similar to: Adapting thresholds for predictions of ordinal logistic regression

Dear all, I have two questions that are almost completely related to how to do things in R. I am running an ordinal probit regression analysis in R. The dependent variable has three levels (0=no action; 1=warning; 2=sanction). I use the lrm command in the rms package: print( res1<- lrm(Y ~ x1+x2+x3+x4+x5+x6, y=TRUE, x=TRUE, data=mydata)) I simply couldn't make any sense of the

Dear List, I have two questions about how to do predictions using lrm, specifically how to predict the ordinal response for each observation *individually*. I'm very new to cumulative odds models, so my apologies if my questions are too basic. I have a dataset with 4000 observations. Each observation consists of an ordinal outcome y (i.e., rating of a stimulus with four possible

This is a follow up to the message I posted 3 days ago about how to estimate mixed ordinal logit models. I hope you don't mind that I am just pasting in the code and comments from an R file for your feedback. Actual estimates are at the end of the post. ### Subject: mixed ordinal logit via "augmented" data setup. ### I've been interested in estimating an ordinal logit model

Hello r helpers! Below is the whole coding for my programme. Before proceed more further, let me explain for you. First of all, I need to compute trimmed mean. Till that step is ok. Then I need to compute ssdw which is sum of square deviation. If I do equal trimming at both tail of distribution that I chose, I will use the first ssd formulae which is "a". But if I am doing unequal

Hello: I hope someone can help. I want to run a multinomial logit model where the response variable is ordinal and the covariates are nominal. The particular type of model I wish to run is a "baseline logit model." Is it possible to do so in R? I have seen that lrm() can run "continuation-ratio" and "proportional odds" logit models, but not "baseline"

I have a spatial data set with ordinal response variable containing four levels. I would like to know if and how spatial autocorrelation can be taken into account when ordinal logistic regression is used (e.g. the function lrm from the Design package). Thanks for your help! Christof

When I run "lrm" from the Design package, I get a warning about contrasts when I include an ordinal variable: Warning message: Variable ordfac is an ordered factor. You should set options(contrasts=c("contr.treatment","contr.treatment")) or Design will not work properly. in: Design(eval(m, sys.parent())) I don't get this message if I use glm with

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

Dear all, I am new to R and would like to run a multinomial logistic regression on my dataset (3 predictors for 1 dependent variables) I have used the vglm function from the VGAM package and got some results. Using the predict() function, I obtained the probability table I was looking for. However, I would like to fully understand how the predict() function generates the probabilities or in

Hi, ?? Are there any packages which prints out p-values for OLR's (like `ologit' from Stata)? I want to run a bunch of OLRs and print the p-value for the first coefficient from each of them. ? I checked polr() under MASS and it doesn't. ?There's a lrm() function under Design which does print out p-values but I couldn't extract p-values from the output. ? Thanks, ? Debs

lrm does some binning to make the calculations faster. The exact calculation is obtained by running f <- lrm(...) rcorr.cens(predict(f), DA), which results in: C Index Dxy S.D. n missing 0.96814404 0.93628809 0.03808336 32.00000000 0.00000000 uncensored Relevant Pairs Concordant Uncertain 32.00000000

Please forgive a rather na??ve question... Could someone please give a quick explanation for the differences in conf intervals achieved via confint.glm (based on profile liklihoods) and the intervals achieved using the Design library. For example, the intervals in the following two outputs are different. library(Design) x = rnorm(100) y = gl(2,50) d = data.frame(x = x, y = y) dd = datadist(d);

Hello All, I have two dataframes and I wish to insert the values of one dataframe into another (let's call them DF1 and DF2). DF1 looks like this: col1.....col2 a...........1 b...........2 c...........3 d...........4 e...........5 f............6 g...........7 where col1 (which is just the first column of the dataframe) is a list of characters and col2 is the numeric value associated with

Hi, I have a grouped data set and would like to calculate weighted proportions for a large number of factor variables within each group member. Rather than using dplyr::count() on each of these factors individually, the idea would be to do it for all factors at once. Does anyone know how this would work? Here is a reproducible example: ############################################################

If you want colors mapped to the _values_ in DF1$C, there are a number of ways to do it: Color_unq<-color.scale(DF1$C,c(1,0),c(0,0,c(0,1)) This will produce colors from the lowest values (red) through the highest (blue). See the help page for color.scale to get different colors. With this you can use color.legend to add a mapping of the values and colors. If you just want different colors,

Full_Name: Long Qu Version: 2.3.1 OS: Windows XP Submission from: (NULL) (64.113.93.235) The QQ-plot of two versions of simulating noncentral F-distributed random numbers has quite different scales: > qqplot(rf(1000,2,15,3),qf(runif(1000),2,15,3)) The rf() function reads: > rf function (n, df1, df2, ncp = 0) { if (ncp == 0) .Internal(rf(n, df1, df2)) else rchisq(n, df1,

Hi folks, Wish y'all a Happy New Year 2010! I need some help with the following: Say I have lots of data sets, on which I have to apply a certain function on the same set of columns in each of the data set. Let's take, for ex, the typical data set is: df1 <- as.data.frame(cbind(rnorm(10),rnorm(10))) names(df1)[1] <- "A" names(df1)[2] <- "B" There are many

I had meant to copy the list on this; must have hit 'Reply' instead of 'Reply All'. P Ehlers -------- Original Message -------- Subject: Re: [R] rbind with partially overlapping column names Date: Mon, 16 May 2011 11:14:11 -0600 From: Peter Ehlers <ehlers at ucalgary.ca> To: Jonathan Flowers <jonathanmflowers at gmail.com> On 2011-05-16 08:56, Jonathan Flowers wrote:

Hi, Attention chi-squared distribution, unlike F distribution, has only df1 as parameter, not df1 and df2. So correct into: outer(1:3, 1:3, function(df1, df2) qchisq(0.95, df1, df2)) outer(1:3, 1:3, function(df1, df2) qchisq(0.95, df1)) ^^^^^^^^^^^^^^^^^^^^ Regards, Vito you wrote: Dear Rs: outer(1:3, 1:3, function(df1, df2) qf(0.95, df1, df2)) I compare this F

Then you need to rethink your data structure. Use a list instead of a data frame. The components of a list can have different lengths, and the "apply" family of functions (lapply(), etc.) can operate on them. Consult any good R tutorial for details. Cheers, Bert Bert Gunter "The trouble with having an open mind is that people keep coming along and sticking things into it."