Floating market parameters - page 3
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
You could say I've found a pattern - fluctuating around a 'fair price', now I'm picking up a suitable method.
Yep... except that it lags relative to the real price and there is no way to reliably detect it on the right side of the quotient. There is no way to predict it from the past because of the inevitable prediction error on the lag scale.
All evidence of stationarity you have conveniently overlooked
There is a picture like this:
What methodology can extrapolate a series like this?
Could someone put this into a neural network for an experiment?
How did you get this function?
It was a long time ago, I don't remember what I was looking for in the wavelets.
How did you get this function?
MathSin(2*Pi/(15+0.05*i)*i)
It was a long time ago, I don't really remember what I was looking for in the wavelets, I just attached what I had
Thank you
Now, colleagues, critique me.
I argue that any extrapolation implies that the time series (TP) has the property of "following" the chosen direction. Indeed, by extrapolating one step ahead by a polynomial of nth degree, we assume the NEED for the first derivative, the second... n-1 of the original series, at least at this step... Do you see where I'm going with this? Quasi-continuity of the first derivative is nothing but a positive autocorrelation coefficient (AC) of BP at the selected timeframe (TF). It is known to be pointless to apply extrapolation to Brownian-type BPs. Why? Because the CA of such series is identically equal to zero! But, there are GRs with negative QA... It is simply incorrect to extrapolate to them (if I'm correct) - the price is likely to go in the opposite direction from the predicted direction.
And for starters: Almost all Forex VRs have a negative autocorrelation function (this is a function constructed from the KA for all possible TFs) - this is a medical fact! The exceptions are some currency instruments on small timeframes, and yes Sberbank and EU RAO stocks on weekly TFs. This, in particular, explains the unsuitability in the modern market of the TS based on the exploitation of moving averages - the same attempt to extrapolate.
Unless I'm mistaken, wavelets, a priori, find themselves in an area where they will not be able to perform their functions correctly.
As far as I understand, you adhere to the "worldview" that the market is a Brownian motion?
But you can try to look at it from a human perspective. There are big players - they move the market, there are liquidity constraints (you cannot withdraw a large sum in a jiffy), there are cycles: financial year, quarterly reports, opening of exchanges, news background, etc. etc.
By the way, interesting to know your opinion on these things:
http://www.onix-trade.net/forum/index.php?s=c04e226e5521ed472b8d31770b40832b&showtopic=47&view=findpost&p=5267
http://www.chronos.msu.ru/RREPORTS/mikhailovsky_biol_vremya/mikhailovsky_biol_vremya.htm
Neutron:
And just as a snack: Almost all BPs in Forex have a negative autocorrelation function (this is a function constructed from CA for all the various TFs) - this is a medical fact!
This is not the first time I've read this statement of yours, but I've never seen proof of it. All the ACFs I have seen are normal ACFs. What does negative ACF mean and how is it worse than positive ACF? Could you give me an example on some cotier so I can replicate it.
Could you give me an example on some kind of quoter so I can replicate
We can.
We will look for the pairwise correlation coefficient between neighbouring samples of the time series. For the selected time frame we have one coefficient in the range from -1 to +1. The coefficient value less than zero indicates the presence of antipersistence between samples, greater than zero - persistence in this TF, close to zero - get out of here! In its turn, persistence serves as an indicator of trendiness/collapse of the symbol on the selected TF. The last property of BP allows to use adequate indicators of the TA.
The correlation coefficient is in a window of n - samples. In this case we used Minutes for 2010 and by thinning them we have built the artificial TF from 1 min to 100 min. n was taken as maximal (how many samples in a year). For each TF we found correlation coefficient and plotted the dependence of this value on TF. I meant exactly this dependence in the quote above.
Fig. shows the found dependence of the pair correlation coefficient for different instruments at different TFs. You can see that almost everywhere the coefficient is negative indicating that the price tends to return to its initial value after the disturbance. This property is more or less characteristic of all symbols and is most clearly seen at small TF (see fig.). I used Alpari's data of 2010.
The question is what to consider "close to zero". For estimation, you may multiply the correlation coefficient at the selected TF by the instrument volatility in points at this TF and compare the obtained value with the brokerage company commission (also in points). If it is larger than the spread, then you will not succeed anyway, because the market is not an ergodic system and as soon as you open a position, everything will change for the worse (for you only).