similar to: Model selection exponential and gamma distribution using cross validation

Hi all, I am attempting to fit, and test the goodness of fit of, a mixed exponential distribution to my dataset which consists of 15minute rainfall intensity data. FYI, the dataset spanning approx.2 years and 7 rainfall stations consists of some three hundred thousand 15min data records, of which some 30 thousand are non-zero rainfall amounts. Could anyone please tell me how i could do

Dear R Users, I am trying to obtain a best-fit analytic distribution for a dataset with 11535459 entries. The data range in value from 1 to 300000000. I use: fitdistr(data, "gamma") to obtain mle's for the parameters. I get the following error: Error in optim(start, mylogfn, x = x, hessian = TRUE, ...) : non-finite finite-difference value [1] And the following warnings:

Dear All, I have two questions regarding distribution fitting. I have several datasets, all left-truncated at x=1, that I am attempting to fit distributions to (lognormal, weibull and exponential). I had been using fitdistr in the MASS package as follows: fitdistr<-(x,"weibull") However, this does not take into consideration the truncation at x=1. I read another posting in this

Hi, I am trying to estiamte parameters for gamma distribution using mle for below data using fitdist & fitdistr functions which are from "fitdistrplus" & "MASS"packages . I am getting errors for both functions. Can someone please let me know how to overcome this issue?? data y1<- c(256656, 76376, 6467673, 46446, 3400, 3100, 5760, 4562, 8000, 512, 4545, 4562,

Greetings, all I am having difficulty getting the fitdistr() function to return without an error on my data. Specifically, what I'm trying to do is get a parameter estimation for fracture intensity data in a well / borehole. Lower bound is 0 (no fractures in the selected data interval), and upper bound is ~ 10 - 50, depending on what scale you are conducting the analysis on. I read in the

Dear all, My question concerns using repetitions and simulations (loops?) in R. I am very new R user, so any help that can be offered would be greatly appreciated! I am using fitdistr() to determine the distribution of empirical univariate datasets, and ks.test to assess the goodness of fit. Because the null distribution of the KS statistic is not known when the distribution parameters are

Hello, I've been attempting to fit the data below with an inverse gamma distribution. The reason for this is outside proprietary software (@Risk) kicked back a Pearson5 (inverse gamma) as the best fitting distribution with a Chi-Sqr goodness-of-fit roughly 40% better than with a log-normal fit. Looking up "Inverse gamma" on this forum led me the following post:

I'm trying to estimate two parameter for a markov chain (exponential). I used maximum likelihood to do it. (fitdistr{MASS},fitdist{fitdistrplus}), but I get just one parameter. Do you have any suggestion to help me? THANKS!! -- View this message in context: http://r.789695.n4.nabble.com/Estimate-two-parameter-for-exponential-dist-tp4648917.html Sent from the R help mailing list archive at

Dear useRs, upon request, the VGAM package (currently version 0.7-1) has been officially released on CRAN (the package has been at my website http://www.stat.auckland.ac.nz/~yee/VGAM for a number of years now). VGAM implements a general framework for several classes of regression models using iteratively reweighted least squares (IRLS). The key ideas are Fisher scoring, generalized linear and

Given a numeric vector of observations, does R have any generic way to estimate the parameters of commonly used distributions (exponential, gamma, etc.) without numerically optimizing the likelihood function? Thanks, David _______________________________________ David R. Bickel http://davidbickel.com Research Scientist Pioneer Hi-Bred International Bioinformatics & Exploratory Research 7250

Why the warning messages (2:4)? > x <- rexp(1000,0.2) > fitdistr(x,"exponential",list(rate=1)) rate 0.219824219 (0.006951308) Warning messages: 1: one-diml optimization by Nelder-Mead is unreliable: use optimize in: optim(start, mylogfn, x = x, hessian = TRUE, ...) 2: NaNs produced in: dexp(x, 1/rate, log) 3: NaNs produced in: dexp(x, 1/rate, log) 4: NaNs

Hi R lovers! I'd like to know how to use the parameter 'start' in the function fitdistr() obviously I have to provide the initial value of the parameter to optimize except in the case of a certain set of given distribution Indeed according to the help file for fitdistr " For the following named distributions, reasonable starting values will be computed if `start'

I'm looking for goodness of fit tests for gamma distributions with large data sizes and for different data. I have a matrix with around 4.000 data values in it and i have fitted a gamma distribution with "fitdistr". You can see the example: > fitdistr(corpo,"gamma",lower=0.001) Errore in optim(x = c(5000, 5000, 5000, 5000, 5000, 5000, 5000, 5000, 5000, :

In glm, is there a way to specify the family to be exponential, or Gamma but with alpha=1? This is required by Dobson Exercise 4.3d, page 48. But without specifying alpha=1, the asnwer is the same as in the book. If reply to the list, please cc me a copy. Thanks. -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read

Hi,Dear all R experts, As far as I know, fitdistr() is only to estimate the parameters in univariate distributions. I have a set of data (x,y) and I assume it follows a bivariate weibull distribution. Could someone tell me a function in R that is suitable for parameter estimation in multivariate cases? Thanks in advance! Cheers, YAN

I just thought of a useful metaphore for the problem I face. I am dealing with a problem in business finance, with two kinds of related events. However, imagine you have a known amount of carbon (so many kilograms), but you do not know what fraction is C14 (and thus radioactive). Only the C14 will give decay events (and once that event has occurred, the atom that decayed will never decay

Dear All, A simple question: packages like fitdistr should be ideal to analyze samples of data taken from a univariate distribution, but what if rather than the raw data of the observations you are given directly and only a histogram? I was thinking about generating artificially a set of data corresponding to the counts binned in the histogram, but this sounds too cumbersome. Another question is

http://r.789695.n4.nabble.com/file/n3216865/Inverse_Gamma.png Hello, I am seeking help in estimating the parameters of an inverse gamma distribution (from the 'actuar' package) using a function like 'fitdistr'. Unfortunately I haven't found such a package using findFn('fit Inverse Gamma') from the 'sos' package and was therefore hoping someone might be aware

I answer my own question: I had overlooked the fact that the normalization factor is also a function of the parameters I want to optimise, hence I should write dbeta2 <- function(x, shape){ res <- x^(shape-1)*(1-x)^(shape-1)/beta(shape, shape) return(res) } after which the results are consistent. ---------- Forwarded message ---------- From: Lorenzo Isella <lorenzo.isella

Dear All, I need to fit a custom probability density (based on the symmetric beta distribution B(shape, shape), where the two parameters shape1 and shape2 are identical) to my data. The trouble is that I experience some problems also when dealing with the plain vanilla symmetric beta distribution. Please consider the code at the end of the email. In the code, dbeta1 is the density of the beta