FIR filter with minimum phase - page 15
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
I finally found the file with the first lectures on econometrics.
We were taught matstatistics, and then almost the same thing, but under the name of "econometrics". In the first lecture the lecturer argued like this. I am quoting it because I think it will be interesting in this thread.
The mathematical statistics is a general mathematical science, applied in very many areas and only in economics has its personal name - econometrics. The reason for this attention is as follows.
In economics, the object and subject of control is human, whose participation makes the system uncertain, i.e. at some points in time the system behaves almost deterministically, at others stochastically, or usually a mixture of both. Uncertainty is the randomness in the timing of switching modes of operation of the system. Namely. The stochastic characteristics of the system change over time. There can be no talk of a normal law or stationarity. It is much worse: the parameters of distribution laws change, the distribution laws themselves change. These switches occur on limited samples - usually up to 50 observations. All this depends on external macroeconomic and political factors arising at uncertain points in time.
Because of this, a very limited number of smoothing tools are used in econometrics, as they do not solve the problem. For example, only Hodrick-Prescott and Kalman filters out of a huge variety of filters are realistically and widely applied. Econometrics focuses on the residual from the smoothing - the stochastic component. It is it that rules the forecasting error, and the uncertainty factors listed above make forecasting extremely difficult.
These circumstances have made econometrics an independent science and led to very limited borrowing from related sciences, even from statistics, not to mention DSP, radio electronics .....
More picture):
The picture is funny. Again, I'd advise you to paint it in bright colours and make it funny.
But again, where's the mat formalization? And if the picture is not for the mat formalization of the process, then (in your terms) forfeit?
EconModel:
some moments in time the system behaves almost deterministically, some moments stochastically or usually a mixture of both.
Personally, it reminds me a lot of quantum mechanics - mixed states, half-dead cats, etc. Although, by and large, the whole universe grows out of quantum mechanics, so there's that.)
But I ask again - where is the mat formalisation?
After you've drawn a nice full picture, we start to consistently neglect everything that we can't describe here and now. We get a simple mathematical model, load it into the computer, identify the parameters, enjoy the growing deposit))
In economics, the object and subject of control is human, whose participation makes the system uncertain, i.e. at some points in time the system behaves almost deterministically, at others stochastically, or usually a mixture of both. Uncertainty is the randomness in the timing of switching modes of operation of the system. Namely. The stochastic characteristics of the system change over time. There can be no talk of a normal law or stationarity. It is much worse: the parameters of distribution laws change, the distribution laws themselves change. These switches occur on limited samples - usually up to 50 observations. It all depends on external macroeconomic and political factors arising at uncertain points in time.
All of this is matstatistics. And not all economic processes are non-stationary.
Econometrics, is matstatistics with a mathematical apparatus simplified for economists to understand
The picture is funny. Again, I would advise you to paint it in bright colours and make it funny.
But again, where's the mat formalization? And if the picture is not for the mat formalization of the process, then (in your terms) forfeit?
After having drawn a nice full picture, we start consistently neglecting everything that we cannot describe here and now. We get a simple mathematical model, load it into the computer, identify the parameters, enjoy the growing deposit))
the conclusions from the scheme are simple - for a speculator to learn other people's decision-making methods, given their trading horizons as well. In order to do this, it is necessary to obtain information about these methods. How to get it and from where is a separate question. I don't have a general solution for it, but private ones (to determine the presence of some subset of methods in the market).
you cannot find them out. You know the methods used by kitchen participants; you don't know the market.
you cannot recognise them. You know the methods used by the kitchens, you don't know the market.
he can't draw the full picture - he wrote above. He doesn't know all or even the main market participants, he doesn't know how to formalise speculators and non-speculators, he doesn't know all or even the main analysis methods used by market participants (not kitchens, the market!) etc.
How do you know everything about me?)