The Statistics of Winter

Question: when is a trend not a trend?

Answer: when it’s been going barely a week.

Or, to put it more technically, for something to become a trend in any meaningful way, the event has to recur repeatedly. ‘Once or twice’ is not ‘repeatedly’. I’m writing this as we’re currently having an actual winter here in the UK, and we also had a winter last year. That’s two in a row, and it’s bound to summon climate-denialist nutcases soon. Two in a row must be a trend, right?

Really, really no.

In fact, we don’t even know yet if this winter even will be cooler than normal. The current cold snap started less than a fortnight ago, and winter doesn’t end until March. It’s barely even December now. For all we know, temperatures may well bounce back to their historical averages in January and February.

And even if we have two cold winters in a row, well, is that actually that odd? A quick glance at Wikipedia suggests that there have been at least five significantly-cold winters here in the last century (1946-47, 1962-63, 1990-91, 2009-10 and maybe 2010-11). And that’s just the ones that have made it to Wikipedia – anecdotal discussion with other people suggests that the winter of (IIRC) 1981 should count as well.

Straight away, we’re heading for half a dozen cold winters. It seems they’re not actually that rare.

Anyway, going with the above list, we have 5 definitely-cold winters in 100 years, which naively implies a 5% chance of any given year being cold. Granted, 5% seems like a small number, but it isn’t that small. So this means that although two randomly-cold ones in a row aren’t very likely, it’s not vanishingly unlikely either. Or, to phrase my point a bit more clearly, cold winter DOES NOT EQUAL no climate change.

Now, if the winter of 2010-11 stays cold and next year’s winter is also cold as well, then maybe there’ll be a trend starting to emerge. (I’ll consider the odds of three cold winters in a row as getting a bit on the low side.) But, at the time being, I don’t feel that any conclusion can be drawn from the current weather, except that you shouldn’t go outside without a hat!


2 Responses to “The Statistics of Winter”

  1. I agree that the winter of ’81 should count as exceptionally cold. I remember it being so cold that you could feel it coming through the walls of the house, something I’ve not experienced since. Even this last week or so it hasn’t got that bad.
    I’m pretty certain ’81 was the winter the Norwegian government told people not to bathe because it was so cold. I could be wrong on this last one as I was only three at the time ๐Ÿ™‚

    • I don’t actually remember ’81 myself, because I would have been -2 at that point! (Possibly the same as the weather? ๐Ÿ˜‰ )

      But my dad has photos of digging my grandmother’s house(!) out of the snow, so I think it’s fair to say that it was pretty cold!

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: