similar to: Weighted Analysis in Data Mining

Hi All, My dependent variable is a ratio that takes a value of 0 (zero) for 95% of the observations and positive non-integer values for the other 5%. What model would be appropriate? I'm thinking of fitting a GLM with a Poisson ~. Now, becuase it takes non-integer values, using the glm function with Poisson family issues warning messages. Warning messages: 1: In dpois(y, mu, log = TRUE) :

Hi, I need a help to know whether I can perform the following in R: I have a set of observations (Ns) and each observation is drawn from a poisson distribution with an unkown mean, lambda. The set of lambdas in their turn are drawn from a common prior distribution which is supposed to be a a mixture of two gamma distributions. Is there a way to determine the poisson means in R, given the Ns and

I have a glm regression (quasi-poisson) of log(mu) on x but I have varying degrees of confidence in the x values, and can attach a numerical weighting to each. Can anyone help me with suggestions of how to analysise this. Is there an R package that would help? Wendy [[alternative HTML version deleted]]

Version 2.4.0 of Rattle has been released to CRAN. The rattle package (http://rattle.togaware.com) is a multi platform (GNU/Linux, Mac/OSX, MS/Windows) GTK based GUI for data mining (for exploring data and building descriptive and predictive models). It has undergone a lot of development over the past year. A companion book introducing data mining using Rattle is under development, with a draft

Version 2.4.0 of Rattle has been released to CRAN. The rattle package (http://rattle.togaware.com) is a multi platform (GNU/Linux, Mac/OSX, MS/Windows) GTK based GUI for data mining (for exploring data and building descriptive and predictive models). It has undergone a lot of development over the past year. A companion book introducing data mining using Rattle is under development, with a draft

Hi, see these links: http://www.liacc.up.pt/~ltorgo/DataMiningWithR/ http://sawww.epfl.ch/SIC/SA/publications/FI01/fi-sp-1/sp-1-page45.html Brian D. Ripley, Datamining: Large Databases and Methods, in Proceedings of "useR! 2004 - The R User Conference", may 2004 http://www.ci.tuwien.ac.at/Conferences/useR-2004/Keynotes/Ripley.pdf looking for a book I suggest: Trevor Hastie , Robert

Greetings, everybody. Can I ask some glm questions? 1. How do you find out -2*lnL(saturated model)? In the output from glm, I find: Null deviance: which I think is -2[lnL(null) - lnL(saturated)] Residual deviance: -2[lnL(fitted) - lnL(saturated)] The Null model is the one that includes the constant only (plus offset if specified). Right? I can use the Null and Residual deviance to

Thank you Thierry. I'm trying to following your suggestion in the example below, but getting: Error in get("xs", envir = my.env) : object 'my.env' not found. library(shiny) library(shinydashboard) myApp <- function(x, ...) { xs <- scale(x) my.env <- new.env() assign("xs", xs, envir = my.env) shiny::runApp(app) } app = shinyApp( ui =

Dear Axel, I've used environment for such problems. assign("xs", xs, envir = my.env) in the myApp function get("xs", envir = my.env) in the server function Best regards, ir. Thierry Onkelinx Statisticus/ Statiscian Vlaamse Overheid / Government of Flanders INSTITUUT VOOR NATUUR- EN BOSONDERZOEK / RESEARCH INSTITUTE FOR NATURE AND FOREST Team Biometrie &

Dear list, I am trying to set up a propensity-weighted regression using the survey package. Most of my population is sampled with a sampling probability of one (that is, I have the full population). However, for a subset of the data I have only a 50% sample of the full population. In previous work on the data, I analyzed these data using SAS and STATA. In those packages I used a propensity weight

Hello, I am Mohiuddin Abdul Qader, final year student from dept of CSE in Bangladesh University of Engineering & Technology(BUET). My major was artificial intelligence & i finished my course on Machine Learning and Pattern Recognition this year. I am very keen to contribute in open source community. I have just completed my thesis on 'Location Based Structured Web Search'. For the

Hi All, I didn't have much success through my Google search in finding any active R-related projects to create a wrapper around TensorFlow in R. Anyone know if this is on the go? Thanks, Axel. [[alternative HTML version deleted]]

Hi All, I didn't have much success through my Google search in finding any active R-related projects to create a wrapper around TensorFlow in R. Anyone know if this is on the go? Thanks, Axel. [[alternative HTML version deleted]]

Hi all, I am interested in obtaining R code related to geographically weighted regression. In particular, I am interested in building geographically weighted Poisson GLMs. The model will contain categorical and continuous x independent variables, with interaction effects between categorical and continuous variables. Anybody have anything I can look at? thanks, Mark. --

Hi All, I am frustrated by mixed-effects model! I have searched the web for hours, and found lots on the nested anova, but nothing useful on my specific case, which is: a random factor (C) is nested within one of the fixed-factors (A), and a second fixed factor (B) is crossed with the first fixed factor: C/A A B A x B My question: I have a functioning model using the aov command (see

On 18 Jan 2014, at 14:31, Axel Urbiz <axel.urbiz at gmail.com> wrote: > Hi All, > > > I'm planning to submit my first package to R, and although I read all the > documentation, I'm not very clear on the following 2 items, from which I'd > appreciate your guidance: > > > 1)I understand it is suggested to use the R dev version to build the >

I have a dataset, a time series comprising count data at five minute intervals. These are the number of people who voted at a particular voting place during a recent election. The next step is to smooth the data and estimate a demand vs time-of-day function; the problem is of interest in preventing long lines at voting places. I am using the R Project software. However, I am not a statistician,

Dear List, I'm trying to solve this simple optimization problem in R. The parameters are the exponents to the matrix mm. The constraints specify that each row of the parameter matrix should sum to 1 and their product to 0. I don't understand why the constraints are not satisfied at the solution. I must be misinterpreting how to specify the constrains somehow. library(alabama) ff <-

Dear List, The gbm package on Win 7 produces different results for the relative importance of input variables in R 32-bit relative to R 64-bit. Any idea why? Any idea which one is correct? Based on this example, it looks like the relative importance of 2 perfectly correlated predictors is "diluted" by half in 32-bit, whereas in 64-bit, one of these predictors gets all the importance

Hi all, How can a multivariate Poisson time series be modeled? Aspects of glm, forecast, dse and dynlm seem relevant but not quite complete--but hopefully what I am missing is how to assemble them effectively. What I am looking to do is model my dependent variable y_t as a Poisson family function of lags of several independent variables and lags of y_t. I would like to include all lags up