similar to: summary(polr.object)

Dear all, I would like to know if there is a function for sorting a data.frame based on one column. sort() does it for a single vector but not for the whole data. order() does it if there are relations between the columns but in my case it is simply a data.frame. Further, I would like to plot other data, pop.size<- c(800, 800, 1500, 1000, 158, 300, 740, 250, 2000, 1500, 250, 700)

Dear all, I get an error message when I use polr() in MASS. These are my data: skugg grupp frekv 4 1 gr3 0 5 2 gr3 3 6 3 gr3 6 10 1 gr5 1 11 2 gr5 12 12 3 gr5 1 > > summary(polr(skugg ~ grupp, weights=frekv, data= skugg.cpy1.dat)) Error in optim(start, fmin, gmin, method = "BFGS", hessian = Hess, ...) :

I am running a binomial glm with response variable the no of mites of two species y->cbind(mitea,miteb) against two continuous variables (temperature and predatory mites) - see below. My model shows overdispersion as the residual deviance is 48.81 on 5 degrees of freedom. If I use quasibinomial to account for overdispersion the dispersion parameter estimate is 2501139, which seems

Hi, I have a problem with a regression I try to run. I did an estimation of the market model with daily data. You can see to output below: /> summary(regression_resn) Time series regression with "ts" data: Start = -150, End = -26 Call: dynlm(formula = ror_resn ~ ror_spi_resn) Residuals: Min 1Q Median 3Q Max -0.0255690 -0.0030378 0.0002787

Hi (1)In polr(), is there any way to calculate a pseudo analogue to the R^2. Just for use as a purely descriptive statistic of the goodness of fit? (2) And: what are the assumptions which must be fulfilled, so that the results of polr() (t-values, etc.) are valid? How can I test these prerequisites most easily: I have a three-level (ordered factor) response and four metric variables. many

Hi, I got a problem with polr function a bit. I have this error: attempt to find suitable starting values failed I wonder what would be an appropriate way to solve this problem? I can try to specify some random starting value but I am afraid that it will cause the MLE to stuck at some local maxima. Is there anyway to cope with this in a more elegant way? Any help would be really appreciated.

Hello R-users, I am using polr function in library(MASS). The code I use is the following: polr(as.ordered(q23p)~.,data=as.data.frame(datapr2)) where datapr2 is a matrix of 63 columns (together with the dependent variable) and 1665 rows. But I am receiving the warning message Error in optim(start, fmin, gmin, method = "BFGS", hessian = Hess, ...) I would be very greatfull if anyone

Hi all, I am using polr(). The resulting coefficients of first levels are always 0. What to do if I wnat to get the coefficients of the last level 0. For example, suppose x has 3 levels, 1, 2, 3 probit <- plor(y ~ x, data1, method='probit') will get coefficients of level 2, 3 of x, but I want coefficients of level 1, 2 Thank you, Tian [[alternative HTML version deleted]]

Hi all, The problem is that when you try to use the function summary of a polr object in a function, it does not work. The problem is not related to the formula or the structure of data involved. It is probably related to the use of the function "vcov" in the code of summary for polr, and the iterative procedure to estimate the Hessian. Anyway, here there is an example extracted from

I am learning R via a textbook that performs analysis with SPSS and SAS. In trying to reproduce the results for an ordinal logit model, I get very similar point estimates for my cut-off points, but the parameters for the covariate q60 do not match. The estimate for q51 also matches. Is this because I need to change a base case for the ordered covariate q60? Can this be done in or is it always the

Hi, I am searching for methods to compare regression models with an ordered categorical response variable (polr versus multinom). The pattern of predictions of both methods (using the same predictor variables) is quite different and the AIC is smaller for the multinom approach. I guess polr has more strict premises for the structure of the response variable, which methods can be used to test for

Dea all, Let's suppose I am studying a questionnaire survey and one of the questions has three ordered categorical responses (say, A, B and C). Eg result<-ordered(c(rep("A",12),rep("B",37),rep("C",6))) Assume the respondents are not grouped. The differences between the subsequent levels can be, I think, modeled with polr: fit<-polr(result~1) summary(fit)

Using ordered probit model, I get errors from dwt and bptest. dwt: Error in durbinWatsonTest.default(...) : requires vector of residuals bptest: Error in storage.mode(y) <- "double" : invalid to change the storage mode of a factor I imagine I have to restate as an individual probit model for each category, but is there an easier way? thanks, bp [[alternative HTML version

For the following model, library(vcd) arth.polr <- polr(Improved ~ Sex + Treatment + Age, data=Arthritis) summary(arth.polr) where Improved is an ordered, 3-level response I'm looking for a *simple* way to test the validity of the proportional odds assumption, typically done via a score test for equal slopes/effects over the predictors. I do find a po.test= option in the repolr package

Hi everyone, I'm trying to understand some R output here for ordinal regression. I have some integer data called "A" split up into 3 ordinal categories, top, middle and bottom, T, M and B respectively. I have to explain this output to people who have a very poor idea about statistics and just need to make sure I know what I'm talking about first. Here's the output:

Hi, I have a problem with initial value for optim in polr that R report. After a call to polr, it complains that: Error in optim(start, fmin, gmin, method="BFGS", hessian= Hess, ...) : initial value in 'vmin' is not finite. Would you please suggest a way round to this problem? Thank you so much in advance. Rgds, - adschai

Hi, I'm trying to fit a ordered logistic regression. The response variable (y) has three levels (0,1,2). The command I've used is: ordlog<-polr(y~x1+x2+x3+x4, data=finalbase, subset=heard, weight=wt, na.action=na.omit) (There are no NA's in y but there are NA's in X's) The error I'm getting is: Warning messages: 1: non-integer #successes in a binomial glm! in:

I'm running polr() and getting warning messages from glm.fit(). It seems reasonable to use glm.control() to turn on the trace and follow what glm.fit() does when called by polr(); or is it? glm.control(maxit=10, trace=TRUE) polr(act~., data=mm) The glm.control() sets the trace TRUE, but there's no change in the output from polr(). Many thanks in advance for any help/pointers.

First, my apologies for not giving all the details in my first post. Second, the problem was somewhat more complicated than simply using help.search('polr') or library(MASS). When I tried these, I got notices that polr could not be found anywhere, and that no package called MASS existed. When I went to the CRAN site, there was no package called MASS. I am not sure how I installed R

John Fox wrote <<< >From your description, it seems possible that there are too many zeros for a Poisson or negative-binomial model. Since the focus of your paper is the methodology, you might want to try a zero-inflated Poisson or negative-binomial model. Though I haven't tried them, I'm aware of two sources of R functions for zero-inflated count models -- zeroinfl(), from