A Cultural Paradox Fun in Mathematics by Jeffrey A. Zilahy - HTML preview

PLEASE NOTE: This is an HTML preview only and some elements such as links or page numbers may be incorrect.
Download the book in PDF, ePub, Kindle for a complete version.

CH 11: 42% of Statistics are Made up

In our media and culture, the bandying about of statistics to compel in arguments is a very common practice. Whether it is a politician trying to convince his electorate, or a talking head trying to make their point, we are constantly inundated with statistics aimed at quantifying the world around us. The truth is that too often statistics are misleading and misinterpreted.

Let’s consider a few examples. There are "shooting the barn" statistics, where you collect data without first determining the results you seek. It gets its name from the metaphor of someone shooting a bunch of arrows into the side of a barn and then circling the area with the most arrows and deeming that the target, a classic case of putting the cart before the horse.

Another flawed approach is Sample Trashing, when perfectly good data is thrown out because it does not conform to what is trying to be proven. It is common for purported psychics to use this approach to throw out all their mistakes while highlighting anything they happen to get correct.

There is also the Statistical Brick Wall, where the numbers in use cannot be verified because the statistical data does not even exist! A great example of this fallacy in play is when scientists predict the annual number of species that go extinct each year. The number is always arbitrarily high because the scientists are taking into account all the species that humans have not discovered yet, which clearly is a number that cannot be verified.

We also need to avoid the condition of “average thinking” where someone thinks if you flip a coin ten times and it comes up heads nine of those times that somehow the next flip should be higher than 50% to obtain tails. There are also examples of very misleading use of numbers, like when a company says their product is "99.44% pure", in some cases this is simply a trademarked phrase and not a mathematical fact.

In very close elections, it is actually possible to create scenarios in which either candidate is the winner. This is why it is so important to decide how votes are counted and how a winner is decided before the election.

img10.png

If everyone believes in it, does that make it true?