Abstract
We obtain marginal tail area approximations for the one-dimensional test statistic based on the appropriate component of the M-estimate for both standardized and Studentized versions which are needed for tests and confidence intervals. The result is proved under conditions which allow the application to finite sample situations such as the bootstrap and involves a careful discretization with saddlepoints being used for each neighbourhood. These results are used to obtain second-order relative error results on the accuracy of the Studentized and the tilted bootstrap. The tail area approximations are applied to a Poisson regression model and shown to have very good accuracy.
Similar content being viewed by others
References
Almudevar A., Field C., Robinson J. (2000). The density of multivariate M-estimates. Annals of Statistics 28:275–297
DiCiccio T., Romano J. (1990). Nonparametric confidence limits by resampling methods and least favorable families. International Statistical Revue 58:59–76
Feuerverger A., Robinson J., Wong A. (1999). On the relative accuracy of certain bootstrap procedures. Canadian Journal of Statistics 27:225–236
Hall P. (1992). The bootstrap and Edgeworth expansion. Springer, New York
Jing B.Y., Robinson J. (1994). Saddlepoint approximations for marginal and conditional probabilities of transformed variables. Annals of Statistics 22:1115–1132
Jing B.Y., Feuerverger A., Robinson J. (1994). On the bootstrap saddlepoint approximations. Biometrika 81:211–215
Jing B.Y., Kolassa J., Robinson J. (2002). Partial saddlepoint approximations for transformed means. Scandinavian Journal of Statistics 29:721–731
Robinson J., Skovgaard I.M. (1998). Bounds for probabilities of small errors for empirical saddlepoint and bootstrap approximations. Annals of Statistics 26:2369–2394
Robinson J., Höglund T., Holst L., Quine M.P. (1990). On approximating probabilities for large and small deviations in R d. Annals of Probability 18:727–753
Robinson J., Ronchetti E., Young G.A. (2003). Saddlepoint approximations and tests based on multivariate M-estimates. Annals of Statistics 31:1154–1169
Weber N., Kokic P. (1997). On Cramer’s condition for Edgeworth expansions in the finite population case. Theory of Stochastic Processes 3:468–474
Author information
Authors and Affiliations
Corresponding author
Additional information
An erratum to this article can be found at http://dx.doi.org/10.1007/s10463-006-0101-5
About this article
Cite this article
Field, C., Robinson, J. & Ronchetti, E. Saddlepoint approximations for multivariate M-estimates with applications to bootstrap accuracy. AISM 60, 205–224 (2008). https://doi.org/10.1007/s10463-006-0083-3
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-006-0083-3