[R] MLE for lambda of Poisson distribution using fitdistr

Peter Ehlers ehlers at ucalgary.ca
Tue Oct 27 15:15:31 CET 2009



Kjetil Halvorsen wrote:
> What is wrong with using
> mean(x)
> to get the MLE of the poisson lambda?
> 
and

  mean(x)/length(x)

to get its estimated variance.

  -Peter Ehlers

> Kjetil
> 
> On Tue, Oct 27, 2009 at 9:17 AM, David Winsemius <dwinsemius at comcast.net> wrote:
>> On Oct 26, 2009, at 11:25 PM, ankush2kn at yahoo.com wrote:
>>
>>> Hi,
>>>
>>> I am using the fitdistr of MASS to get the MLE for the lambda of a Poisson
>>> distribution.
>>> When i run the fitdistr command, i get an output that looks like -
>>>
>>>    lambda
>>>    3.750000
>>>    (0.03343)
>>>
>>> Couple of questions -
>>> 1. is the MLE 0.03343 for the lambda of the given distribution then?
>>> 2. How would I calculate the variance of the MLE for the lambda?
>> It would be more typical statistical usage to have output of the form:
>>  estimate ( se(estimate) ) .... so I was expecting 3.75 to be the estimate.
>> Looking at the help page and running str(.) on the fitdistr object of the
>> first example confirms my expectations. Why did you think the help page was
>> suggesting otherwise?
>>
>> --
>>
>> David Winsemius, MD
>> Heritage Laboratories
>> West Hartford, CT
>>
>> ______________________________________________
>> 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.




More information about the R-help mailing list