Skip to content

Dropping predictor variables based on adjusted R square

2 messages · Shivi82, Jim Lemon

#
Hello experts,

I have recently (1month) started using R. Earlier I was using SAS to work on
analytic assignments. 
In SAS there is an option - forward selection, backward selection, step wise
selection where in it removes the least impacting predictor variable from
the set  of variables based on adjusted r square and leaves us with the
highest impacting variables to predict.
Is there any similar functionality or function in R studio. Kindly suggest.
Thanks.  



--
View this message in context: http://r.789695.n4.nabble.com/Dropping-predictor-variables-based-on-adjusted-R-square-tp4707186.html
Sent from the R help mailing list archive at Nabble.com.
#
Hi Shiv82,
For a start, look at the "step" function in the stats package. There
are a number of functions in other packages that offer different
variable selection procedures.

Jim
On Thu, May 14, 2015 at 9:35 PM, Shivi82 <shivibhatia at ymail.com> wrote: