Statistics analyst Gary Smith: Even if COVID-19 deaths are randomly distributed among the population (and they surely aren’t), data mining will, more likely than not, discover a geographic cluster of victims… (Lots of things can start to appear meaningful.)
Tag: statistics
The perils of data mining in science
Findings patterns in data is easy. Finding meaningful patterns that have a logical basis and can be used to make accurate predictions is elusive. We can see this from 18th-century attempts to cure scurvy through 21st century claims about the stock market or history.
An eye-opening science-related COVID roundup
Reliance on expertise can, depending on the circumstances, be a form of superstition. And, in short, the numbers solemnly announced by the suits on TV are often just a crock. And none of this is doing the reputation of science any good.
Why COVID-19 rates are difficult to compute
Among other things: “Things appear deceptively dire if we calculate death rate solely by reference to reported COVID-19 cases; but the picture is deceptively benign if we measure deaths against an inflated conjecture about the non-reporting population. ” – McCarthy
Fake stats debunker Ioannidis on COVID-19 stats: Not reliable
Ioannidis: School closures may also diminish the chances of developing herd immunity in an age group that is spared serious disease…
Michael Egnor: The bird does NOT do math
Egnor: Dr. Pepperberg could have been more forthright: Parrots can’t do statistics. No animal (except man) can do statistics, because statistical reasoning is abstract and only human beings are capable of abstract thought. Parrots think concretely—they think of particular things and relations between particular things, but they cannot think without particular things—they can’t think abstractly.
Rob Sheldon on why statisticians are in a panic
The panic in sociology, psychology, nutrition science, and pharmacology has been growing as >70% papers with “p-values” smaller than 0.05 are discovered to be unrepeatable.
Simpson’s Paradox: Numbers are stranger than we think
One outcome of Simpson’s Paradox is that machines cannot replace statisticians in analysing results. A great deal depends on interpretation, as Marks shows. “Clustering remains largely an art.”
Proven: If you torture a Big Data enough, it will confess to anything
In his fascinating new book The AI Delusion, economics professor Gary Smith reminds us that computers don’t have common sense. He also notes that, as data gets larger and larger, nonsensical coincidences become more probable, not less.
Media are flabby from a diet of junk science
Should we believe them when they tell us that the drinking four cups of coffee daily lowers our risk of death people with spouses live longer? A statistician and a physician team up to explain why not: A subtler manifestation of dishonesty in research is what amounts to statistical cheating. Here is how it works… Read More…
Requests for actual statistics FRAUD not unusual, science writer finds
There may be an additional, more sinister explanation for the ongoing reproducibility crisis, he suggests: A stunning report published in the Annals of Internal Medicine concludes that researchers often make “inappropriate requests” to statisticians. And by “inappropriate,” the authors aren’t referring to accidental requests for incorrect statistical analyses; instead, they’re referring to requests for unscrupulous Read More…