Viewport width =
October 7, 2013 | by  | in Opinion |
Share on FacebookShare on Google+Pin on PinterestTweet about this on Twitter

Playing (Statis)tricks on Your Mind

tudies show that 87.2 per cent of statistics are made up on the spot. 100 per cent of people who vote in the VUWSA elections will eventually die. Sex Panther by Odeon—they’ve done studies, you know: 60 per cent of the time, it works every time. As you can see, statistics can be twisted in the most deceptive and abhorrent ways. This week’s Mad Science focusses on how to scrutinise statistics.

First lesson: correlation does not equal causation. Many European studies have found a correlation between the birth rate and the number of stork nests. Hurrah! Many of us can validate our naïve belief that storks and only storks bring babies. Wrong. The actual reason for this correlation, according to a STAT193 lecturer who crushed my soul, was that more building construction occurred as the population increased, which in turn provided more nesting places for storks.

Second lesson: don’t be the Average Joe—learn the difference between average and median. For example, take the number of times five people will attempt to try twerking after watching Miley at the VMAs—0, 0, 1, 2, 477. The median, a.k.a. the middle number when they are arranged in ascending numerical order, is once (and no-one is judging). The average is all the twerking attempts added together divided by the number of people—96. If the data is skewed too heavily by one person, it will sway the average but not the median, and thus the ‘average’ person seems like they have waaaaay too much free time (hate to be mean).

Third lesson: being the fastest-growing something might not be all that impressive. Say there are 250 vegans on campus, and their number is growing at a rate of 0.2 per cent per day. Say there are only five bacon-eaters on campus, and two more discover this God-like meat by the end of the day. The number of bacon-eaters has grown by 40 per cent. This sounds more impressive than the vegans’ percentage, but in reality, they still reflect a much smaller group (until two months later when their population reaches 5.7 billion, assuming no heart attacks).

Final lesson: saying something is 99-per-cent accurate can be both true and meaningless. Say one in 8000 people actually are actually Beliebers, and the test for this ghastly affliction is 99-per-cent accurate. That means the test would falsely tell one in 100 people they were Beliebers when they actually had musical taste. This means the tester would tell 80 of those 8000 people they’re Beliebers—even though statistically, only one of them actually is. So for any one person, a “you’re a Belieber” result only has a one-in-80 chance of being true—a base-rate fallacy.

Share on FacebookShare on Google+Pin on PinterestTweet about this on Twitter

About the Author ()

Comments are closed.

Recent posts

  1. VUW Halls Hiking Fees By 50–80% Next Year
  2. The Stats on Gender Disparities at VUW
  3. Issue 25 – Legacy
  4. Canta Wins Bid for Editorial Independence
  5. RA Speaks Out About Victoria University Hall Death
  6. VUW Hall Death: What We Know So Far
  8. New Normal
  9. Come In, The Door’s Open.
  10. Love in the Time of Face Tattoos

Editor's Pick

Uncomfortable places: skin.

:   Where are you from?  My list was always ready: England, Ireland, Scotland, Wales, puppy dogs’ tails, a little Spanish, maybe German, and—almost as an afterthought—half Samoan. An unwanted fraction.   But you don’t seem like a Samoan. I thought you were [inser

Do you know how to read? Sign up to our Newsletter!

* indicates required