John Best

This PR is probably relevant: JuliaDiff/ChainRules.jl#246. If I understand the AD machinery being used here (I don't), once sparse array support is added, rules for sparse Choleskys can be added...

For what it's worth, the `pullback` and `pushforward` of `cholesky` with a sparse argument appears to work: ```julia julia> n = 100 julia> ρ = 0.5 julia> Q = spdiagm(-1...

This does work for dense matrices, so it might be a good method to add. For now, at least for Julia v0.6 I see the following options work: ``` C...

I've used some of the `sp` objects in e.g. my [change of support example](https://github.com/jkbest2/PointProcessCoS/blob/master/ppcos_quads.R). They provide a nice way of structuring spatial data, but can be unwieldy at times. For...

This should be resolved by kaskr/adcomp#298.

I'm honestly not sure what's happening here. I suspect you're right and it's called somewhere in the eigenvalue code. Something changed in the standard libraries and CppAD lost the definitions...

Great, thanks for the confirmation Paul! I'm just happy Kasper was able to work his magic so quickly. Jim, I feel pretty confident that this is taken care of on...

Just stumbled on this issue. I started working on a [Laplace approximation package](https://github.com/jkbest2/LaplaceApproximations.jl) a while ago, but it has a long way to go before it's generally usable. Ideally I...

I found that starting values for the Ricker model were very important. I tried a default `0` value for both my population dynamics parameters, which works for Gompertz, but divides...

Another option is to access the fitted values and their *variance* as ```r SD_rep$par.random SD_rep$diag.cov.random ``` Then take the square root to get the standard error.