Comparison of Linear Normal Experiments
Hansen, Ole Havard ; Torgersen, Erik N.
Ann. Statist., Tome 2 (1974) no. 1, p. 367-373 / Harvested from Project Euclid
Consider independent and normally distributed random variables $X_1,\cdots, X_n$ such that $0 < \operatorname{Var} X_i = \sigma^2; i = 1,\cdots, n$ and $E(X_1,\cdots, X_n)' = A'\beta$ where $A'$ is a known $n \times k$ matrix and $\beta = (\beta_1,\cdots, \beta_k)'$ is an unknown column matrix. (The prime denotes transposition.) The cases of known and totally unknown $\sigma^2$ are considered simultaneously. Denote the experiment obtained by observing $X_1,\cdots, X_n$ by $\mathscr{E}_A$. Let $A$ and $B$ be matrices of, respectively, dimensions $n_A \times k$ and $n_B \times k$. Then, if $\sigma^2$ is known, (if $\sigma^2$ is unknown) $\mathscr{E}_A$ is more informative than $\mathscr{E}_B$ if and only if $AA' - BB'$ is nonnegative definite (and $n_A \geqq n_B + \operatorname{rank} (AA' - BB'))$.
Publié le : 1974-03-14
Classification:  Informational inequality,  invariant kernels,  normal models,  62B15,  62K99
@article{1176342672,
     author = {Hansen, Ole Havard and Torgersen, Erik N.},
     title = {Comparison of Linear Normal Experiments},
     journal = {Ann. Statist.},
     volume = {2},
     number = {1},
     year = {1974},
     pages = { 367-373},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176342672}
}
Hansen, Ole Havard; Torgersen, Erik N. Comparison of Linear Normal Experiments. Ann. Statist., Tome 2 (1974) no. 1, pp.  367-373. http://gdmltest.u-ga.fr/item/1176342672/