similar to: Cook's distance

Hello: I am trying to understand the method 'hatvalues(...)', which returns something similar to the diagonals of the plain vanilla hat matrix [X(X'X)^(-1)X'], but not quite.  A Fortran programmer I am not, but tracing through the code it looks like perhaps some sort of correction based on the notion of 'leave-one-out' variance is being applied. Whatever the

Dear All, I am a beginner creating R packages. I followed the Leisch (2009) tutorial and the document ?Writing R Extensions? to write an example. I installed R 2.12.2 (I also tried R2.13.2), the last version of Rtools and the recommended packages in a PC with Windows 7 Home Premium. I can run R CMD INSTALL linmod in the command prompt and the R CMD check linmod. The following outputs are

I am reading Section 5 and 6 of http://cran.r-project.org/doc/contrib/Leisch-CreatingPackages.pdf It seems that I have to do the following two steps in order to make an R package. But when I am testing these package, these two steps will run many times, which may take a lot of time. So when I still develop the package, shall I always source('linmod.R') to test it. Once the code in

I'm trying to write some functions extending influence measures to multivariate linear models and also allow subsets of size m>=1 to be considered for deletion diagnostics. I'd like these to work roughly parallel to those functions for the univariate lm where only single case deletion (m=1) diagnostics are considered. Corresponding to stats::hatvalues.lm, the S3 method for class

Hi there, I am stuck trying to solve what should be a fairly easy problem. I have a data frame that essentially consists of (ID, time as seqMonth, variable, value) and i want to find the regression coefficient of value vs time for each combination of ID and Variable. I have tried several approaches and none of them seems to work as i expected. For example, i have tried:

Dear R-Helpers Given a function like foo <- function(data,var1,var2,var3) { f <- formula(paste(var1,'~',paste(var2,var3,sep='+'),sep='')) linmod <- lm(f) return(linmod) } By typing foo(mydata,'a','b','c') I get the result of the linear model a~b+c. How can I rewrite the function so that the formula can be updated inside the function,

I am struiggling a bit with this function 'hatvalues'. I would like a little more undrestanding than taking the black-box and using the values. I looked at the Fortran source and it is quite opaque to me. So I am asking for some help in understanding the theory. First, I take the simplest case of a single variant. For this I turn o John Fox's book, "Applied Regression Analysis

Hi, folks linmod=y~x+z summary(linmod) The summary of linmod shows the standard error of the coefficients. How can we get the sd of y and the robust standard errors in R? Thanks! [[alternative HTML version deleted]]

Hi, folks, As seen in the following codes: x1=rlnorm(10) x2=rlnorm(10,mean=2) y=rlnorm(10,mean=10)### Fake dataset linmod=lm(log(y)~log(x1)+log(x2)) After the regression, I would like to know the mean of y. Since log(y) is normal and y is lognormal, I need to know the mean and variance of log(y) first. I tried mean (y) and mean(linmod), but either one is what I want. Any tips? Thanks in

Hi folks, I created a subset of a dataframe (i.e., selected only men): subdata <- subset(data,data$gender==1) After a residual diagnostic of a regression analysis, I detected three outliers: linmod <- lm(y ~ x, data=subdata) plot(linmod) Say, the cases 11,22, and 33 were outliers. Here comes the problem: When I want to exclude these three cases in a further regression analysis, - for

Hi all, In using the identify command, I get the following message > plot(hatvalues(scireg3)) > abline(h=.0154,lty=2) # plots a reference line at (k + 1)/n > identify(1:1165, hatvalues(scireg3),row.names(sciach)) Error in xy.coords(x, y) : 'x' and 'y' lengths differ which doesn't allow me to see the observation number when I scroll over with the mouse. What

I understand that the hat matrix is a function of the predictor variable alone. So, in the following example why do the values on the diagonal of the hat matrix change when I go from an unweighted fit to a weighted fit? Is the function hatvalues giving me something other than what I think it is? library(ISwR) data(thuesen) attach(thuesen) fit <- lm(short.velocity ~ blood.glucose)

Forgive me if this is a trivial question, but I couldn't find it an answer in former forums. I'm trying to reproduce some SAS results where they set two parameters equal. For example: y = b1X1 + b2X2 + b1X3 Notice that the variables X1 and X3 both have the same slope and the intercept has been removed. How do I get an estimate of this regression model? I know how to remove the intercept

Dear R-Help, I'm new to R and struggling with weighting data when I run regression. I've tried to use search to solve my problem but haven't found anything helpful so far. I (successfully) import data from SPSS (15) and try to run a linear regression on a subset of my data file where WEIGHT is the name of my weighting variable (numeric), e.g.: library(foreign)

I am using the Unix version of R (version 1.7.0), installed via fink on a G4 Macintosh. I recently upgraded from version 1.6.0 and found that the "car" library now has a problem: ---Begin transcript--- >library(car) Attaching package 'car': The following object(s) are masked from package:base : dfbeta dfbeta.lm dfbetas dfbetas.lm hatvalues hatvalues.lm

Hi, I'm just starting out with Sweave, and I can't get a plot(linmod) to display all four plots: << bild >>= x1 <- runif(100) x2 <- rexp(100) y <- 3 + 4*x1 + 5*x2 + rnorm(100) mod <- lm(y~x1+x2) plot(mod) @ Some Text <<fig=TRUE>>= <<bild>> @ This plots only the first image of the four-page plot.lm() result. I don't want to use

Hello, Thank you very much for looking at this. I have a "seasonal" user for R. I teach my undergrads and graduates students statistics using R and often find myself trying to solve problems to process student collected data in an efficient way. In this case, I have a data.frame with multiple observations. These are gas concentrations in a chamber and are used to measure into rates,

Dear R-Help List, I'm trying to implement Firth's (1993) bias correction for log-linear models. Firth (1993) states that such a correction can be implemented by supplementing the data with a function of h_i, the diagonals from the hat matrix, but doesn't provide further details. I can see that for a saturated log-linear model, h_i=1 for all i, hence one just adds 1/2 to each count,

The following code demonstrates an annoyance with plot.lm(): library(DAAGxtras) x11(width=3.75, height=4) nihills.lm <- lm(log(time) ~ log(dist) + log(climb), data = nihills) plot(nihills.lm, which=5) OR try the following xy <- data.frame(x=c(3,1:5), y=c(-2, 1:5)) plot(lm(y ~ x, data=xy), which=5) The "Cook's distance" text overplots the label for the point with the

Hi Community, I'm trying to reconcile Cook's Distances computed in glm. The following snippet of code shows that the Cook's Distances contours on the plot of Residuals v Leverage do not seem to be the same as the values produced by cooks.distance() or in the Cook's Distance against observation number plot. counts <- c(18,17,15,20,10,20,25,13,12) outcome <- gl(3,1,9)