search for: qrx

...tter but, perhaps, easily fixed. I think one line which reordered the column names of the $qr list element of the object returned by qr() would fix things (and similarly for chol) Example: > A <- 1:10 > B <- A^2 > C <- B-A > D <- rep(1, 10) > X <- cbind(A,B,C,D) > qrX <- qr(X) > qrX$pivot [1] 1 2 4 3 > oo <- order(qrX$pivot) > Q <- qr.Q(qrX) > R <- qr.R(qrX) > Q%*%R A B C D [1,] 1 1 1 2.875732e-14 [2,] 2 4 1 2.000000e+00 [3,] 3 9 1 6.000000e+00 [4,] 4 16 1 1.200000e+01 [5,] 5 25...

...version of qr() in version 1.7.0. (version below). 1. The documentation states that LAPACK=TRUE is the default, but the code has LAPACK=FALSE. 2. With LAPACK=TRUE qr() is never pivoting, even in cases where it very clearly should be. e.g. set.seed(0) X<-matrix(rnorm(40),10,4);X[,1]<-X[,2] qrx<-qr(X,LAPACK=TRUE) qrx$pivot # note, no pivoting qr.R(qrx) # note zero on leading diagonal is not in trailing block 3. ?qr includes the statement: Using LAPACK (including in the complex case) uses column pivoting 4. If I call F77_NAME(dgeqp3) directly I get correct pivoting. platform i686-pc...

...y data) .... Warning: a final empty element has been omitted the part of the args list of 'list' being evaluated was: (coefficients = fit$beta, residuals = fit$y - fit$eta, fitted.values = fit$eta, effects = effects, weights = w, rank = qrank, assign = attr(x, "assign"), qr = qrx, smooth = fit$s, nl.df = fit$df - 1, ) Any ideias? Thank you very much in advance, Marta PS: happy new year :-) -- ....................................................................... Marta M. Rufino (PhD) ..... Instituto Nacional de Investiga??o Agr?ria e das Pescas (INIAP/IPIMAR), Centro...

...e inverse before being allowed to use solve(A).) So, how should you calculate least squares estimates? We recommend betahat <- qr.coef(qr(X), y) If you want other results from the least squares calculation, such as fitted values or residuals, you may want to save qr(X) so you can reuse it qrX <- qr(X) betahat <- qr.coef(qrX, y) res <- qr.resid(qrX, y) ... There are alternatives but solve(t(X) %*% X) %*% t(X) %*% y is never a good one. Seber and Lee discuss discuss such calculations at length in chapter 11 of their "Linear Regression Analysis (2nd ed)" (Wiley, 20...

...rears its head. Here is the tail of the output from reg-tests-1.Rout.fail > ## as.hclust.twins() lost labels and more till (incl) 1.6.2 > > > ## PR#2867 qr(LAPACK=TRUE) didn't always pivot in 1.7.0 > set.seed(1) > X <- matrix(rnorm(40),10,4) > X[,1] <- X[,2] > (qrx <- qr(X, LAPACK=TRUE)) Error in qr(X, LAPACK = TRUE) : error code -14983444 from Lapack routine dqeqp3 Execution halted As an R novice, I am puzzled that the call to dgeqp3 has more arguments than dgeqp3 itself. The call has an extra argument "rwork". But this could explain the...

...= hcag$merge[ ,2:1]) + ) + } Loading required package: cluster > ## as.hclust.twins() lost labels and more till (incl) 1.6.2 > > > ## PR#2867 qr(LAPACK=TRUE) didn't always pivot in 1.7.0 > set.seed(1) > X <- matrix(rnorm(40),10,4) > X[,1] <- X[,2] > (qrx <- qr(X, LAPACK=TRUE)) Error in qr(X, LAPACK = TRUE) : error code -1 from Lapack routine dqeqp3 Execution halted

Hello list. I'm trying to rebuild the 2.6.9.67.0.20.EL kernel, but it fails even without modifications. How did I try it? Created a (non-root) build environment (not a mock ) Installed the kernel.scr.rpm and did a rpmbuild -ba --target=`uname -m` kernel-2.6.spec 2> prep-err.log | tee prep-out.log The build failed at the end: Processing files: kernel-xenU-devel-2.6.9-67.0.20.EL Checking