[R] lags and differences

Prof Brian Ripley ripley at stats.ox.ac.uk
Tue May 11 20:47:50 CEST 2004


Lags apply to time series, and are ignored by lm.  You need to do 
something like

    dat <- ts.intersect(y1=diff(y), x1, x11 = lag(x1,-1), dframe=TRUE)
    lm(y1 ~ x1 + x11, data=dat)

On Tue, 11 May 2004, fciclone wrote:

> Dear all, could someone please clarify me if this 
> works, so as to implement lags and differences for 
> example in y and in a independent x1 of a  regression?
> 
> model<-lm((diff(y), -i)~x1+lag(x1,-1), data=anydata)

And DON'T tag onto an irrelevant post from another thread, as the posting 
guide specifically asks you not to!


-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595




More information about the R-help mailing list