Quantile-regression-based clustering for panel data

Yingying Zhang, Huixia Judy Wang, Zhongyi Zhu

Research output: Contribution to journalArticlepeer-review

35 Scopus citations

Abstract

In panel data analysis, it is important to identify subgroups of units with heterogeneous parameters. This can not only increase the model flexibility but also produce more efficient estimation by pooling information across units within the same group. In this paper, we propose a new quantile-regression-based clustering method for panel data. We develop an iterative algorithm using a similar idea of k-means clustering to identify subgroups with heterogeneous slopes at a single quantile level or across multiple quantiles. The asymptotic properties of the group membership estimator and corresponding group-specific slope estimator are established. The finite sample performance of the proposed method is assessed through simulation and the analysis of an economic growth data.
Original languageEnglish (US)
Pages (from-to)54-67
Number of pages14
JournalJournal of Econometrics
Volume213
Issue number1
DOIs
StatePublished - Nov 2019
Externally publishedYes

Bibliographical note

KAUST Repository Item: Exported on 2021-04-10
Acknowledged KAUST grant number(s): OSR-2015-CRG4-2582
Acknowledgements: The authors would like to thank two anonymous reviewers and the editor for constructive comments and helpful suggestions. This research is supported by National Science Foundation grant DMS-1712760, the OSR-2015-CRG4-2582 grant from KAUST, the National Natural Science Foundation of China grants 11671096, 11690013 and 11731011, a fellowship from China Scholarship Council, the Key Laboratory for Applied Statistics of MOE, Northeast Normal University130028849, and the IR/D program from the National Science Foundation. Any opinion, findings, and conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of the National Science Foundation.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

ASJC Scopus subject areas

  • History and Philosophy of Science
  • Economics and Econometrics
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Quantile-regression-based clustering for panel data'. Together they form a unique fingerprint.

Cite this