R help - Sep 2010 - how to seperate " "? or how to do regression on each variable when I have multiple variables?

Dear All,

I have data which contains 14 variables. And I have to regress one of
variables on each variable (simple 13 linear regressions)

I try to make a loop and store only R-squared

 colnames(boston)
 [1] "CRIM"    "ZN"      "INDUS"  
"CHAS"    "NOX"     "RM"      "AGE"
 [8] "DIS"     "RAD"     "TAX"    
"PTRATIO" "B"       "LSTAT"   "MEDV"

name <-  colnames(boston)

r <- rep(0, 13)
for(i in 1: 13) {
  r[i] <- summary(lm(MEDV ~ name[i], data = boston))$r.squared
}

but this doesn't work because name have " " for each variable. How
to
remove " " for name of each variable?
Or do you know the way I can do regression MEDV on each variable?

Thank you ahead,
Soyeon

Try this:

lapply(names(boston), function(x)summary(update(lm(MEDV ~ 1, boston), ~
get(x))))

On Mon, Sep 20, 2010 at 2:03 PM, Soyeon Kim <yunni0731@gmail.com> wrote:
> Dear All,
>
> I have data which contains 14 variables. And I have to regress one of
> variables on each variable (simple 13 linear regressions)
>
> I try to make a loop and store only R-squared
>
>  colnames(boston)
>  [1] "CRIM"    "ZN"      "INDUS"  
"CHAS"    "NOX"     "RM"      "AGE"
>  [8] "DIS"     "RAD"     "TAX"    
"PTRATIO" "B"       "LSTAT"   "MEDV"
>
> name <-  colnames(boston)
>
> r <- rep(0, 13)
> for(i in 1: 13) {
>  r[i] <- summary(lm(MEDV ~ name[i], data = boston))$r.squared
> }
>
> but this doesn't work because name have " " for each
variable. How to
> remove " " for name of each variable?
> Or do you know the way I can do regression MEDV on each variable?
>
> Thank you ahead,
> Soyeon
>
> ______________________________________________
> R-help@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.
>


-- 
Henrique Dallazuanna
Curitiba-Paraná-Brasil
25° 25' 40" S 49° 16' 22" O

	[[alternative HTML version deleted]]

Hi Soyeon,
Here are a few options:

## Use get() to find the predictor
r <- rep(0, 13)
for(i in 1: 13) {
 r[i] <- summary(lm(MEDV ~ get(name[i]), data = boston))$r.squared
}

## Use as.formula(paste()) to construction the model
for(i in 1: 13) {
 r[i] <- summary(lm(as.formula(paste("MEDV ~ ", name[i],
sep="")),
data = boston))$r.squared
}

## Just square the correlations (this is how I would do it)
r <- cor(boston)["MEDV",]^2

Best,
Ista
On Mon, Sep 20, 2010 at 1:03 PM, Soyeon Kim <yunni0731 at gmail.com>
wrote:
> Dear All,
>
> I have data which contains 14 variables. And I have to regress one of
> variables on each variable (simple 13 linear regressions)
>
> I try to make a loop and store only R-squared
>
> ?colnames(boston)
> ?[1] "CRIM" ? ?"ZN" ? ? ?"INDUS" ?
"CHAS" ? ?"NOX" ? ? "RM" ? ? ?"AGE"
> ?[8] "DIS" ? ? "RAD" ? ? "TAX" ? ?
"PTRATIO" "B" ? ? ? "LSTAT" ? "MEDV"
>
> name <- ?colnames(boston)
>
> r <- rep(0, 13)
> for(i in 1: 13) {
> ?r[i] <- summary(lm(MEDV ~ name[i], data = boston))$r.squared
> }
>
> but this doesn't work because name have " " for each
variable. How to
> remove " " for name of each variable?
> Or do you know the way I can do regression MEDV on each variable?
>
> Thank you ahead,
> Soyeon
>
> ______________________________________________
> 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.
>


-- 
Ista Zahn
Graduate student
University of Rochester
Department of Clinical and Social Psychology
http://yourpsyche.org