[R] Error when using fitdist function in R

[Prof Brian Ripley]

On 10/04/2013 08:29, PIKAL Petr wrote:
> Hi
>
> where is function fitdist from? Do you by chance mean fitdistr from MASS package?

No, from the output.  More likely

fitdistrplus::fitdist   Fit of univariate distributions to non-censored
                         data

> What is result of str(k)?
>
> Without these questions answered you hardly get any useful answer.

Also, the data seem to be integers: a gamma distribution is for real 
positive values only.  Having zero values would give the results you see.

>
> Regards
> Petr
>
>
>
>> -----Original Message-----
>> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
>> project.org] On Behalf Of Paul Bernal
>> Sent: Tuesday, April 09, 2013 11:19 PM
>> To: r-help at r-project.org
>> Subject: [R] Error when using fitdist function in R
>>
>> Hello everyone,
>>
>> I  was trying to do some distribution fitting with a numerical field
>> called Tolls. The sample size = 999 rows.
>>
>> Basically I assigned the Toll data to a new variable K by doing:
>> k<-dtest$Toll
>>
>> After that, tried to fit a gamma distribution by doing: fitG<-
>> fitdist(k,
>> "gamma")
>>
>> Then the following messages showed (oh and I checked for empty rows
>> before doing this):
>>
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> Warning in dgamma(c(363328L, 376216L, 367032L, 314826L, 311892L,
>> 313340L,  :
>>    NaNs produced
>> [1] "Error in optim(par = vstart, fn = fnobj, fix.arg = fix.arg, obs =
>> data,  : \n  non-finite finite-difference value [2]\n"
>> attr(,"class")
>> [1] "try-error"
>> attr(,"condition")
>> <simpleError in optim(par = vstart, fn = fnobj, fix.arg = fix.arg, obs
>> =
>> data,     ddistnam = ddistname, hessian = TRUE, method = meth, lower =
>> lower,     upper = upper, ...): non-finite finite-difference value [2]>
>> Error in fitdist(k, "gamma") :
>>    the function mle failed to estimate the parameters,
>>                  with the error code 100
>>>
>>
>> 	[[alternative HTML version deleted]]
>>
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide http://www.R-project.org/posting-
>> guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>


-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595