Hello and welcome to the Dollars and Sense edition of Slate Money, your weekly guide to the Business and Finance News of the Week.

I'm Felix Salmon of Fusion in New York, and on the show this week, the revolving door between government and lucrative

Wall Street jobs, dollar store mergers, and some nerdery on premium bonds.

I'm joined by my regular guest, Kathy O'Neill, head of the lead program for data journalism

at Columbia University.

Hi, Felix. And Slate's own money box

columnist Jordan Weissman. Hey, Felix. How you doing? I'm fantastic. I'm always happy when I'm on this

podcast. First thing which I'm going to do is we are going to go back to that car trick. This is going

to be the fourth podcast in a row. We have back to that car trick. This is going to be the fourth

podcast in a row we have talked about this car trick. We have talked about this car trick more

than we have talked about Argentina, Tim Geithner or any other subject. For some reason, this is the

subject which refuses to go away. We devoted an entire segment to the car trick last week.

And if you didn't listen to last week's podcast, you should stop listening to this one and listen to last ones because it was awesome with Emmanuel Derman, a special guest from Columbia University.

But there's one more thing which we wanted to add.

Amazingly, even after devoting a whole segment to this card trick,

there was a big thing we missed. And I am going to introduce this with a little voicemail

that was left for us by the one, the only Matt Levine of Bloomberg View, the world's greatest

finance blogger. And he wrote in and said this.

Hey guys. I wanted to push back on the idea that there's no way to define the probability

for the magician's card trick. It's actually a pretty common trick, right, for a magician

to pick one card from a shuffled deck. Sometimes he gets it right because he's a magician.

Sometimes he gets it wrong because he's building to a different effect. He's going to pull the card out of your pocket later or something like that. You can sort of estimate how often magicians do this and how often they get it right. You divide those two numbers and that gives you a rough estimate for the probability that this magician is going to get it right this time. Now you can object to that, right? Kathy would object, well, we don't

...