A great book on testing and optimisation - page 13
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
FOXXXi писал(а) >>
If you dig further, there may be only one such moment in a hundred, and you have not forgotten to count the profits.
There goes the skin of unkilled bears again.
I have long made another habit: not to forget about the black swans, which according to the calculations should be no more than 1 piece per hundred, but in the state it turns out a whole flock.
I have long made a habit of not forgetting the black swans, which according to the calculations should be no more than 1 per hundred, but in the state it turns out to be a whole flock.
Yes, you have a whole flock, you work with non-stationary series, and you seem to have no luck with stationary series - that's Reshetov's maths.
You've got a pack, you work with a non-stationary row, and you've got a fucked-up stationary row - that's Reshetov's maths. What's the point of keeping them in mind?
Get some rest.
the forum is alive, at least you can have a laugh at the weekend :)
GARCH works either way :), it's just the volatility of volatility has increased... in fact, what everyone uses does not work. that is why it is the portfolio growth that is included for incorporating creativity and combining different ideas. the best will always be the best, as the rest are pulling behind them.
as for crises, the models work, it's just that they have not been tuned to that frequency with many people and the concept of liquidity is missing.
VaR for example, what you probably mean, and it didn't work because of the 19.09.2008 events, because according to many banks the volatility is predicted for 10 days...
though not all banks do, the best ones have high frequency, and you can see it in their results for 2, 3 quarters :))
interesting that Foxy writes and proves that everything works. his posts give me the impression that he does not know how to use any of these models.
Kudos to Goldtrader, the approach works! as for outliers and correlations... there are fundamental reasons for that, you have to keep an eye on everything.
>> Rest.
And I suggest you, stop torturing the tester and get your ass handed to the black swans.
FOXXXi писал(а) >>
And I suggest you stop torturing the tester.
I still won't give it up, because it's a good one.
>> I won't leave him anyway, because he's a good one.
I'm not arguing that it's good, but it's "a little" for other purposes.
It's interesting that Foxy writes and proves that everything works. his posts give the impression that he doesn't know how to use any of these models.
Show me exactly where the doubts arose?
Show me exactly where the doubts are?
No one has any doubts yet.
>> >> >> that's a solid CU, judging by the pictures. You can go straight to the real one. That's where all the doubts will appear.