O'Reilly logo

R Statistical Application Development by Example Beginner's Guide by Prabhanjan Narayanachar Tattar

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Model selection

The method of removal of covariates in the The multicollinearity problem section depended solely on the covariates themselves. However, it may happen more often that the covariates in the final model will be selected with respect to the output. Computational cost is almost a non-issue these days and especially for not-so-very-large datasets! The question that arises then is can one retain all possible covariates in the model, or do we have any choice of covariates which meet a certain regression metric, say R2 > 60 percent? The problem is that having more covariates increases the variance of the model which having lesser of them will have large bias. The philosophical Occam's Razor principle applies here, and the best model is ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required