Just a quick note that CRAN now has the updated version 3.1.0 of the revss package. As always, I want to thank the CRAN team, and specifically Dr. Uwe Ligges, for their tireless work! ∞
Major Update for revss Package for R – v3.1.0
The revss Package for R Receives Major Update to Version 3.1.0 This is a big one! The revss package for R, which provides robust estimation for small samples, received a major, breaking update. The entire calculation engine was rewritten, new functionality added, and massive Monte Carlo analyses were run to calculate bias reduction factors. It Read the full article…
MBBEFDLite has its mature release
The MBBEFD Distribution After two years, the MBBEFDLite package for R is finally mature! As a brand-new actuary, in my first job, I had the privilege of working with Dr. Stefan Bernegger at Swiss Reinsurance. Albeit I did not have much to do with him—I was a one-exam, no experience new actuary and he was Read the full article…
Building R 4.2 for Windows with OpenBLAS
This post outlines the steps needed for building R 4.2 for Windows with OpenBLAS using the the new Rtools42 build system. With the soon-to-be released new UCRT toolchain for building R on Windows, the build process changes once again. First and foremost, we Windows users owe a deep debt of gratitude first to Duncan Murdoch Read the full article…
Building R 4+ for Windows with OpenBLAS
This post outlines the steps needed to build R 4+ for Windows with OpenBLAS. The release of R 4.0 includes significant changes to the Windows build system from prior versions—for the better! Before anything, we all owe Jeroen Ooms significant gratitude for the many hours he spent working on the build system. Thank you, Jeroen!! Read the full article…
histoRicalg: The effort to document historic and historical numerical algorithms in R
Recently, the R-consortium accepted a new project called histoRicalg. The main goal of the project is to document and transfer knowledge of some older algorithms used by R and by other computational systems. There is a lot of R written in Fortran—much of which is in the old F77 format—and in C whose original implementations Read the full article…
Delaporte package: The SPARCmonster is sated
Finally, finally after months of pulling out my hair, the Delaporte project on CRAN passes all of its checks on Solaris SPARC. The last time it did that, it was still using serial C++. Now it uses OpenMP-based parallel Fortran 2003. What a relief! One of these days I should write up what I did Read the full article…
Updated R & BLAS Timings
With the recent releases of R 3.2.4 and OpenBLAS 2.17, I decided it was time to re-benchmark R speed. I’ve settled on a particular set of tests, based on my experience as well as some of Simon Urbanek’s work which I separated into two groups: those focusing on BLAS-heavy operations and those which do not. Read the full article…
Gelman on Meehl
Today, Andrew Gelman posted about a paper written over thirty years ago by Paul Meehl. Even though I believe actuaries are less exposed than social science statisticians to some of the pitfalls of what Gelman calls the “garden of forking paths,” we are still exposed, and I’d recommend reading Gelman’s posts on the issue. I Read the full article…
I’ve updated the directions as to how to build 64-bit R for Windows linking to OpenBLAS, as the entire R build process for Windows will change for R version 3.2 and subsequent. I’ve turned it into a static page, instead of a post, in case the build process changes again. While the title has 3.2 in it, the URL doesn’t, so it should be future-proof. Then again, that’s number 47 on the list of 996 famous last words! As always, I’m interested in hearing if anyone successfully builds it and how much of a difference it makes. ∞