Econometrics: let's discuss the CU balance sheet. - page 20
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
If you have a globe glued to your ears with pages of your favourite formulas, that's no reason to call yourself a "down-to-earth person".
The approach is generally approved. What did Koshi do wrong? Can't fit in the globe? Well, take it off before it gets too big.
Either I'm stupid or you are.
Once again.
You are sitting at your computer, most likely MS, and you are told, let's switch to apple, it's a beautiful game (in koshi). You don't need Apple and especially not the game, you know, you don't need it. You have everything and there is a lot of interesting things you do not have time for. And you are offered to play with toys.
What is there to understand?
And if you are serious, give references to the application of Cauchy in trading. Any thought should start with a literature search. If you do it, you may get a very useful cointegration in your mind instead of Coshi.
Really hilarious. You have no idea...yep... The masters of mathematical drainage have got their naughty hands on cointegration as well :-)
(but... even if they find how to make a stationary curve and cointegrated by all rules - but...no way to figure out what to do with it :-) how to make a TC out of it :-)
And seriously, give references to the application of Cauchy in trading. Any thought should start with a literature search. If you do that, you might get a very useful cointegration in your head instead of Cauchy.
Faa. Please correct the "c" to "h" in your post. Because I want to put it in the annals and readers will think I'm buying a simple typo.
// Though it's a funny one in itself - Freud cries.
Faa. Please correct the "c" in your post with a "z". Because I want to put this in the annals, and readers will think I'm buying a simple typo.
// Although it's a funny one in itself - Freud cries.
It's not a typo - it's part of the dissertation manual. The first chapter is an Overview of Literature.
This is not a typo - it is part of the dissertation guidelines. The first chapter is the Literature Review.
Ah, shit. That's even funnier. Posted.
Good for you.
The concept of correlation is dealt with in detail in correlation analysis, regression analysis, and since these are very close things, sometimes called regression-correlation analysis. These are the textbooks. It's chewed up, even in this thread Avals has made remarks about it. The main thing is don't take it out of the annals.
.
An Eskimo enters a literary institute. They ask him: Have you read Pushkin? - No. Have you read Gogol? - No, but have you read Tolstoy? - To which the Chukcha replies: The Chukcha is a writer, not a reader.
.
Congratulations to all the writers on behalf of the readers. Let's go, guys, get on the bikes, the main thing is to ride with your head held high, so it'll be funnier.
Congratulations to all the writers on behalf of the readers. Come on guys, get on your bikes, the main thing is to ride with your head held high so it's funnier.
Okay, thank you.
Good luck with your thesis.
I understand when Avals gets stuck, but I can't explain everything to everyone - take the same Expert Advisor, run it on the same story but with a smaller lot and get an equity increase of about 2% over the whole period and get a STATIONARY EQUITY RANGE!
In short, a literacy.
Stationarity is (among other things) the invariance of the distribution of a random variable (e.g. MO) over time. Generally speaking, for each moment of time the MO is different, but if all values at each moment coincide, then the series is stationary (let it be so, I deliberately simplify by omitting the higher moments). It is defined by MO at each moment not by averaging over the given realization (on the time interval from 0 to T), but by averaging over the ensemble of all possible realizations - until we prove that the process is ergodic, which we will not prove, because, for example, a non-stationary process cannot be ergodic at all - and it is (non)stationarity we are trying to find out.
We have two series here. The first, the initial one, is the equity itself, let it be E. It is the cumulative sum of the other series, the sequence of daily earnings P. Accordingly, the second series is the first difference of the first series. The series P is stationary because the daily earnings are constant on average, i.e. the expectation of earnings tomorrow is always the same for us, let it be 10 rubles.
Now to the series E. Suppose we have 100 rubles in our account. What is the expectation of the value of E tomorrow? Correct, 100+10=110 rubles as equity increases by this amount on the average each day. In other words, expectation of equity for the TS increases by RUB 10 per day, i.e. it is not constant over time and the series is non-stationary. In econometrics and in general in applied statistics, such series are called integrated time series of order 1 and are denoted by I(1).
Phew, I hope I've made it clear.
In short, a literacy lesson.
Stationarity is (among other things) invariance of indicators of distribution of a random variable (e.g. MO) in time. Generally speaking, for each moment of time the MO is different, but if all values at each moment of time coincide, then the series is stationary (let it be so, I deliberately simplify by omitting the higher moments). It is defined by MO at each moment not by averaging over the given realization (on the time interval from 0 to T), but by averaging over the ensemble of all possible realizations - until we prove that the process is ergodic, which we will not prove, because, for example, a non-stationary process cannot be ergodic at all - and it is (non)stationarity we are trying to find out.
We have two series here. The first, the initial one, is the equity itself, let it be E. It is the cumulative sum of the other series, the sequence of daily earnings P. Accordingly, the second series is the first difference of the first series. The series P is stationary because the daily revenue is constant on average, i.e. the expectation of revenue tomorrow is always the same for us, let it be 10 rubles.
Now to the series E. Suppose we have 100 rubles in our account. What is the expectation of the value of E tomorrow? Correct, 100+10=110 rubles as equity increases by this amount on the average each day. In other words, expectation of equity for the TS increases by RUB 10 per day, i.e. it is not constant in time and the series is non-stationary. In econometrics and in general in applied statistics, such series are called integrated time series of order 1 and are denoted by I(1).
Phew, I hope I've made it clear.
Why so many letters?
1. No one touches ergodicity. And you do not need to touch it - so now it all gets into such thickets....
2. stationarity means constancy of MO
3. In practice, MO values cannot coincide - this is not a fairy tale, but real life. Therefore for stationarity it is enough to change the MO within certain limits
4. "by averaging over an ensemble of all possible realisations" - I wrote above.... Well, you can't "spell it out" without reading exactly what you are "spelling out". There are no implementations - there is only one implementation. Focus on an example - ONE implementation. ONE.
5. Once again I explain what to do in this case - chop a row, compare MOs if not different within 3 - 5% stationary.
6. the first difference - I don't need it. Maybe someone needs it, but not me. Maybe I don't need it. Or maybe I do need it - maybe, but not for this example.
We worked our jaws vigorously, but why?