An explicit large-deviation approximation to one-parameter tests
Skovgaard, Ib M.
Bernoulli, Tome 2 (1996) no. 3, p. 145-165 / Harvested from Project Euclid
An approximation is derived for tests of one-dimensional hypotheses in a general regular parametric model, possibly with nuisance parameters. The test statistic is most conveniently represented as a modified log-likelihood ratio statistic, just as the R*-statistic from Barndorff-Nielsen (1986). In fact, the statistic is identical to a version of R*, except that a certain approximation is used for the sample space derivatives required for the calculation of R*. With this approximation the relative error for large-deviation tail probabilities still tends uniformly to zero for curved exponential models. The rate may, however, be O(n-1/2) rather than O(n-1) as for R*. For general regular models asymptotic properties are less clear but still good compared to other general methods. The expression for the statistic is quite explicit, involving only likelihood quantities of a complexity comparable to an information matrix. A numerical example confirms the highly accurate tail probabilities. A sketch of the proof is given. This includes large parts which, despite technical differences, may be considered an overview of Barndorff-Nielsen's derivation of the formulae for p* and R*.
Publié le : 1996-06-14
Classification:  conditional inference,  large-deviation expansions,  modified log-likelihood ratio test,  nuisance parameters,  parametric inference
@article{1193839221,
     author = {Skovgaard, Ib M.},
     title = {An explicit large-deviation approximation to one-parameter tests},
     journal = {Bernoulli},
     volume = {2},
     number = {3},
     year = {1996},
     pages = { 145-165},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1193839221}
}
Skovgaard, Ib M. An explicit large-deviation approximation to one-parameter tests. Bernoulli, Tome 2 (1996) no. 3, pp.  145-165. http://gdmltest.u-ga.fr/item/1193839221/