In “Fables of the Reconstruction (Or, How to Make Your Own Hockey Stick),” the blogger Iowahawk says:
What follows started as a comment I made over at Ace’s last week which he graciously decided to feature on a separate post (thanks Ace). In short, it’s a detailed how-to-guide for replicating the climate reconstruction method used by the so-called “Climategate” scientists. Not a perfect replication, but a pretty faithful facsimile that you can do on your own computer, with some of the same data they used.
A good read. And fun with stats. Check it out. (HT: Geoffrey K.)
On a related note, read “The ‘Science’ of Global Warming” (Macleans.ca, Thursday, December 3, 2009 10:00am) by Mark Steyn. He writes:
Yet perhaps the most important revelation is not the collusion, the bullying, the politicization and the evidence-planting, but the fact that, even if you wanted to do honest “climate research” at the Climatic Research Unit, the data and the models are now so diseased by the above that they’re all but useless. Let Ian “Harry” Harris, who works in “climate scenario development and data manipulation” at the CRU, sum it up. Mr. Harris was attempting to duplicate previous results—i.e., to duplicate all that science that’s supposedly settled, and the questioning of which consigns you to the Climate Branch of the Flat Earth Society. How hard should it be to confirm settled science? After much cyber-gnashing of teeth, Harry throws in the towel:
“ARGH. Just went back to check on synthetic production. Apparently—I have no memory of this at all—we’re not doing observed rain days! It’s all synthetic from 1990 onwards. So I’m going to need conditionals in the update program to handle that. And separate gridding before 1989. And what [#%] happens to station counts?
“OH [#&] THIS. It’s Sunday evening, I’ve worked all weekend, and just when I thought it was done I’m hitting yet another problem that’s based on the hopeless state of our databases. There is no uniform data integrity, it’s just a catalogue of issues that continues to grow as they’re found.”
You cannot do good statistics with bad data. Nor can you do science. (HT: Harry B.)
In stats and science, reality must come first.
In the Middle Ages, as large denominations of money came to be used, 100 became a common base for computation. Italian manuscripts of the fifteenth century contained such expressions as “20 p 100″ and “x p cento” to indicate 20 percent and 10 percent. When commercial arithmetics appeared near the end of that century, use of percent was well estasblished. For example, Giorgio Chiarino (1481) used “xx. per .c.” for 20 percent and “viii in x perceto” for 8 to 10 percent. During the sixteenth and seventeenth century, percent was used freely for computing profit and loss and interest. (NCTM p146,147}
