Modeling different kinds of spatial dependence in stock returns

• DOI: 10.1007/s00181-011-0528-2
• Publication Date: 2011-12-06T06:52:28Z
• Authors: Matthias Arnold; Sebastian Stahlberg; Dominik Wied
• Keywords: 0502 economics and business; 05 social sciences

The paper modifies previously suggested GMM approaches to spatial autoregression in stock returns. Our model incorporates global dependencies, dependencies inside industrial branches and local dependencies. As can be seen from Euro Stoxx 50 returns, this combination of spatial modeling and finance allows for superior risk forecasts in portfolio management.