similar to: Possible bug with lrm.fit in Design Library

Hi, I've come across a strange error when using the lrm.fit function and the subsequent predict function. The model is created very quickly and can be verified by printing it on the console. Everything looks good. (In fact, the performance measures are rather nice.) Then, I want to use the model to predict some values. I get the following error: "fit was not created by a Design

Hello, I am trying to get the 'rank' function to work for me, but not sure what I am doing wrong. Please help. I ran the following commands: data = read.table("test1.csv", head=T, as.is=T, na.string=".", row.nam=NULL) X1 = as.factor(data[[3]]) X2 = as.factor(data[[4]]) X3 = as.factor(data[[5]]) Y = data[[2]] model = lm(Y ~ X1*X2*X3, na.action = na.exclude) fmodel =

Hello I'm using logistic regression from the Design library (lrm), then fastbw to undertake a backward selection and create a reduced model, before trying to make predictions against an independent set of data using predict.lrm with the reduced model. I wouldn't normally use this method, but I'm contrasting the results with an AIC/MMI approach. The script contains: # Determine full

Hello, Fitting a piecewise smooth curve to a set of points (and a piecewise linear function in particular) seems to be a recurring question on this list. Nevertheless, I was not able to find an answer to a question that bothers me. Suppose I have the following data set, and would want to fit it with a piecewise smooth curve, In this model data, one curve is valid for up to 3 and another one for

> On Sep 14, 2017, at 12:30 AM, Bonnett, Laura <L.J.Bonnett at liverpool.ac.uk> wrote: > > Dear all, > > I am using the publically available GustoW dataset. The exact version I am using is available here: https://drive.google.com/open?id=0B4oZ2TQA0PAoUm85UzBFNjZ0Ulk > > I would like to produce a nomogram for 5 covariates - AGE, HYP, KILLIP, HRT and ANT. I have

I'm trying to learn how to use the lrm() function by simulating data using an old dataset but it's giving me an error I don't understand: (nst$regular already exists) nst$regular<-as.ordered(nst$regular) nst$age<-rnorm(n=942,mean=43.20488,sd=17.03) nst$age<-round(age,digits=0) regform<-regular~age reglrm<-lrm(regform,nst) summary(reglrm) Error in

Hello, I have question regarding the lrm function and estimating the odds ratio between different levels of a factored variable. The following code example illustrates the problem I am having. I have a data set with an outcome variable (0,1) and an input variable (A,B,C). I would like to estimate the effect of C vs B, but when I perform the summary I only get A vs B and A vs C, even though I

Hi Does anyone know whether the rms package provides a confidence interval for the bootstrap-corrected Dxy or c-index? I have fitted a logistic model, and would like to obtain the 95% confidence interval of the bootstrap-corrected area under the ROC curve estimate. Thanks. [[alternative HTML version deleted]]

The code library(Design) f <- lrm(y~x1+x2+x1*x2, data=data) plot(f) produces a plot of log odds vs x2 with 0.95 confidence intervals. How do I get a plot of odds ratios vs x2 instead? Thanks -- View this message in context: http://r.789695.n4.nabble.com/Odds-ratios-from-lrm-plot-tp4033340p4033340.html Sent from the R help mailing list archive at Nabble.com.

Dear all, I'm using the lrm function from the package "Design", and I want to extract the p-values from the results of that function. Given an lrm object constructed as follows : fit <- lrm(Y~(X1+X2+X3+X4+X5+X6+X7)^2, data=dataset) I need the p-values for the coefficients printed by calling "fit". fit$coef (gives a list of only the coefficients) fit$pval, fit$p,

I would appreciate if someone could tell me how to fit a non-intercept model using lrm (and not glm). The -1 in the formula of the glm does not work with lrm. Thanks, Clarissa [[alternative HTML version deleted]]

Dear useR's, I was comparing results for a logistic regression model between different library's. themodel formula is arranged as follows: response ~ (intercept) + value + group OR: glm( response ~ (intercept) + value + group , family=binomial(link='logit')) lrm( response ~ (intercept) + value + group ) ROC( from = response ~ (intercept) + value + group ,

Hi, I am planning to externally validate a logistic prediction model in a new cohort. Outcome is mortality. The betacoefficients were derived from a previous published article. It seems not possible in R to assign fixed beta coefficients to predictors like lrm (death ~ intercept+beta1*var1+beta2*var2...). How do i solve this problem? Thank you in advance. Joey L -- View this message in context:

Hi, I am wondering if there is a way to specify the prevalence of events in logistic regression using lrm() from Design package? Linear Discriminant Analysis using lda() from MASS library has an argument "prior=" that we can use to specify the prevalent of events when the actual dataset being analyzed does not have a representative prevalence. How can we incorporate this information in

Hi I'm sure this is straightforward, but I can't find an answer. I'm trying to find the function that returns the number of dependent variables/rank of the regression/degrees of freedom/something similar. Any ideas? Thanks! Paul [[alternative HTML version deleted]]

Dear all, I have been using the lrm function in R to run an ordinal logistic regression and I am a bit confused about the methods for checking the model assumptions. I have produced residual plots in R of the score.binary type which I think look ok. However, the partial type plots show bell shaped patterns and have crossing lines, indicating violation of parallelism. However, I noticed

I cannot seem to get the aic or extractaic call to work with multinomial logistic regression models. Here is what I am doing: library('Design') lrm1<-lrm(r1~p1) #where p1 is multinomial and r1 is binomial library('MASS') aic(lrm1) Error in if (fam %in% c("gaussian", "Gamma", "inverse.gaussian")) p <- p + : argument is of length zero

Hello all, Could someone tell me what I am doing wrong here? I am trying to fit a binary logistic model using the lrm function in Design. The dataset I am using has a dichotomous response variable, 'covered' (1-yes, 0-no) with explanatory variables, 'nepall', 'title', 'abstract', 'series', and 'author1.' I am running the following script and

Dear R-list, Is there a function or technique by which the probability (or log odds) range of a logistic model (fit <- lrm(Y~X)) can be derived? The aim is to obtain min & max of the estimated probabilities of Y. Could summary.Design() be used for that or is there another method/trick? Thanks, Jan _______________________________________________________________________ ir. Jan

Dear R helpers, >From the lrm( ) model used for binary logistic regression, we used the L.R. model value (or the G2 value, likelihood-ratio chi-squared statistic) to evaluate the goodness-of-fit of the models. The model with the lowest G2 value consequently, has the best performance and the highest accuracy. However our model includes rsc() functions to account for non-linearity. We