UNIGE document Scientific Article
previous document  unige:48297  next document
add to browser collection
Title

Tree-based varying coefficient regression for longitudinal ordinal responses

Authors
Published in Computational Statistics & Data Analysis. 2015, vol. 86, p. 65-80
Abstract A tree-based algorithm for longitudinal regression analysis that aims to learn whether and how the effects of predictor variables depend on moderating variables is presented. The algorithm is based on multivariate generalized linear mixed models and it builds piecewise constant coefficient functions. Moreover, it is scalable for many moderators of possibly mixed scales, integrates interactions between moderators and can handle nonlinearities. Although the scope of the algorithm is quite general, the focus is on its usage in an ordinal longitudinal regression setting. The potential of the algorithm is illustrated by using data derived from the British Household Panel Study, to show how the effect of unemployment on self-reported happiness varies across individual life circumstances
Keywords Recursive partitioningVarying coefficient modelsMixed modelsGeneralized linear modelsLongitudinal data analysisOrdinal regressionStatistical learning
Identifiers
Full text
Structures
Research group NCCR LIVES
Citation
(ISO format)
BUERGIN, Reto Arthur, RITSCHARD, Gilbert. Tree-based varying coefficient regression for longitudinal ordinal responses. In: Computational Statistics & Data Analysis, 2015, vol. 86, p. 65-80. https://archive-ouverte.unige.ch/unige:48297

202 hits

1 download

Update

Deposited on : 2015-03-18

Export document
Format :
Citation style :