Thursday, March 05, 2015. 10:17 AM

My research papers, policy analysis and random thoughts on topics such as crisis, regulations and financial risk.

Jon Danielsson - London School of Economics

Why risk is so hard to measure

Jon Danielsson and Chen Zhou
March 2015

We consider the robustness of standard risk analysis techniques, with a special emphasis on those in Basel III and focussing on he relationship between value--at--risk and expected shortfall, the small sample properties of these risk measures and the impact of using an overlapping approach to construct data for longer holding periods. We find that VaR is superior to ES practical applications, that time scaling is superior to using overlapping data and that risk forecasts are extremely uncertain at very low sample sizes.