Why is the normal distribution not normal? - page 12
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
What dispersion has brought people to. It's horrible! :)
xxx:
You'd have to work so hard editing a maths textbook to read 'Dispersion' instead of 'Depression'.
xxx:
- why are you in variance today?
- xxx: ah, I have such a standard deviation today...
Then it simply has nothing to do with the mentioned laureate. It also has nothing to do with the topic under discussion (I suppose Sergei meant increments of the form x(n)-x(n-1), similarly for models, including ARCH). As for your example, when I have free time I'll have a look at it. By the way, if it's not a problem for you, could you post the material, it's really interesting.
Why it may not? Yes it does and it is direct. The series x(n)-x(n-1) modulo will be as autocorrelated as the ARCH model uses. The volatility (variance) is run based on the previous increments (actually modulo) with some weighting factors. The model of course says nothing about the direction of the increments. You've provided the link yourself.
Who will carry out a comparative analysis of the returns series and eurusd series?
Immediately after the analysis, I will post how the synthetic series was obtained (not for the sake of luring, but just for objectivity).
The file attached is 20000 data long.
I forgot to upload it. :о)
PS series is presented in pips i.e. integers
GSH timeseries
Why not? It does, and directly. The series x(n)-x(n-1) modulo will be as autocorrelated as the ARCH model uses. The volatility (variance) is run based on the previous increments (actually modulo) with some weighting coefficients. The model of course says nothing about the direction of the increments. You've provided the link yourself.
Not really. Your resulting series doesn't carry any "information" about the past. In other words, try taking the series |Open(n)-Close(n)|-|Open(n-1)-Close(n-1)| and see its correlation.
PS: I suggest you listen to our arguers. It's so weird, we argue and they don't :o)
Already something and apart from the pictures will there be a comparison with the real row?
Already something and apart from pictures will there be a comparison with the real range?
What do you mean by a real range? i.e. a real range of prices?
What do you mean by real series? i.e. real price series?
Well, yes, but not the price but the first difference, we are talking about a model of real quotes, so we need to compare with them.
It seems to be already found out that the real series has non-normal distribution.
Now we should adjust the synthetics in such way, that it has similar parameters to the differences of the quotes.
Then we can say that we are close to knowing what processes take place during the formation of a series of quotes.
Yes, but not the prices, but the first difference, so we are talking about a model of real quotes and we need to compare with them.
We have already found out that the real series has a non-normal distribution.
Now we need to fit the synthetics so that it would have similar parameters to the quote differences.
Then we may say that we are close to the idea of what processes are taking place during the quotes series forming.
I don't care how old you are.
It's just that when it comes to putting real money on the table, people like you are quick to sidestep the conversation.
And when you nail them, they start stinking and squealing. You're a wimp.
P.S. okay, I can't win my 5 grand, morons like Neutron and Urain just don't have it .
Because that's the kind of thing only morons can say.
I'm ready to apologise and pay $10,000 ($5,000 each) if they prove Neutron was right.
You're just pissed off that no one wants to communicate with you, and why should anyone want to communicate with you that you bring to the forum other than your ponzi scheme.