« Equivalents to SAS, SPSS modules in R | Main | New features in ggplot2 version 0.85 »

January 15, 2010


Feed You can follow this conversation by subscribing to the comment feed for this post.

Is the goal to explain the concept of PCA? That might hard be if a phrase like, "we only want to look at the part of our data in which these two groups differ the most," won't be considered deep enough. But the results of population genetics PCA plots seem very intuitive to me: e.g. http://www.gnxp.com/blog/uploaded_images/nature07331-f1.2-774974.jpg

Out of curiosity, how did you learn they had applied PCA? There are some great ways to do hierarchical clustering with this spatial data. I'd love to get my hands on the data. Netflix 2, perhaps? :)

I checked in with Amanda Cox, a graphics editor at the NYT involved in this visualization. She had a very cool PCA analysis of the data, but I don't have permission to share it.

That's too bad. The first thing I thought when I saw the interactive graphic was, "I wish the NYT let you download their database so I can load it into R and run PCA on the spatial patterns".

Does anyone know how to make a map like NYT's ?

You can create colored maps in R in several ways. And you can download a Google map as a background. I'm guessing that overlaying a map and using alpha transparency with the colors would get you something pretty close.

The comments to this entry are closed.

R for the Enterprise

Got comments or suggestions for the blog editor?
Email David Smith.
Follow revodavid on Twitter Follow David on Twitter: @revodavid

Search Revolutions Blog