Monday, September 21, 2015

risk - What approaches are there for stress testing a portfolio?


Wikipedia lists three of them:



  • Extreme event: hypothesize the portfolio's return given the recurrence of a historical event. Current positions and risk exposures are combined with the historical factor returns.

  • Risk factor shock: shock any factor in the chosen risk model by a user-specified amount. The factor exposures remain unchanged, while the covariance matrix is used to adjust the factor returns based on their correlation with the shocked factor.


  • External factor shock: instead of a risk factor, shock any index, macro-economic series (e.g., oil prices), or custom series (e.g., exchange rates). Using regression analysis, new factor returns are estimated as a result of the shock.


But I was wondering if there is a more comprehensive list.



Answer



Well all that you have cited seems quite all you can do with scenario maybe I can add another one which is portfolio dependent. Instead of looking to arbitrary scenarios you first decompose the factor to which you portfolio is the most sensitive to, and then look for scenarios that are specifically impacting this combination of risk factors.


Anyway,scenario losses can be quite an effective tool in risk management because it shows in a simple way where is your risk standing but it shouldn't be viewed as a standalone indicator.


One flaw is that it usually tell you something about only a few scenarios,but you can't be really sure that other scenarios won't impact you more. Moreover the more you have scenarios the less you know how to order them with respect to each other or with respect to some kind of likelihood.


Otherwise in the field of capital requirement area, I start to ear about Stressed-VaR which means among other things that you raise in a considerable way correlations between risk factors (as it usually happens during crisis) as well as volatility of risk factors.


In the end Scenarios or Stressed-VaR, look a little bit like some "cuisine" with no real theoretical grounds to support the whole building and that's the problem.


Regards



No comments:

Post a Comment

technique - How credible is wikipedia?

I understand that this question relates more to wikipedia than it does writing but... If I was going to use wikipedia for a source for a res...