similar to: multinomRob: Error in eigen [..] infinite or missing values in 'x'

Dear all, I am facing some problem with how to fit a "Baseline category Logit model" with R. Basically I am considering famous "Alligator" data as discussed by Agresti. This data can also be found here: https://onlinecourses.science.psu.edu/stat504/node/174 (there is also an accompanying R file, however the underlying R code could not load the data properly!!!) Below are

All, What would be the most efficient way to load the data at the following address into a dataframe? http://ratings.fide.com/top.phtml?list=men Thanks, David -- View this message in context: http://r.789695.n4.nabble.com/Loading-Chess-Data-tp4642006.html Sent from the R help mailing list archive at Nabble.com.

We would like to announce the availability on CRAN of a new package multinomRob. It does robust estimation of overdispersed multinomial regression models. The package is also able to estimate overdispersed grouped multinomial logistic and multivariate-t logistic models. The code is relatively general; for example, it allows for equality constraints across parameters and it can handle datasets in

We would like to announce the availability on CRAN of a new package multinomRob. It does robust estimation of overdispersed multinomial regression models. The package is also able to estimate overdispersed grouped multinomial logistic and multivariate-t logistic models. The code is relatively general; for example, it allows for equality constraints across parameters and it can handle datasets in

Hi Faradj, What a problem! I think I have worked it out, but only because the result is the one you said you wanted. # the sample data frame is named fkdf Y2Xby3<-function(x) { nrows<-dim(x)[1] X<-rep(0,nrows) for(i in 1:(nrows-2)) { if(!is.na(x$Y[i])) { if(x$Y[i] == 1 && any(is.na(x$Y[(i+1):(i+2)]))) X[i]<-1 if(i > 1) { if(X[i-1] == 1) X[i]<-0 } }

Hi, I would like to use the multinomRob function to test election results. However, depending on which independent variables I include and how many categories I have in the dependent variable, the model cannot be estimated. My data look like this (there are 68 observations): > head(database) RESTE09 GAUCHE09 PDC09 PLR09 UDC09 MCG09 RESTE05 GAUCHE05 PDC05 D1 1455

Dear Jim, wow! It worked! Thanks a lot. I did as you suggested and it worked well with the real data. Although it gave me this error: Error in if (!is.na(x$Y[i])) { : argument is of length zero. For some reason the X1 produced less observations than it is in the data. But it's not a big deal - I identified those cases and simply deleted from the data (it was countries that only appeared

Hi everyone, I am trying to generate a conditional dummy variable ?X" with the following rules set X=1 if Y is =1, two years prior to the NA. [0,0,NA]. For example, if the pattern for Y is 0,0,NA then the X variable is =0 for all the two years prior to the NA. If the pattern for Y is 0,1,NA or 1,0,NA then the X =1 . To be clear, if 1,1,NA then the X=1 that first specific year, it

Does the following work for you? ggplot2::ggplot(plotFrame, aes(x = time, y = depth, height = cycle, group = depth)) + ggridges::geom_ridgeline(fill="red", min_height=-0.25) Bill Dunlap TIBCO Software wdunlap tibco.com On Tue, Oct 17, 2017 at 12:43 PM, Roy Mendelssohn - NOAA Federal < roy.mendelssohn at noaa.gov> wrote: > I have tried: > > ggplot(plotFrame, aes(x =

The min_height = -0.25 is there to make it show cycle values down to -1/4. You may want to change it to -1 so it shows more of the cycle values. Bill Dunlap TIBCO Software wdunlap tibco.com On Tue, Oct 17, 2017 at 1:26 PM, Roy Mendelssohn - NOAA Federal < roy.mendelssohn at noaa.gov> wrote: > yes, thanks, and I was getting close to that. One thing I found is the > manual says the

I have tried: ggplot(plotFrame, aes(x = time, y = cycle, height = cycle, group = depth)) + geom_ridgeline() ggplot(plotFrame, aes(x = time, y = depth, height = cycle, group = depth)) + geom_ridgeline() ggplot(plotFrame, aes(x = time, y = depth, group = depth)) + geom_density_ridges() none are producing a plot that was a ridgeline for each depth showing the time series at that depth. The plot

...and your question is...? ... and the code you tried that didn't work was? Bert On Oct 17, 2017 12:22 PM, "Roy Mendelssohn - NOAA Federal" < roy.mendelssohn at noaa.gov> wrote: > Hi All: > > I am just not understanding ggridges. The data I have are time series at > different depths in the ocean. I want to make a joy plot of the time > series by depth.

Hi All: I am just not understanding ggridges. The data I have are time series at different depths in the ocean. I want to make a joy plot of the time series by depth. If I was just doing a ggplot2 line plot I would be doing: ggplot(plotFrame, aes(x = time, y = cycle, group = depth)) + geom_line() but translating that to ggridges has not worked right. Below is the result from dput() of a

yes, thanks, and I was getting close to that. One thing I found is the manual says the height is the distance above the y-line, which should be, but doesn't have to be positive. In fact, the time series are estimates of a cycle, and has negative values, which unfortunately are not included in my sub-sample. And the negative values are not handled properly (the series disappears for

I am having difficulty understanding how I would constrain a data set by filtering out 'records' based on certain criteria. Using SQL I could query using 'select * from my.data where LithClass in ('sand', 'clay')' or some such. Using subset, there seem to be ghosts left behind (that is, all of the LithClass *.Labels* remain after subset) > dput(tcc)

Hello, Two lapply questions (system info and sample data below): 1) Why does the first form of command1 add the name of y _after_ the str() output rather than before as does the second (preferred) form? # command1 version1 invisible(lapply(ls(pattern='bn'), function(y) cat(y, "\n", str(get(y)), "\n") )) # command1 version2 (preferred output)

Hi - I'd like to construct and plot the percents by year in a small data set (d) that has values between 1988 and 2007. I'd like to have a breakpoint (buy no discontinuity) at 1996. Is there a better way to do this than in the code below? > d year percent se 1 1988 30.6 0.32 2 1989 31.5 0.31 3 1990 30.9 0.30 4 1991 30.6 0.28 5 1992 29.3 0.25 6 1994 30.3

Hi, I'm trying to move to R the last few data handling routines I was performing in SAS. I'm working on stomach content data. In the simplified example I provide below, there are variables describing the origin of each prey item (nbpc is a ship number, each ship may have been used on different trips, each trip has stations, and individual fish (tagno) can be caught at each

Greetings This is a long email. I'm struggling with a data set comprising 2,278 hydroacoustic estimates of fish biomass density made along line transects in two lakes (lakes Michigan and Huron, three years in each lake). The data represent lakewide surveys in each year and each data point represents the estimate for a horizontal interval 1 km in length. I'm interested in comparing

I am getting a really strange error when I am using predict on an ksvm model. The error is "Error in .local(object, ...) : test vector does not match model !". I do understand that this happens when the test vectors do not match the Model. But in this case it is not so. I am attaching a portion of both the test data used for prediction and the data used to build the model. I could