Zero sample correlation does not necessarily mean there is no linear relationship - page 18

New comment
 
HideYourRichess:
Shame on you, that's not what it was about.


I don't follow you...

I was talking about 'pipsqueak'.

 
HideYourRichess:

. No need to logarithm anything...

. The thing about standardisation is that it's strange. Why do you need it? ...

Well, if you don't know, you don't need it. And if you don't know, it's only natural that you don't need it.

But there are people who do know.

 
timbo:

If you don't know, you don't need it. And since you don't know, it's only natural that it doesn't give you anything.

However, there are people who do know.

There's no need to play dumb. Once again, there is no "physical" sense in standardisation. Because there are no conditions to carry out such standardisation. The same applies to the logarithm of prices.
 
HideYourRichess:
You don't have to be a fool about it. Once again, there is no "physical" sense in standardisation. Because there are no conditions to carry out such standardisation. The same applies to the logarithm of prices.
You're not explaining, you're just bluntly repeating what was said earlier. That adds nothing to the discussion. Just because you don't know or understand something doesn't make it wrong.
 
Well, what's there to explain? It's been said several times already - there must be a sense in any mathematical actions. You can't, say, compare warm and soft. How can it be explained even more precisely here - I just don't know, well you "can't" do it in our universe. The same applies to the question of "standardisation" and "logarithm".
 

By the way. One question has arisen. I still haven't seen the answer to it. Why is logarithmetic being done? (I mean prices).

 
Vinin:

By the way. One question has arisen. I still haven't seen the answer to it. Why is logarithmetic being done? (I mean prices).


The logarithm of price increments seems clear, while the logarithm of price is also unclear.

Logarithm in increments eliminates the effect of base change. When a share was 1 rouble and changed by several percents in a day, then after the share grew to 100 roubles, these few percents became roubles. Therefore comparing them (increments) in absolute terms makes no sense. You can do it in percentage terms, or logarithms

 
Avals:


The logarithm of price increments seems clear, while the logarithm of price is also unclear.

In increments, logarithm eliminates the effect of a change in basis. When a share was worth 1 rouble and changed by a few per cent in a day, then after the share rose to 100 roubles, these few per cent became roubles. Therefore comparing them (increments) in absolute terms makes no sense. You can do it in percentage terms or in logarithms.


I do understand that. I usually use the percentage of price change. I just wanted to know about the price itself.
 
Vinin:

That's pretty clear. I usually use a percentage of the price change. I just wanted to know about the price itself. Why?

So no one can guess it :)
 
Logarithms are used to establish explicitly that a quantity with a distribution resembling a normal distribution has a lower bound of zero. In deriving the Black-Scholes formula, it is assumed that the price distribution is lognormal, i.e. it is not the price that is normally distributed, but its logarithm.
1...111213141516171819202122232425...60
New comment