Among experts it’s well understood that “big data” doesn’t solve problems of bias. But how much should one trust an estimate from a big but possibly biased data set compared to a much smaller random sample? In Statistical paradises and paradoxes in big data, Xiao-Li Meng provides some answers which are shocking, even to experts.
“Set your calendar.”
"New books by a physicist and science journalist mount aggressive but ultimately unpersuasive defenses of multiverses."
Interesting and sad, and offers another example of a very tough problem. Science needs to enforce standards against nonsense. There should be a very, very high threshold for believing claims of a perpetual motion machine. And for much else. (I once read that before the relatively recent proof of Fermat's Last Theorem a distinguished math professor used to regularly get "proofs" submitted to him. He got enough, in fact, that he printed some postcards and charged a grad student for sending them out. The cards read something like, "Dear Sir and/or Madam: Thank you for submitting your proof of Fermat's Last Theorem. Your first error appears on page ___, line ___." The grad student had to fill in the blanks.)
But thresholds against very unlikely things and nonsense should not develop into an awful groupthink that mindlessly claims authority where there is no good ground for claiming such authority. A theory of Alzheimer's that repeatedly failed but was stubbornly adhered at the cost of discouraging virtually all other theories is a good example.
Not cited, probably unread and unloved, but good for most academic careers.
But the frustrated academic can always turn to a kind of fraud: "Some of The World's Most-Cited Scientists Have a Secret That's Just Been Exposed".
At the other end of the spectrum: "The top 100 papers: Nature explores the most-cited research of all time."
Includes a couple of pictures I had not seen before of Big Al playing the violin.
I, for one, wish him the best of luck.
Dr Peter Scott-Morgan, 61, decided to challenge what it meant to be human when he refused to accept his fate following a diagnosis of motor neurone disease in 2017.
He said he wanted to push the boundaries of what science can achieve so decided to extend his life and become fully robotic .
I don't know about that, but I'd bet radical change is more likely comes true than the dopey prediction Lord Kelvin supposedly made around 1900: "There is nothing new to be discovered in physics now.”
This bit is both unsurprising and surprising. The surprising part to me is that an editor would admit it:
What surprised you the most about being an editor of a major general interest economics journal?
I never thought that the single best predictor of getting a paper accepted, would be clear and accessible writing, including an explanation of where the paper breaks down, instead of putting the onus of this discovery on the reader.
Link via Marginal Revolution.