Skip to Content


By Andrie de Vries


How many packages exist on CRAN?  Joseph Rickert went fishing for packages and said the answer is 6,789 (on June 18th, 2015).

But is that really the same answer for everybody?

John Mount Ph. D.
Data Scientist at Win-Vector LLC

An A/B test is a very simple controlled experiment where one group is subject to a new treatment (often group "B") and the other group (often group "A") is considered a control group. The classic example is attempting to compare defect rates of two production processes (the current process, and perhaps a new machine).

by Sean Wells, Senior Software Engineer, Microsoft and David Russell

DeployR exists to solve a number of fundamental R analytics integration problems faced by application developers. For example, have you ever wondered how you might execute an R script from within a Web-based dashboard, an enterprise middleware solution, or a mobile application? DeployR makes it very simple. In fact, DeployR makes it very simple for any application developed in any language to:

Sometimes the oldest technologies need a revamp. Bearings have been with us since machines were invented, but have largely kept the same design: rolling speres between two concentric rings, separated by a retainer to keep them from rubbing together. But it turns out that a simple tweak eliminates the need for the retainer, while reducing friction tenfold:


by Bill Jacobs, Director Technical Sales, Microsoft Advanced Analytics

In the course of working with our Hadoop users, we are often asked, what's the best way to integrate R with Hadoop?

The answer, in nearly all cases is, It depends.                                        

by Andrie de Vries

A few days ago I watched a YouTube video of a TEDx presentation "The surprising beauty of mathematics" by Jonathan Matte at TEDxGreensFarmsAcademy.

In this presentation, Jonathan speaks eloquently about his love for mathematics, and specifically about a way of generating the Archimedes spiral using a series of embedded squares.

by B. W. Lewis

This note warns about potentially misleading results when using the use=pairwise.complete.obs and related options in R’s cor and cov functions. Pitfalls are illustrated using a very simple pathological example followed by a brief list of alternative ways to deal with missing data and some references about them.

For anyone who works with financial data and has access to a Bloomberg terminal, there is a new R package to interface to Bloomberg data services: RBlpapi. (If you had searched for an R connection to Bloomberg you wouldn’t have found this one — Bloomberg is happy to have software that connects to its public API, but not to use its name, apparently.)