Show simple item record

dc.contributor.advisorRoyset, Johannes O.
dc.contributor.authorMiranda, Sofia I.
dc.dateDec-14
dc.date.accessioned2015-02-18T00:17:57Z
dc.date.available2015-02-18T00:17:57Z
dc.date.issued2014-12
dc.identifier.urihttp://hdl.handle.net/10945/44618
dc.descriptionApproved for public release; distribution is unlimiteden_US
dc.description.abstractWe present a novel regression framework centered on a coherent and averse measure of risk, the superquantile risk (also called conditional value-at-risk), which yields more conservatively fitted curves than classical least squares and quantile regressions. In contracts to other generalized regression techniques that approximate conditional superquantiles by various combinations of conditional quantiles, we directly and inperfect analog to classical regressional obtain superquantile regression functions as optimal solutions of certain error minimization problems. We show the existence and possible uniqueness of regression functions, discuss the stability of regression functions under perturbations and approximation of the underlying data, and propose an extension of the coefficient of determination R-squared and Cook’s distance for assessing the goodness of fit for both quantile and superquantile regression models. We present two classes of computational methods for solving the superquantile regression problem, compare both methods’ complexity, and illustrate the methodology in eight numerical examples in the areas of military applications, concerning mission employment of U.S. Navy helicopter pilots and Portuguese Navy submarines, reliability engineering, uncertainty quantification, and financial risk management.en_US
dc.description.urihttp://archive.org/details/superquantilereg1094544618
dc.publisherMonterey, California: Naval Postgraduate Schoolen_US
dc.rightsCopyright is reserved by the copyright owner.en_US
dc.titleSuperquantile regression: theory, algorithms, and applicationsen_US
dc.typeThesisen_US
dc.contributor.departmentOperations Research
dc.subject.authorSuperquantileen_US
dc.subject.authorregressionen_US
dc.subject.authorbuffered reliabilityen_US
dc.subject.authoruncertainty quantifcation, surrogate estimationen_US
dc.subject.authorsuperquantile trackingen_US
dc.subject.authordualization of risken_US
dc.description.serviceLieutenant, Portuguese Navyen_US
etd.thesisdegree.nameDoctor of Philosophy in Operations Researchen_US
etd.thesisdegree.levelDoctoralen_US
etd.thesisdegree.disciplineOperations Researchen_US
etd.thesisdegree.grantorNaval Postgraduate Schoolen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record