Machine learning in trading: theory, models, practice and algo-trading - page 3340

New comment
 

A wonderful book as a monument to shamelessness and unscrupulousness!

The main thing is to hang up your plate and crow - you will find suckers (or maybe very calculating people), who will fall for the plate, not understanding, or realising that everything that is presented is well known from mathematical statistics tools.

Statistics is several thousand years old. Developing and enriching mathematical statistics, observing random processes around us, tried to answer the following questions;

1. What are the characteristics of these random processes?

2. What are the causes of these random processes?

3. What is the future of these random processes?

Now there are clever guys who start shouting about "causal inference" as an explanation of the meaning of this innovative term in all seriousness and start popularly presenting the basics of regression analysis on the example of linear regression.

It's just mind-blowing!

And this new tableau for very old clauses is rolling!

Today in R, the only language for statistics that is well structured and documented, there are over 10,000 packages and over 120,000 functions that are tools for answering the above questions, one of which is to find out Causes and Consequences.

Why do we need new plates? So that the clever guys can cash in and not be asked stupid questions about having a basic education.

 
Well, then answer the simplest question: how does associative connection differ from causal connection, since you know everything? And then we'll decide who to put a monument of shamelessness or shame on :)

And finding out causes and effects is not a causal conclusion, let me ask you? :)

So this adrenaline surge is connected with what specific problems of misunderstanding? What do you feel threatened by?
 
Maxim Dmitrievsky #:
Well, then answer the simplest question: how does associative connection differ from causal connection, since you know everything? And then we will already decide who to put a monument of shamelessness or shame on :)

And finding out causes and effects is not causal inference, let me ask you? :)

So this adrenaline rush is connected with what specific problems of misunderstanding? What do you feel threatened by?

Your "causal inference is shown in the first section of the book on the example of linear regression: everything that is written there is taught to students and many other things that the author did not bother to state, for example, the limits of applicability of linear regression, by the way, which is the most important thing.

So don't hide behind questions.

Let's be substantive.

Which chapter of the book does NOT use tools known in statistics (and available in R)?

Don't talk about meta-students - that's an ensemble of models, also an idea with a beard.

 
СанСаныч Фоменко #:

Your "causal inference is shown in the first section of the book on the example of linear regression: everything that is written there is taught to students and many other things that the author did not bother to state, for example, the limits of applicability of linear regression, by the way, which is the most important thing.

So don't hide behind questions.

Let's get to the point.

Which chapter of the book does NOT use tools known in statistics (and available in R)?

Don't talk about meta-students - that's an ensemble of models, also an idea with a beard.

Let's get to the point: What is the difference between an associative relationship and a causal relationship?

The author bothered to state the limits of applicability of linear regression. Minus point.

Meta learners are not an ensemble of models, minus a point.

What other section of the book do you disagree with, or rather what else did you not understand from the book?
 

After all, you weren't banned from google, were you? You can read how statistical inference differs from causal inference, right?

 
Maxim Dmitrievsky #:

After all, you weren't banned from google, were you? You can read how statistical inference differs from causal inference, right?

There's a clear association in the sequence "A", "B", "C".

 [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
 [1,] "l"  "y"  "A"  "v"  "B"  "C"  "s"  "n"  "u"  "z"  
 [2,] "p"  "x"  "a"  "n"  "A"  "B"  "j"  "y"  "d"  "C"  
 [3,] "A"  "B"  "e"  "a"  "r"  "w"  "C"  "f"  "z"  "q"  
 [4,] "d"  "s"  "q"  "c"  "w"  "A"  "B"  "k"  "z"  "C"  

How do I know it is an asociation and not a casuation or vice versa?

 
mytarmailS #:

There is a clear asociation in the form of the sequence "A", "B", "C".

How to understand that it is an asociation and not a casuation or vice versa

I don't know what the alphabet is or where there's a clear association.

 
Maxim Dmitrievsky #:

I don't know what the alphabet is or where the obvious association is here.

Each line is a new observation.

Each line has a repetition of A B C.

A B is associated with C.

 
mytarmailS #:

every line is a new observation

each line has a repetition of A B C

A B is associated with C

Well, at least compare the frequency of their occurrence with the frequency of co-occurrence of other letters, I guess. And the nature of the data has to be understood.

Does AB actually cause C to appear, or a set of other letters.

Especially since they're not consecutive.

 
Maxim Dmitrievsky #:

Does AB actually cause C to appear, or a set of other letters

Well that's the question, there is an asociation on the face of it...
How to understand if it's just an asociation or if AB actually causes C

1...333333343335333633373338333933403341334233433344334533463347...3512
New comment
Reason: