similar to: Problems with Z in rhierMnlRwMixture using bayesm

Is anyone familiar with a way to account for sampling weights (e.g., in order to cope with selection bias) for individual respondents using the bayesm package (e.g., rhierMnlRwMixture)? In the regular MNL this can easily be done in STATA using the mlogit function with pweights option. However, I am unfamiliar with a way to do it in HB estimation. Any help or hints are appreciated. Best, Klaus

Hello! I am using rhierMnlRwMixture from bayesm package. I would like to use it with a categorical covariate (Z). I have 2 clariciation questions: 1. If the covariate is categorical, do I have to represent it as dummy variable(s)? (e.g., 2 dummy variables for a 3-level categorical variable)? 2. Do those dummy variables have to be centered? Help file for rhierMnlRwMixture says: "Z should not

Hi all, I have managed to get the r-scale usage algorithm to work, but I need to obtain the final results from this. As I understand it, this code is designed to generate a matrix after processing and store it somewhere????? Here is the code..... I get this part of the code, it all makes sense. ## if(nchar(Sys.getenv("LONG_TEST")) != 0) {R=1000} else {R=5} { data(customerSat)

Dear All, I've been using mcmcsamp() successfully with a few different mixed models but I can't get it to work with the following. Is there an obvious reason why it shouldn't work with a model of this structure ? *brief summary of objective: I want to test the effect of no-fishing marine reserves on the abundance of a target species. I have samples at coral reef sites inside and

Hi all, I'm running a multidimensional scaling model on data that are first transformed into a similarity matrix using the program daisy in the cluster package. If I already provide the similarity matrix, the plotting routine will give me the variable names on the plot itself. But, it seems that when I use the daisy program to create the similarity matrix, I can't get the program

Hi all, I am running regressions with many covariates, most of which remain the same each time (control variables). Instead of writing 30 demographic variables every regression, is there a way I could call them all at once using a variable called, perhaps "demog"? I have tried: > demog <- list(age1, age2, age3) but I get an error when I try to call a list in a regression. I also

Version 2.0-2 of bayesm is available on CRAN. This version includes bug fixes for rhierMnlRwMixture and rhierLinearModel. peter rossi _______________________________________________ R-packages mailing list R-packages at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/r-packages

Version 2.0-2 of bayesm is available on CRAN. This version includes bug fixes for rhierMnlRwMixture and rhierLinearModel. peter rossi _______________________________________________ R-packages mailing list R-packages at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/r-packages

I've attached a perl script that I wrote to build smbpasswd from /etc/passwd. Please note that this writes a samba-2.0 format smbpasswd file. This script will: # - create accounts that exist in /etc/passwd and not in smbpasswd # - remove accounts that exist in smbpasswd and not in /etc/passwd # - preserve existing password, flags and LCT fields in smbpasswd # - sets new account passwords to

Hello, I'm having trouble correctly specifying the random effects for a nlme model. The general summary of what I'm trying to do is that I've got a data set that has multiple individuals and multiple machines that took measurements from those individuals. At least one of the machines has drift during the day causing a visually linear decrease in the readout during the day, so I have

Greetings- We use smbclient -M to send a Message of the Day to clients every once in a while. The clients are NT4 (SP3), and the server is Samba 1.9.19-prealpha. However, the same problem appears with version 2.0.0. The issue is: once the file to be sent exceeds approximately 675 bytes (smbclient reports sending 975 bytes, presumably including some overhead), the message turns up blank on the

Dear r-help, I am trying to plot several scatter plots with marginal histograms on one page. Ideally, a page is equally divided into 4 figure regions. Within each figure region, a scatter plot with marginal histograms will be plotted. I followed Dr. Paul Murrell's code released online to successfully plot the scatter plot with marginal histograms. The code applies "layout()" to

Dear All, I am fairly new to R. I work mainly in SAS. Now, I know that SAS is approved by the FDA for submissions. My question is, does the FDA approve {R} for clinical trial submissions. Also has anyone ever tried to produce TFL's using R. I would like to know how difficult it to produce the TFL's in R as compared to SAS. I know that in SAS it is not difficult once you know

R-help, I am tring to create a plot with two y-axis. I found an example which is fine but the problem is that the range of the second y-axes appears in the first y-axes causing confusion. The example I refer to is : ################################## dev.off() ## start with a new graphics device # X11() or postscript() plot(x<-rnorm(100),y<-rnorm(100)) z<-rnorm(100)*250 par(new=T)

Greetings, again. This is not strictly an R question, so please feel free to ignore it if you like. My question is about the substance of correspondence analysis. Specifically, is it appropriate to use ca on a matrix of values such that the columns and/or rows are not mutually exclusive? To be more detailed: - The standard use of ca is illustrated in the example of corresp() (from MASS):

Below you will find the output from a failed multi-level model run. I am trying to estimate the following model: Pr(PLFP=1)= logistic regression -> B1_j * bm + B2_j * wm + B3_j bf + B4_j wf + B5 yrsed+ B6 age+ B7 age^2+e_ij B1_j = G01 + G11 bmxd + d1 B2_j = G02 + G12 wmxd + d2 B3_j = G03 + G13 bfxd + d3 B4_j = G04 + G14 wfxd + d4 d1-d4 freely correlated Note that there is no

Greetings - In trying to do a multiple correspondence analysis, I need to coerce a data frame such that each of its columns will be a factor. Can someone offer advice on how to make this happen? I've tried this: > logic.resources.f.df<-apply(logics.resources.df, 2, factor) but: > is.factor(logic.resources.f.df$interests) [1] FALSE I've also tried individually, >

Greetings. I'm using plot.mca (from MASS) to construct some correspondence analyses of data drawn from focus-group transcripts. My question is simple albeit rather open-ended: I'm wondering what options there might be to plot.mca for tailoring the plots to my needs. The documentation to the function is somewhat sparse. Thanks- Andy Perrin

Greetings- I've got some plots I'd like to include in a LaTeX document; specifically, I'd like to include them via pictex() so I can edit some of the particulars directly. However, an odd problem is coming up: a diagonal line is drawn from bottom-left to upper-right when using pictex(). This does not happen using X11() or postscript() with the same series of commands. Any ideas why

Can anyone explain this behavior? Essentially, I've created a short file to be read in via source() that gets some descriptive information on a series of variables in a data frame. For each variable, I do three things: print('last.hc.actors') quantile(last.hc.actors,probs=seq(0,1,0.1),na.rm=T) stem(last.hc.actors) where the variable name is (in this case) last.hc.actors. All that