Wednesday, September 30, 2009

What's the difference between Bayesian and classical statistics

Some interesting comments on the subject to be found here: What's the difference between Bayesian and classical statistics - Statistical Modeling, Causal Inference, and Social Science

I would say that Bayesians are the ones who are actually addressing the problems that most frequentists only think that they are...which I suppose is the same thing as Bill Jefferys' comment:
Since my background and training are in the physical sciences, I've noticed that all but the most sophisticated of my colleagues (that is, those that have learned enough statistics to be dangerous :0), think that a confidence interval is a credible interval. Which is natural, if mistaken.
Of course the IPCC proved that these entities are the same, back in the TAR...

1 comment:

crandles said...

This Week In Petroleum
http://tonto.eia.doe.gov/oog/info/twip/twip.asp

Seems to be trying to carefully and simply explain what it is doing and err, failing miserably?:

"For example, for a 95-percent confidence level, we calculate a range of prices within which there is a 95-percent likelihood the delivered price for the commodity will fall (for the month the commodity goes to physical delivery). In other words, there is a 5 percent chance the price for that specific month) will fall outside of the 95 percent confidence interval."

Maybe they have enough data to work on that the need to distinguish confidence intervals from credible intervals just isn't important.

Just seemed like the sort of thing to make your blood boil so I thought I would share it ;)