UNIGE document Doctoral Thesis
previous document  unige:72616  next document
add to browser collection
Title

Tree-based methods for moderated regression with application to longitudinal data

Author
Director
Defense Thèse de doctorat : Univ. Genève, 2015 - GSEM 8 - 2015/04/17
Abstract The dissertation proposes contributions to longitudinal data analysis and moderated regression analysis and is structured into three parts. The first part develops a decorated parallel coordinate plot for longitudinal categorical data, featuring a jitter mechanism revealing the diversity of observed longitudinal patterns, allowing the tracking of each individual pattern and filter options for highlighting typical patterns. The second and the third parts develop semi-parametric methods for moderated regression that combine linear regression models with tree-based algorithms. Specifically, the method of the second part allows fitting tree-structured varying coefficients in multivariate generalized linear mixed models for longitudinal data, and the method of the third part implements coefficient-wise tree-structured varying coefficients in generalized linear models. For general use, the methods are implemented in the freely available packages TraMineR and vcrpart for the statistical software environment R.
Keywords Longitudinal data analysisGraphical methodsRegression analysisStatistical learningRegression treesVarying coefficient modelsMixed modelsGeneralized linear modelsOrdinal regression models
Identifiers
URN: urn:nbn:ch:unige-726162
Full text
Thesis (1.4 MB) - public document Free access
Appendix (645 Kb) - public document Free access
Structures
Citation
(ISO format)
BUERGIN, Reto Arthur. Tree-based methods for moderated regression with application to longitudinal data. Université de Genève. Thèse, 2015. https://archive-ouverte.unige.ch/unige:72616

510 hits

510 downloads

Update

Deposited on : 2015-05-18

Export document
Format :
Citation style :