Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.2 7/1/84; site wuphys.UUCP
Path: utzoo!decvax!tektronix!uw-beaver!cornell!vax135!houxm!ihnp4!mgnetp!we53!busch!wucs!wuphys!mff
From: mff@wuphys.UUCP (Swamp Thing)
Newsgroups: net.flame
Subject: Good example of lying with statistics
Message-ID: <338@wuphys.UUCP>
Date: Sat, 27-Jul-85 12:35:49 EDT
Article-I.D.: wuphys.338
Posted: Sat Jul 27 12:35:49 1985
Date-Received: Sun, 28-Jul-85 19:58:43 EDT
Distribution: na
Organization: Physics Dept., Washington Univ. in St. Louis
Lines: 33
Xref: tektronix net.flame:11982 

You can see an excellent example of lying with statistics on TV right now.
It's the new Bayer aspirin commercial which gives results of a survey.
Doctors were asked which of the 4 brand-name pain-killers would they want if
stranded on a desert island.  The results were:

	Bayer:  43%

	Exrta-strength Tylonol:  22%

	Tylonol:  20%

	Advil:  5%

The announcer then states that Bayer is preferred by almost 2 to one over all
of the others.  What he doesn't say is that there is essentially a tie between
aspirin and tylonol (43 vs 42) if the two tylonol products are summed.  Some
marketing jerk knew damn well that a survey asking doctors whether they
preferred aspirin or generic tylonol would produce a tie, so he came up with
a survey which would make Baeyer appear to be the winner.




						Mark F. Flynn
						Department of Physics
						Washington University
						St. Louis, MO  63130
						ihnp4!wuphys!mff

"There is no dark side of the moon, really.
 Matter of fact, it's all dark."

				P. Floyd