Remembering veterans: Box and Jenkins - page 9
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
That's weird. At first it was all about them. Turns out they weren't even needed here at all. Then what is the point of this thread?
AVALS asks about filling the model: what to predict and has an opinion on it. Box and Jenkins don't write what to forecast (level, increment, risk or something else), it's about the rules of ARMA model development. For myself personally, I learnt from the thread about testing. It used to be emotion, now it's the result of a unit root test.
That's weird. At first it was all about them. Turns out they weren't even needed here at all. Then what's the point of this thread?
faa1947: Боремся с нестационарностью чтобы быть уверенным в прогнозе. Что прогнозировать - определяет Ваша модель, Ваша зависимая переменная, а не Бокс и Дженкинс.
I don't know about your model, but our model should predict profits in the form of trades ))))
Predicting the price series is a theory. The practice is deals. Preferably profitable ))))
As the Chinese proverb says, it makes no sense to look for meaning in what does not make sense.
Once again. Struggling with non-stationarity to be sure of the prediction. What to predict is determined by your model, your dependent variable, not Box and Jenkins.
How does non-stationarity interfere with you?
How does unsteadiness bother you?
faa1947 Let's take EURUSD quotes, for example m15. Replace each day's candle at 15:45 with the same candle - for example Close-Open=20 pips. Or direction depending on the trend: +20 if last hour has passed more than 0 pips, and -20 otherwise.
We measure the non-stationarity of the whole series or series of increments. Take any test - it will show exactly the same as on the initial series of the unsteady EURUSD. That said, there is not even a probabilistic relationship on the second chart, but an unsteady relationship. Just a grail on the unsteady series :) And there is no need to bring the whole series to a stationary one.
On the example of mash-ups: residual = cotier - f1 - f2, where f is the value of the two averages.
But your question has stumped me.
Would it probably be more appropriate: price - f1 + f2? Because in your case the trade signal must be triggered at the level of the sum of two averages, i.e. the price must cross the level at the height of about two prices for the signal to change its sign.
If it is more correct to assume that the residuals between the TS and the quote for the case of two masks crossing, where: price is the current price, f1 and f2 are the last readings of two muvings with different periods and the formula: residuals = price - f1 + f2, then we obtain that the residuals are Equity, assuming that the spread is zero.
And if this is the case, then your statement, and I quote:
You can only trust the test and the forward test if the residuals = kotir - the TS is stationary! i.e. passes the unit root test.
is absurd. Absurd because:
1. Whether there are stationary equities for CU, I don't know, as I have never seen any stationary equities yet.
2. Stationarity implies no trendiness, i.e. such a BP is a perfect sideways move. If equity is stationary and stationary BPs have MO = Const, this very MO will be around the initial deposit.
So, don't engage in epigonism, but learn the maths - it rules. And give up worshipping such tricks, as Boxes and Jenkinsons - sectarianism has not brought anyone good, apart from the founders of the sects. However, some of the founders didn't end well either.
faa1947 Let's take EURUSD quotes, for example m15. Replace each day's candle at 15:45 with the same candle - for example Close-Open=20 pips. Or direction depending on the trend: +20 if it has gone over 0 pips in the last hour, and -20 otherwise.
We measure non-stationarity of the whole series or series of increments. Take any test - it will show exactly the same as on the initial series of the unsteady EURUSD. That said, there is not even a probabilistic relationship on the second chart, but an unsteady relationship. Just a grail on the unsteady series :) And there is no need to bring the whole series to a stationary one.
There is a lot of things that could be invented.
We are talking about very specific things that I understand and understand equally with millions of other people.
What you have described is so far a numbers game. Maybe correct, maybe not. You have not provided any evidence. Generally accepted deductions on stationarity and non-stationarity I have cited. I reply that my calculations are in line with the calculations that people have been using for 40 years.