similar to: passing an extra argument to an S3 generic

Barrett & Ling, JASA, 1992, v.87(417), pp184-191 define general classes of influence measures for multivariate regression models, including analogs of Cook's D, Andrews & Pregibon COVRATIO, etc. As in univariate response models, these are based on leverage and residuals based on omitting one (or more) observations at a time and refitting, although, in the univariate case, the

I'm following up on a question I posted 8/10/2010, but my newsreader has lost this thread. > Barrett & Ling, JASA, 1992, v.87(417), pp184-191 define general > classes of influence measures for multivariate > regression models, including analogs of Cook's D, Andrews & Pregibon > COVRATIO, etc. As in univariate > response models, these are based on leverage and

I'm trying to write a formula method for canonical correlation analysis, that could be called similarly to lm() for a multivariate response: cancor(cbind(y1,y2,y3) ~ x1+x2+x3+x4, data=, ...) or perhaps more naturally, cancor(cbind(y1,y2,y3) ~ cbind(x1,x2,x3,x4), data=, ...) I've adapted the code from lm() to my case, but in this situation, it doesn't make sense to include an

Dear R-Helpers, I suspect I'm about to ask a FAQ, but I haven't been able to find an answer in the FAQ, AItR or an R Site Search. When I look at the methods of summary (below) it says, "Non-visible functions are asterisked". I looked at the help file for summary.princomp, which did not comment on it being non-visible. I ran its help file example, which printed visible output. I

R-users E-mail: r-help@r-project.org Hi! R-users. I am just wondering what the definition of "dffits" in R language is. Let me show you an simple example. function() { library(MASS) xx <- c(1,2,3,4,5) yy <- c(1,3,4,2,4) data1 <- data.frame(x=xx, y=yy) lm.out <- lm(y~., data=data1, x=T) lev1 <- lm.influence(lm.out)$hat sig1 <-

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

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

Hi, I have been struggling with this problem for some time now. Internet, books haven't been able to help me. ## I have factorial design with counts (fruits) as response variable. > str(stubb) 'data.frame': 334 obs. of 5 variables: $ id : int 6 23 24 25 26 27 28 29 31 34 ... $ infl.treat : Factor w/ 2 levels "0","1": 2 2 2 2 1 1 1 2 1 1 ... $ def.treat :

Hi, I have the following code from Splus that I'd like to migrate to R. So far, the only problem is the arima.filt function. This function allows me to filter an existing time-series through a previously estimated arima model, and obtain the residuals for further use. Here's the Splus code: # x is the estimation time series, new.infl is a timeseries that contains new information # a.mle

Hi, I found that using different contrasts (e.g. contr.helmert vs. contr.treatment) will generate different fitted probabilities from multinomial logistic regression using multinom(); while the fitted probabilities from binary logistic regression seem to be the same. Why is that? and for multinomial logisitc regression, what contrast should be used? I guess it's helmert? here is an example

In Venables \& Ripley 3rd edition (p. 231) the proportional odds model is described as: logit(p<=k) = zeta_k + eta but polr apparently thinks there is a minus in front of eta, as is apprent below. Is this a bug og a feature I have overlooked? Here is the naked code for reproduction, below the results. ------------------------------------------------------------------------ --- version

Is there any reason that rstandard.glm doesn't have a "pearson" option? And if not, can it be added? Background: I'm currently teaching an undergrad/grad-service course from Agresti's "Introduction to Categorical Data Analysis (2nd edn)" and deviance residuals are not used in the text. For now I'll just provide the students with a simple function to use, but I

Hi, I am trying to test the proportional-odds model using the "polr" function in the MASS library with the dataset of "housing" contained in the MASS book ("Sat" (factor: low, medium, high) is the dependent variable, "Infl" (low, medium, high), "Type" (tower, apartment, atrium, terrace) and "Cont" (low, high) are the predictor variables

I would like to do a SS type III analysis on a proportional odds logistic regression model. I use drop1(), but dropterm() shows the same behaviour. It works as expected for regular main effects models, however when the model includes an interaction effect it seems to have problems with matching the parameters to the predictor terms. An example: library("MASS"); options(contrasts =

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)

Full_Name: Heather Turner Version: 2.2.0 OS: Windows XP Submission from: (NULL) (137.205.240.44) Standardized residuals as calculated by rstandard.lm, rstandard.glm and plot.lm are Inf/NaN rather than zero when the un-standardized residuals are zero. This causes plot.lm to break when calculating 'ylim' for any of the plots of standardized residuals. Example:

Dear useRs, I have some trouble with the calculation of Cook's distance in R. The formula for Cook's distance can be found for example here: http://en.wikipedia.org/wiki/Cook%27s_distance I tried to apply it in R: > y <- (1:400)^2 > x <- 1:100 > lm(y~x) -> linmod # just for the sake of a simple example >

Hi! I'm trying to do a lm() test on three objects. My problem is that R protests and says that the variable lengths differ for one of the objects (Sweden.GDP.gap). But I have double checked that the number of observations are the same. All three objects should contain 9 observations but R only accepts 9 observations in two of the objects. The third must have 10! Very confusing because there

Hi, I want to calculate the t- and p-values for a linear model using the Newey West estimator. I tried this Code and it usually worked just fine: > oberlm <- lm(DYH ~ BIP + Infl + EOil, data=HU_H) > coeftest(oberlm, NeweyWest(oberlm, lag=2)) t test of coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 0.1509950 0.0743832 2.0300 0.179486 BIP