東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

High-Dimensional Statistical Models ...

Ge, Yawei,

FindBook

Google Book

Amazon

博客來

High-Dimensional Statistical Models and Hypothesis Tests With a Focus on Forensic and Genetic Applications /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	High-Dimensional Statistical Models and Hypothesis Tests With a Focus on Forensic and Genetic Applications // Yawei Ge.
作者:	Ge, Yawei,
面頁冊數:	1 electronic resource (97 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: A.
Contained By:	Dissertations Abstracts International85-12A.
標題:	Statistics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30994522
ISBN:	9798382800721

High-Dimensional Statistical Models and Hypothesis Tests With a Focus on Forensic and Genetic Applications /
Ge, Yawei,

High-Dimensional Statistical Models and Hypothesis Tests With a Focus on Forensic and Genetic Applications /Yawei Ge. - 1 electronic resource (97 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: A.

We consider the applications of statistical methods in the field of forensic science and genetic science, where we are able to record more and better traits from the study objects as the advance of modern technology. In forensic science, we are moving from the traditional microscope comparisons to 3D scans with computer based algorithms in response to the need of objective methods. We propose beta-mixture distributions to model the cross-correlation functions (CCF) for matching and non-matching bullets, and further apply the score-based likelihood ratios to quantify the strength of evidence. We also propose a screening procedure and analyze the use of reference database which improves the performance of prediction. In genetic science, we analyze the experiment data which is designed to understand the underlying relations among biomass, metabolites, microbiome, genotypes of sorghum and levels of nitrogen. The recorded number of microbiome and metabolites by advanced measurement technology is larger than the sample size, which is known as the "large p, small n" scenario. We propose a high-dimensional linear mixed effect model to quantify the effect of multiple groups of factors to biomass. Further, we propose a high-dimensional test procedure to conduct the simultaneous test of coefficients while controlling a group of high-dimensional nuisance variables to replace the conventional F-test. We show the properties of the proposed test statistic through theorems and simulations.

English

ISBN: 9798382800721Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

High-dimensional test

High-Dimensional Statistical Models and Hypothesis Tests With a Focus on Forensic and Genetic Applications /
LDR:03042nmm a22004573i 4500 001 2430726
005 20250603111605.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798382800721
035 $a (MiAaPQD)AAI30994522
035 $a AAI30994522
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Ge, Yawei, $e author. $0 (orcid)0009-0001-8353-1477 $3 3819197
245 1 0 $a High-Dimensional Statistical Models and Hypothesis Tests With a Focus on Forensic and Genetic Applications / $c Yawei Ge.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (97 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: A.
500 $a Advisors: Hofmann, Heike; Qiu, Yumou Committee members: Yu, Cindy; Nordman, Daniel; Liu, Peng.
502 $b Ph.D. $c Iowa State University $d 2024.
520 $a We consider the applications of statistical methods in the field of forensic science and genetic science, where we are able to record more and better traits from the study objects as the advance of modern technology. In forensic science, we are moving from the traditional microscope comparisons to 3D scans with computer based algorithms in response to the need of objective methods. We propose beta-mixture distributions to model the cross-correlation functions (CCF) for matching and non-matching bullets, and further apply the score-based likelihood ratios to quantify the strength of evidence. We also propose a screening procedure and analyze the use of reference database which improves the performance of prediction. In genetic science, we analyze the experiment data which is designed to understand the underlying relations among biomass, metabolites, microbiome, genotypes of sorghum and levels of nitrogen. The recorded number of microbiome and metabolites by advanced measurement technology is larger than the sample size, which is known as the "large p, small n" scenario. We propose a high-dimensional linear mixed effect model to quantify the effect of multiple groups of factors to biomass. Further, we propose a high-dimensional test procedure to conduct the simultaneous test of coefficients while controlling a group of high-dimensional nuisance variables to replace the conventional F-test. We show the properties of the proposed test statistic through theorems and simulations.
546 $a English
590 $a School code: 0097
650 4 $a Statistics. $3 517247
650 4 $a Microbiology. $3 536250
650 4 $a Forensic sciences. $3 606870
650 4 $a Genetics. $3 530508
653 $a High-dimensional test
653 $a Hypothesis test
653 $a Cross-correlation functions
653 $a 3D scans
653 $a Genetic application
690 $a 0463
690 $a 0774
690 $a 0410
690 $a 0369
710 2 $a Iowa State University. $b Statistics. $e degree granting institution. $3 3819198
720 1 $a Hofmann, Heike $e degree supervisor.
720 1 $a Qiu, Yumou $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-12A.
790 $a 0097
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30994522