Sanov Property, Generalized $I$-Projection and a Conditional Limit Theorem
Csiszar, Imre
Ann. Probab., Tome 12 (1984) no. 4, p. 768-793 / Harvested from Project Euclid
Known results on the asymptotic behavior of the probability that the empirical distribution $\hat P_n$ of an i.i.d. sample $X_1, \cdots, X_n$ belongs to a given convex set $\Pi$ of probability measures, and new results on that of the joint distribution of $X_1, \cdots, X_n$ under the condition $\hat P_n \in \Pi$ are obtained simultaneously, using an information-theoretic identity. The main theorem involves the concept of asymptotic quasi-independence introduced in the paper. In the particular case when $\hat P_n \in \Pi$ is the event that the sample mean of a $V$-valued statistic $\psi$ is in a given convex subset of $V$, a locally convex topological vector space, the limiting conditional distribution of (either) $X_i$ is characterized as a member of the exponential family determined by $\psi$ through the unconditional distribution $P_X$, while $X_1, \cdots, X_n$ are conditionally asymptotically quasi-independent.
Publié le : 1984-08-14
Classification:  Kullback-Leibler information,  $I$-projection,  large deviations in abstract space,  exponential family,  asymptotic quasi-independence,  maximum entropy principle,  60F10,  60B10,  62B10,  94A17,  82A05
@article{1176993227,
     author = {Csiszar, Imre},
     title = {Sanov Property, Generalized $I$-Projection and a Conditional Limit Theorem},
     journal = {Ann. Probab.},
     volume = {12},
     number = {4},
     year = {1984},
     pages = { 768-793},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176993227}
}
Csiszar, Imre. Sanov Property, Generalized $I$-Projection and a Conditional Limit Theorem. Ann. Probab., Tome 12 (1984) no. 4, pp.  768-793. http://gdmltest.u-ga.fr/item/1176993227/