#NICAR - Day One

Feb. 26, 2014, 10 p.m.Journalism

It’s that most wonderful time of the year, the annual NICAR conference. For the uninitiated, this is the conference where journalists from all over the country (and from many other countries) get together to talk data, open records, technology and all the other wonderful components that make up the world of computer-assisted reporting (i.e. CAR or data journalism).

This year’s conference is conveniently located in Baltimore and, as in previous years, is off to a strong start. My goal is to leave birdland with a better understanding of statistics and the R programming language. I spend most of my days writing PHP, Python and JavaScript to clean up and visualize data, but the more I explore R, the more I am convinced that it would be a fantastic tool for cleaning, analyzing and even visualizing data.

Getting a better grasp on statistics

One of the highlights for today was the “Enhance your stories with statistics” session. The speakers moved a bit quick, but they helped answer one of the questions I always have when applying statistcs: what statistical test should I use to analyze my variables? I’ll still need a lot of googling, but I at least have a better understanding of when to use a T-test, ANOVA or Fischer’s Exact test. All I have to do now is find a story to apply this info.

Using R in the newsroom

I love Python. PHP can certainly get the job done. JavaScript, surprisingly, makes a lot of sense to me. R, however, just seems odd. Steven Rich put it best today: “The best thing about R is that it was written by statisticians… The worst thing about R is that it was written by statisticians.”

Through my own studies and a session today, I’ve started forming a collection of code snippets that I know will work to solve common problems. Need to read a csv file into RStudio? I can write the code for that. Need to mash together a shapefile with a dataset and render it? I can google the code to do that…

I just need practice. Part of me wants to commit to using R for every data cleaning and analysis task I undergo for the next two weeks. The other part of me, though, likes hitting deadlines and not going insane. Either way, I’ll be finding some time to get a better grasp on R.


Tomorrow should be a little more relaxed but equally rewarding. Melissa and I’s “Most Dangerous Intersections” story is being featured in the “Year in CAR” presentation at 9 a.m., so we’ll get 2 or 3 minutes to share how we put it together and brag about its impact. After that, it’s a full slate of data journalism, and I’ll hopefully be recapping the highlights here tomorrow.

Until then…