Discussion of article "Probability theory and mathematical statistics with examples (part I): Fundamentals and elementary theory" - page 2
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 they do match on average, otherwise it's not a forecast. But there are characteristic deviations in specifics. I judge visually by the changes that something is changing in the market and the trend will reverse.
Frankly speaking, I consider the approach related only to forecasting to be insufficient (because of the inherent non-stationarity of the market). It needs to be supplemented with an approach related to the definition of discrepancy (the moment when the model parameters change). In an embryonic form it can be seen in the examples to the article, but I would like to write more about it in the third part.
I didn't want to, but I will...
I don't know what the whole cycle of your articles will be about, but if the articles will once again predict the price, no matter how - using statistics, theory ..., dancing with a tambourine ... tambourine dancing...
then alas, it has been discussed 100500 times on this resource and on others, the result of these studies will be either the price is random in nature or there are patterns (on history), here you have it "on a platter"!
perhaps with your preparation and good presentation it will be interesting
but for practical purposes, you need to be able to evaluate trading strategy in the future, not to predict price series.
If your series of articles on evaluation of trading strategies from the position of probability theory, imho, it will be a masterpiece.
In my opinion, all my previous articles are devoted to the issues of TS evaluation from the position of theorver) The first three are rather for abstract systems, and the fourth one is for a system on gaps (which used the conclusions from the second one).
Although, the article on gaps is more devoted to another topic - the use of the SB model.
In my opinion, all my previous articles are devoted to the issues of TS estimation from the theorist's point of view) The first three are rather for abstract systems, and the fourth one is for a system on gaps (which used the conclusions from the second one).
Although, the article on gaps is more devoted to another topic - the use of the SB model.
Strange, but for some reason I missed your article "Application of Monte Carlo method to optimise trading strategies".
This is exactly what I was looking for the last months, now I have something to think about.
Thank you!
Strangely enough, I missed your article "Applying Monte Carlo method to optimise trading strategies" for some reason.
This is exactly what I've been looking for for the last few months, now I have something to think about.
Thank you!
You're welcome! That topic needs further development - we need to move from bootstrap on trades to testing on modelled prices. It seems that custom symbols and fxsaber's library for testing allow to do it.
Frankly speaking, I consider the approach related only to forecasting to be insufficient (due to the inherent non-stationarity of the market). It needs to be supplemented with an approach related to the definition of discrepancy (the moment when the model parameters change). In an embryonic form it can be seen in the examples to the article, but I would like to write more about it in the third part.
It is interesting to learn more about the topic of modelling.
Interesting to hear more about the modelling topic.
If we are talking about giving recipes for building a good probabilistic model, which will allow building a profitable TS, it is hardly possible at all. In any case, I have outlined the basic principles of my approach in the article about gaps and I am not planning any texts about this direction yet.
I use standard examples of models for this series of articles, so as not to overcomplicate the presentation.
But maybe you mean something more specific - for example, econometric modelling or Monte Carlo modelling, etc. In that case, clarification is needed.
If we are talking about giving recipes for building a good probabilistic model that will allow building a profitable TS, it is hardly possible at all. In any case, I have outlined the basic principles of my approach in the article about gaps and I am not planning any texts about this direction yet.
I use standard examples of models for this series of articles in order not to overcomplicate the presentation.
But maybe you mean something more specific - for example, econometric modelling or Monte Carlo modelling, etc. In that case, clarification is needed.
The question is more about the theory of building scientific models. Where to get ideas, what formulas to use for modelling, how to evaluate the quality of the model, and there forecasting, discord.
Two more parts on random variables and random processes are planned.
This is great, because among traders there is a widespread illiteracy in rumours).
I am afraid that in this series we will not get to processes with continuous time - we will have to limit ourselves to discrete time ( econometrics approach).
Isn't it the same thing?
Continuous time can be reduced to discrete time by discretisation. Discrete time can be reduced to continuous time by interpolation (but nobody needs this in practice, because the tools for analysing the world around us (deduction techniques) are discrete).
I don't know what the whole cycle of your articles will be about, but if the articles will once again predict the price, no matter how - using statistics, theorising .... tambourine dancing...
then alas, it has been discussed 100500 times on this resource and on others, the result of these studies will be either the price is random in nature or there are patterns (on history), here you have it "on a platter"!
Trading is what price prediction is all about. You may not like the term, but that's essentially what it is. Simplified, you need to enter a trade for 1 bar, and you give a prediction before entering - up or down. You make a prediction (implicitly) that your trade will be profitable, otherwise you would not have opened it.
On the next bar the trade is closed, and you can evaluate the quality of your forecast (aka the quality of the trading system).