Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/237773 
Year of Publication: 
2021
Series/Report no.: 
Tinbergen Institute Discussion Paper No. TI 2021-040/III
Publisher: 
Tinbergen Institute, Amsterdam and Rotterdam
Abstract: 
We introduce a new method for dynamic clustering of panel data with dynamics for cluster location and shape, cluster composition, and for the number of clusters. Whereas current techniques typically result in (economically) too many switches, our method results in economically more meaningful dynamic clustering patterns. It does so by extending standard cross-sectional clustering techniques using shrinkage towards previous cluster means. In this way, the different cross-sections in the panel are tied together, substantially reducing short-lived switches of units between clusters (flickering) and the birth and death of incidental, economically less meaningful clusters. In a Monte Carlo simulation, we study how to set the penalty parameter in a data-driven way. A systemic risk surveillance example for business model classification in the global insurance industry illustrates how the new method works empirically.
Subjects: 
dynamic clustering
shrinkage
cluster membership persistence
Silhouette index
insurance
JEL: 
G22
C33
C38
Document Type: 
Working Paper

Files in This Item:
File
Size
1.12 MB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.