Higher-order approximations to conditional distribution functions
Kolassa, John E.
Ann. Statist., Tome 24 (1996) no. 6, p. 353-364 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
This paper derives higher-order terms in the double-saddlepoint expansion of Skovgaard for a unidimensional conditional cumulative distribution function. Expansions for continuous and lattice random variables are derived. Results are applied to the sufficient statistic in logistic regression.
Publié le : 1996-02-14
Classification:  Conditional probability,  hypergeometric distribution,  lattice variable,  tail probability,  62E20,  60E99 
@article{1033066213,
     author = {Kolassa, John E.},
     title = {Higher-order approximations to conditional distribution functions},
     journal = {Ann. Statist.},
     volume = {24},
     number = {6},
     year = {1996},
     pages = { 353-364},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1033066213}
}

Kolassa, John E. Higher-order approximations to conditional distribution functions. Ann. Statist., Tome 24 (1996) no. 6, pp.  353-364. http://gdmltest.u-ga.fr/item/1033066213/