R help - Mar 2005 - calling objects in a foreloop

I want to organize outputs from several regressions into a handy table.  When I
try the following, each of my "fit_s" is replaces instead of read.  Is
there a
way to read from the regression summaries that does not require writing
separate lines of code for each?
-Ben Osborne
> fit1<-lm(dBA.spp16$sp2.dBA.ha~dBA.spp16$sp1.dBA.ha)
> fit2<-lm(dBA.spp16$sp3.dBA.ha~dBA.spp16$sp1.dBA.ha)
> fit3<-lm(dBA.spp16$sp3.dBA.ha~dBA.spp16$sp2.dBA.ha)
> fit4<-lm(dBA.spp16$sp5.dBA.ha~dBA.spp16$sp4.dBA.ha)
> fit5<-lm(dBA.spp16$sp6.dBA.ha~dBA.spp16$sp4.dBA.ha)
> fit6<-lm(dBA.spp16$sp5.dBA.ha~dBA.spp16$sp6.dBA.ha)
> fit7<-lm(dBA.spp16$sp1.dBA.ha~dBA.spp16$sp4.dBA.ha)
> fit8<-lm(dBA.spp16$sp1.dBA.ha~dBA.spp16$sp5.dBA.ha)
>
> dBA.spp16.fits<-matrix(NA, nrow=8, ncol=5)
>
colnames(dBA.spp16.fits)<-c("formula","intercept","slope","R^2","adj.R^2")
>
> for (i in 1:8){
+
dBA.spp16.fits[i,1]<-summary(as.name(paste("fit",i,sep="")))$call
+
dBA.spp16.fits[i,2]<-summary(as.name(paste("fit",i,sep="")))$coef[1,1]
+
dBA.spp16.fits[i,3]<-summary(as.name(paste("fit",i,sep="")))$coef[2,1]
+
dBA.spp16.fits[i,4]<-summary(as.name(paste("fit",i,sep="")))$r.squared
+
dBA.spp16.fits[i,5]<-summary(as.name(paste("fit",i,sep="")))$adj.r.squared
+ }
Error in "[<-"(`*tmp*`, i, 1, value = NULL) :
        number of items to replace is not a multiple of replacement length

# Because:
> i<-1
> summary(as.name(paste("fit",i,sep="")))
Length  Class   Mode
     1   name   name
>
-- 
Botany Department
University of Vermont
109 Carrigan Drive
Burlington, VT 05405

benjamin.osborne at uvm.edu
phone: 802-656-0297
fax: 802-656-0440

On Mon, 14 Mar 2005, Benjamin M. Osborne wrote:
> I want to organize outputs from several regressions into a handy table. 
When I
> try the following, each of my "fit_s" is replaces instead of
read.  Is there a
> way to read from the regression summaries that does not require writing
> separate lines of code for each?

Put the lm objects into a list rather than into separate variables, then 
you can loop or lapply() over the list.

fits<-vector("list",8)
fits[[1]]<-lm(dBA.spp16$sp2.dBA.ha~dBA.spp16$sp1.dBA.ha)
fits[[2]]<-lm(dBA.spp16$sp3.dBA.ha~dBA.spp16$sp1.dBA.ha)
etc

dBA.spp16.fits<-matrix(NA, nrow=8, ncol=5)
for (i in 1:8){
     summ<-summary(fit[[i]])
     dBA.spp16.fits[i,2]<-summ$coef[1,1]
     dBA.spp16.fits[i,3]<-summ$coef[2,1]
     dBA.spp16.fits[i,4]<-summ$r.squared
     dBA.spp16.fits[i,5]<-summ$adj.r.squared
}

Other things to note

1/  You can't put the formula into a numeric matrix
2/ lm(dBA.spp16$sp2.dBA.ha~dBA.spp16$sp1.dBA.ha) can be more elegantly 
written as
    lm(sp2.dBA.ha~sp1.DB.ha, data=dBA.spp16)


When you find yourself doing computations on the names of objects rather 
than on their values it is usually a bad sign.


 	-thomas