Paul Wilmott on Quantitative Finance, Chapter 19, Value at Risk (VaR) #Finance

16 thoughts on “Paul Wilmott on Quantitative Finance, Chapter 19, Value at Risk (VaR) #Finance”

1. Un esempio con excel?

2. God bless you man, 11 years later and your video helped me finish my final paper on VaR after articles, videos and books couldn't make me understand some things!!! (talking about the ICDF)

3. The way you explain stuff is extremely slow! I played the video at 1.5x and it's still very slow. You might want to speed up your explanation and writing.

4. These things are as easy as a bachelor's course.

   As a programer I'm fascinated by building models tobforrcast the future robust with Bayesian inference to update the actual distribution. Additionally mommy amagrmemt with continuous Kelly criterion. I am currently reading a paper about quantum trading, and sure to be a blessing tobyeild fruitful results as soon as I try quantum subroutines on any quantum computer
   Besides I would top off my program with an extra cherry 🍒
   Reinforcement learning that makes learning interactive as model adapts and gets rewarded to recurrent market structure. (and so do you your account)
   I am interested in trading options hedging and handling losses mutual I have the knowledge that some would pay a ton for.
   If you're reading that means you're like me and interested
   Frankly I need money, I'll help you with your account if I have a cut too. A win-win situation where everyone is happy. I am ready to help you model even meet you in person and teach you all the different tools you need from:
   AI, statistics,to mathematics. I'll help you discover the bliss and joy of simulating different scenarios discovering hidden characteriatics
   In plain sight.

5. Thanks Nathan.. appreciate it

6. thank you sir

7. Thank you…

8. good

9. this is just standard statistics.

10. I'm a bit confused what the argument is. My point about assuming no drift was just that as delta t gets smaller, the drift terms go to zero faster than the volatility terms in the calculations. If I'm trying to determine the chance I will lose $1 million today, a 10% return over a year doesn't really matter in my calculation much, it is just a 0.04% change per day. A typical volatility might be 2% a day, an effect 50 times bigger.

11. Yes you are wrong, the fun thing about a gaussian process is that it is additative all the way. So, 5000000*0+1=1. Variances are also additative, standard deviations are not.

12. Typically I think about drift in terms of years, e.g. my estimate of a particular stock might be up 20% over the next year. Volatility matters at all time scales. As you zoom in to small time scales the volatility overwhelms any drift. As you zoom out to longer time scales the drift starts to matter in the calculations (but there is still volatility). If you're hedging and looking at the daily risk, drift becomes almost insignificant.

13. Thank u very much 🙂 it's amazing

14. @NathanWhitehead That's a great idea. What system do you use to get the blackboard effect?

    Also any more study notes? And have you checked out the posting by BionicTurtle, highly reccomended.
    Thanks

15. @delightP Cool, glad they're helpful. It's also great to write up your notes and put them online, it helps keep you honest. I know putting up these videos did that for me!

16. Hi, Thanks for these vids, using them as review for my study of the book.
    Thanks again.

Comments are closed.