The Sultonov Regression Model (SRM) - claiming to be a mathematical model of the market. - page 2
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
Because of your persistence, I have to start by demonstrating the predictive capability of the model by analysing the function Y=tgx and introducing the first 8 pairs of digits:
Did you even read exactly what I wrote - and the input parameters (price) have a normal distribution? And this data is price?
Due to your stubbornness, I have to start by demonstrating the predictive ability of the model by analysing the function Y=tgx and introducing the first 8 pairs of digits:
Don't pay attention to normality - that's DEMI's personal opinion.
Go back to your plan.
Where did the analytical line get the error from?
Did you even read exactly what I wrote - and the inputs (price) have a normal distribution? And this data is price?
Don't be fooled by normality, it's going to be fun here without you.
Don't be fooled by normality..........
You've been demoted from econometrician to accountant. Shame on you!
I politely refer such bosses to their mammoth contemporaries, Box and Jenkins. They didn't require normality back then and were able to predict, well, abnormal series.
Although I'm not always polite, by the way.
You've been demoted from econometrician to accountant. Shame on you!
Don't defame accounting.
A normal distribution law is needed in order to (sharing my knowledge):
1. MNC - estimates satisfy Gauss-Markov conditions;
2. When we investigate the residual component, by the resulting model, i.e. e(i)=Y(i)-Ymodel(i), to prove that e(i) is Gaussian noise, i.e. the residual(error) will be stationary, as it is white noise, in fact it is a guarantee that forecasting by Ymodel, we will continue to trust.
Now on RMS.
1. Is the ISC being used here?
2. Is it a question of model residuals?
faa1947 hi!)
All the basic assumptions of correlation and regression theory are based on the assumption that the data under study is normally distributed. Do your inputs (price) have a normal distribution?
Well am I right my friend?
yes absolutely!
faa listen, so normality is not needed, stationarity is not needed, and why the model has no predictive value is not clear....
yes absolutely!
faa listen, so normality is not needed, stationarity is not needed, and why the model has no predictive value is not clear....
Have you read the article, on Sultanov's model? Is there an ISC there, I'm just not aware of it?) Two points are described by ISC and Residuals.
By the way about stationarity you're wrong, faa muses on cointegration (paired trading is based on it, in my opinion, well he will speak for himself, I spoke for myself).