{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/78605"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/78605","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Novel Statistical Methods: Quantile Estimation, Inference, and Related Applications in Medical Research","abstract":"Ph.D.","abstract_html":"Ph.D.","abstract_has_math":false,"creators":["Yang, Xin"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Hutson, Alan","Biostatistics"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-10-26T02:56:29Z","date_published":"2018-10-26T02:56:29Z","updated_at":"2026-07-27T19:05:12Z","subjects":["statistics"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/78605","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hutson, Alan","Biostatistics"]},{"key":"dc:creator","label":"Author","values":["Yang, Xin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-10-26T02:56:29Z","2018","2018-08-09 21:33:50"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["statistics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/78605"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ph.D.","In this dissertation, selected topics with respect to the quantile estimation, inference, and relatedapplications in medical research are presented.First, new types of quantile estimators are developed. One is based on estimating the momentsof fractional order statistics, which quantile density estimators can be derived simultaneously withthe quantile estimator. The other is an extension of the well-known Bernstein Polynomial quantileestimator, which can be readily dierentiated to obtain the rst order derivative, i.e. the quantiledensity estimator. Both methods can deal with censored data in a straightforward and ecientway.Second, we study a general family of distributions, which is generated by providing a base distribution,that is related to the kernel density estimator asymptotically. It includes a reparameterizedskew normal distribution and a new class of bimodal distributions as special cases and also hints ata kernel-type density estimator of a single order statistic. Tests of normality are constructed basedon this kernel related function, and the kernel-type density estimator is utilized to construct thenonparametric condence interval for an arbitrary quantile based on a Studentized-t analogy thatprovides a simple and less biased alternative to the traditional bootstrap percentile-t condenceinterval.Third, we investigate the optimal strategies of estimating the mean and standard deviation.A generalized best linear unbiased estimator (BLUE) is proposed to provide the optimal unbiasedestimation for both single studies and the overall study. The approach not only can be easilyextended to deal with summary statistics that are not covered in the literature, such as tertiles anddeciles, but also makes the global eect and condence interval less likely to be biased as comparedwith the existing methods."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Novel Statistical Methods: Quantile Estimation, Inference, and Related Applications in Medical Research"]}]}],"canonical_facts":{"dc:contributor":["Hutson, Alan","Biostatistics"],"dc:creator":["Yang, Xin"],"dc:date":["2018-10-26T02:56:29Z","2018","2018-08-09 21:33:50"],"dc:description":["Ph.D.","In this dissertation, selected topics with respect to the quantile estimation, inference, and relatedapplications in medical research are presented.First, new types of quantile estimators are developed. One is based on estimating the momentsof fractional order statistics, which quantile density estimators can be derived simultaneously withthe quantile estimator. The other is an extension of the well-known Bernstein Polynomial quantileestimator, which can be readily dierentiated to obtain the rst order derivative, i.e. the quantiledensity estimator. Both methods can deal with censored data in a straightforward and ecientway.Second, we study a general family of distributions, which is generated by providing a base distribution,that is related to the kernel density estimator asymptotically. It includes a reparameterizedskew normal distribution and a new class of bimodal distributions as special cases and also hints ata kernel-type density estimator of a single order statistic. Tests of normality are constructed basedon this kernel related function, and the kernel-type density estimator is utilized to construct thenonparametric condence interval for an arbitrary quantile based on a Studentized-t analogy thatprovides a simple and less biased alternative to the traditional bootstrap percentile-t condenceinterval.Third, we investigate the optimal strategies of estimating the mean and standard deviation.A generalized best linear unbiased estimator (BLUE) is proposed to provide the optimal unbiasedestimation for both single studies and the overall study. The approach not only can be easilyextended to deal with summary statistics that are not covered in the literature, such as tertiles anddeciles, but also makes the global eect and condence interval less likely to be biased as comparedwith the existing methods."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/78605"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["statistics"],"dc:title":["Novel Statistical Methods: Quantile Estimation, Inference, and Related Applications in Medical Research"],"dc:type":["Text","Dissertation"]},"updated_at":"2026-07-27T19:05:12Z"}