similar to: se.contrast: matrix contrast.obj doesn't work as documented (PR#1613)

Hi all, Regular and avid readers of this column will know that Don Driscoll and I have recently posted two messages requesting assistance concerning an apparent failure of "se.contrast" to produce an se for a contrast. So far, an ominous silence rings in our ears, but read on Gentle Reader, and see if even the machinations of "debug" doesn't stimulate you to respond with a

I am having some difficulty understanding the implication of lazy evaluation mixed with DUP=F in a .Fortran call. In qr.qty from base DUP is not used as an argument so defaults to T. I am calling qr.qty with a very large array and would like to set DUP=F in the .Fortran call so that qr.qty would be defined as copied below. Is there some risk that a variable used as the argument in the original

Hi all, Just to follow up Don Driscoll's earlier post, can anyone please explain why "se.contrast" fails here?? > shp<-factor(rep(c("reserve","strip"),each=96)) > > > site<-factor(rep(c("1g","1p","1t","2g","2p","2t","3g","3p","3t","4g","4p

With this example set.seed(123) A <- matrix(runif(40), nrow = 8) y <- 1:nrow(A) A.laqr <- qr(A, LAPACK=TRUE) both qr.qy(A.laqr,y) and qr.qty(A.laqr,y) give the respective error messages Error in qr.qy(A.laqr, y) : 'b' must be a numeric matrix Error in qr.qty(A.laqr, y) : 'b' must be a numeric matrix However when Lapack is not used as in A.liqr <- qr(A,

I think there are two bugs in aov() that shows up when the right hand side of `formula' contains both `-1' and an Error() term, e.g., aov(y ~ a + b - 1 + Error(c), ...). Without `-1' or `Error()' there is no problem. I've included and example, and the source of aov() with suggested fixes below. The first bug (labeled BUG 1 below) creates an extra, empty stratum inside

I believe you are right, but can you please explain why anyone would want to fit this model? It differs only in the coding from aov(y ~ a + b + Error(c), data=test.df) and merely lumps together the top two strata. There is a much simpler fix: in the line if(intercept) nmstrata <- c("(Intercept)", nmstrata) remove the condition (and drop the empty stratum later if you

Dear R people, I do not have much knowledge about linear algebra but currently I need to understand what the function qr.qty is actually doing. The documentation states that it calculates t(Q) %*% y via a previously performed QR matrix decomposition. In order to do that, I tried following basic example: m<-matrix(c(1,0,0,0,1,0,0,0,1,0,0,1),ncol=3) # 4x3 matrix

Hi list, I tried to use nls to do some nonlinear least square fitting on my data with 340 observations and 10 variables, but as I called nls() function, I got this error message: Error in qr.qty(QR, resid) : 'qr' and 'y' must have the same number of rows Then I traced back a little bit into nls() function, the error seemed to happen when calling nlsiter() internal function, but

I need to perform a QR-decomposition of a sparse matrix, so I've been trying to use the Matrix package. Unfortunately I don't seem to be getting exactly the same results as if I had used the qr() command from the base package. Here is an example of what I'm doing. > spdata <-rpois(50,1) > y <- rnorm(10,0,1) > S <-

Dear R-experts! I have y(x) data, dim(y) == dim(x) == c(2000, 2) I'd like to fit them with nls: fit.result <- nls ( y ~ f(x, p1, p2, p3), start = list(p1 = ... , p2 = .. , p3 = ..) ) Actually I want to fit y[,1] ~ x[,1] and y[,2] ~ x[,2] *simulaneously*, with the same parameters set {p1, p2, p3}. I tried to feed R tha above formula, R errors with:

Hi, I have a problem with fitting a model: I made a dataframe with this data: a <- 1:3 b <- 1:3 c <- c(3, 2, 3, 2, 1, 2, 3, 2, 3) df <- expand.grid(a,b) df$result <- c names(df) <- c("A","B", "result") Although I can make a graph of the data: require(lattice) wireframe(result~A*B, data=df) I can't get a model to

Hi, I installed R-3.1.1 on AIX-5.3 and my installation hanged up while installing Matrix Package. so i killed the gmake ; gmake install the software nad tired installing Matrix package manually - [ncmr0202][/gpfs1/home/shivali/gang/R-3.1.1/bin/package]> /gpfs1/home/shivali/gang/R-3.1.1/bin/R CMD INSTALL Matrix the package compiled successfully but while loading Matrix package the

G'day, I'm fitting a simple one-way nested anova and would like to obtain standard errors or confidence limits. I'm using se.contrast to try to get se for the contrast between the two levels of the main effect, but I get an error message (see below). What is going on? Don > shp<-factor(rep(c("reserve","strip"),each=96)) >

Hi, Please help. Regards, Shivali ---------------------------- Original Message ---------------------------- Subject: Re: [Rd] AIX-5.3 Issue installing Matrix Package From: shivali at mail.ncmrwf.gov.in Date: Wed, October 8, 2014 3:31 pm To: "Ei-ji Nakama" <nakama at ki.rim.or.jp> Cc: "Martin Maechler" <maechler at stat.math.ethz.ch>

Hi, I have a least square fitting problem with linear inequality constraints. pcls seems capable of solving it so I tried it, unfortunately, it is stuck with the following error: > M <- list() > M$y = Dmat[,1] > M$X = Cmat > M$Ain = as.matrix(Amat) > M$bin = rep(0, dim(Amat)[1]) > M$p=qr.solve(as.matrix(Cmat), Dmat[,1]) > M$w = rep(1, length(M$y)) > M$C = matrix(0,0,0)

I'm trying to estimate a "diagonal reference model" in nls. In its basic form, the model consists of two factors with equal categories and a dependent variable. The model fits the main effects of the two factors such that they are proportional to each other. So the model I want to fit is: Y=p*m[f1]+(1-p)*m[f2] The m-parameters indicate the "average" main effect of factors

Hi Could anyone please tell me what to do to resolve this error message? I tried to run a gam with the mgcv package and got the following error: "Error in qr.qty(qrc, sm$S[[1]]): NA/NaN/Inf in foreign function call (arg 5)" (I have 116 covariates, I'm using the "cr" basis to speed things up, the binomial family and, where necessary, have set the required k to lower than

Does anybody know what are the attributes of a glm fit object that will allow the "predict call" to produce an se.fit? I am deleting most of the attributes as the size of the final object is 5Gb and I want to reduce it to under 20Mb, but that causes as error when I ask for an se.fit . mod.b$fitted.values <- 1:10 mod.b$prior.weights <- 1:10 mod.b$data <-mod.b$data[1:10,]

# r-bugs@r-project.org The problem occurs when the model matrix has a single column. > elastic <- data.frame(stretch=c(46,54,48,50,44,42,52), distance=c(183,217,189,208,178,150,249)) > elastic.lm <- lm(distance ~ -1 + stretch, data=elastic) > predict(elastic.lm,se=T) Error in XRinv^2 %*% rep(res.var, p) : non-conformable arguments The fix is to replace XRinv <-

I have found some "issues" (bugs?) with nls confidence intervals ... some with the relatively new "port" algorithm, others more general (but possibly in the "well, don't do that" category). I have corresponded some with Prof. Ripley about them, but I thought I would just report how far I've gotten in case anyone else has thoughts. (I'm finding the code