Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/623
DC FieldValueLanguage
dc.contributor.authorJazaa Saleh Al-Mutairien_US
dc.date.accessioned2019-03-03T05:56:15Z-
dc.date.available2019-03-03T05:56:15Z-
dc.date.issued2016en_US
dc.identifier.urihttp://hdl.handle.net/123456789/623-
dc.description.abstractIn this thesis, confidence intervals for population quantiles were constructed based on order statistics from a sample of random size, 𝑁, regardless of the parent distribution. Inner and outer confidence intervals for the population quantile interval were investigated on the same basis. Confidence intervals for population quantile differences were also examined. Distribution-free expressions for computing the coverage probabilities of these intervals were theoretically derived and numerically evaluated using different probability distributions of 𝑁, such as binomial, negative binomial, and Poisson distributions, with different selections of their respective parameters. A real life example representing the duration of remission of 20 leukemia patients was analyzed to illustrate the applicability of the results developed in this thesis.en_US
dc.language.isoen_USen_US
dc.publisherΒ Kuwait university - college of graduate studiesen_US
dc.subjectConfidence Intervalsen_US
dc.subjectOrdered Dataen_US
dc.subjectPopulation Quantilesen_US
dc.titleConfidence Intervals for Population Quantiles Based on Ordered Data from Samples of Random Sizeen_US
dc.typethesisen_US
dc.contributor.supervisorProf. Mohammad Z. Al-Raqaben_US
dc.contributor.universityID213126035en_US
dc.contributor.emailthesis@grad.ku.edu.kwen_US
dc.description.conclusionsIn what follows, the methods developed previously will be applied to analyze the duration of remission data assuming a random sample size 𝑁 and that 30 patients begin the therapeutic program at time 𝑑=0. From past experience, it is known that 40% of patients had left the therapeutic program for one reason or another. Consequently, a binomial random sample size is a reasonable assumption. That is 𝑁 ~ 𝐡(30,0.6). Based on the observed ordered data shown previously, CIs for the population quantiles πœ‰π‘, (0<𝑝<1), and quantile intervals (πœ‰π‘,πœ‰π‘ž), (0<𝑝<π‘ž<1), can be obtained with corresponding confidence coefficients of at least 1βˆ’π›Ό=0.90. Tables 5.2 to 5.4 present these CIs.en_US
dc.date.semesterSpringen_US
dc.description.examinationYen_US
dc.description.gpa3.27en_US
dc.description.credits27en_US
Appears in Programs:0480 Statistics & Operations Research
Files in This Item:
File Description SizeFormat 
Final Thesis Submitted to CGS.pdf2,83 MBAdobe PDFView/Open    Request a copy
Arabic Cover Page Submitted to CGS.pdf62,54 kBAdobe PDFView/Open    Request a copy
Show simple item record

Page view(s) 50

97
Last Week
0
Last month
0
checked on Oct 20, 2020

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.