UNIGE document Scientific Article
previous document  unige:96747  next document
add to browser collection

Coefficient-wise tree-based varying coefficient regression with vcrpart

Published in Journal of Statistical Software. 2017, vol. 80, no. 6, p. 1-33
Abstract The tree-based TVCM algorithm and its implementation in the R package vcrpart are introduced for generalized linear models. The purpose of TVCM is to learn whether and how the coefficients of a regression model vary by moderating variables. A separate partition is built for each potentially varying coefficient, allowing the user to specify coefficient-specific sets of potential moderators, and allowing the algorithm to select moderators individually by coefficient. In addition to describing the algorithm, the TVCM is evaluated using a benchmark comparison and a simulation study and the R commands are demonstrated by means of empirical applications.
Keywords Regression treesVarying coefficient modelsgeneralized linear modelsStatistical learningR packageCART
Full text
Article (Published version) (753 Kb) - public document Free access
Other version: http://www.jstatsoft.org/v80/i06/
Research group NCCR LIVES
(ISO format)
BUERGIN, Reto Arthur, RITSCHARD, Gilbert. Coefficient-wise tree-based varying coefficient regression with vcrpart. In: Journal of Statistical Software, 2017, vol. 80, n° 6, p. 1-33. doi: 10.18637/jss.v080.i06 https://archive-ouverte.unige.ch/unige:96747

374 hits



Deposited on : 2017-09-14

Export document
Format :
Citation style :