Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

jimrandomh comments on What is Bayesianism? - Less Wrong

81 Post author: Kaj_Sotala 26 February 2010 07:43AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (211)

You are viewing a single comment's thread.

Comment author: jimrandomh 27 February 2010 02:33:08AM *  4 points [-]

A frequentist asks, "did you find enough evidence?" A Bayesian asks, "how much evidence did you find?"

Frequentists can be tricky, by saying that a very small amount of evidence is sufficient; and they can hide this claim behind lots of fancy calculations, so they usually get away with it. This makes for better press releases, because saying "we found 10dB of evidence that X" doesn't sound nearly as good as saying "we found that X".

Comment author: PhilGoetz 27 February 2010 05:43:34AM 1 point [-]

Since when do frequentists measure evidence in decibels?

Comment author: JGWeissman 27 February 2010 05:54:10AM 1 point [-]

jimrandomh claimed that frequentists don't report amounts of evidence. So you object that measuring in decibels is not how they don't report it? If they don't reports amount of evidence, then of course they don't report it in the precise way in the example.

Comment author: toto 27 February 2010 08:15:24PM *  1 point [-]

Frequentists (or just about anybody involved in experimental work) report p-values, which are their main quantitative measure of evidence.

Comment author: JGWeissman 27 February 2010 09:21:18PM 4 points [-]

Evidence, as measured in log odds, has the nice property that evidence from independent sources can be combined by adding. Is there any way at all to combine p-values from independent sources? As I understand them, p-values are used to make a single binary decision to declare a theory supported or not, not to track cumulative strength of belief in a theory. They are not a measure of evidence.

Comment author: Academian 17 March 2010 01:46:03PM *  4 points [-]

Log odds of independent events do not add up, just as the odds of independent events do not multiply. The odds of flipping heads is 1:1, the odds of flipping heads twice is not 1:1 (you have to multiply odds by likelihood ratios, not odds by odds, and likewise you don't add log odds and log odds, but log odds and log likelihood-ratios). So calling log odds themselves "evidence" doesn't fit the way people use the word "evidence" as something that "adds up".

This terminology may have originated here:


I'm voting your comment up, because I think it's a great example of how terminology should be chosen and used carefully. If you decide to edit it, I think it would be most helpful if you left your original words as a warning to others :)

Comment author: JGWeissman 17 March 2010 04:53:32PM 0 points [-]

By "evidence", I refer to events that change an agent's strength of belief in a theory, and the measure of evidence is the measure of this change in belief, that is, the likelihood-ratio and log likelihood-ratio you refer to.

I never meant for "evidence" to refer to the posterior strength of belief. "Log odds" was only meant to specify a particular measurement of strength in belief.

Comment author: ciphergoth 17 March 2010 02:44:00PM *  0 points [-]

Can you be clearer? Log likelihood ratios do add up, so long as the independence criterion is satisfied (ie so long as P(E_2|H_x) = P(E_2|E_1,H_x) for each H_x).

Comment author: Academian 17 March 2010 02:56:52PM 2 points [-]

Sure, just edited in the clarification: "you have to multiply odds by likelihood ratios, not odds by odds, and likewise you don't add log odds and log odds, but log odds and log likelihood-ratios".

Comment author: Morendil 17 March 2010 02:55:09PM 1 point [-]

As long as there are only two H_x, mind you. They no longer add up when you have three hypotheses or more.

Comment author: ciphergoth 17 March 2010 02:59:42PM 0 points [-]

Indeed - though I find it very hard to hang on to my intuitive grasp of this!

Comment author: Academian 20 March 2010 12:51:28AM 1 point [-]

Here is the post on information theory I said I would write:


It explains "mutual information", i.e. "informational evidence", which can be added up over as many independent events as you like. Hopefully this will have restorative effects for your intuition!

Comment author: Academian 17 March 2010 03:08:38PM 0 points [-]

Don't worry, I have an information theory post coming up that will fix all of this :)

Comment author: Cyan 28 February 2010 03:09:16AM 1 point [-]

There's lots of papers on combining p-values.

Comment author: JGWeissman 28 February 2010 05:57:33AM 2 points [-]

Well, just looking at the first result, it gives a formula for combining n p-values that as near as I can tell, lacks the property that C(p1,p2,p3) = C(C(p1,p2),p3). I suspect this is a result of unspoken assumptions that the combined p-values were obtained in a similar fashion (which I violate by trying to combine a p-value combined from two experiments with another obtained from a third experiment), which would be information not contained in the p-value itself. I am not sure of this because I did not completely follow the derivation.

But is there a particular paper I should look at that gives a good answer?

Comment author: Cyan 28 February 2010 02:56:00PM *  0 points [-]

I haven't actually read any of that literature -- Cox's theorem suggests it would not be a wise investment of time. I was just Googling it for you.

Comment author: JGWeissman 28 February 2010 05:50:26PM 0 points [-]

Fair enough, though it probably isn't worth my time either.

Unless someone claims that they have a good general method for combining p-values, such that it does not matter where the p-values come from, or in what order they are combine, and can point me at one specific method that does all that.