Is any prediction doomed? - 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
"Don't predict - use" - what is probably meant here is "buy the Grail for the money" and don't worry about it. Just mow the dough.
That's about right, except that probabilistic estimates have nothing to do with it. Under non-stationarity, they are meaningless. Numerosity.
Actually, you don't have to go far; it is enough to carefully read what successful traders tell, for example in Schwager's book. (If you do not know anything about the market, you cannot make any comments or ask any questions. However, where are they and where are the local experts on terrain. Worth thinking about. :)
You have not read Schwager. Open "New Market Wizards" and let's do it. I'll give you a hint - William Eckhart, Jill Blake etc.
And probabilistic estimates and non-stationarity - one does not contradict the other. If the price as a time series is non-stationary, it does not prevent you from finding price patterns that have a probabilistic estimate and making predictions based on that
You haven't read any Schwager. Open New Market Wizards and let's get to it. I'll give you a hint - William Eckhart, Jill Blake, etc.
I do not know how you read it, but in order not to be unfounded we open Schwager and read it. For example the same Eckhart, mathematician: "...had to admit, that mathematical logic is not like logic in the operating room", "...came to the pit with too many ready-made ideas about how markets work", "...came with the idea that I could apply to markets in the most straightforward way analytical methods, which I had picked up in the field of mathematics. That's where I was very wrong." And that's coming from one of the Turtles' dads. And the reasoning about the pitfalls of normal statistics, in futures, etc. - here of course you need to be clear that his statistics are not very classical and exploit patterns rather than numerology.
As the saying goes - "sit down two, go read".
And probabilistic estimates and non-stationarity - one does not contradict the other. If the price as a time series is non-stationary, it does not prevent you from finding price patterns that have a probabilistic estimate and making predictions based on that
I don't know how you read it, but not to be unsubstantiated, open and read. For example the same Eckhart, the mathematician: "...forced to admit that mathematical logic is quite different from the logic in the operating room". "...came into the pit with too many ready-made ideas about how markets work", "...came in with the idea that I could apply to markets in the most straightforward way the analytical techniques I had learned in the field of mathematics. I was very wrong about that." And that's coming from one of the Turtles' dads.
As the saying goes - "sit down two, go read."
This is the basis of a classical terver, probability estimates are only meaningful in stationarity conditions. And all the main laws like large numbers and convergence are about this.Eckhart uses statistical methods and probability estimates? Yes. What difference does it make whether he applies them straightforwardly or curvilinearly? What difference does it make how many perceptions he comes into the hole with?
Once again, price as a time series is non-stationary. You have found that with about 80% probability the price rises when the two indicators cross. Can you apply this to the TS? Yes.
Does Eckhart use statistical methods and probability estimates? Yes. What difference does it make whether he applies them straightforwardly or curvilinearly? What difference does it make how many perceptions he comes into the hole with?
Well, as if he said it all there himself, why make it up for him and try to interpret it as you see fit.
Once again, price as a time series is non-stationary. You have found that there is about an 80% probability that price rises when two indicators cross. Can you apply this to the TS? Yes.
No. Because it's not a pattern, it's numerology. There's nothing substantive behind those "probabilities" (which aren't really probabilities at all) other than self-delusion.
There, that's it now. Good luck.
Well, as if he said it himself there, why make it up?
What's two for? I was quoting him!
No.
Why not? So, if you found out that when two indicators cross, the price goes up with 80% probability and it goes down with 20% probability - it cannot be the basis of TS? You have tested the market over the last five years and estimated the probabilities. What prevents you from doing so?
No. Because it's not a pattern, it's numero uno. Behind these "probabilities" (which aren't really probabilities at all) there's nothing substantive but self-delusion.
There, that's it now. Good luck.
)))))))))))))))
A man is lost in the desert. He walks on the dunes for a day, two, three. He is dying of thirst. A caravan comes towards him, a mahout dismounts from his camel and hands the man a flask of water.
The man takes a stone and swings at the mahalla, shouting "Go away, mirage!
))))))
Self-deception, my ass.
So any pattern in the market is useless to look for - numero uno and self-delusion
You've made me happy)))
Here's an example for you too. Take any pair with the franc or gold at the moment and tell me - how can you determine their overbought/oversold state. The franc and the gold, for fundamental reasons, just go in one direction and that is it. So, trying to catch a bottom or a top, you get two more as a gift. Working in a hedge will only make things worse, in my opinion.
The franc is heavily oversold right now. The franc is so oversold, that I wouldn't make a conclusion about buying it on Monday, because its behavior doesn't fit the economic reasons. Personally, I would prefer to wait out of the market, and then on Tuesday-Wednesday, we'll "look and see". But this is MY analysis, MY forecasts and MY vision of the market, the results of this analysis with all their profits and losses will also be mine.
This is about something else. Multicurrency analysis and, as a consequence, forecasting the behaviour of several instruments actually has a basis in purely economic considerations, aligning at certain points in time the fundamental movements that are now precisely observed in the behaviour of the franc.
Again, don't be so categorical...