Skip to main content
Message Font: Serif | Sans-Serif
 
No. of Recommendations: 5
I didn't really pay much attention to the polling and such in the run up to the presidential election, so this probably old news. (I was part of the 0.1%, apparently.) However, Nature ran this article (in conjunction with Scientific American), entitled "Why math is like the honey badger".

http://www.nature.com/news/why-math-is-like-the-honey-badger...

I liked the name, I found the article interesting, and I think it has some quotes I'm going to have to remember:

"Like the infamous honey badger, math don’t care. Math don’t give a s$%."

To be honest, I wasn't really familiar with the honey badger either. There's a movie if you aren't, so don't worry. It's an article about math, particularly statistical modeling, so you know it has to be cool. I think it's worth a read.

There was a related article in the LA Times:

http://www.latimes.com/news/nationworld/nation/la-fi-electio...

I think this bit from Dean Chambers (a conservative commentator and consultant) sums up the problem with the current crop of conservatives:

"Chambers' own calculations showed Romney winning big. But the longtime commentator and consultant erred, he said, because he didn't take polls at face value, refusing to include some polls out of concern that they over-sampled Democrats. In other words, Chambers said, he threw out data that seemed to favor Obama too much."

Whether it's the election, the economy, global warming, etc., when conservatives "analyze" the data, they through out the stuff they don't like so they reach the conclusion that want to reach.

-Anthony
Print the post Back To Top
No. of Recommendations: 1
My, they've come a long way in nature programs since Marlin Perkins. "Eww, that's disgusting. But the honey badger doesn't give a s$&t." :-)

But math also does not give a s$&t. I had this debate with someone on another board just two weeks ago. He kept asking me whether or not I could form an opinion about projections from the Bayesian analyses that were being bandied about. I kept telling him that my opinion did not matter. Math doesn't care about my opinion. Math simply is. It doesn't give s$&t. He couldn't seem to grasp that (or didn't want to).

I think you are correct. A lot of denialists (of whatever...election polling, climate change, etc) toss the stuff they don't like to reach the conclusion they want. Done properly the math will give you the answer, and it doesn't care whether or not you like it.

1poorguy
Print the post Back To Top
No. of Recommendations: 4
"Chambers' own calculations showed Romney winning big. But the longtime commentator and consultant erred, he said, because he didn't take polls at face value, refusing to include some polls out of concern that they over-sampled Democrats. In other words, Chambers said, he threw out data that seemed to favor Obama too much.

I suspect what he really meant is, "when I factored in all of the vote-blocking we were assured would happen in Florida, Ohio and Pennsylvania, the data ended up skewing for Romney".

6
Print the post Back To Top
No. of Recommendations: 1
To be honest, I wasn't really familiar with the honey badger either

Them's fighting words.
Print the post Back To Top
No. of Recommendations: 5
1pg: But math also does not give a s$&t. I had this debate with someone on another board just two weeks ago. He kept asking me whether or not I could form an opinion about projections from the Bayesian analyses that were being bandied about. I kept telling him that my opinion did not matter. Math doesn't care about my opinion. Math simply is. It doesn't give s$&t. He couldn't seem to grasp that (or didn't want to).

Mmmm. Beware, there is quite a lot of irony contained within that short paragraph.

"Bayesian" analysis represents the only part of mathematics which really does produce conclusions that are relative to the individual points of view of the readers. Five different people can read a Bayesian study, and reach five different equally-valid conclusions. Each reader has his or her own "prior" knowledge; factor in the new data, and each arrives at a different "posterior" position. Yes, the five have moved closer to each other, but they still differ. In short, Bayesian math does care about your opinion -- and it is just about the only kind of math that does.

LC
Print the post Back To Top