similar to: maximum likelihood method to fit a model

Hi the list, I have a problem of memory space while running step() function: Error: cannot allocate vector of size 50.9 Mb I've tried with: > memory.size(max = FALSE) [1] 803.4714 #which should be the amount of memory currently in use > memory.limit(size = NA) [1] 1015.480 #which should be the memory size > memory.size(max = TRUE) [1] 997.75 #which should be the

Full_Name: saraux Version: 2.6.1 OS: Windows vista Submission from: (NULL) (193.157.180.37) I would like to compute a glm with a distribution of poisson, using a maximum of likelihood method. But it seems not to work with a distribution of poisson. The same code with another distrubution (binomial for example) works. Here is the command I typed:

Hello all, I'm sure I'm missing something simple here, but I can't figure out how to modify the glm.fit() function and then get R to use it (sort of). I'm doing something along the lines of: glm.fit<-edit(glm.fit) # add something trivial to the top of the glm.fit function like: print("Hello world!") #now have a modified glm.fit in position 1/.GlobalEnv

Hi, I am thinking about IWLS vs ML estimation. When I use glm() for a 2-parameter distribution (e.g., Weibull), I can otain the MLE of scale parameter given shape parameter through IWLS. Because this scale parameter usually converges to the MLE. In this point, I am wondering: i) can you say that the direct MLE, which is obtained by maximizing a likelihood function, is equalvant to the indirect

Dear all, I'm trying to get the variance/covarince matrix after fitting a quantile regression model (either linear or non linear), in order to get the variance of my predictions and be able to calculate the median squared error. The commands working for the lm models (corr=T or vcov=T) do not seem to work for the rq models. Could you advise me a way of getting it? Best regards

Dear all, When doing nonlinear regression, we normally use nls if e are iid normal. i learned that if the form of the variance of e is not completely known, we can use the IRWLS (Iteratively Reweighted Least Squares ) algorithm: for example, var e*i =*g0+g1*x*1 1. Start with *w**i = *1 2. Use least squares to estimate b. 3. Use the residuals to estimate g, perhaps by regressing e^2 on

Hi! I tested two different implementations of the robust MCD estimator: cov.mcd from the MASS package and covMcd from the rrcov package. Tests were done on the hbk dataset included in the rrcov package. Unfortunately I get quite differing results -- so the question is whether this differences are justified or an error on my side or a bug? Here is, what I did: > require(MASS) >

What kind of special magic does glm have? I'm working on a logistic regression solver (L-BFGS) in c and I've been using glm to check my results. I came across a data set that has a very high condition number (the data matrix transpose the data matrix) that when running my solver does not converge, but the same data set with glm was converging ( I love R :) ). I noticed that glm using

We have a choice when calculating the Huber location estimate: > set.seed(221205) > y <- 7 + 3*rt(30,1) > library(MASS) > huber(y)$mu [1] 5.9117 > coefficients(rlm(y~1)) (Intercept) 5.9204 I was surprised to get two different results. The function huber() works directly with the definition whereas rlm() uses iteratively reweighted least squares. My surprise is

Hi, Does anyone know if there is a function to find the maximum likelihood estimates of glm using Newton Raphson metodology instead of using IWLS. Thanks Valeska Andreozzi -------------------------------------------------------- Department of Epidemiology and Quantitative Methods FIOCRUZ - National School of Public Health Tel: (55) 21 2598 2872 Rio de Janeiro - Brazil

esto me convierte la cadena de caracteres en dos y eso no es lo que quiero además el resultado final de la cadena debe ser: "98989","121212" Luis -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- Luis Ridao Cruz Faroe Marine Research Institute Nóatún 1, P.O. Box 3051 FO-110 Tórshavn Faroe Islands Tel : (+298) 353900 Fax: : (+298) 353901 e-mail: luisr@hav.fo

lo que necesito es "98989","121212" y no : paste(unlist(strsplit(char,",")),collapse=",") [1] "98989,121212" Luis -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- Luis Ridao Cruz Faroe Marine Research Institute Nóatún 1, P.O. Box 3051 FO-110 Tórshavn Faroe Islands Tel : (+298) 353900 Fax: : (+298) 353901 e-mail: luisr@hav.fo

Dear R-Help List, I'm trying to implement Firth's (1993) bias correction for log-linear models. Firth (1993) states that such a correction can be implemented by supplementing the data with a function of h_i, the diagonals from the hat matrix, but doesn't provide further details. I can see that for a saturated log-linear model, h_i=1 for all i, hence one just adds 1/2 to each count,

R-users E-mail: r-help@r-project.org I have a quenstion on "gam()" in "gam" package. The help of gam() says: 'gam' uses the _backfitting algorithm_ to combine different smoothing or fitting methods. On the other hand, lm.wfit(), which is a routine of gam.fit() contains: z <- .Fortran("dqrls", qr = x * wts, n = n, p = p, y = y *

Greetings, My question is more algorithmic than prectical. What I am trying to determine is, are the GAM algorithms used in the mgcv package affected by nonnormally-distributed residuals? As I understand the theory of linear models the Gauss-Markov theorem guarantees that least-squares regression is optimal over all unbiased estimators iff the data meet the conditions linearity,

Hello, I would like to know if there is any package that allow us to fit Generalized Linear Models via Maximum Likelihood and Linear Models using Generalized Least Squarse in R as the functions glim and gls, respectively, from S-Plus. Also, anybody know if there is any package that fit Log-Linear Models using Generalized Least Squares? Any help will be very useful. Thanks, -- Frederico

Dears I am searching information about how to use raw data, when it is used, didn't find to much information on R help. Any suggestion on links about this theme? atte -- Luis Iván Ortiz Valencia Doutorando Saúde Pública - Epidemiologia, IESC, UFRJ Estatístico Msc. Spatial Analyst Msc. [[alternative HTML version deleted]]

Dear R-users! I would like to fit exponential, Weibull and log-logistic via glm() like functions. Does anyone know a way to do this? Bellow is a bit longer description of my problem. Hm, could family() be adjusted/improved/added to allow for these distributions? SAS procedure GENMOD alows to specify deviance and variance functions to help in such cases. I have not tried that option and I do not

Hi, I have tried to install the R package Rcplex on windows xp without success. I have only cplex_studio124.win-x86-32 version. I have modified the makevars.win file as indicated in the installation guide ( http://cran.r-project.org/web/packages/Rcplex/INSTALL ), then I zipped the whole folder to order an installation from a zipped file (utils :menuInstallLocal()) The message I had is file

Full_Name: Stephen Weigand Version: 1.9.0 OS: Mac OS X 10.3.4 Submission from: (NULL) (68.115.89.235) When running an iteratively reweighted least squares program R crashes and the following is written to the console.app (when using R GUI) or to stdout (when using R from the command line): Parameter 5 to routine DSTEIN was incorrect Mac OS BLAS parameter error in DSTEIN, parameter #0,