Possibility matrix for regression results

Excel Help for Possibility Matrix For Regression Results in Excel Multiple Regression Analysis and Forecasting Template

Possibility Matrix For Regression Results

Rate this: (4/5 from 2 votes)

	How does one create a decision model combining all regression results which also aids  addition/elimination of independet variables and helps to arrrive at a decision whther to go ahead with the predciiton or not and also other things like addition/elimination of variables. a minimum acceptance level (mathematical figure) could be part of this model and possibiltities listed. Im doing this because situations will arise like for eg R square > 85%  , P> 5 % , Correlation high between  one independent X1 and dependent Y, Collinearity is also high say > 70 % between X1 & X2, then what do we do??
	Posted by shaju304 on 22 Oct 2013

Replies - Displaying 1 to 2 of 2

Order Replies By: Most Recent | Chronological | Highest Rated

	Feature selection possibilities in the output Rate this: (4/5 from 2 votes) There are various methods for feature selection with the linear regression modeling. We have already been investigating possible solutions for this issue.   Currently, we can see the individual p-values and R-squared as well as R-squared matrix between the independent variables in the analysis. The most common approach to removing independent variables that are highly correlated with others is to do so one by one by removing the one with the highest R-squared in the multicollinearity matrix. As a secondary approach low value variables can be eliminated by evaluating the independent analysis. This is currently a manual process; however we are considering options to add automated feature selection based on broad sweeping rules in a future version.
	Excel Business Forums Administrator
	Posted by Excel Helper on 23 Oct 2013

Thank you Rate this: (4/5 from 2 votes) Hi. Well, im in need of such a matrix for my current business requirements.Ive got stuck in interpreting such possibilitites and arriving at a decision.Manually it would take me ages.Ive placed an enquiry for your software, its great because its well integrated onto excel. If you can build a customized solution for me, then it would be great. Im yet expecting a reply from your sales team.Im from Bombay, India. My business email [email protected] +91 9819619949 Kindly revert to me at the earliest.

Posted by shaju304 on 23 Oct 2013

Displaying page 1 of 1