Matstat Econometrics Matan - page 19
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
It's a clinic ))
That's right. Ward 3. On the first floor. "Crisis and Emergency Department")).
It's a clinic ))
Indeed it is!
Right. Ward 3. On the first floor. "Crisis and Emergency Department")).
Is this where they treat doctors?
Do they treat doctors here?
If you are a doctor, they treat doctors. And if you're a candidate, they treat candidates. We treat everyone. Don't worry.
I apologize to the author for the flood, but since most of the local rowdy's already checked in the branch, it's still doomed, unless a moderator comes and cleans up everything starting from about page five.
Constructive dialogue, I don't think, is flooding.
You just don't need to get personal and insult each other.
And also claim that one science is better than the other and you don't understand anything.
Exalting your knowledge in one area over another person's knowledge in another area.
That's very low and unprofessional. It's like when I was a kid, the expression, "snooty.
But childhood is long behind us, and we are adults now, and conduct a constructive dialogue more productively, without arrogance.
Treat each other with respect, because by and large there are not stupid people here.
That doesn't apply to you personally, it's a generalized statement of mine.
As for the topic, some educational institutions have been mentioned.
Here, trying to understand one of the fields, specifically "Quantitative Finance" from HSE, some questions arise.
That's why this thread was born. Has anyone taken the HSE training in quantitative finance?
Has anyone approached the GARCH series models and their modifications with transition functions?
Why do so many people here forget one simple truth, like correlation. Everything is equally or less dependent on each other. In finance all the more so.
Quantitative finance is the study of this. Some people here understand what I am writing about.
And who don't get it, yes, everyone is looking specifically for stationarity in models, their symbioses, multi-dimensional assets, etc.
And when a competent portfolio of assets is put together, then yes, whatever about fear, as has been expressed here that it does not exist, because it is mathematically excluded.
The mathematical expectation of the whole portfolio is zero. And if one asset rips, it should not affect the whole portfolio, but compensate with other assets.
This is the correlation of markets. I think there is no need to bring an analogy with nature, etc. Everyone understands what interrelation is.
You just need to apply it correctly. And to look at one SB and mush about it when there are a huge number of other models, I don't know why we are stuck in one place.
To continue the topic.
A lot of people here mention data thinning.
There is a method called PCA (Principal Component Analysis), which isone of the main ways to reduce the dimensionalityof the data while losing the least amount of information.
Has anyone studied this method? Any conclusions about its applicability?
I know that asset selection is thinned by this method. But I don't know if a dataset can be thinned by it without losing dimensionality.
As I see it, the main problem with thinning is dimensionality reduction. That is, the sample becomes a different size.
In a simple case, there are recommendations from the same lecturers of universities, not to throw out an element from a set, and replace it with an average value of neighboring elements for example.
At least this is how outliers are removed, in the simple approach. But with a caveat that there are other approaches, which are not explained.
Therefore PCA as a thinning idea, can be well investigated.
P.S. Clever site links, even finds articles on a similar topic
Oh how ))
Look what an interesting hook I found on foreign sites.
This is a translation of an article from bourgeois.
And the maximization function turns into a cost function ))
Maybe the example that I sent you works on the principle of likelihood after all?
There are derivatives there too. Have you seen the getCost function?
Or in getCost, it is not much of a calculation?
Look what an interesting hook I found on foreign sites.
This is a translation of an article from bourgeois.
And the maximization function turns into a cost function ))
Maybe the example that I sent you works on the principle of likelihood after all?
There are derivatives there as well. Have you seen the getCost function?
Or maybe the getCost function has a different calculation?
The standard approach in optimization is to multiply the target by minus and maximization turns into minimization (and vice versa).
Already tried to explain to you that if the errors are Gaussian distributed, then MNC==MLE. If the errors are distributed by Laplace, thenMNC==MLE==MLE method of least moduli. You can figure out for yourself the type of error distribution whenMLE==MLE by Huber.
In experiments, the type of error distribution is either known by some additional consideration, or it is chosen experimentally (usually in the form of a suitable loss function).