Sometimes you need to draw a simple network diagram, like this Hasse diagram
but you don’t have a good graph drawing tool. Get Graphviz! Easy to learn, scriptable, and FREE.
Want to save the planet? How about starting by saving the birds. Here’s a Pareto graph that gives a strong hint of where to start:
That’s right, get the cat population under control. Eradicate feral cat colonies, and euthanize cat collections (oh, and institutionalize obsessive cat ladies). The whole country needs to grow up and get that “cute little kitty” lie out of their heads, and replace it with something more realistic, like “bird murderer.”
Update: One Dallas suburb is infested with feral cats, protected by a well-connected cat lady.
Fisher’s iris dataset is the basis for this extended example in the calculation and visualization of correlations. The ggpairs() function gives an impressive coded scatterplot matrix. And an old friend makes a last-minute cameo appearance.
Update: Dirk Eddelbuettel just released tint 0.0.3 (tint is not Tufte) with some nifty examples. I wanted to try it out, so I’ve updated the example using tint and added two margin plots to illustrate the Simpson’s Paradox situation. Tip from R Bloggers.
When I first read about the Juice Labs Chart Chooser, I was decidedly underwhelmed. After a second look, I’m impressed–these guys have some clever tricks, and they’re yours for the downloading.
Heck, it’s just fun to resize the browser window on this thing–they’ve done some HTML5 wizardry that’s quite clever.
Meg McLain tells a great story about the relative risk of being killed by terrorists in the US. Unfortunately, she comes up with this baffling graphic which appears to use the sort of number scales beloved of President Obama’s budget speechwriters:
Sure, there’s a scale problem, when the multipliers range from 6 to 17,600, but generations of scientists and engineers have handled that with a logarithmic scale:
This still doesn’t give the compressed range that MM’s chart shows. Aha! Perhaps she’s using the little-known log-log scale (beloved by statisticians who deal with generalized linear models)–let’s see:
Pretty close. But how would any reasonable person expect a layperson to understand this exotic measurement scale?
Update (28 September). In her comments section, Dr Kiesling admonishes me not to “go all Tufte” and tosses out the phrase “mathematically pedant.” How flattering! I bet LK was the kind of girl who slugged guys in junior high to get their attention.
Charlie Park has a nice post describing Tufte’s slopegraphs (old chart, new name).
Kaiser Fung likes these a lot; he’s been calling them Bump charts.
I introduce these to my undergrads when we discuss the paired t test.