Compile all data produced by rolling regression into one - r

Question

I am doing a rolling regression with a huge database, and the reference column used for rolling is called "Q" with the value from 5 to 45 for each data block. At first I tried with simple codes step by step, and it works very good:
fit <- as.formula(EB~EB1+EB2+EB3+EB4)
#use the 20 Quarters data to do regression
model<-lm(fit,data=datapool[(which(datapool$Q>=5&datapool$Q<=24)),])
#use the model to forecast the value of next quarter
pre<-predict(model,newdata=datapool[which(datapool$Q==25),])
#get the forecast error
error<-datapool[which(datapool$Q==25),]$EB -pre
The result of the code above is:
> head(t(t(error)))
[,1]
21 0.006202145
62 -0.003005097
103 -0.019273856
144 -0.016053012
185 -0.025608022
226 -0.004548264
The datapool has the structure below:
> head(datapool)
X Q Firm EB EB1 EB2 EB3
1 1 5 CMCSA US Equity 0.02118966 0.08608825 0.01688180 0.01826571
2 2 6 CMCSA US Equity 0.02331379 0.10506550 0.02118966 0.01688180
3 3 7 CMCSA US Equity 0.01844747 0.12961955 0.02331379 0.02118966
4 4 8 CMCSA US Equity NA NA 0.01844747 0.02331379
5 5 9 CMCSA US Equity 0.01262287 0.05622834 NA 0.01844747
6 6 10 CMCSA US Equity 0.01495291 0.06059339 0.01262287 NA
...
Firm B(also from Q5 to Q45)
...
Firm C(also from Q5 to Q45)
The errors produced above are all marked with "X" value in "datapool", so I can know from which firm does the error come from.
Since I need to run the regression for 21 times (quarters 5-24,6-25,...,25-44), so I do not want to do it manully, and have thought out the following codes:
fit <- as.formula(EB~EB1+EB2+EB3+EB4)
for (i in 0:20){
model<-lm(fit,data=datapool[(which(datapool$Q>=5+i&datapool$Q<=24+i)),])
pre<-predict(model,newdata=datapool[which(datapool$Q==25+i),])
error<-datapool[which(datapool$Q==25),]$EB -pre
}
The codes above works, and no error come out, but I do not know how to compile all errors produced by each regression into one datapool automatically? Can anyone help me with that?

Answer 1

(I say again: Really bad idea to use the name 'error' for a vector.) It is the name of a core function. This is how I would have attempted that task. (Using the subset parameter and indexing than the tortured which statements.
fit <- as.formula(EB~EB1+EB2+EB3+EB4)
pre <- numeric(len=21)
errset <- numeric(len=21)
for (i in 0:20){
model<-lm(fit,data=datapool, subset= Q>=5+i & Q<=24+i )
pre[i]<-predict(model,newdata=datapool[ datapool[["Q"]] %in% i:(25+i), ])
errset[i]<-datapool[25+i,]$EB -pre
}
errset
No gaurantees this won't error out by running out tof data at the beginning or end since you have not offered either data or a comprehensive description of the data-object.