[R] vif

[arun]

Hi Eliza,

Then, "res" needs a slight modification


library(car)
 res<- lapply(colnames(h),function(x) {x1<- h[,x];dat1<- do.call(rbind,lapply(seq_len(ncol(mat1)),function(i){ x2<- m[,mat1[,i]];GG<- lm(x1~x2[,1]+x2[,2]+x2[,3]+x2[,4]);GGsum<- summary(GG); data.frame( Models=paste(colnames(x2),collapse=","), Multiple_Rsq= GGsum$r.squared, Adjusted_Rsq = GGsum$adj.r.squared, Pval = paste(GGsum$coef[-1,4],collapse=","),Vif=paste(vif(GG),collapse=","),stringsAsFactors=FALSE)  })); dat1[rev(order(dat1[,3])),][1:10,]})

names(res)<- colnames(h)
A.K.





________________________________
From: eliza botto <eliza_botto at hotmail.com>
To: "smartpink111 at yahoo.com" <smartpink111 at yahoo.com> 
Sent: Thursday, October 3, 2013 12:42 PM
Subject: vif



Dear Arun,
There is one small question however. 
what if i also want in the table a column for "vif" values of each model. 
vif values can be generated for any model in the following way

GG<-lm(h[,any column]~m[,any column]+m[,any other column] +m[,any other column] +m[,any other column])
library(car)
vif(GG)

Here will be get 4 "vif" values. I want to make a new column which could contain these values seperated by comma, very much similar to the way we did with Pr(>|t|) values.

thanks in advance

elisa


> Date: Thu, 3 Oct 2013 09:01:53 -0700
> From: smartpink111 at yahoo.com
> To: r-help at r-project.org
> Subject: Re: [R] a simple question
> 
> Hi,
> Try:
> 
> 
> set.seed(494)
>  h<- matrix(sample(1:40,4*124,replace=TRUE),ncol=4)
> 
>  set.seed(39)
>  m<- matrix(sample(1:100,10*124,replace=TRUE),ncol=10)
>  colnames(h)<- paste0("h",1:4)
>  colnames(m)<- paste0("m",1:10)
> mat1<-combn(colnames(m),4)
> 
>  res<- lapply(colnames(h),function(x) {x1<- h[,x];dat1<- do.call(rbind,lapply(seq_len(ncol(mat1)),function(i){ x2<- m[,mat1[,i]];GG<- lm(x1~x2[,1]+x2[,2]+x2[,3]+x2[,4]);GGsum<- summary(GG); data.frame( Models=paste(colnames(x2),collapse=","), Multiple_Rsq= GGsum$r.squared, Adjusted_Rsq = GGsum$adj.r.squared, Pval = paste(GGsum$coef[-1,4],collapse=","),stringsAsFactors=FALSE)  })); dat1[rev(order(dat1[,3])),][1:10,]})
> 
> names(res)<- colnames(h)
> 
> 
> A.K.
> 
> 
> 
> 
> 
> ________________________________
> From: eliza botto <eliza_botto at hotmail.com>
> To: "smartpink111 at yahoo.com" <smartpink111 at yahoo.com> 
> Sent: Thursday, October 3, 2013 11:07 AM
> Subject: a simple question
> 
> 
> 
> 
> Dear Arun,
> I hope you are fine. I actually
> wanted to discuss the following problem.
> I have a linear model of the
> following form. 
> GG<-lm(h[,any column]~m[,any
> column]+m[,any other column] +m[,any other column] +m[,any other column])
> where,
> h is matrix with 4 columns and
> 124 rows
> m is matrix with 10 columns and
> 124 rows
> what I want is the following
> make a loop command to run the
> linear model of all the possible combinations of columns of “m” with each
> column of “h”. 
> more precisely, if i take column
> 1 of matrix “h”, it should be linear modeled with every combination of 10 (210
> combinations) columns of “m”.
> All the columns of “h” & “m”
> have certain names (you can suppose any).  The summary(GG) will give Multiple R-squared,    Adjusted R-squared  and 4 values of Pr(>|t|). 
> I want in the end a table in the
> following format.
> 
> Models                                                                           Multiple R-squared        Adjusted R-squared       Pr(>|t|)
> Name of columns of m separated by
> comma      Multiple R-squared         Adjusted R-squared       Pr(>|t|) separated by comma
> 
> For Example 
> 
> Models                                                                           Multiple R-squared        Adjusted R-squared       Pr(>|t|)
> eliza, allen, murphy, jack                                                 0.544                                     0.56                         0.000114,0.000112,0.01114,0.002114
> 
> where,
> eliza, allen, murphy, jack are column names.
> 
> The models are to be enlisted in the order of their Adjusted R-squared values. The models with highest Adjusted R-squared value should be on the top and so on. i m only interested in top 10 models. so the remaining should be ignored. 
> 
> I tried to put in my question everything but if there is anything wrong plz inform me.
> 
> Thankyou very much in advance,
> 
> Eliza
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.