Find a dubious statistical "fact" and 'talk back to it', citing ideas from Huff's text. The fact can come from an advertisement, news report, text you read, etc.

The post should include:

1. the 'fact';
2. information about the context; and
3. your interpretation of that information, citing Huff.

PLEASE DO NOT USe COLGATE AS AN EXAMPLE.

Reference: How to lie with Statistics by Darrell Huff

HOW TO TALK BACK TO A STATISTIC 123 Who Says So? About the first thing to look for is bias-the laboratory CHAPTER 10 with something to prove for the sake of a theory, a reputa- tion, or a fee; the newspaper whose aim is a good story; How to Talk Back labor or management with a wage level at stake. Look for conscious bias. The method may be direct mis- to a Statistic statement or it may be ambiguous statement that serves as well and cannot be convicted. It may be selection of favorable data and suppression of unfavorable. Units of measurement may be shifted, as with the practice of using one year for one comparison and sliding over to a more favorable year for another. An improper measure may be used: a mean where a median would be more informative So FAR, I have been addressing you rather as if you were ( perhaps all too informative), with the trickery covered a pirate with a yen for instruction in the finer points of by the unqualified word "average." cutlass work. In this concluding chapter I'll drop that Look sharply for unconscious bias. It is often more literary device. I'll face up to the serious purpose that I dangerous. In the charts and predictions of many statis- like to think lurks just beneath the surface of this book: ticians and economists in 1928 it operated to produce explaining how to look a phony statistic in the eye and face remarkable things. The cracks in the economic structure it down; and no less important, how to recognize sound were joyously overlooked, and all sorts of evidence was and usable data in that wilderness of fraud to which the adduced and statistically supported to show that we had previous chapters have been largely devoted. no more than entered the stream of prosperity. Not all the statistical information that you may come up- It may take at least a second look to find out who-says- on can be tested with the sureness of chemical analysis so. The who may be hidden by what Stephen Potter, the or of what goes on in an assayer's laboratory. But you can Lifemanship man, would probably call the "O.K. name." prod the stuff with five simple questions, and by finding Anything smacking of the medical profession is an O.K. the answers avoid learning a remarkable lot that isn't so. name. Scientific laboratories have O.K. names. So do 12124 HOW TO LIE WITH STATISTICS HOW TO TALK BACK TO A STATISTIC 125 colleges, especially universities, more especially ones eminent in technical work. The writer who proved a few chapters back that higher education jeopardizes a girl's chance to marry made good use of the O.K. name of Cor- nell. Please note that while the data came from Cornell the conclusions were entirely the writer's own. But the O O.K. name helps you carry away a misimpression of "Cornell University says . . ." When an O.K. name is cited, make sure that the author- ity stands behind the information, not merely somewhere alongside it. You may have read a proud announcement by the Chicago Journal of Commerce. That publication had made a survey. Of 169 corporations that replied to a poll on price gouging and hoarding, two-thirds declared that they were absorbing price increases produced by the Korean war. "The survey shows," said the Journal (look sharp whenever you meet those words! ), "that corpora- tions have done exactly the opposite of what the enemies of the American business system have charged." This is an obvious place to ask, "Who says so?" since the Journal of Commerce might be regarded as an interested party. It is also a splendid place to ask our second test question: How Does He Know? BIG NOSE AND THROAT MAN It turns out that the Journal had begun by sending its questionnaires to 1,200 large companies. Only fourteen