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

切換: 標籤 | MARC模式 | ISBD

Stop Signal Reaction Times: New Esti...

Soltanifar, Mohsen .

FindBook

Google Book

Amazon

博客來

Stop Signal Reaction Times: New Estimations with Longitudinal, Bayesian and Time Series Based Methods.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Stop Signal Reaction Times: New Estimations with Longitudinal, Bayesian and Time Series Based Methods./
作者:	Soltanifar, Mohsen .
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	181 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-01, Section: B.
Contained By:	Dissertations Abstracts International82-01B.
標題:	Biostatistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27829472
ISBN:	9798662393042

Stop Signal Reaction Times: New Estimations with Longitudinal, Bayesian and Time Series Based Methods.
Soltanifar, Mohsen .

Stop Signal Reaction Times: New Estimations with Longitudinal, Bayesian and Time Series Based Methods. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 181 p.

Source: Dissertations Abstracts International, Volume: 82-01, Section: B.

Thesis (Ph.D.)--University of Toronto (Canada), 2020.

This item must not be sold to any third party vendors.

The stop signal reaction times (SSRT), a measure of the unobserved latency of the stop signal process in Stop Signal Task (SST) has been a focal point of the estimation. It was theoretically formulated as constant and random variable indices. The first index has been formulated using the independent horse race model of go and stop trials by Gordon Logan in 1994. The second index was estimated by Eric Jan Wagenmaker and colleagues in 2012 using the Bayesian Parametric Approach (BPA) and Ex-Gaussian assumption for the underlying go reaction times (GORT), signal respond reaction times (SRRT) and SSRT. Both of the mentioned estimation methods of SSRT assume equal impact of the preceding trial type (go/stop) on the current stop trial for its measurement. In case of violation of this assumption, the appropriate estimations of SSRT are required to address the measurement error. In this dissertation, we estimate SSRT under violation of the assumption in three frequentist longitudinal, mixture Bayesian and time series based methods. The frequentist longitudinal estimation method considers two clusters of SST trials and introduces Mixture SSRT and Weighted SSRT as two new distinct indices of SSRT being asymptotically equivalent under special conditions. The Bayesian estimation method considers degenerate mixture Bayesian estimation of SSRT using the cluster type SSRT estimation with underlying Ex-Gaussian assumption for GORT, SRRT and SSRT. In our proposed method we use the Two Stage Bayesian Parametric Approach (TSBPA) with uninformative priors. We compare the new Bayesian Mixture estimation of SSRT with the current single estimation in stochastic order and discuss the results for various underlying assumptions in terms of types of distributions, priors and weights. Finally, the time series based estimation method assumes lognormal distributions for GORT and SRRT; and, applies state-space missing data EM algorithm on each subjects SST data encompassing the order of (go/stop) trials yielding the order SST data. Then, using the Logan 1994 formula for the ordered SST data, the state-space index of SSRT is calculated. In all three methods, our examples of empirical SST data and simulated data are investigated to compare the new index to the established ones.

ISBN: 9798662393042Subjects--Topical Terms:

1002712
Biostatistics.
Subjects--Index Terms:

Ex-Gaussian distribution

Stop Signal Reaction Times: New Estimations with Longitudinal, Bayesian and Time Series Based Methods.
LDR:03482nmm a2200361 4500 001 2273124
005 20201105110348.5
008 220629s2020 ||||||||||||||||| ||eng d
020 $a 9798662393042
035 $a (MiAaPQ)AAI27829472
035 $a AAI27829472
040 $a MiAaPQ $c MiAaPQ
100 1 $a Soltanifar, Mohsen . $3 3550557
245 1 0 $a Stop Signal Reaction Times: New Estimations with Longitudinal, Bayesian and Time Series Based Methods.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 181 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-01, Section: B.
500 $a Advisor: Escobar, Michael.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2020.
506 $a This item must not be sold to any third party vendors.
520 $a The stop signal reaction times (SSRT), a measure of the unobserved latency of the stop signal process in Stop Signal Task (SST) has been a focal point of the estimation. It was theoretically formulated as constant and random variable indices. The first index has been formulated using the independent horse race model of go and stop trials by Gordon Logan in 1994. The second index was estimated by Eric Jan Wagenmaker and colleagues in 2012 using the Bayesian Parametric Approach (BPA) and Ex-Gaussian assumption for the underlying go reaction times (GORT), signal respond reaction times (SRRT) and SSRT. Both of the mentioned estimation methods of SSRT assume equal impact of the preceding trial type (go/stop) on the current stop trial for its measurement. In case of violation of this assumption, the appropriate estimations of SSRT are required to address the measurement error. In this dissertation, we estimate SSRT under violation of the assumption in three frequentist longitudinal, mixture Bayesian and time series based methods. The frequentist longitudinal estimation method considers two clusters of SST trials and introduces Mixture SSRT and Weighted SSRT as two new distinct indices of SSRT being asymptotically equivalent under special conditions. The Bayesian estimation method considers degenerate mixture Bayesian estimation of SSRT using the cluster type SSRT estimation with underlying Ex-Gaussian assumption for GORT, SRRT and SSRT. In our proposed method we use the Two Stage Bayesian Parametric Approach (TSBPA) with uninformative priors. We compare the new Bayesian Mixture estimation of SSRT with the current single estimation in stochastic order and discuss the results for various underlying assumptions in terms of types of distributions, priors and weights. Finally, the time series based estimation method assumes lognormal distributions for GORT and SRRT; and, applies state-space missing data EM algorithm on each subjects SST data encompassing the order of (go/stop) trials yielding the order SST data. Then, using the Logan 1994 formula for the ordered SST data, the state-space index of SSRT is calculated. In all three methods, our examples of empirical SST data and simulated data are investigated to compare the new index to the established ones.
590 $a School code: 0779.
650 4 $a Biostatistics. $3 1002712
650 4 $a Quantitative psychology. $3 2144748
650 4 $a Mathematics. $3 515831
653 $a Ex-Gaussian distribution
653 $a Mixture models
653 $a State-space missing time series
653 $a Stop signal reaction times
690 $a 0308
690 $a 0632
690 $a 0405
710 2 $a University of Toronto (Canada). $b Dalla Lana School of Public Health. $3 3186959
773 0 $t Dissertations Abstracts International $g 82-01B.
790 $a 0779
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27829472