similar to: ols function in rms package

Dear R help, I'm having some trouble with model formulas for the ols function in the rms package. I want to have two variables represented as restricted cubic splines, and also include an interaction as a product of linear terms, but I get an error message. library(rms) d <- data.frame(x1 = rnorm(50), x2 = rnorm(50), y = rnorm(50)) ols(y ~ rcs(x1,3) + rcs(x2,3) + x1*x2, data=d) Error in

How can I extract the adjusted R^2 value from an ols object (using rms package)? library(rms) x <- rnorm(10) y <- x + rnorm(10) ols1 <- ols(y ~ x) Typing "ols1" displays adjusted R^2 among other things, but how can I assign it to a variable? I tried str(ols1) but couldn't see where to go from there. Thanks, Mark Seeto

Dear R-help, In the rms package, I have fitted an ols model with a variable represented as a restricted cubic spline, with the knot locations specified as a previously defined vector. When I save the model object and open it in another workspace which does not contain the vector of knot locations, I get an error message if I try to predict with that model. This also happens if only one workspace

Hello, I have a general question about combining imputations as well as a question specific to the rms and Hmisc packages. The situation is multiple regression on a data set where multiple imputation has been used to give M imputed data sets. I know how to get the combined estimate of the covariance matrix of the estimated coefficients (average the M covariance matrices from the individual

I?ve been using Frank Harrell?s rms package to do bootstrap model validation. Is it the case that the optimum penalization may still give a model which is substantially overfitted? I calculated corrected R^2, optimism in R^2, and corrected slope for various penalties for a simple example: x1 <- rnorm(45) x2 <- rnorm(45) x3 <- rnorm(45) y <- x1 + 2*x2 + rnorm(45,0,3) ols0 <- ols(y

I have installed Hmisc and Design. When I use ols, I get the following error message: Error in if (!length(fname) || !any(fname == zname)) { : missing value where TRUE/FALSE needed The model that I am running is: > ecools <- ols(eco$exp ~ eco$age + eco$own + eco$inc + inc2, x=TRUE) I have tried several other combinations of arguments that take TRUE/ FALSE values, but no luck.

Dear All, I'm trying to use the ols function in the Design library (version 2.1.1) of R to estimate parameters of a linear model, and then use the contrast function in the same library to test various contrasts. As a simple example, suppose I have three factors: feature (3 levels), group (2 levels), and patient (3 levels). Patient is coded as a non-unique identifier and is

Dear R-help, I don't understand why Gls gives me an error when trying to fit a model with AR(2) errors, while gls (from nlme) does not. For example: library(nlme) library(rms) set.seed(1) d <- data.frame(x = rnorm(50), y = rnorm(50)) gls(y ~ x, data=d, correlation = corARMA(p=2)) #This works Gls(y ~ x, data=d, correlation = corARMA(p=2)) # Gives error # Error in

Hi everyone, I'm having some difficulty getting "simple effects" for the ols() function in the rms package. The example below illustrates my difficulty -- I'll be grateful for any help. #make up some data exD <- structure(list(Gender = structure(c(1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L), .Label = c("F", "M"), class = "factor"),

Hello, I have a question about the ?plot.predict? function in Frank Harrell's rms package. Do you know how to superpose in the same graph the prediction curve of ols and raw data points? Put most simply, I would like to combine these two graphs: > fit_linear <- ols (y4 ~ rcs(x2,c(5,10,15,20,60,80,90)), x=TRUE, y=TRUE) > p <- Predict(fit_linear,x2,conf.int=FALSE) > plot (p,

Dear R users, I tried to fit a cox proportional hazard model to get estimation of stratified survival probability. my R code is as follows: cph(Surv(time.sur, status.sur)~ strat(colon[,13])+colon[,18] +colon[,20]+colon[,9], surv=TRUE) Error in if (!length(fname) || !any(fname == zname)) { : missing value where TRUE/FALSE needed Here colon[,13] is the one that I want to stratify and the

A new version of rms is now available on CRAN for Linux and Windows (Mac will probably be available very soon). Largest changes include latex methods for validate.* and adding the capability to force a subset of variables to be included in all backwards stepdown models (single model or validation by resampling). Recent updates: * In survplot.rms, fixed bug (curves were undefined if

A new version of rms is now available on CRAN for Linux and Windows (Mac will probably be available very soon). Largest changes include latex methods for validate.* and adding the capability to force a subset of variables to be included in all backwards stepdown models (single model or validation by resampling). Recent updates: * In survplot.rms, fixed bug (curves were undefined if

Dear all, this might be not only an R-question but also a statistical. When I do a logistic regression analysis (species distribution modeling) with function lrm (Design package) I get the follwoing error message: > tadl1<-lrm(triad~fd+dista+fd2+dista2+fd:dista+dista:geo2, x=T, y=T) Error in if (!length(fname) || !any(fname == zname)) { : missing value where TRUE/FALSE needed The

hi all - i have a function that needs to call glm() with a weights argument that includes a variable whose name comes from the caller. so instead of: fit <- glm(formula, poisson(), data, weights = 1-z, ...), i do something like this: fit <- do.call("glm", list(formula=formula, family=poisson(), data=data, weights = call("-", 1, as.name(zname)), ...))

Sorry for the non-R question, but how do I reply through the Nabble interface and have my reply emailed to the person I'm replying to (in case they don't use Nabble), with cc to the mailing list? If I choose the option to reply to the person by email, I don't see an option to cc to the mailing list. If I reply to the list, there's an option to email the post to someone, but I

I'm trying to create a data frame in which some of the column names contain a dash "-". A simple example: d <- data.frame(x = c(0, 1)) d <- data.frame(d, y = c(0,1)) names(d)[2] <- "a.-5" d x a.-5 1 0 0 2 1 1 d <- data.frame(d, y = c(0,1)) d x a..5 y 1 0 0 0 2 1 1 1 names(d)[2] <- "a.-5" d x a.-5 y 1 0 0 0 2 1 1 1 Why

Dear all, When fitting an "ols.model", the confidence interval at 95% doesn't cover the plotted data points because it is very narrow. Does this mean that the model is 'overfitted' or is there a specific amount of serial correlation in the residuals? Which R functions can be used to evaluate (diagnostics) major model assumptions (residuals, independence, variance) when

Dear R-users, I am using R 2.13.0 and rms 3.3-0 , but can not reproduce figure 7.8 of the handouts *Regression Modeling Strategies* ( http://biostat.mc.vanderbilt.edu/wiki/pub/Main/RmS/course2.pdf) by the following code. Could any one help me figure out how to solve this? setwd('C:/Rharrell') require(rms) load('data/counties.sav') older <- counties$age6574 + counties$age75

This isn't a question about R, but I'm hoping someone will be willing to help. I've been looking at calibration plots in multiple regression (plotting observed response Y on the vertical axis versus predicted response [Y hat] on the horizontal axis). According to Frank Harrell's "Regression Modeling Strategies" book (pp. 61-63), when making such a plot on new data