question
On Sat, 28 Jun 2003, Jan de Leeuw wrote:
Is it correct that lsfit(matrix(0,10,1),1:10,intercept=FALSE) returns zero residuals ?
No. I would use lm.fit for such problems, and that seems to behave (probably rather coincidentally).
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