A Primer on Clinical Trials

Over on the Scientific American blogs, Dr Judy Stone begins a series of online articles describing the ins and outs of clinical trials.  Most folks have no idea how complicated or time-consuming the process is.

• Molecules to Medicine

Stay tuned, I’ll keep these updated.

Tip from Boing, Boing.

Bayesian Gaydar

Sanjay Srivastava describes The Precisely Fuzzy Science of Gaydar: “…, a quick calculation tells us that for a randomly-selected member of the population, if your gaydar says “GAY” there is a 9% chance that you are right. Eerily accurate? Not so much. If you rely too much on your gaydar, you are going to make a lot of dumb mistakes.”

Tip from Andrew Gelman.

Weekly geekery

Statistics

• Taking the bias out of crowd counting.  (Tip from the Geek Press)
• A bad vita trumps bad statistics.  (Outraged tip from The Endeavour)
• Doing statistical graphics?  Worry about color.  (Tip from the Endeavour)

Security

• Typosquatting.  (Tip from the Geek Press)

Food and Drink

• We took my sister-in-law out to dinner at Il Sogno a couple of weeks back, and discovered a tasty green pea pesto.  I’ve reverse-engineered it:
• 2 cups fresh peas (a small bag of frozen ones worked fine)
• 1/4 cup ricotta cheese
• 6 mint leaves (to taste)
• juice of 1/2 lemon
• dash of salt
• Pulse in a food processor to chunky, not smooth.

Politics

• The ugly truth about candidates “throwing their support” to competitors.  Plus some comments on the current Republican field. (How could anyone have EVER been serious about Tim Pawlenty for President?  C’mon, President T-PAW?  Really?)

Weekly geekery

Back from a hectic JSM in Miami, so back with the odd items.

Statistics

• Paul Meier’s survival function converges to zero
• Through the eyes of a statistician (JSM award winner)
• Even more statistics videos from JSM
• user333 wanted an autocorrelated binary sequence; I introduced him to a simple Markov chain

Recipes from Miami

• mango mojito (but mulling is for rubes–juice a lime per drink and chop a mint leaf–shake with cube ice in a cocktail shaker)
• steamed yuca (had this at Nikki’s in Little Havana–mmm, good)

• fie on your panini, I’m holding out for a medianoche (Mexicanos are peppery, Cubanos are cheesy)
• coffee flan (this was topped with coffee ice cream at the trendy Yuca bistro on Lincoln Avenue)
• pineapple popsicles (found this one in Southwest Airline’s inflight magazine–they added cilantro!, but I like ‘em with fresh mint)

Statistics for Experimental Biologists

The Endeavor’s John Cook just tweeted @StatFact about four kinds of statistics, which led me to this wonderful site, Statistics for Experimental Biologists.

What a fabulous resource for my Statistics 1403 course!

Reproducible research

Great article in the NY Times about Keith Baggerly’s push for open data and reproducible analysis of results.  Curiously enough, one of my students hit upon a tiny example of the problem this semester:

…I decided to run my own descriptive statistics on their data sets to make sure their reports were all represented in the same way (and thus, I could compare them to my own results). Good thing I did! It turns out that some of the means reported in the articles were incorrect due to an error on the part of the researcher during data entry. It seems that they used – instead of 0 when a group did not have, say, an infant or a juvenile male in a group, which resulted in the means of infant or juvenile male being figured based on a number less than N. This is a problem because they were reported as the means of N number of groups and the overall … ratio became inflated as the result.

Science is all about doing reproducible experiments, but I fear many researchers lose track of that principle.

Baggerly is a big proponent of using tools like Sweave to make analysis transparent.

Tip from R Bloggers.

Data mining for cheaters

Using data forensics to detect cheaters on standardized tests..is there anything statistics can’t do?

Tip from the Geek Press.

If you gamble, know when to stop

It’s explained in gory detail here.

Tip from Thnik Again!

The Poisson mnemonic

“Mnemonic” is mnemonic for the Poisson distribution.  I give this a Geek².

Tip from the Endeavor.

Simpson’s Paradox bites Paul Krugman on the ass

Nobel Prize winner Paul Krugman makes an undergrad mistake in educational statistics, and Iowahawk takes time out from redneck hotrodding to call him on it, with deadly effect.

Best line ever in a statistics post:  “Mr. Krugman (please note – I don’t call anyone “Doctor” unless they can write me a prescription for drugs) doesn’t mention where he gets his dropout statistic from. I suspect a database somewhere in his lower intestine.”

Note to Krugman:  search for Simpson’s Paradox on Wikipedia.

Update (6 March).  Iowahawk answers his critics, many of whom think Appeal to Authority is epistemologically superior to Run the Friggin’ Numbers.  Hey, science is tough, especially for educated idiots who don’t even know what it is.