similar to: glm(weights) and standard errors

System: R 2.3.1 on a Windows XP computer. I am validating several cancer prognostic models that have been published with a large independent dataset. Some of the models report a probability of survival at a specified timepoint, usually at 5 and 10 years. Others report only the linear predictor of the Cox model. I have used Harrell's c index for censored data (rcorr.cens) as a measure of

Hi, Does anyone know if the D'agostino test is available with R ? Alex

In the next month or two I've got to upgrade a number of servers that are currently on an EOL'd version of 4-STABLE. I foresee that I'll have very limited time to do full OS upgrades on these systems in the coming several years, so I want to make sure I bring them onto an extended-life branch. Right now 4.11 has the furthest projected EOL date (Jan 31 2007), and the projected EOL

Dear R I am trying to understand and use the flexible parametric survival model suggested by Royston and Parmar. However I am stuck trying to plot the adjusted survival curves for different covariates in the following code: library(flexsurv) library(graphics) spl <- flexsurvspline(Surv(futime, fustat) ~ rx+ecog.ps+resid.ds+age, data = ovarian, k=2, scale="odds") spl the code

Dear R-list readers: Royston described the effect of sample size on the p-value obtained from the Shapiro-Francia test (Estimating departure from normality. Stat Med 1991;10:1283-93). He developed two indices from the Shapiro-Francia test (i) V' - an index of departure from normality and (ii) v' - a plot of the cumulative squared residuals. He mentioned the availability (in

Hi, I was reading a paper published in JCO "Prediction of risk of distant recurrence using 21-gene recurrence score in node-negative and node-positive postmenopausal patients with breast cancer treated with anastrozole or tamoxifen: a TransATAC study" (ICO 2010 28: 1829). The author uses a method to estimate the 9-year risk of distant recurrence as a function of continuous recurrence

Hi all, I want to use weights for a logistic regression. In SAS, all I have to do is to specify my weight vector (they are fractions) and use proc logistic on my binary output. When I tried to do the same in R, I got an error message because my weights were not integer. I understand that the weight option in R is to be used when the dependent variable is a proportion so that the weight is the

Dear All! my data is on pairs of countries, i and j, e.g.: y,i,j 1,AUT,BEL 2,AUT,GER 3,BEL,GER I would like to create a dummy (indicator) variable for use in regression (using factor?), such that it takes the value of 1 if the country is in the pair (i.e. EITHER an i-country OR an j-country). Thank you for your help, Serguei ________________________________________ Austrian Institute of

Hello R folks, I have three questions. I am trying to run a logistic regression (binomial family) where the response variable is a proportion. According to R Documentation in "a binomial GLM prior weights are used to give the number of trials when the response is the proportion of successes." However when I run my code I get the following error message: Error in

Howyd all? Seems that I have been routed. Possibly by a physical B&E, but who knows? Probably some of you do.... anyways, some politically sensitive email was deleted from a user account and the line low -tr & inserted into my .xinitrc . Duncan (Dhu) Campbell

These are new boxes. http://www.supermicro.com/products/system/1U/5015/SYS-5015B-MT.cfm core 2 Q6600 CPU 8Gb 667 RAM Boxes were memtested from Fri-Mon okay. 6.3-RELEASE (amd64) installs fine. Build cycle okay. Running (no load) for a week or so. However, when I try to configure gmirror they hang on boot. After some fiddling it appears issuing #kldload geom_mirror hangs the boxes very hard.

I handed out some results from glm() and the students ask "how many observations were dropped due to missing values"? How would I know? In other stat programs, the results will typically include N and the number dropped because of missings. Without going back to R and fiddling about to find the total number of rows in the dataframe, there is no way to tell. Somewhat

On Wed, Jul 20, 2005 at 12:00:36PM +0000, freebsd-security-request@freebsd.org wrote: > From: Joachim Str?mbergson <watchman@ludd.ltu.se> > Subject: Adding OpenBSD sudo to the FreeBSD base system? > To: freebsd-security@freebsd.org > Message-ID: <42DCC503.5000408@ludd.ltu.se> > Content-Type: text/plain; charset=ISO-8859-1; format=flowed > > Aloha! > >

Hello, I am trying to perform a glm analysis on a 68x13113 matrix (named data.spect). The first column corresponds to the predictor (data.spect[,1]) and the rest to the response variables (data.spect[,2:13113]). When I try this code glmObject <- glm(data.spect[,2:13113]~data.spect[,1]) I get the following error: Error: (subscript) logical subscript too long Could anyone help me on

Hi, Where can I find information ( freely available on the Internet , and also books or other sources ) on how having sampling weights changes the calculation of the standard error (of means and proportions)? How good is R for this type of procedure? And SAS? thanks Robert [[alternative HTML version deleted]]

I have a question about weights in glm for binomial model. Can I use any arbitrary number between 0 and 1 as weights instead of integer? I kept getting warning message when I did that. Thanks.

Hi, I have a supposedly representative sample from a stratified survey. Hence, all observations have an associated sample weight each which inflate the sample to population size. I want to run a glm probit regression on the data but I am not clear about if or better how I can use the weights in it. From the description of the weights argument of glm it seems to me that I cannot plug these

I am using R 2.1.1 under Mac OS 10.3.9. Two related problems (see notes 1. and 2. below) are illustrated by results of the following: y <- rnorm(10) x <- z <- 1:10 is.na(x[9]) <- TRUE lm0 <- lm(y ~ 1) lm1 <- lm(y ~ 1, weights = rep(1, 10)) add1(lm0, scope = ~ x) ## works ok add1(lm1, scope = ~ x) ## error lm2 <- lm(y ~ 1, offset = 1:10) add1(lm0, scope = ~ z) ##

Dear all Could someone explain to why weights does not works in lm and glm in the example below? Thanks in advance, Roseli. function(model){ www<-fitted(model) lm(formula(model),weights=www) } The message error is: Error in eval(expr,envir,enclos): object "www" not found. [[alternate HTML version deleted]]

Dear all, I am trying to use the 'glm' package as part of a semiparametric technique that involves weighting a likelihood in various ways, i.e. L(theta;data)=Sum_i=1,..,n (W_i)(log L(theta;data_i)) Where W_i can be a kernel weighting function, or W_i can be an indicator of 'non-missingness' divided by a propensity score. In a Monte Carlo exercise, the option glm(...,