Abstract
Inference in high dimensional parameter space poses many challenges. One of these is the possible use of saddlepoint approximations. Motivated by a recent use of the saddlepoint approximation to construct a conditional test, we argue that the precision is questionable. We illustrate this by an example giving a 50% relative error in the calculation of the p-value. A power study of the underlying test reveals a low power in many situations. As an alternative it is suggested to use the likelihood ratio test.
Similar content being viewed by others
References
Booth, J.G., Butler, R.W., Huzurbazar, S. and Wood, A.T.A. (1995). Saddlepoint approximations for P-values of some tests of covariance matrices. Journal of Statistical Computation and Simulation 53, 165–180.
Davison, A.C., Fraser, D.A.S., Reid, N. and Sartori, N. (2014). Accurate directional inference for vector parameters in linear exponential families. Journal of the American Statistical Association 109, 302–314.
Jensen, J.L. (1991). A large deviation type approximation for the “Box class” of likelihood ratio criteria. Journal of the American Statistical Association 86, 437–440.
Jensen, J.L. (1995). Saddlepoint approximations. Clarendon Press, Oxford.
Shun, Z. and McCullagh, P. (1995). Laplace approximation of high dimensional integrals. Journal of the Royal Statistical Society B 57, 749–760.
Venables, W.N. and Ripley, B.D. (2002). Modern applied statistics with S. Springer-Verlag, New York.
Wu, J. and Wong, A.C.M. (2003). A note on determining the p-value of Bartlett’s test of homogeneity of variances. Communications in Statistics - Theory and Methods32, 91–101.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jensen, J.L. On the Use of Saddlepoint Approximations in High Dimensional Inference. Sankhya A 83, 379–392 (2021). https://doi.org/10.1007/s13171-019-00188-x
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13171-019-00188-x