[ExI] The Republican Party Isn't Really the Anti-Science Party

[Anders Sandberg]

On 2013-11-13 08:17, rex wrote:
> Interesting idea, Anders, but I don't understand it. We have a record
> of hurricane numbers h[i] for years i = 1:N, and temperature records for
> those years. We could do a linear regression to try to estimate how
> much of the variance in hurricane numbers is accounted for by 
> temperature,
> but where does the biased coin model enter into it?

I wanted to give an easy example, rather than get into the statistics.

Yes, we can try to model how hurricanes are affected by temperature, and 
maybe it is even possible to say something sensible about it. But going 
in the opposite direction, looking for evidence of higher temperatures 
in the hurricane frequency, does not work at all. There are few data 
points, but worse, we do not know the map hurricane "frequency -> 
temperature". Sure, we could first do the regression and then use it, 
but then we are just feeding the data back twice - we are not learning 
anything new.

Looking at https://en.wikipedia.org/wiki/Atlantic_hurricane_season shows 
a pretty noisy time series; the trend is definitely smaller than the 
variability.


Hehehe... another political thread hi-jacked by statistics! :-)

-- 
Dr Anders Sandberg
Future of Humanity Institute
Oxford Martin School
Oxford University