Please use this identifier to cite or link to this item:
http://hdl.handle.net/2122/13542
Authors: | Sottile, Gianluca* Adelfio, Giada* |
Title: | Clusters of effects in quantile regression models | Journal: | Computational Statistics | Series/Report no.: | /34 (2019) | Issue Date: | 2019 | DOI: | 10.1007/s00180-018-0817-8 | Keywords: | quantile regression coeffcients modelling, multivariate analysis, functional data, curves clustering | Subject Classification: | COMPUTATIONAL STATISTICS | Abstract: | In this paper we propose a new method for nding similarity of effects in a multivariate regression context. Using quantile regression, the effect of each covariate on a response variable is represented as a function of percentiles. Col- lecting all these curves, describing the effects of each covariate on the response, we could assess if there are covariates with similar effects. Moreover, we provide a exible algorithm which could be used not only for clustering the coefcient effects of a quantile regression framework, but also for nding clusters of generic curves. We provide also some simulated results and applications on real data, highlighting the exibility of the proposed approach in several research elds. |
Appears in Collections: | Article published / in press |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
sottile-adelfioCSDA.pdf | 728.92 kB | Adobe PDF | View/Open |
WEB OF SCIENCETM
Citations
2
checked on Feb 7, 2021
Page view(s)
37
checked on Apr 24, 2024
Download(s)
61
checked on Apr 24, 2024