similar to: Negative Binomial Predictions

Good Day, I have several ASCII data files that I would like to import into R. They all have a SAS import file which is used to bring the data into SAS and I am hoping to use this to bring the data into R. There are lots of variables involved and the ASCII data file is 2308 columns long so I would certainly prefer to figure out a smart way of converting the data to R. The ASCII data is a

Hi All, Could someone help me decode what this error means ? > BIC(nb.80) Error in log(attr(object, "nobs")) : Non-numeric argument to mathematical function > BTW, nb.80 is a negative binomial glm model created using the MASS library with the call at the bottom of the message In the hopes of trying to figure this out I tried the following workaround but it did not work

Hi All, I am working on some ordinal logistic regresssions using LRM in the Design package. My response variable has three categories (1,2,3) and after using the creating my model and using a call to predict some values and I wanted to use a simple .5 cut-off to classify my probabilities into the categories. I had two questions: a) first, I am having trouble directly accessing the

Good Day All, I am working on some xyplots using the Lattice Library. My X-axis is the date and I am reproducing charts similar to those found in the R Gallery (see here: http://www.sr.bham.ac.uk/~ajrs/R/gallery/plot_midday_weather_profiles.txt) However, the key difference is that some of my data is missing (not collected at that time). For instance, I might have a whole month that I do

Good Day All, I have a negative binomial model that I created using the function glm.nb() with the MASS library and I am performing a cross-validation using the function cv.glm() from the boot library. I am really interested in determining the performance of this model so I can have confidence (or not) when it might be applied elsewhere If I understand the cv.glm() procedure correctly, the

Hello ; I am doing a regression of count data (number of award and there are some covariates) I have estiamted the parameters of negative binomial distribuion (lambda is a function of covaraites, GLM model) by glm.nb function and training dataset. Now I want to predict the number of award (for example y=0, y=1, y=2,) or testing dataset. I dont know how to calculate this numbers? I would be very

Dear all, I'm using zeroinfl() from the pscl-package for zero inflated Poisson regression. I would like to calculate (aproximate) prediction intervals for the fitted values. The package itself does not provide them. Can this be calculated analyticaly? Or do I have to use bootstrap? What I tried until now is to use bootstrap to estimate these intervals. Any comments on the code are welcome.

Dear R-Help listers, I am trying to estimate an proportional odds logistic regression model (or ordered logistic regression) and then make predictions by supplying a hypothetical x vector. However, somehow this does not work. I guess I must have missed something here. I first used the polr function in the MASS package, and I create a data frame and supply it to the predict function (see below):

Dear R helpers, running the following code of a glm model of the family poisson, gives predicted values < 0. Why? library(MASS) library(stats) library(mvtnorm) library(pscl) data(bioChemists) poisson_glm <- glm(art ~ fem + mar + kid5 + phd + ment, data = bioChemists, family = poisson) predicted.values = predict(poisson_glm) range(predicted.values) Thank you in advance for any hints.

Dear All, I am using the function vuong from pscl package to compare 2 non nested models NB1 (negative binomial I ) and Zero-inflated model. NB1 <-  glm(, , family = quasipoisson), it is an object of class: "glm" "lm" zinb <- zeroinfl( dist = "negbin") is an object of class: "zeroinfl"   when applying vuong function I get the following: vuong(NB1,

Hi all-- I am in the process of helping colleagues write up a ms in which we fit zero-inflated Poisson models. I would prefer plotting the rate ratios and 95% CI (as I've found Gelman and others convincing about plotting tables...), but our journals usually like the numbers themselves. Thus, I'm looking at a recent JAMA article in which both numbers and dotplot of RR and 95% CI are

Hello, Frank was nice enough to point me to the val.prob function of the Design library. It creates a beautiful graph that really helps me visualize how well my model is predicting probabilities. By default, there are two lines on the graph 1) fitted logistic calibration curve 2) nonparametric fit using lowess Right now, the nonparametric line doesn't look very good. The

Dear Friends, My problem is related to how to measure probabilities from a probit model by changing one independent variable keeping the others constant. A simple toy example is like this Range for my variables is defined as follows y=0 or 1, x1 = -10 to 10, x2=-40 to 100, x3 = -5 to 5 Model output <- glim(y ~ x1+x2+x3 -1, family=binomial(link="probit")) outcoef <-

Hi, I am trying to replicate Lambert (1992)'s simulation with zero-inflated Poisson models. The citation is here: @article{lambert1992zero, Author = {Lambert, D.}, Journal = {Technometrics}, Pages = {1--14}, Publisher = {JSTOR}, Title = {Zero-inflated {P}oisson regression, with an application to defects in manufacturing}, Year = {1992}} Specifically I am trying to recreate Table 2. But my

Please help getting the R squared value in asymptotic regression model I use the code below model1<-nls(GN1~SSasymp (nrate,a,b,c), data = data.1 ) and R produced the modell coefficients without the R squared value? -- Ahmed M. Attia Research Assistant Dept. Of Soil&Crop Sciences Texas A&M University ahmed <ahmedatia@zu.edu.eg>.attia@ag.tamu.edu Cell phone:

Are you referring to the zeroinfl() function in the countreg package? If so, I think predict(fm_zinb2, type = "zero", newdata = some.new.data) will give you pi for each combination of covariate values that you provide in some.new.data where pi is the probability to observe a zero from the point mass component. As to your second question, I'm not sure that's possible, for any

I am running a zero inflated regression using the zeroinfl function similar to the model below: fm_zinb2 <- zeroinfl(art ~ . | ., data = bioChemists, dist = "poisson") summary(fm_zinb2) I have three questions: 1) How can I obtain a value for the parameter pie, which is the fraction of the population that is in the zero inflated model vs the fraction in the count model? 2) For

Hello, I am working with zero inflated models for a current project and I am getting wildly different results from R's zeroinfl(y ~ x, dist="negbin") command and Stata's zinb command. Does anyone know why this may be? I find it odd considering that zeroinfl(y ~ x, dist="poisson") gives identical to output to Stata's zip function. Thanks, --david [[alternative

I have installed R on my machine. Can anyone now suggest to me the best book/e-book from where I can learn the R language most efficiently? Thanks in advance -- Siddhant Gupta III Year Department of Biotechnology IIT Roorkee India [[alternative HTML version deleted]]

I am trying to drop rows of a dataframe based on values of the column PID, but my strategy is not working. I hope someoen can tell me what I am doing incorrectly. # Values of PID column > jdata[,"PID"] [1] 16608 16613 16355 16378 16371 16280 16211 16169 16025 11595 15883 15682 15617 15615 15212 14862 16539 [18] 12063 16755 16720 16400 16257 16209 16200 16144 11598 13594 15419 15589