“Lies, damned lies, and statistics” is a phrase describing the persuasive power of statistics to bolster weak arguments, “one of the best, and best-known” critiques of applied statistics.[2] It is also sometimes colloquially used to doubt statistics used to prove an opponent’s point.
from wikipedia, which leads me to my question:
what is this critique?
In: 0
Statistics gives us different ways to look at groups of numbers. Sometimes this provides illumination, but some ways of looking at things are stupid.
For example: if aliens came along and notices that humans wear bras they might design a bra with one cup since, on average, humans have one breast. That is correct, but useless.
Nearly all human beings have a higher than average number of legs. This is true, but it’s not helpful.
You can look up Simpson’s Paradox for a more complicated example.
You can use a ruler incompetently and get an inaccurate measurement. You can use statistics incompetently and think you understand something when you don’t or you can use statistics maliciously and mislead people. There are plenty of people who are incompetent, and plenty of people who are dishonest, so anytime you see a statistic used to support a point you have to look at it very carefully. That pretty much requires some training in statistics, which most people don’t get.
So a quoted number may not be wrong, it may simply be used badly. This is particularly true of the “average”, technically the arithmetic mean, which is by far the most popular type of statistic thrown around.
Latest Answers