Skip to content
Back to formatted view

Raw Message

Message-ID: <DB85D372832A8947A36106275ABC2BDC0161EDB8@EXCHF3.lse.ac.uk>
Date: 2012-09-20T12:09:21Z
From: C.Steinwender at lse.ac.uk
Subject: Quantile regression with large number of fixed effects

Dear R users, 

I am trying to estimate a median regression with fixed effects. I have an unbalanced panel data set with 5,000 individuals and 10 years, resulting in a total of 20,000 observations.

When I try to add individual (firmid) fixed effects to the quantile regression using the following command:
result<-rq(y~x+factor(firmid),tau=0.5)

I get the following error message: 
"Error: cannot allocate vector of size 536.9 Mb"

I assume this has to do with the large number of fixed effects (because it worked when I only used year fixed effects). I have already set the memory to the (I believe) maximum limit using 
memory.limit(4000)

What can I do to implement this regression in R? 

Many thanks in advance,

Claudia

Please access the attached hyperlink for an important electronic communications disclaimer: http://lse.ac.uk/emailDisclaimer