# I know, I\’m sorry,

Two in a day on Ritchie.

Discussing the normal distribution:

Yes, that’s the normal distribution – a widely recognised statistical phenomenon. As Wikipedia says of this diagram:

Dark blue is less than one standard deviation from the mean. For the normal distribution, this accounts for about 68% of the set (dark blue), while two standard deviations from the mean (medium and dark blue) account for about 95%, and three standard deviations (light, medium, and dark blue) account for about 99.7%.

What this says is that if you observe a phenomena (almost any phenomena) most results cluster around something that might be called normality. But there will always be so data which is way out of the normal range.

Now I don’t ignore stuff way outside the normal – Black Swan theory teaches the importance of that – but equally, and quite candidly, the vast majority of the time we can identify the outliers in any population (like toll roads and Catalonian anarchists) and say they are absolutely irrelevant to the formulation of policy that is likely to have any consequence for real people right now living their lives in the normal range of expectation. Or to put it another way – we can safely ignore this stuff.

So we can safely ignore the stuff that\’s two more more standard devations from the normal can we?

Good Oh. So what the top 2.5% of society earns or how they are taxed is something we can safely forget about then.

Good, glad we\’ve got that sorted.

## 6 thoughts on “I know, I\’m sorry,”

1. Agreed. If we design a tax/welfare system that suits low and average earners (75% of the population, or whatever) then by definition, the same rules and rates ought to apply to those at the top and the bottom.

2. And all that guff in response to someone proving him wrong about roads and tax.

3. The concept of ‘Normal distribution’ is nothing less than a scandal; the worse because it allows (apparently) the further scandal of ‘prediction’.

4. I wonder if Murphy the ultra-mong has even the slightest idea, off the top of his pointy head, what the probability density function of a normal distribution of mean μ and standard deviation σ a) is b) means.

Silly boy shouldn’t bandy grown-up words about.

5. So coming to the conclusion that you’ve changed your mind and no longer want to do stuff you did before you knew better is some kind of sin?

I suspect that Richard’s evident frustration with the libertarian blogosphere is that none of its members seem capable of even reconsidering their position, much less changing it in the face of evidence.

Self-evidently, the abuse he deletes – and has a perfect right to delete – is alive and well. Just read the posts here.