Econometrics: one step ahead forecast - page 64
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
So what gives?
.
If you could play the convergence--
like, for example, the price broke through the bag up--
we buy the bag - we sell the price - in the end - we're always on the plus side.
.
But there is no such possibility.
The returns are traded as a flat, for example. The problem with flappers is something else - the trendiness or returns relative to them in their pure form are too insignificant compared to the risk (variance). I.e. they can only be part of a strategy, a filter for example.
Exactly! Like a dog dangling against its own tail
If we could play on the convergence - for example, the price breaks the cap up - we buy the cap - sell the price - and in the end we are always in the black.
.
But there is no such possibility.
Why not? If only we had a desire. There was such an idea - statarbitrage between price and waving (i.e. on one financial instrument). I did not develop it because I was roughly told that such a system is loss-making. But I myself have not yet become sure of it.
Obviously, there is some sort of return of price to wage (or wage to price). Another thing is that the difference between the two can maintain its sign for a long time, too long. And you cannot instantly buy/sell the product, it must be accumulated, and then at some point, enter the opposite position at a price that is equal in volume to the one accumulated with the product. Then we need to support this position with entering bars until the difference is reversed. That is when we cover everything and fix profit on the total amount of trades.
Please don't speak about losses on spread. They are not large at all. This system has several other problems. The main problem is that the average time of return is not too large, however the statistical distribution of return time is too thick-tailed and there are often large "spikes" causing significant equity drawdowns.
In addition, such a system does not work in a netting accounting system, as a position with zero volume is a lack of a position and nothing else.
Here is a typical prediction error graph.
How is it possible to get such a smooth curve from this one?
In addition, such a system does not work in a netting system because a position with zero volume is no position and nothing else.
.
To put it crudely, there's a mash-up - there's a price.
the current upset let it be 200 p. -
too much.
Let's sell.
And then - surprise - the swing changes direction and jumps to the price.
And so it goes for 5 days.
.
Where does arbitrage come in?
It is not about the paper. The original logic of the system is completely broken by netting.
Fuck it. A corpse goes to the morgue. Such a "system" could only come about under the influence of DC's position accounting :)
jartmailru: The next thing you know, surprise, the wagon changes direction and jumps to the price. And so for 5 days.
.
Where can arbitrage happen here?
First of all, it's not arbitrage, it's statarbitrage. Secondly, I already wrote about it a bit earlier:
This system has several other problems. And the main one is that the average return time is not too long, but the statarbitrage return time distribution is too thick-tailed, and there are often very large "spikes" leading to significant equity drawdowns.
It's not about the paper. The original logic of the system is completely broken by netting.
In addition, such a system does not work in a netting system because a position with zero volume is no position and nothing else.