[R] R-newbie-question, fixed effects panel model, large number of observations

From: Thomas Wilde <thomas.wilde_at_gmx.de>
Date: Sun 12 Feb 2006 - 03:21:19 EST


Hi,

I'm trying to fit a fixed effect (LSDV) panelmodel with R. I have a dataset with y as dependent, x1&x2 as indeps, t as time index and i as an id-variable for each individual. There are three observations for each individual (t=1, t=2, t=3).

I want to try a simple regression, but with individual intercepts:



# reading in some data ...

mydata <- read.csv(...)
attach(mydata)

# fit modell

mymodel <- lm(y ~ -1 + factor(i) + x1 + x2) summary(mymodel)


Works fine when the size of my dataset doesn't exceed about n=5000 observations, but I have some more. Can I do a partitioned regression with R, are there any other options already implemented in R ?

Thanks,
Thomas



R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Sun Feb 12 03:27:13 2006

This archive was generated by hypermail 2.1.8 : Fri 03 Mar 2006 - 03:42:27 EST