Get ready for the New York R Conference

by Joseph Rickert

Last year, I wrote the New York R Conference “set the bar pretty darn high for a first time conference”. Not only was there an outstanding lineup of speakers, but the energy and enthusiasm that conference attendees brought with them, or maybe just generated on the spot, was remarkable.

This year I am definitely looking forward to a repeat performance. On April 8^th and 9^th the conference will again be held at Work Bench on 5^th Avenue in Manhattan. Last year, I thought that the Work Bench space with its hardwood floors and floor to ceiling windows played a big part in setting the vibe for the event. I am a big fan of small, single track conferences and have come to appreciate that space selected for a small event can contribute to ways in which people interact.

Many of the speakers who gave outstanding presentations last year, including Andrew Gelman, Hilary Parker, Vivian Peng, Bryan Lewis, Max Kuhn and Wes McKinney, will be returning again this year and will be joined by a new caste of R luminaries that includes JJ Allaire, Drew Conway, Simon Urbanek, Matt Dowle and Rachel Shutt. (The book, “Doing Data Science” that Rachel wrote with Cathy O’Neil a couple of years ago is still a very good read and a great place for people looking to do data science with R to start.)

I don’t have a complete set of abstracts for all of the talks that are preparation, but I have seen a few that look particularly intriguing. Andrew Gelman will use the notion of the “penumbra” of a social network to illuminate the political relevance of small groups in the population. I expect that, once again, Bayesian Analysis will be lighting up the conference.

In a talk entitled “Thinking small about big data” it appears that Bryan Lewis will take a contrarian look at big data and present some techniques along with the relevant R packages to squeeze information out of a large data set without making a big deal about it.

JJ Allaire will present a new notebook interface for R that works with R markdown documents and integrates with RStudio. Not being heavily involved in notebooks, I have just assumed that they presented an alternate, competing paradigm to working within the confines of an IDE – apparently that is not the case. The possibilities are richer than I imagined, and I am intrigued.

Nathan Stephens will be talking about Shiny Gadgets, RStudio Addins and HTML Templates, new tools designed to further enrich the superb RStudio ecosystem.

Other languages will also be spoken at the conference. After all, the Ley line of global sophistication runs right down 5^th avenue and New York is a city of polyglots. Ben Lerner will talk about high-performance Python, Niels Bantilan will described lessons learned from building a hybrid R-Python predictive analytics pipeline and Stefan Karpinsky will talk about using Julia plus R for data science.

NYR sits somewhere in between an R user group meeting and a full blown conference like useR!2016 promises to be. If you would like to be able to immerse yourself in some serious R talk and interact with world-class players in R, statistics and data science then you would most like enjoy NYR. This Spring there are four big R events in the United States: NYR in April, R/Finance (Chicago) in May, and BioC 2016 and useR!2016 both in June at Stanford. Try to make at least one. 

If you'd like to attend NYR, follow the link below to register and use the code MicrosoftR for a 20% discount.

NY R Conference, April 8-9: 2016 Tickets