search for: qraux

Here is a modified version of qraux.Rd, an edited version of R-2.14.0/src/library/base/man/qraux.Rd This gives some details and an example for the case of pivoting. In this case, it is not true that X = QR; rather X[, pivot] = QR. It may save some other people bugs and time to have this information. Tim Hesterberg ----------------...

...,] 5.17 1.0 [8,] 4.53 1.7 [9,] 5.33 1.7 [10,] 5.14 1.7 > n=10 > p=2 > y <- c(4.81,4.17,4.41,3.59,5.87,3.83,6.03,4.89,4.32,4.69) > ny=1L > tol=1e-07 > coefficients=double(p) > residuals=double(n) > effects=double(n) > rank=integer(1L) > pivot=1:n > qraux=double(n) > work=double(2*n) > > > > fittt<-.Fortran("dqrls", qr =qr, n = n, + p = p, y = y, ny = ny, tol = tol, coefficients=coefficients, + residuals = residuals, effects = effects, + rank = rank, pivot = pivot,...

...e enlightenment. Thanks, --Mike > X [,1] [,2] [,3] [1,] 1 1 1 [2,] 1 2 1 [3,] 1 3 1 [4,] 1 4 1 > qr(X) $qr [,1] [,2] [,3] [1,] -2.0 -5.0000000 -2 [2,] 0.5 -2.2360680 0 [3,] 0.5 0.4472136 0 [4,] 0.5 0.8944272 0 $rank [1] 2 $qraux [1] 1.5 1.0 0.0 $pivot [1] 1 2 3 attr(,"class") [1] "qr" > qr(X,LAPACK=T) $qr [,1] [,2] [,3] [1,] -5.4772256 -1.8257419 -1.825742e+00 [2,] 0.3087742 -0.8164966 -8.164966e-01 [3,] 0.4631613 -0.3270981 -1.378276e-16 [4,] 0.6175484 -0.7892454 9.0...

...leteness, the QR decompositions per "R" under LINPACK and LAPACK are shown below: > qr(PLLH) $qr alpha theta alpha -1144.6262175869414932095 0.01290777720653695122277 theta -0.0000112768491646264 0.00000000987863187747112 $rank [1] 2 $qraux [1] 1.99999999993641619511209 0.00000000987863187747112 $pivot [1] 1 2 attr(,"class") [1] "qr" > > qr(PLLH, LAPACK=TRUE) $qr alpha theta alpha -1144.62621758694149320945 0.01290777720653695122277 theta -0.000005638424582...

man for `qr` says that the function uses LINPACK's DQRDC, while it in fact uses DQRDC2. ``` The QR decomposition of the matrix as computed by LINPACK or LAPACK. The components in the returned value correspond directly to the values returned by DQRDC/DGEQP3/ZGEQP3 ```

...;lm" has a "qr" component, "is.qr" failed to detect that "lm.D9" was not a "qr" object. The obvious thing might be to tighten the definition of "is.qr", perhaps "is.qr" <- function(x) all(c("qr", "rank", "qraux", "pivot") %in% names(x)) And may I add my congratulations to the core group. Cheers, Jonathan. --please do not edit the information below-- Version: platform = sparc-sun-solaris2.7 arch = sparc os = solaris2.7 system = sparc, solaris2.7 status = Patched major = 0 minor =...

...access functions to the various residual variables that should result from a repeated measures ANOVA ? MyAOVObject$residuals does not exist, and simply printing MyAOVObject gives a very long print of all fields in the result list, many of which I can't see what they are exactly : $error.qr$qraux, for instance. What I would like basically is to inspect those residuals as to sphericity for instance. I'd be curious to know how other R users proceed for checking ANOVA assumptions in the repeated measures case. Thanks a lot for your help, Y. Noel Dpt. of Psychology U. of Lille 3 FRANC...

...fit(), which is a routine of gam.fit() contains: z <- .Fortran("dqrls", qr = x * wts, n = n, p = p, y = y * wts, ny = ny, tol = as.double(tol), coefficients = mat.or.vec(p, ny), residuals = y, effects = mat.or.vec(n, ny), rank = integer(1), pivot = 1:p, qraux = double(p), work = double(2 * p), PACKAGE = "base") It may indicate that QR decomposition is used to derive an additive model instead of backfitting. I am wondering if my guess is correct, or this "the _backfitting algorithm" has another meaning. -- ***** r.otasu...

...q(.1, by=.1, length.out=12), 4) qr(x) And the output from 'R' is: $qr [,1] [,2] [,3] [1,] -0.5477226 -1.2780193 -2.008316e+00 [2,] 0.3651484 -0.3265986 -6.531973e-01 [3,] 0.5477226 -0.3781696 -1.650163e-16 [4,] 0.7302967 -0.9124744 8.078153e-01 $rank [1] 2 $qraux [1] 1.182574 1.156135 1.589436 $pivot [1] 1 2 3 attr(,"class") [1] "qr" The differences that I see is in the last value of qraux. I was expecting 1.83205 not 1.589436. Also the last row of the decomposition shows: [4,] 0.7302967 -0.9124744 8.078153e-01 I was expecting...

...age.mode(x) <- "double" storage.mode(y) <- "double" z <- .Fortran("dqrls", qr = x, n = n, p = p, y = y, ny = ny, tol = as.double(tol), coefficients = mat.or.vec(p, ny), residuals = y, effects = y, rank = integer(1), pivot = 1:p, qraux = double(p), work = double(2 * p), PACKAGE = "base") to if (storage.mode(x) != "double") storage.mode(x) <- "double" if (storage.mode(y) != "double") storage.mode(y) <- "double" z <- .Fortran("dqrls",...

...: num [1:1615, 1:2] -15.6232 0.0292 0.0248 0.0159 0.0295 ... .. .. ..- attr(*, "dimnames")=List of 2 .. .. .. ..$ : chr [1:1615] "1" "2" "3" "4" ... .. .. .. ..$ : chr [1:2] "(Intercept)" "x" .. ..$ rank : int 2 .. ..$ qraux: num [1:2] 1.02 1.02 .. ..$ pivot: int [1:2] 1 2 .. ..$ tol : num 1e-11 .. ..- attr(*, "class")= chr "qr" ..$ family :List of 12 .. ..$ family : chr "binomial" .. ..$ link : chr "logit" .. ..$ linkfun :function (mu) .. ....

...0.2581988897 0.19904444749 -0.30629424692 -0.18166608573 14 0.2581988897 0.21462454012 0.09912429448 0.02910278133 15 0.2581988897 0.27300895524 -0.05280046529 -0.19460726218 I some how got idea (after studying) about QR, but here how should I interpret these values? $qraux [1] 1.258198890 1.151445509 1.139760525 1.291373419 What are these values and how should I interpret them? > anova.stress$rank [1] 4 what does it mean rank 4? How can I know R and R square? Apart from the above 1) how can I interpret fitted and residuals? Can I put the plot and show these v...

...-------- In R: > qr(cbind(1,1,diag(3))) $qr [,1] [,2] [,3] [,4] [,5] [1,] -1.7320508 -0.5773503 -1.732051 -0.5773503 -0.5773503 [2,] 0.5773503 0.8164966 0.000000 -0.4082483 -0.4082483 [3,] 0.5773503 0.7071068 0.000000 -0.7071068 0.7071068 $rank [1] 2 $qraux [1] 1.5773503 1.7071068 0.0000000 0.7071068 0.7071068 $pivot [1] 1 3 2 4 5 It seems that there is a problem here (and S gets this right). I think the changes to the Linpack pivoting strategy in dqrdc2 fail in this example. -- Brian D. Ripley, ripley at stats.ox.ac.uk Professor...

...as.integer(ngoodobs), 82 p = nvars, y = w * z, ny = ncols, tol = min(1e-07, 83 control$epsilon/1000), coefficients = numeric(nvars), 84 residuals = numeric(ngoodobs), effects = numeric(ngoodobs), 85 rank = integer(1), pivot = 1:nvars, qraux = double(nvars), 86 work = double(2 * nvars), PACKAGE = "base") 87 if (nobs < fit$rank) 88 stop(paste("X matrix has rank", fit$rank, "but only", 89 nobs, "observations")) 90 start <- c...

...6 0.316 0.316 ... ..- attr(*, "dimnames")=List of 2 .. ..$ : chr [1:10] "1" "2" "3" "4" ... .. ..$ : chr [1:3] "(Intercept)" "Predictor.1" "Predictor.2" ..- attr(*, "assign")= int [1:3] 0 1 2 $ qraux: num [1:3] 1.32 1.34 1.42 $ pivot: int [1:3] 1 2 3 $ tol : num 1e-07 $ rank : int 3 - attr(*, "class")= chr "qr" > # Here's my version: > version _ platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major 2 min...

...p=ncol(X) n=NROW(y) ny=NCOL(y) tol=1e-7 #this is the fortran routine called by lm - regressing y on X here z <- .Fortran("dqrls", qr = X, n = n, p = p, y = y, ny = ny, tol = as.double(tol), coefficients = mat.or.vec(p, ny), residuals = y, effects = y, rank = integer(1), pivot = 1:p, qraux = double(p), work = double(2 * p), PACKAGE = "base") This code runs very quickly - suggesting that in principle R should have no problem at all handling very large data sets, but uses >100mb during processing and z is about a 20mb object. Scaling this up to a much larger dataset with...

...627 -0.88476903 -1.09492912 0.20247856 -0.23114458 -0.95123387 7 8 0.07521515 0.30208051 Use of debug( lm.influence ) indicates the NaN appears in this line of lm.influence: res <- .Fortran("lminfl", model$qr$qr, n, n, k, as.integer(do.coef), model$qr$qraux, wt.res = e, hat = double(n), coefficients = if (do.coef) matrix(0, n, k) else double(0), sigma = double(n), tol = 10 * .Machine$double.eps, DUP = FALSE, PACKAGE = "base")[c("hat", "coefficients", "sigma", "wt.res")] I don'...

Dear R Core, working on my dynamic factor modelling package, which requires several subroutines to create and update several system matrices, I come back to the issue of being annoyed by R not supporting multiple assignment out of the box like Matlab, Python and julia. e.g. something like A, C, Q, R = init_matrices(X, Y, Z) would be a great addition to the language. I know there are several

...e-04 [3,] 1.830025e-03 [4,] 1.830025e-03 [5,] 3.671781e-03 [6,] 3.671781e-03 [7,] 7.331832e-03 [8,] 7.331832e-03 [9,] 1.466366e-02 [10,] 1.466366e-02 [11,] 2.932733e-02 [12,] 2.932733e-02 [13,] 5.865466e-02 [14,] 5.865466e-02 [15,] 7.038559e-01 [16,] 7.038559e-01 $rank [1] 1 $qraux [1] 1.000915 $pivot [1] 1 $tol [1] 1e-11 attr(,"class") [1] "qr" $family Family: gaussian Link function: identity $linear.predictors [1] 74702.88 74702.88 149405.76 149405.76 299769.24 299769.24 [7] 598580.75 598580.75 1197161.51 1197161.51 239432...

...op("argument is not a QR decomposition") R <- qr$qr if (!complete) R <- R[seq.int(min(dim(R))), , drop = FALSE] R[row(R) > col(R)] <- 0 if(pivot) R <- R[, order(qr$pivot)] R } -------------------------------------------------- % File src/library/base/man/qraux.Rd qr.R(qr, complete = FALSE, pivot = FALSE) \item{pivot}{logical expression of length 1. If \code{TRUE}, then columns of the result are permuted to be in the same order as the original \code{x}.} zapsmall(qr.R(a)) # columns are int b1 c1 c2 b2 c3 zapsmall(qr.R(a, pivot = TRUE...