Timeline for Which measure to determine Risk?
Current License: CC BY-SA 3.0
12 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 8, 2013 at 13:22 | history | tweeted | twitter.com/#!/StackQuant/status/409674342940049409 | ||
| Dec 2, 2013 at 13:55 | vote | accept | user1332526 | ||
| Dec 2, 2013 at 12:26 | answer | added | Richi Wa | timeline score: 1 | |
| Dec 2, 2013 at 2:39 | comment | added | Matt Wolf | There are no robust methods in risk management, though there are sound and reasonable ones. That is all I can tell you from a practitioner's point of view, someone whose positions have been "frozen" all of a sudden intraday multiple times because the exchange halted the stock and re-opened it days, sometimes weeks, later. Someone who had to deal with multi limit-up/limit-down days. You get the point, I hope; there are no robust risk management models that capture such events. Look to properly handle 95% of the cases, which is what is already provided and deal with the rest on your own. | |
| Dec 1, 2013 at 14:35 | comment | added | user1332526 | As for my part, I am not advocating conventional risk models! I am interested in robust and coherent methods in risk management. However research in this field is not advanced enought to make these models attractive for funds and banks. So by the end of the day I have to produce a risk estimate that will make people believe that they have a grasp of their exposure, when it's written on the wall that they don't! | |
| Dec 1, 2013 at 4:19 | comment | added | Matt Wolf | ...just adding one additional thought: Does it matter what your professor or even Ito thinks how risk should be defined if you adhere to theoretical models no matter how remote they are from reality if your trading desks lose tens of millions just because traders were not forced earlier to reduce risk. And all that because your "models" did not yet flag limit violations because they are so abstracted from reality. | |
| Dec 1, 2013 at 4:12 | comment | added | Matt Wolf | The reason why one gets away pricing derivatives in the risk-neutral probability space (given certain conditions are met) is because the drift is already accounted for through the underlying and because of the hedge argument. This, however, is not the case when you take a straight exposure to cash equity. Of course you can always setup an equity pricing model where you end up with a stochastic differential in which the drift term "vaporized" but I question its usefulness. For pricing its perfectly fine as long as everyone agrees on the same way (such as B-S) but risk? | |
| Nov 30, 2013 at 21:20 | comment | added | user1332526 | Thanks for the comment, I am aware of these facts. I am not a fan of VaR either and I guess jump diffusions are great but one needs to be carefull and compare the extra cost of modelling with the benefit gained from employing such models. Anyways, I used these simple concepts to illustrate my problem which should be independent of the risk measure or process at hand. | |
| Nov 30, 2013 at 15:04 | comment | added | Matt Wolf | I am not a believer in Value at Risk (VaR) and when I think about true exposure to firm-specific risk then you are in effect at the mercy of the specific equity return and hence risk. The classic theoretical model of assuming a BM driven process with specific drift is anyway a flawed concept no matter how you turn it. For equity linked or direct equity exposure other models, such as those that incorporate jumps, are way superior vs the traditional Ornstein–Uhlenbeck process, for example. My point is that you deliberately chose to expose yourself to the equity drift -> use it. | |
| Nov 29, 2013 at 14:14 | review | First posts | |||
| Nov 29, 2013 at 15:39 | |||||
| Nov 29, 2013 at 14:06 | history | edited | user1332526 | CC BY-SA 3.0 |
added 201 characters in body
|
| Nov 29, 2013 at 13:56 | history | asked | user1332526 | CC BY-SA 3.0 |