[Dave2042 (Dave)]

Originally Posted by Shiraz

sure its is too low to qualify as a detection under the 5 sigma rule that the particle physicists have embraced. However, if you are 95% confident that you have found something, you cannot ignore it either. The particle physicists would just plough on with more runs until they had more confidence, but that is not an option with a strictly one-off gravitational wave detection. I would think that co-incident 2 sigma events at each of the two detectors would have to be quite significant - although who knows how they assess confidence when they are looking for something from a group of "sort of predictable" structured signals, at 2 sites and against noise that presumably has both random and structured components.

Let's see what they do, but it is interesting that that have already begun to publicise the extra candidate events, even those below 2sigma. My guess is that, now they have one hard detection and a lot of real noise to study, they will be able to increase the confidence estimates on any other candidate events.

Good points. I have always felt that there is a danger of missing the wood for the trees in discussions of statistical significance and sigmas.

The reasons, as I see it, that sigma is so critical in particle physics are:

1. It is generally not known what is 'expected', or predicted by an accepted theory. Indeed, whether the 'blip' is real, is a driver of whether we like one theory over another, given the endless variants of possible theory.
2. You can simply do more runs and drive sigma up as high as you like, or to zero, and settle the matter.

This is not like that.

1. We strongly expect gravitational radiation to exist, for widely accepted theoretical reasons, as well as having the second 'simultaneous' signal telling us this is not just a glitch.
2. We can't just do more runs. This is what we have and we need to work with it.

This is more than just an appeal to Bayesian stats. My point is a more fundamental one about what sigma is. All it tells you is something about the likelihood the signal could have been generated randomly. This number operates in total blindness to any theoretical background or extraneous but relevant information. That's kind of fair in much of modern particle physics, but certainly not here.

The worst (but I feel clearest) example of this misunderstanding is the one where we look at climate stats and say that the probability of the rising temperature data being random is 5%, and conclude there is only a 95% chance we are causing global warming. In fact we know (in the usual sense of the word) that it's warming and we are doing it, from basic science. The uncertainty exists only in relation to our ability to measure the current effect above a lot of background noise.