The authors report an avalanche of experimental results, and claim the classifier can “correctly distinguish between gay and straight men 81% of the time, and 74% for women.” OK, that’s the sensitivity of the gadget. What about specificity, i.e. how well does it correctly distinguish folks who are not-so-gay? Without that second number (as well as an estimate of prevalance), it’s not possible to estimate the false positive and false negative rates for this thing. Very important, if some of the more Orwellian applications mentioned by the authors come to pass.
Update: Dan Simmons, writing at the Andrew Gelman blog, writes a rambling, fascinating takedown of this “research,” from both the scientific and MSM points of view. Based on just the statistical problems, I’m changing the grade to a “D-.”
Most Latinos of the south are either a mixture of Spanish and Indian, or sometimes pure Indian….Are they, as nativists insist, of very low IQ–83–and have they enstupidated the Spanish? Horrendously primitive?
Without thinking about it, I had the entrenched idea that they were just that. I wasn’t conscious that it was either an idea or entrenched–just a fact. It didn’t occur to me that I knew virtually nothing about these people, or that there was anything to know.
What pulled me up short was their architecture.
and gives us a cultural history lesson along the way.
Writing in The New Atlantis, Daniel Sarewitz says “Science, pride of modernity, our one source of objective knowledge, is in deep trouble.” The public has swallowed the myth of scientism and Vannevar Bush’s self-serving rationalization for federally-funded Big Science:
Scientific progress on a broad front results from the free play of free intellects, working on subjects of their own choice, in the manner dictated by their curiosity for exploration of the unknown.
The case against science is straightforward: much of the scientific literature, perhaps half, may simply be untrue. Afflicted by studies with small sample sizes, tiny effects, invalid exploratory analyses, and flagrant conflicts of interest, together with an obsession for pursuing fashionable trends of dubious importance, science has taken a turn towards darkness.
Get your face outta that stupid screen! The latest First World Problem is Death by GPS:
Most death-by-GPS incidents do not involve actual deaths—or even serious injuries. They are accidents or accidental journeys brought about by an uncritical acceptance of turn-by-turn commands: the Japanese tourists in Australia who drove their car into the ocean while attempting to reach North Stradbroke Island from the mainland; the man who drove his BMW down a narrow path in a village in Yorkshire, England, and nearly over a cliff; the woman in Bellevue, Washington, who drove her car into a lake that their GPS said was a road; the Swedish couple who asked GPS to guide them to the Mediterranean island of Capri, but instead arrived at the Italian industrial town of Carpi; the elderly woman in Belgium who tried to use GPS to guide her to her home, 90 miles away, but instead drove hundreds of miles to Zagreb, only realizing her mistake when she noticed the street signs were in Croatian.
Apparently “the map is not the territory” isn’t taught in modern schools.