[R-sig-Geo] Variables inside a for

Fernando Miguez miguez at illinois.edu
Tue Dec 2 03:11:01 CET 2008


Hi Raphael,

If you truly only need to run 4 regressions you might be less confused 
if you just do

test1 <- lm(TX01 ~ INCOME, data = database)
test2 <- lm(TX02 ~ INCOME, data = database)
test3 <- lm(TX03 ~ INCOME, data = database)
test4 <- lm(TX04 ~ INCOME, data = database)

If you need to do this 100 times it is not very practical. Here I'm 
going to assume that your data are in a data frame with the first 100 
columns being dependent variables and column 101 being the independent 
variable. Your first option is to select the component from the lm 
object you are interested in, let's assume the coefficients. Then

n <- 100
mat <- matrix(nrow=n,ncol=2)
for(i in 1:n){
mat[i,] <- lm(data[,i] ~ data[,101])$coef
}

The resulting matrix mat will hold the coefficients of the 100 
regressions. Again, if you really need the whole lm object then you 
could do the following

n <- 100
arr <- array(list(),c(1,n))
for(i in 1:n){
arr[[i]] <- lm(data[,i] ~ data[,101])
}

The resulting array will have the 100 lm objects, which you can then 
examine.

Hope this helps,

Fernando

Raphael Saldanha wrote:
> Hi!
> 
> I had a database with some variables in sequence. Let me say: TX01, TX02,
> TX03 and TX04.
> 
> But I need to run some regressions changing the variables... so:
> 
> variable <- paste("TX0", 1:4, sep="")
> 
> for(i in 1:4){
> test[i] <- lm(variable[i] ~ INCOME, data=database)
> }
> 
> But doesn't work... lm tries to find a variable inside database named
> variable[i] ...
> 
> Suggestions?
> 
> 
> King regards!
> 
> Raphael Saldanha
> Brasil
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 

-- 
Fernando E. Miguez
Energy Biosciences Institute
http://netfiles.uiuc.edu/miguez/www/




More information about the R-sig-Geo mailing list