On large deviations and choice of ancillary for p* and r*
Barndorff-Nielsen, Ole E. ; Wood, Andrew T.A.
Bernoulli, Tome 4 (1998) no. 1, p. 35-63 / Harvested from Project Euclid
The large deviation properties of p*, the approximation to the conditional density of the maximum likelihood estimator, and r*, the modified directed likelihood, are studied. Attention is restricted to curved exponential models. Various specifications of an approximate ancillary, which are required in the construction of p*and r*, are considered, including: a modified directed likelihood ancillary, a*, and an unmodified directed likelihood ancillary, ao. It is shown that if a* is used then p* and r* achieve saddlepoint accuracy on both normal and large deviation regions; if, on the other hand, ao is used in the construction of p*, then saddlepoint accuracy is not achieved, though the relative error still stays bounded on large deviation regions. It is also shown that if ao rather than a* is held fixed in the sample space differentiations needed to calculate r*, then saddlepoint accuracy is still attained in both normal and large deviation regions. On a first impression, the last result is a little surprising because, in a repeated sampling framework, ao is only ancillary to order O(n-1/2). However, this finding is also of direct practical interest because, from the point of view of calculation, ao is often substantially easier to work with than a*. An important aspect of our approach is the development of guidelines, referred to as Laplace-spa calculus, for the construction of invariant saddlepoint-style approximations to marginal and conditional densities. Finally, connections between recent work by Jensen and the results of this paper are discussed and clarified.
Publié le : 1998-03-14
Classification:  conditional inference,  Laplace's approximation,  likelihood ancillary,  relative error,  saddlepoint approximation,  tail-area approximation
@article{1175865489,
     author = {Barndorff-Nielsen, Ole E. and Wood, Andrew T.A.},
     title = {On large deviations and choice of ancillary for p* and r*},
     journal = {Bernoulli},
     volume = {4},
     number = {1},
     year = {1998},
     pages = { 35-63},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1175865489}
}
Barndorff-Nielsen, Ole E.; Wood, Andrew T.A. On large deviations and choice of ancillary for p* and r*. Bernoulli, Tome 4 (1998) no. 1, pp.  35-63. http://gdmltest.u-ga.fr/item/1175865489/