[R] adding observations to lm for fast recursive residuals?
ivo_welch-rstat8783@mailblocks.com
ivo_welch-rstat8783 at mailblocks.com
Wed Sep 15 16:53:56 CEST 2004
dear R community: i have been looking but failed to find the
following: is there a function in R that updates a plain OLS lm()
model with one additional observation, so that I can write a function
that computes recursive residuals *quickly*?
PS: (I looked at package strucchange, but if I am not mistaken, the
recresid function there takes longer than iterating over the models
fresh from start to end.) I know the two functions do not do the same
thing, but the main part (OLS) is the same:
> handrecurse.test <- function( y, x ) { z<- rep(NA, T); for (i in
2:T) { z[i] <- coef(lm(y[1:i] ~ x[1:i]))[2]; }; return(z); }
> system.time(handrecurse.test(y,x))
[1] 0.69 0.00 0.70 0.00 0.00
> system.time(length(recresid( y~x )))
[1] 1.44 0.07 1.59 0.00 0.00
pointers appreciated. regards, /iaw
---
ivo welch
More information about the R-help
mailing list