TY - JOUR
T1 - Sequential Linearization of Empirical Likelihood Constraints with Application to U-Statistics
AU - Wood, A. T.A.
AU - Do, K. A.
AU - Broom, B. M.
N1 - Funding Information:
We are grateful to Peter Hall for supplying us with his proof of Wilks’s theorem for U-statistics. This research was partially supported by the University of Canberra Research Grants Scheme. Computer resources were provided by both the Australian National University and the University of Canberra. The article has benefited from helpful suggestions by two referees and an Associate Editor.
PY - 1996/12
Y1 - 1996/12
N2 - Empirical likelihood for a mean is straightforward to compute, but for nonlinear statistics significant computational difficulties arise because of the presence of nonlinear constraints in the underlying optimization problem. It is certainly the case that these difficulties can be overcome with sufficient time, care, and programming effort. However, they do make it difficult to write general software for implementing empirical likelihood, and therefore these difficulties are likely to hinder the widespread use of empirical likelihood in applied work. The purpose of this article is to suggest an approximate approach that sidesteps the difficult computational issues. The basic idea, which may be described as “sequential linearization of constraints,” is a very simple one, but we believe it could have significant ramifications for the implementation and practical use of empirical likelihood methodology. One application of the linearization approach, which we consider in this article, is to the problem of constructing empirical likelihood for U-statistics. However, the sequential linearization idea can be applied in the empirical likelihood context to a broad range of smooth statistical functional.
AB - Empirical likelihood for a mean is straightforward to compute, but for nonlinear statistics significant computational difficulties arise because of the presence of nonlinear constraints in the underlying optimization problem. It is certainly the case that these difficulties can be overcome with sufficient time, care, and programming effort. However, they do make it difficult to write general software for implementing empirical likelihood, and therefore these difficulties are likely to hinder the widespread use of empirical likelihood in applied work. The purpose of this article is to suggest an approximate approach that sidesteps the difficult computational issues. The basic idea, which may be described as “sequential linearization of constraints,” is a very simple one, but we believe it could have significant ramifications for the implementation and practical use of empirical likelihood methodology. One application of the linearization approach, which we consider in this article, is to the problem of constructing empirical likelihood for U-statistics. However, the sequential linearization idea can be applied in the empirical likelihood context to a broad range of smooth statistical functional.
KW - Bootstrap calibration
KW - Nondegenerate
KW - Nonlinear constraint
KW - Nonlinear functional
KW - Wilks's theorem
UR - http://www.scopus.com/inward/record.url?scp=0009219247&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0009219247&partnerID=8YFLogxK
U2 - 10.1080/10618600.1996.10474718
DO - 10.1080/10618600.1996.10474718
M3 - Article
AN - SCOPUS:0009219247
SN - 1061-8600
VL - 5
SP - 365
EP - 385
JO - Journal of Computational and Graphical Statistics
JF - Journal of Computational and Graphical Statistics
IS - 4
ER -