Carlos Parada

> Hi, using the alternative parameterization is an option. However, to my knowledge, alternative parameterization has not been used widely in research papers. With the current parameterization, the parameter θ...

> I think for consistency we should use the same parameters as for `Logistic` here - also in the case of e.g. `LogNormal` we don't use the (possibly) more interpretable...

> > I think for consistency we should use the same parameters as for `Logistic` here - also in the case of e.g. `LogNormal` we don't use the (possibly) more...

I would intuitively expect `+` to be the convolution if we're working with the random variables; it feels a bit weird to have one symbol here and another for `AffineDistribution`....

To keep this issue from tearing our community apart, I propose a compromise: [circled ast](https://www.compart.com/en/unicode/U+229B) :p (Could actually work, though? It's an asterisk, but the circle visually distinguishes it. Or...

Actually, it looks like there's already an alternate notation for convolution -- since it can be thought of as a tensor product: 

I'd love to see these added! Feel free to make a PR so we can evaluate and merge it.

I will add a slight comment (which you can feel free to ignore) -- I personally had exactly this problem when working with Distributions.jl a couple months ago as a...

> You removed the one argument constructor it seems. Can you please also address my comment above and add some tests for this new (currently missing) constructor? > > It...

> They are tested with the standard tests in https://github.com/JuliaStats/Distributions.jl/blob/master/test/univariates.jl. See > > https://github.com/JuliaStats/Distributions.jl/blob/02bcbf8169160cc499832f05c83e9308ecdb2457/test/ref/continuous_test.ref.json#L1826 > > etc. Got it, thanks! I think this should fix it.