Quantcast

Multiple Linear Regression vs. Data Mining

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Multiple Linear Regression vs. Data Mining

manal alghamdi

Dear Weka List,

If I run MLR and found that some risk factors are not significant, but when I run them in Data Mining using e.g. Information gain they show that they are important and significant, would that be true?? Can Information Gain, correlation, or any other attribute evaluation show significance to some risk factors that were shown in the SPSS using Multiple Linear Regression.

Thanks

_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Multiple Linear Regression vs. Data Mining

Eibe Frank-3
No, the (standard) attribute ranking schemes in WEKA only measure the strength of the association between an attribute and the class, they do not test for statistical significance.

Cheers,
Eibe

On 29/12/2016 1:34 pm, "manal alghamdi" <[hidden email]> wrote:

Dear Weka List,

If I run MLR and found that some risk factors are not significant, but when I run them in Data Mining using e.g. Information gain they show that they are important and significant, would that be true?? Can Information Gain, correlation, or any other attribute evaluation show significance to some risk factors that were shown in the SPSS using Multiple Linear Regression.

Thanks

_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html


_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Loading...