Modelling Financial Markets Comovements during Crises: A Dynamic Multi-Factor Approach

Abstract

paricular J. Breitung, M. Hallin and M. Marcellino, for useful discussions and valuable comments. Special thanks to the Editors, Eric Hillebrand and Siem Jan Koopman, and two anonymous referee for very helpful comments and suggestions that greatly helped to improve the paper. Riccardo Borghi has provided very insightful comments on a previous version of the paper. The usual disclaimer applies. Riccardo Pianeti acknowledges …nancial support from the Centre for Econometric Analisis at Cass and the EAMOR Doctoral Programme at Bergamo University.y KNG Securities, London (UK). We propose a novel dynamic factor model to characterise comovements between returns on securities from di¤erent asset classes from di¤erent countries. We apply a global-classcountry latent factor model and allow time-varying loadings. We are able to separate contagion (asset exposure driven) and excess interdependence (factor volatility driven). Using data from 1999 to 2012, we …nd evidence of contagion from the US stock market during the 2007-09 …nancial crisis, and of excess interdependence during the European debt crisis fromMay-2010 onwards. Neither contagion nor excess interdependence is found when the average measure of model implied comovements is used.JEL: C3, C5, G1.

“I am Delighted!”: The Effect of Perceived Customer Value on Repurchase and Advocacy Intention in B2B Express Delivery Services

“…A concept that is widely used in previous studies and related to recommendation intention is socalled WOM (word of mouth), which is understood as a form of informal recommendation in relation to a certain product or service [95][96][97][98]. Specifically, WOM could be defined as the comments made by customers about a given service or product [99]. Recently, other studies have used a new concept that has evolved in different digital environments: electronic word of mouth (e-WOM), which analyzes purchase decisions based on customer recommendations on the web [100].…”

Estimating and testing high dimensional factor models with multiple structural changes

“…Next, perform the test F N T (l+1 jl ). If rejected 13 , estimate l + 1 change points, either jointly or sequentially, and then perform the test F N T (l + 2 jl + 1 ). Repeat this procedure until the null can not be rejected.…”

Accurate Confidence Regions for Principal Components Factors*

“…For example, Hakkio and Keeton (2009); Erdem and Tsatsaronis (2013) extract factors to construct financial conditions indexes. Moreover, in Belsivi, Pianeti and Urga (2016), the factors represent comovements between returns on securities of different asset classes from different countries while, in Greenaway‐McGrevy et al . (2018), the common factors from exchange rates are given a risk‐based interpretation.…”