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

Hypothesis Tests for High-Dimensiona...

University of Toronto (Canada)., Statistics.

FindBook

Google Book

Amazon

博客來

Hypothesis Tests for High-Dimensional Functional Data /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Hypothesis Tests for High-Dimensional Functional Data // David Colin Decker.
作者:	Decker, David Colin,
面頁冊數:	1 electronic resource (155 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
Contained By:	Dissertations Abstracts International86-05B.
標題:	Statistics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31483083
ISBN:	9798342750882

Hypothesis Tests for High-Dimensional Functional Data /
Decker, David Colin,

Hypothesis Tests for High-Dimensional Functional Data /David Colin Decker. - 1 electronic resource (155 pages)

Source: Dissertations Abstracts International, Volume: 86-05, Section: B.

High-dimensional functional data have the feature that each observational unit consists of many functional recordings. Such data are commonly generated by modern medical devices. Examples include medical imaging devices (for example fMRI and EEG devices), high through-put time-course gene sequencing devices, and high through-put devices that measure time-course microbiome composition. In the case of fMRI studies of brain activity, a time-series is recorded discretely at around 100 sites corresponding to electrodes placed on the scalp of each participant.In both the paired two-sample and independent two-sample settings we develop two-sample tests of equality of many functional means. We use a novel mixed-norm test statistic and develop a Gaussian multiplier bootstrap procedure to estimate the quantile of the test statistic under the null hypothesis of equality of overall mean. Our tests are shown theoretically to be accurate and powerful even when the number of functional recordings per observation is much larger than the sample size.Our procedure allows us to control the family-wise error incurred by testing many simultaneous functional hypotheses without conservative multiple testing corrections, and makes no assumption at all on the dependence structure across the functional recordings within each observation.In addition to proving theoretical guarantees related to the power and level of our test, we show that our test compares favorably to current state of the art tests by way of a simulation study and the analysis two `real world' data sets generated by an EEG and fMRI study.

English

ISBN: 9798342750882Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Medical imaging devices

Hypothesis Tests for High-Dimensional Functional Data /
LDR:02982nmm a22004213i 4500 001 2428917
005 20250420214350.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798342750882
035 $a (MiAaPQD)AAI31483083
035 $a AAI31483083
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Decker, David Colin, $e author. $3 3816443
245 1 0 $a Hypothesis Tests for High-Dimensional Functional Data / $c David Colin Decker.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (155 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: 86-05, Section: B.
500 $a Advisors: Volgushev, Stanislav; Kong, Dehan.
502 $b Ph.D. $c University of Toronto (Canada) $d 2024.
520 $a High-dimensional functional data have the feature that each observational unit consists of many functional recordings. Such data are commonly generated by modern medical devices. Examples include medical imaging devices (for example fMRI and EEG devices), high through-put time-course gene sequencing devices, and high through-put devices that measure time-course microbiome composition. In the case of fMRI studies of brain activity, a time-series is recorded discretely at around 100 sites corresponding to electrodes placed on the scalp of each participant.In both the paired two-sample and independent two-sample settings we develop two-sample tests of equality of many functional means. We use a novel mixed-norm test statistic and develop a Gaussian multiplier bootstrap procedure to estimate the quantile of the test statistic under the null hypothesis of equality of overall mean. Our tests are shown theoretically to be accurate and powerful even when the number of functional recordings per observation is much larger than the sample size.Our procedure allows us to control the family-wise error incurred by testing many simultaneous functional hypotheses without conservative multiple testing corrections, and makes no assumption at all on the dependence structure across the functional recordings within each observation.In addition to proving theoretical guarantees related to the power and level of our test, we show that our test compares favorably to current state of the art tests by way of a simulation study and the analysis two `real world' data sets generated by an EEG and fMRI study.
546 $a English
590 $a School code: 0779
650 4 $a Statistics. $3 517247
650 4 $a Biostatistics. $3 1002712
650 4 $a Medical imaging. $3 3172799
653 $a Medical imaging devices
653 $a Brain activity
653 $a Family-wise error
690 $a 0463
690 $a 0574
690 $a 0308
710 2 $a University of Toronto (Canada). $b Statistics. $e degree granting institution. $3 3816444
720 1 $a Volgushev, Stanislav $e degree supervisor.
720 1 $a Kong, Dehan $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-05B.
790 $a 0779
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31483083