I've just encountered a very minor discrepancy between R and Splus that seems a bit puzzling. In R if you have a square (p by p) singular matrix, call it A, and you do, qr.coef(qr(A),diag(p)) you get an answer with rows of NA's. Quite properly, I thought. However, in Splus you get the same result except that the NA's are replaced by 0's. This seems to imply the convention 1/0 = 0. Is there some deeper rationale for this convention? I realize that it might be more reasonable to have sent this to Snews, but I've sworn off Snews recently in favor of this forum. url: http://www.econ.uiuc.edu Roger Koenker email roger at ysidro.econ.uiuc.edu Department of Economics vox: 217-333-4558 University of Illinois fax: 217-244-6678 Champaign, IL 61820 -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._