Just hit the “*arXiv* streets”:

`N. Dalmasso, T. Pospisil, A. B. Lee, R. Izbicki, P. E. Freeman, A. I. Malz, "Conditional Density Estimation Tools in Python and `

**R** with applications to photometric redshifts and likelihood-free cosmological inference", *arXiv.org > astro-ph > arXiv:1908.11523v1*

I look forward to *codetools* being an **R** package on CRAN. Meanwhile, for the impatient, there’s a Github version.

##### Postscript

Dr Drew Cameron has some comments about this work and paper. I look forward to delving into the Dalmasso, *et al* paper once I have a chance to look at their codes.

My interests are different, however, in that I want to borrow their empirical likelihood methods for other applications.

I do think Dr Cameron’s comment on nested sampling is interesting, and I wonder if there might not be an application of the higher dimensional version of *slice sampling* in its place.

Note parallel multivariate variations on slice sampling are now known, although I’m not aware of work on how well these go.

And, just for information, there’s very recent work on something called *generalized elliptical slice sampling with regional pseudo-priors* which I have not read.

There is also another 2019 connection to elliptical slice sampling called Bayesian Tensor Filtering which is interesting because:

- David Blei is involved
- It is connected to slice sampling
- It is related to tensor methods in Statistics which I am just studying, after McCullagh and Gross. These have apparently been used in finance under different names for quite a while.