stats question about information gain in linear multiple regression - futures io
futures io futures trading



stats question about information gain in linear multiple regression


Discussion in Emini and Emicro Index

Updated by androiduser14916
    1. trending_up 697 views
    2. thumb_up 1 thanks given
    3. group 3 followers
    1. forum 2 replies
    2. attach_file 1 attachments




Welcome to futures io: the largest futures trading community on the planet, with well over 100,000 members
  • Genuine reviews from real traders, not fake reviews from stealth vendors
  • Quality education from leading professional traders
  • We are a friendly, helpful, and positive community
  • We do not tolerate rude behavior, trolling, or vendors advertising in posts
  • We are here to help, just let us know what you need
You'll need to register in order to view the content of the threads and start contributing to our community.  It's free and simple.

-- Big Mike, Site Administrator

(If you already have an account, login at the top of the page)

 
Search this Thread
 

stats question about information gain in linear multiple regression

(login for full post details)
  #1 (permalink)
Point Roberts, WA, USA
 
Experience: Advanced
Platform: IB and free NT
Broker: IB
Trading: ES
 
aquarian1's Avatar
 
Posts: 3,871 since Dec 2010
Thanks: 1,472 given, 2,480 received

I have a stats question on linear regression.

In working with my spreadsheet, I was looking for a predictive relationship between several "independent" (X) variables (for ES) to one "dependent" (Y).
A simple regression between X1 and Y gave R-squared=0.757.

A multiple regression (X1,X2, X3, X4, X5, X6, X7 to y gave R-squared=0.762.



1. Does this mean that the information gain of x2..x7 was almost nothing (and x1 is giving the bulk of the information)?
2. Should I be applying any of the functions below, and if yes, what help would they give?


------------------------------------
@CORREL calculates the correlation coefficient of values in range1 and range2.
@COV calculates the covariance of the values in two ranges.
@RSQ calculates the square of the Pearson product moment correlation coefficient. @fisher calculates the Fisher transformation of a value. @fisherINV calculates the inverse of the Fisher transformation.

Notes:
Correlation and covariance both measure the relationship between two sets of data. However, the correlation statistic is independent of the unit of measure, while the covariance statistic is dependent on the unit of measure.

Visit my futures io Trade Journal Reply With Quote

Can you help answer these questions
from other members on futures io?
Horizontal Line Indicator
Platforms and Indicators
PASPro won't show on a chart for certain combinations of ticks per bar and currencies
NinjaTrader
Need a near crosses scan help for TOS
ThinkOrSwim
How to place NT8 indicator output into a grid, under each bar?
NinjaTrader
EQIX - Digital REITs - any experiences?
Stocks and ETFs
 
 
(login for full post details)
  #3 (permalink)
New York
 
Experience: Advanced
Platform: NinjaTrader
Trading: ES
 
Posts: 16 since Jan 2014
Thanks: 0 given, 8 received



aquarian1 View Post
I have a stats question on linear regression.

In working with my spreadsheet, I was looking for a predictive relationship between several "independent" (X) variables (for ES) to one "dependent" (Y).
A simple regression between X1 and Y gave R-squared=0.757.

A multiple regression (X1,X2, X3, X4, X5, X6, X7 to y gave R-squared=0.762.



1. Does this mean that the information gain of x2..x7 was almost nothing (and x1 is giving the bulk of the information)?
2. Should I be applying any of the functions below, and if yes, what help would they give?


------------------------------------
@CORREL calculates the correlation coefficient of values in range1 and range2.
@COV calculates the covariance of the values in two ranges.
@RSQ calculates the square of the Pearson product moment correlation coefficient. @fisher calculates the Fisher transformation of a value. @fisherINV calculates the inverse of the Fisher transformation.

Notes:
Correlation and covariance both measure the relationship between two sets of data. However, the correlation statistic is independent of the unit of measure, while the covariance statistic is dependent on the unit of measure.


Check out multicollinearity.
BIC and akaike information criterion

Reply With Quote
The following user says Thank You to androiduser14916 for this post:


futures io Trading Community Traders Hideout Emini and Emicro Index > stats question about information gain in linear multiple regression


August 4, 2018


Upcoming Webinars and Events
     



Copyright © 2020 by futures io, s.a., Av Ricardo J. Alfaro, Century Tower, Panama, +507 833-9432, info@futures.io
All information is for educational use only and is not investment advice.
There is a substantial risk of loss in trading commodity futures, stocks, options and foreign exchange products. Past performance is not indicative of future results.
no new posts