Andreas Noack
Andreas Noack
Would it make sense for the applications you have in mind to overload the `Histogram` type in `StatsBase` and thereby making it a distribution?
Maybe. I haven't really thought enough about it but it be worth trying out.
Reopening this since it doesn't appear to be resolved
It's very old code. I think we should just use `sum` here and when compute the second central moment below. It would be great if you could prepare a PR...
As argued on the list, I don't see the problem in extending the Poisson distribution to include `λ=0`. I doubt that `skewness/kurtosis` will be used for anything in the degenerate...
Okay, let me try to break the filibuster attempt. If we were paid to spend all our time on `Distributions` I think your proposal is reasonable. However, our resources are...
``` R > rpois(10, 0) [1] 0 0 0 0 0 0 0 0 0 0 ```
I hadn't noticed that Wikipedia defines the distribution for `x > 0`. That surprises me and it also differs from [R](https://stat.ethz.ch/R-manual/R-devel/library/stats/html/GammaDist.html) and [Wolfram](https://mathworld.wolfram.com/GammaDistribution.html). IMO, the current behavior for `Gamma` is...
Looks like Wolfram is inconsistent here. I don't think it changes the point, though. For the record then R does use the right limit ```R > dgamma(0.0, 0.8, 5.0) [1]...
> Could this be the reason for the discrepancy? Yes. That is the difference. See https://en.wikipedia.org/wiki/Directional_statistics. ```julia julia> sqrt(1 - abs(mean(exp.(complex.(0.0, x))))) 0.5492460106924333 ``` Indeed, this could be better documented,...