by Amari.
Publié le : 1995-10-14
Classification:  Nonparametric statistical manifolds,  Orlicz spaces,  62A25
@article{1176324311,
     author = {Pistone, Giovanni and Sempi, Carlo},
     title = {An Infinite-Dimensional Geometric Structure on the Space of all the Probability Measures Equivalent to a Given One},
     journal = {Ann. Statist.},
     volume = {23},
     number = {6},
     year = {1995},
     pages = { 1543-1561},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176324311}
}
Pistone, Giovanni; Sempi, Carlo. An Infinite-Dimensional Geometric Structure on the Space of all the Probability Measures Equivalent to a Given One. Ann. Statist., Tome 23 (1995) no. 6, pp.  1543-1561. http://gdmltest.u-ga.fr/item/1176324311/