regression - R - setting assessment criteria for regsubsets in leaps package -


I'm trying to make a regression using the best subset selection.

Here is the equivalent of what I'm doing based on chick white data from the dataset package as an example.

  leaps_test & lt; - Regsubsets (Weight ~ time + diet, data = chick white, nbest = 1)   

Still I want to be able to control that using the residual yoga classes (RSS) How is the best subset "evaluation done? If this happens, then Regsbates works by default, and I still want to know how to change this criteria, I want to evaluate on the basis of the criteria.

? Regsubsets.default Since this function returns the best models of all sizes till Nvmax and since different model selection criteria such as AIC, BIC, CIC, DIC, ... compared to the models of different sizes The results are different, the result cost-complexity is not dependent on the business option.

However, if you have different associated parameters, you can specify a different scale in conspiracy command.

plot.regsubsets

plot (x, labels = obj $ xnames, main = NULL, scale = c ("bic", "cp" "Adjr2", "r2"), col = gray (seq (0, 0.9, length = 10)), ...)

Comments

Popular posts from this blog

Pass DB Connection parameters to a Kettle a.k.a PDI table Input step dynamically from Excel -

multithreading - PhantomJS-Node in a for Loop -

c++ - MATLAB .m file to .mex file using Matlab Compiler -