The Normal Distribution
September 30, 2006
Evolution is all about populations. And genetics. And selection pressure and genetic drift and speciation.
But it’s mostly about the normal distribution.
So what is the normal distribution?
Ok, imagine you measured the height of 10,000 people. You can easily get the average height by adding all the heights together and dividing by 10,000. Say this came out as 5’8″.
What proportion of the group were exactly 5’8″ tall? How many were 5’7″ or 6’2″?
So, you divide all the heights into groups. Say from 0″ to 1″, from 1″ to 2″, etc, all the way up to 12’6″ to 12’7″
Then you counted the number pf people who fell into each group, and plotted it onto a chart. The chart would look something like this:
… but probably not as nice and smooth because reality is never as neat as theory.
The shape of that chart is a normal distribution. It also gets called ‘The Bell Curve’ because it looks like the cross-section of a bell.
One thing to notice is that it’s easy to get the average from a normal distribution. It’s the value under the highest point of the distribution.
Most naturally occurring measurements (like height, IQ, length of tongue, etc) follow a normal distribution. There are lots of statistical measurements that you can use to check whether measurements are normally distributed (like ‘skewness’ and ‘kurtosis’) but we won’t bother with them just now, they just complicate things.
The Oxford English Dictionary defines evolution as ‘any net change in the genetics of a population’.
To all intents and purposes we can take this as ‘any change to the normal distribution of a characteristic within a population’.
That’s why evolution is all about the normal distribution. Except when it isn’t, but I’m not going to worry about that.
If you’re interested in writing software, check out my other blog: Coding at The Coal Face
Written while listening to: