© 2010 Ugur Akinci
In technical communication we should be careful not to fall in for “false correlations”. We should hesitate before accepting a high correlation between two variables as the sign of a “causality” between them.
A hilarious recent case in point is the high correlation British mathematicians have found between the number of cell ph0ne relay towers and babies born in every county across the United Kingdom!
So does this mean that cell phone towers really increase fertility? Of course not, even though the “mathematical evidence” is indisputable: For every extra mobile phone mast in an area, there are 17.6 more babies born above the national average. And the result is so statistically significant that the probability this relationship is happening by chance is 0.00003% !
So what’s the explanation? Simple…
Think about it a few minutes and see if you’ll be able to figure it out. (I have to admit, I couldn’t.)
There is a THIRD VARIABLE that is related to both of these variables (number of cell towers and number of babies born) positively and strongly: COUNTY POPULATION.
The more populous a county, the more cell phone towers it has. It also has more babies born there. Case closed.
P.S. I first thought the missing variable was “cell phone ownership” and not the county population. I thought people who owned cell phones had better jobs and made more money; and thus they had the budget to afford more babies. “Population” is of course a much simpler and a lot more elegant solution to the puzzle of “missing third variable”.