Hello, The following document is _not_ about lm(), it's about creating packages but it includes an example that might answer to what you want, a simple lm() substitute. (It uses the QR decomposition, not Cholesky)
http://cran.r-project.org/doc/contrib/Leisch-CreatingPackages.pdf Hope this helps, Rui Barradas Em 29-11-2012 19:58, Mohammad Ahmed escreveu: > Help Please > Hello, > > I want to find the whole hat matrix not only the hat values. Is there anyway > that could be extracted from lm function ?. If not, please suggest something > else. > Direct computations using chol2inv or solve are not stable if t(X)%*%X has > high determinant. In this case lm is still able to produce correct fitted > values, hat_value, residuals...etc but direct computations fail to do so. > Thus I guess extracting the hat matrix from lm function will be perfect. > > Thank you > [[alternative HTML version deleted]] > > > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
