Discussion of article "Calculating the Hurst exponent"
It was like I was in an upside down world and the code was now being executed from the bottom up instead of top down:
void OnStart()
{
double close[]; //Declare dynamic array of closing prices
int copied=CopyClose(symbol,timeframe,0,1001,close); //copy the closing prices of the selected pair to the
//array close[]
ArrayResize(close,1001); //make an array
ArraySetAsSeries(close,true);
if(bars<1001) //create the condition of 1001 bars of history
{
Comment("Too few bars are available! Try another timeframe.");
Sleep(10000); //delay the inscription for 10 seconds
Comment("");
return;
}
...
Wow, just when you start to work on a topic and then you get an article on it... cool, thanks :)
But, this is a little wrong way, wrong understanding of the essence of forecasting on fractals, one hirst will not give anything at all, everything is much more complicated.
And the second part is an advert at all... well, how can it be so :(
Very interesting. Thank you to the author. And it would be possible to show an example of not only research in the past, but also the subsequent application. Having established a correlation on past data, we need to understand how it lives on in the future.
Wow, just when you start to work on a topic and then you get an article on it... cool, thanks :)
But, this is a little wrong way, wrong understanding of the essence of forecasting on fractals, one hirst will not give anything at all, everything is much more complicated.
And the second part is an advert at all... well, how could it be :(
Maxim, thanks for your comment!
Yes, you are right, of course the calculation of the Hurst coefficient is just a base to get at least a slightest idea about the application of some kind of mat statistics in the study of time series. I support your remark and I also think that it would be naive and wrong to use only coefficient analysis for forecasting market dynamics. Of course, it is necessary to build a strategy on the basis of aggregate indicators and using various indicators and sources.
In the next article I will definitely show you my correct understanding of fractal analysis.
Thanks again for your comment.
P.S. I was asked to make a review of the MT5 tools for such analysis. I took the opportunity to promote it.
I am not personally embarrassed by advertising. Where without it nowadays. It is everywhere now. Who prevents you from putting internal filters.
An extremely weak article that could have been a term paper 30 years ago.
If you read the article, it completely leaves out the modern state of affairs related to Hurst.
For some reason, the author believes that this coefficient can be estimated by ANC, and that there are no other methods of estimation in this case.
For example, the FGN package with the HurstK(z) function, in which non-parametric estimation of the Hurst coefficient is performed, which gives a much more accurate value.
If the author had bothered to do a literature review in this area, he would not have passed by the classic paper that in particular introduces the concept of fractional ARIMA, which allows us to consider the Hurst coefficient not only as such, but within the framework of appropriate models, moreover the author would have seen that there are packages in R that have generalised the Hurst coefficient.
The Hurst coefficient outside the framework of models is of little interest and Hurst's ideas were developed within the framework of fractionally differentiated models - Fractionally differentiated ARIMA aka ARFIMA(p,d,q) models
The fracdiff package provides a fairly complete set of tools in this area.
And this is not all in the field related to the Hurst coefficient.
Once again I state that any articles in the field of time series processing without an appropriate review of the tools available within R look extremely ignorant with a lag of several decades
An extremely weak article that could have been a term paper 30 years ago.
If you read the article, the current state of affairs related to Hurst is completely left out of the picture.
For some reason, the author believes that this coefficient can be estimated by ANC, and that there are no other methods of estimation in this case.
For example, the FGN package with the HurstK(z) function, in which non-parametric estimation of the Hurst coefficient is performed, which gives a much more accurate value.
If the author had bothered to do a literature review in this area, he would not have passed by the classic paper that in particular introduces the concept of fractional ARIMA, which allows us to consider the Hurst coefficient not only as such, but within the framework of appropriate models, moreover the author would have seen that there are packages in R that have generalised the Hurst coefficient.
The Hurst coefficient outside the framework of models is of little interest and Hurst's ideas were developed within the framework of fractionally differentiated models - Fractionally differentiated ARIMA aka ARFIMA(p,d,q) models
The fracdiff package provides a fairly complete set of tools in this area.
And this is not all in the field related to the Hurst coefficient.
Once again I state that any articles in the field of time series processing without a proper review of the tools available within R look extremely ignorant with a lag of several decades
Come on... Sana Sanych... The only paper in 15 years that in any way reveals the calculation of the Hurst index. No matter how it's written, there's a code, you can figure it out by the code.
Unlike you, San Sanych, the author of the article knows how to calculate the Hurst index. And you? And you can only write some scraps from R. But with the appearance of such an expert. It is very annoying to see your comments everywhere, maybe you should somehow change your approach to the case...?
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use
New article Calculating the Hurst exponent has been published:
The article thoroughly explains the idea behind the Hurst exponent, as well as the meaning of its values and the calculation algorithm. A number of financial market segments are analyzed and the method of working with MetaTrader 5 products implementing the fractal analysis is described.
Thus, our hypothesis is confirmed, and the market demonstrates the considerable anti-persistent process on this horizon — the Hurst exponent H=0.490 which is almost three standard deviations lower than the expected value E=0.557.
Let's fix the result and use a slightly higher timeframe (H2) and accordingly twice smaller number of bars in history (1000 values). The results are as follows:
Author: Dmitriy Piskarev