[
https://issues.apache.org/jira/browse/RNG-103?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Alex D Herbert resolved RNG-103.
--------------------------------
Resolution: Implemented
In master.
> LargeMeanPoissonSampler to use KempSmallMeanPoissonSampler
> ----------------------------------------------------------
>
> Key: RNG-103
> URL: https://issues.apache.org/jira/browse/RNG-103
> Project: Commons RNG
> Issue Type: Improvement
> Components: sampling
> Affects Versions: 1.3
> Reporter: Alex D Herbert
> Assignee: Alex D Herbert
> Priority: Trivial
> Fix For: 1.3
>
> Time Spent: 0.5h
> Remaining Estimate: 0h
>
> The LargeMeanPoissonSampler requires a Poisson sample using a mean of {{<1}}
> when the mean is fractional. This is done using a SmallMeanPoissonSampler.
> This can be changed to a KempSmallMeanPoissonSampler which has more stable
> performance with RNGs that are very slow. This is due to the algorithm
> requiring only 1 uniform deviate per sample.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
