similar to: anova.mlm (single-model case) does not handle factors? (PR#8679)

predict.lm(..., type="terms") gives wrong standard errors. Below, I have provided what I believe are the necessary fixes. However, there are subtleties, and the code needs careful checking. Some of the looping is surely not necessary, but it is surely best to begin with the minimum necessary changes. My tests, including checks against S-PLUS, have extended to fitting spline curves. I

>From e980153 Tue Apr 25 14:42:27 2000 To: r-help@stat.math.ethz.ch Subject: Wrong SEs in predict.lm(..., type="terms") For what it is worth, I am using RW-1.0.0 under Windows 98. I submitted this earlier to r-help. There is one change below to my proposed corrected code: predict.lm(..., type="terms") gives wrong standard errors. Below, I have provided what I believe are

On Sat, 12 Aug 2006, takahashi kohske wrote: > Dear list members: > > I'd like to one-way repeated measured anova by using mlm. > I'm using R-2.3.1 and my code is: > > dat<-matrix( c(9,7,8,8,12,11,8,13, 6,5,6,3,6,7,10,9, > 10,13,8,13,12,14,14,16, 9,11,13,14,16,12,15,14), > ncol=4, dimname=list(s=1:8, c=1:4)) >

Would someone be so kind as to explain in English what the ANOVA code (anova.lm) is doing? I am having a hard time reconciling what the text books have as a brute force regression and the formula algorithm in 'R'. Specifically I see: p <- object$rank if (p > 0L) { p1 <- 1L:p comp <- object$effects[p1] asgn <-

Full_Name: Yves Rosseel Version: 2.2.1 OS: Submission from: (NULL) (157.193.116.152) The code below sketches a possible implementation of a function 'mlh.mlm' which I think would be a good complement to the 'anova.mlm' function in the stats package. It tests a single linear hypothesis of the form H_0: LBT'= 0 where B is the matrix of regression coefficients; L is a matrix

Sorry about the lack of detail. I am running R v.1.2.2. I can recast my question (which I think I have partially answered) more succinctly as follows: 1. This seems to work (note that group takes values 1,2,3,4, or 5): my.newfun <- function(x) myfile <- lm(award ~ ilogemp + ilogage, x) test.by <- by(wintemp, as.factor(wintemp$group), my.newfun) 2. This does not work (leaving aside

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

When I fit a multivariate linear model, and the formula is defined outside the call to lm(), the method summary.mlm() fails. This works well: > y <- matrix(rnorm(20),nrow=10) > x <- matrix(rnorm(10)) > mod1 <- lm(y~x) > summary(mod1) ... But this does not: > f <- y~x > mod2 <- lm(f) > summary(mod2) Error en object$call$formula[[2L]] <- object$terms[[2L]]

Hello, I've just fitted a model with multi-responses, and I get an object of class "lm" "mlm". My problem is that as soon as I invoke the predict method for a dataframe "newdata", the methods runs and give me back prediction at the fitting points but not for newdata. Does someone has an explanation for this behavior, and some ideas to make predict.mlm work

It seems that confint.default returns an empty data.frame for objects of class mlm. For example: ``` nobs <- 20 set.seed(1234) # some fake data datf <- data.frame(x1=rnorm(nobs),x2=runif(nobs),y1=rnorm(nobs),y2=rnorm(nobs)) fitm <- lm(cbind(y1,y2) ~ x1 + x2,data=datf) confint(fitm) # returns: 2.5 % 97.5 % ``` I have seen proposed workarounds on stackoverflow and elsewhere, but

I would like to perform multiple comparisons or post-hoc testing on the independent variable in an Anova.mlm object generated by the Anova function of the car package. I have defined a multivariate linear model and subsequently performed a repeated measures ANOVA as per the instructions in section #3 of the following comprehensive tutorial on the subject from the Gribble lab at UWO:

Hi, Am newish to stats and R, so I certainly appreciate any help. Basically I have 50 inidividuals whom I have 6 photos each of their optic nerve head. I want to check that the orientation of the nerve head is consistent, ie the 6 replicates show minimal or preferably no rotation differences. I'll draw an arbitrary line between some blood vessels (same reference in each set of replicates) and

I used the supersmoother function in the modreg package as follows: super <- supsmu(ilogemp,award) Then I decided that I might want additional explanatory variables (other than ilogemp) in my model. The ppr function in modreg seemed a logical extension of supsmu from univariate to multidimensional explanatory variables. As a "check" I ran the following: pprest <-

Folks, The projection pursuit regression function in the base R seems to crash when the optimization level is set to zero, i.e. the initial ridge terms are accepted without refitting. I encountered this problem in an out-of-sample prediction exercise using predict. But further investigation suggests the issue is with the ppr fit and predict just sppeds up the crash. The other optlevels seem to be

Dear R fans, I have got a difficult sounding problem. For fitting a linear model using continuous response and then for re-fitting the model after excluding every single variable, the following functions can be used. library(MASS) model = lm(perf ~ syct + mmin + mmax + cach + chmin + chmax, data = cpus) dropterm(model, test = "F") But I am not sure whether any similar functions is

I believe there is a coding error in the first part of predict.mlm in the splines package, but perhaps someone could explain the logic to me if I'm wrong. I don't see how the second if (missing(newdata)) could ever be true. (I would show the code but I'm using email on a different machine than R today.) Paul Gilbert

I'm looking for something in R to fit a multivariate linear model robustly, using an M-estimator or any of the myriad of other robust methods for linear models implemented in robustbase or methods based on MCD or MVE covariance estimation (package rrcov). E.g., one can fit an mlm for the iris data as: iris.mod <- lm(cbind(Sepal.Length, Sepal.Width, Petal.Length, Petal.Width) ~ Species,

Hello, I am using the function "lm" to fit several responses at the same time (100 responses). At the end of the fit, I get an object of class "mlm". I would like to know if there is a way to access to each of the 100 underlying models separately (is it a list, ... ?). Which syntax should I use to see and use the 15th model (for instance) just like it is possible for classical

Hi, yet another anova.mlm problem - it doesn't seem to end. This time, I have a setup with a few within-subject factors and a between-subject factor (SGROUP). Consider the most simple case with only one within-factor (apo): > mlmfit0 <- lm(data.n ~ 0 + SGROUP) > mlmfit1 <- lm(data.n ~ 1 + SGROUP) > anova(mlmfit1,mlmfit0,test="Spherical",M=~hemi,X=~1) Analysis of