Dynamic Interbank Network Analysis Using Latent Space Models

Tinbergen Institute Discussoin Paper 2017-101/II

38 Pages Posted: 27 Oct 2017

See all articles by Fernando Linardi

Fernando Linardi

Government of the Federative Republic of Brazil - Central Bank of Brazil

Cees G. H. Diks

University of Amsterdam - Faculty of Economics and Business (FEB); Tinbergen Institute - Tinbergen Institute Amsterdam (TIA)

Marco van der Leij

CeNDEF, University of Amsterdam; Tinbergen Institute; De Nederlandsche Bank - Research Department

Iuri Lazier

University of São Paulo (USP)

Date Written: September 14, 2017

Abstract

Longitudinal network data are increasingly available, allowing researchers to model how networks evolve over time and to make inference on their dependence structure. In this paper, a dynamic latent space approach is used to model directed networks of monthly interbank exposures. In this model, each node has an unobserved temporal trajectory in a low-dimensional Euclidean space. Model parameters and latent banks' positions are estimated within a Bayesian framework. We apply this methodology to analyze two different datasets: the unsecured and the secured (repo) interbank lending networks. We show that the model that incorporates a latent space performs much better than the model in which the probability of a tie depends only on observed characteristics; the latent space model is able to capture some features of the dyadic data such as transitivity that the model without a latent space is not able to.

Keywords: network dynamics, latent position model, interbank network, Bayesian inference

JEL Classification: C11, D85, G21

Suggested Citation

Linardi, Fernando and Diks, Cees G. H. and van der Leij, Marco Juri and Lazier, Iuri, Dynamic Interbank Network Analysis Using Latent Space Models (September 14, 2017). Tinbergen Institute Discussoin Paper 2017-101/II. Available at SSRN: https://ssrn.com/abstract=3059618 or http://dx.doi.org/10.2139/ssrn.3059618

Fernando Linardi (Contact Author)

Government of the Federative Republic of Brazil - Central Bank of Brazil ( email )

P.O. Box 08670
SBS Quadra 3 Bloco B - Edificio-Sede
Brasilia, Distr. Federal 70074-900
Brazil

Cees G. H. Diks

University of Amsterdam - Faculty of Economics and Business (FEB) ( email )

Roetersstraat 11
Amsterdam, 1018 WB
Netherlands
+31 20 525 53 29 (Phone)
+31 20 525 4349 (Fax)

Tinbergen Institute - Tinbergen Institute Amsterdam (TIA) ( email )

Gustav Mahlerplein 117
Amsterdam, 1082 MS
Netherlands

Marco Juri van der Leij

CeNDEF, University of Amsterdam ( email )

Roetersstraat 11
Amsterdam, NL-1018WB
Netherlands
+31 20 525 7356 (Phone)

HOME PAGE: http://home.staff.uva.nl/m.j.vanderleij

Tinbergen Institute ( email )

Burg. Oudlaan 50
Rotterdam, 3062 PA
Netherlands

De Nederlandsche Bank - Research Department ( email )

P.O. Box 98
1000 AB Amsterdam
Netherlands

Iuri Lazier

University of São Paulo (USP) ( email )

Rua Luciano Gualberto, 315
São Paulo, São Paulo 14800-901
Brazil

Register to save articles to
your library

Register

Paper statistics

Downloads
43
Abstract Views
302
PlumX Metrics