서브메뉴
검색
Modeling Intensively Measured, Longitudinal, and Multidimensional Item Responses: Capturing Continuous-Time Latent Change Processes via Neural Stochastic Differential Equations
Modeling Intensively Measured, Longitudinal, and Multidimensional Item Responses: Capturing Continuous-Time Latent Change Processes via Neural Stochastic Differential Equations
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151157
- ISBN
- 9798382632360
- DDC
- 151
- 서명/저자
- Modeling Intensively Measured, Longitudinal, and Multidimensional Item Responses: Capturing Continuous-Time Latent Change Processes via Neural Stochastic Differential Equations
- 발행사항
- [Sl] : The University of North Carolina at Chapel Hill, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 56 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
- 주기사항
- Advisor: Bauer, Daniel J.
- 학위논문주기
- Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2024.
- 초록/해제
- 요약I develop a novel deep learning framework for second-order latent growth modeling using intensive longitudinal data. Specifically, I propose a neural stochastic differential equations (SDEs) approach wherein the latent trajectories follow SDEs parameterized by neural networks (NNs), providing enhanced modeling capacity relative to prior methods. To provide insight into the temporal distribution of item responses, I propose an extension of the usual second-order latent growth model (SLGM) wherein measurement times and response missingness are jointly modeled via a neural SDE-based marked point process. I discuss identifiability of the proposed model class, then derive a scalable approximate marginal maximum likelihood estimator and conduct a brief simulation study to demonstrate proof-of-concept. I conclude with a discussion of various implementation challenges as well as future directions.
- 일반주제명
- Quantitative psychology
- 일반주제명
- Computer science
- 일반주제명
- Statistics
- 키워드
- Deep learning
- 키워드
- Forecasting
- 키워드
- Neural networks
- 기타저자
- The University of North Carolina at Chapel Hill Psychology
- 기본자료저록
- Dissertations Abstracts International. 85-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161069
■00520250211151157
■006m o d
■007cr#unu||||||||
■020 ▼a9798382632360
■035 ▼a(MiAaPQ)AAI31236692
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a151
■1001 ▼aUrban, Christopher J.
■24510▼aModeling Intensively Measured, Longitudinal, and Multidimensional Item Responses: Capturing Continuous-Time Latent Change Processes via Neural Stochastic Differential Equations
■260 ▼a[Sl]▼bThe University of North Carolina at Chapel Hill▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a56 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-11, Section: B.
■500 ▼aAdvisor: Bauer, Daniel J.
■5021 ▼aThesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2024.
■520 ▼aI develop a novel deep learning framework for second-order latent growth modeling using intensive longitudinal data. Specifically, I propose a neural stochastic differential equations (SDEs) approach wherein the latent trajectories follow SDEs parameterized by neural networks (NNs), providing enhanced modeling capacity relative to prior methods. To provide insight into the temporal distribution of item responses, I propose an extension of the usual second-order latent growth model (SLGM) wherein measurement times and response missingness are jointly modeled via a neural SDE-based marked point process. I discuss identifiability of the proposed model class, then derive a scalable approximate marginal maximum likelihood estimator and conduct a brief simulation study to demonstrate proof-of-concept. I conclude with a discussion of various implementation challenges as well as future directions.
■590 ▼aSchool code: 0153.
■650 4▼aQuantitative psychology
■650 4▼aComputer science
■650 4▼aStatistics
■653 ▼aDeep learning
■653 ▼aForecasting
■653 ▼aLatent growth model
■653 ▼aNeural networks
■653 ▼aStochastic differential equations
■690 ▼a0632
■690 ▼a0984
■690 ▼a0463
■71020▼aThe University of North Carolina at Chapel Hill▼bPsychology.
■7730 ▼tDissertations Abstracts International▼g85-11B.
■790 ▼a0153
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161069▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
