waterfall 1.0.0 released

Sometime, approximately forever ago, I put together a small package to produce waterfall charts in R. It provided two functions, one using base graphics and one using lattice graphics. I planned to document this and also create a version in ggplot. I never got around to either and through bit

Pigeon Flocks for Decision Science

There’s a great article on PLOS ONE about using pigeons for cancer detection. Pigeons ( Columba livia ) as Trainable Observers of Pathology and Radiology Breast Cancer Images Pathologists and radiologists spend years acquiring and refining their medically essential visual skills, so it is of considerable interest to understand how

1000-year storms in South Carolina

Homeland Security Watch has an excellent post on the recent claims that South Carolina has faced at 1000-year storm. Focusing on the annual exceedance probability (AEP), the story post throws a bit of a damper on it. The post quotes an awful editorial in the Charleston Post and Courier: Catastrophic

Stop Making 3D Plots

FlowingData gave a list of charting rules to follow. I disagree with one, in that pie charts are never acceptable because it is difficult to perceive the differences in size between one pie chart and another. This is especially true in 3D plots. Take this plot, for instance: In this

Why I Bought a Mega Millions Ticket

Yesterday’s post needed a picture of a Maryland lottery ticket for illustration. I couldn’t find a good one online, so I dropped a dollar and picked one up. So why did I pick a Mega Millions ticket, rather than Powerball? Powerball sounds cooler. What gives? Someone’s gonna win, and it

Maryland Lottery Proceeds Don’t Pay for Education

This morning, I watched an episode of Last Week Tonight from last November.1 2 This episode, investigating state lotteries, explained how lotteries are sold to the public by showing how they fund schools. It’s long, but watch it if you haven’t: But we live in Maryland, and we cannot be

Radiolab has a show on randomness (the embed feature doesn’t work) where they discuss an experiment of flipping a coin 100 times. A string of tails appeared 7 times, which seems to be relatively small. Indeed, given 7 coin tosses, the probability of all 7 coming up tails is