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
On a random walk the best prediction is the current position. Einstein established this a hundred years ago.
If it is a random stray.
Taking the cotier difference = subtracting the previous observation from the current one. Graph:
Descriptive statistics
The probability that the distribution is normal = zero.
Calculate the number of negative and positive outliers:
Almost exactly in half.
I calculate the number of differences, followed by a difference of the opposite sign (loss), and the number of differences followed by a difference of the same sign (profit). Profit divided by loss = 0.96.
So what? Where's the trend? When forecasting, I highlight the deterministic component and extrapolate one step ahead. Everything above says nothing, or rather says that it is impossible to predict, because the information about the deterministic component of the quotient is lost.
A trend is a channel formed by price.
if you have the time and inclination -
make a model on history (let's say six months to a year ago)
unload the model to a TSV or txt file -
1.using quotes (if you want to use something else, also this (if it is not done from the quotes) - but for today
2.model (not for today but for the period when it was created)
The better and more complicated the model, the more interesting it is ...
I want to check something, as time will be ...
(keep the model if I get it then check it)
I added it while you were answering. One more time plz.
The trend is the channel formed by the price.
Once again:
A trend is a channel formed by price.
Then one more time.
When forecasting, I highlight the deterministic component (hastily called trend), which I extrapolate one step ahead. Everything above says nothing, or to be more precise, it says that it is impossible to make a forecast because we have lost the information about the deterministic component of the quote.
All my attempts to predict returns have come to nothing.
(save the model if I can do it later)
Yes the model for your kotir I wrote:
eurusd = c(1)* eurusd(-1) + c(2) * hp(-1) +c(3) * hp(-2)
where hp is the Hedrock-Prescott indicator.
That's the thing, there's nothing abstruse about it. It's a simple equation called regression. I have suggested many times on this forum to practice these regressions, and I take it upon myself to evaluate them and post the result.
When forecasting, I highlight the deterministic component (I hastily call it a trend), which I extrapolate one step ahead.
Is the deterministic component some kind of average? Is it HP? And how does the prediction of the average help in trading? We trade on prices, not on averages, and there is enough difference between the former and the latter to make a profit.
where HP is the Hedrock-Prescott indicator.
I see.... thought there was something else...prescot isn't interesting...