The main reason people should stop saying, "That confirms my priors," is because it doesn't even make any sense. Any evidence you get at all should change your prior probability, unless you've gotten pieces of evidence that weigh both for and against the hypothesis and perfectly cancel each other out, in which case the net effect is no evidence. So it's by definition impossible to "confirm your priors": If your prior stayed the same, then you got no net evidence either way, and if you got evidence that confirms something, you should necessarily update your priors.
As you say in the article, what people really mean by "confirm my priors" is "confirm my beliefs." That can be done by simply finding evidence that weighs in favor of the hypotheses you already thought were more likely. This will make you more confident in your beliefs, but that's not the same thing as being more confident in your priors. By definition, becoming more confident in your beliefs means that you no longer agree with your old prior. People are just using the word "prior" wrong - to represent a proposition that you hold a binary attitude of belief or nonbelief towards, rather than to describe a degree of confidence in a proposition.
As a side note, I think the SMBC comic is wrong. The entire point of Bayesianism as a philosophy is to make you less confident in your beliefs by treating them as non-binary judgements that change over time, rather than just thinking in terms of "this claim is true/false," which tends to make people overconfident. And the Bayesians that I know of, Nate Silver among them, actually succeed at this and tend not to render overconfident judgements. They also don't pretend to use math unless they actually are doing the math. Meanwhile, other pundits tend to produce very overconfident judgements. To be fair, though, I might have a biased sample that includes a lot of Bayesians who do it right, rather than the ones who misuse Bayesian reasoning.
This is very silly. You don't subscribe to Bayesianism, so obviously *you* shouldn't say priors. Lots of people have different beliefs, so they do.
Was that really worth a post? Did this make a useful contribution to discourse? Why not just argue against Bayesianism, instead of this snarky 'you're not Nate Silver', shaming people for speaking in a way that more precisely communicates their beliefs?
You're not Nate Silver, so you shouldn't try to improve the way you talk and reason about things in the way that he does. You shouldn't try to reason in a quantitative way, because that would be "pretending to do math", and no doubt, implicitly, *pretentious*.
I can't fathom why Bentham's Bulldog liked this, inflicting upon me the substack version of bullying nerds because they care about stuff.
I'm pretty sure this article started as an anger towards jargon (literally an abbreviation for person's *prior beliefs* , Wiki "Klayman and Ha used Bayesian probability and information theory as their standard of hypothesis-testing, rather than the falsificationism used by Wason. According to these ideas, each answer to a question yields a different amount of information, which depends on the person's *prior beliefs.* ") which then bent its way into "I don't like these people, so they are Subjective Bayesians that don't even care about combatting this little thing called Confirmation Bias so I won't look at each X post and see it's all self-deprecating humor, and also overstep and say the elusive actual Subjective Bayesian in the Smbc comic does no math, rather than less math."
Belief is expectation of predictive accuracy. Prior does not require actionability,, only the weighted tendency. And it's always in context of new information, which belief is not. The terms stand as pragmatically distinct.
Whether they're being misused is a separate question.
It's worth noting that people working in philosophy of probability, in my experience, generally think probability tracks degrees of belief. Some of them may be objective Bayesians, but this is still compatiable with priors talk.
So I don't think talking about priors is really sticking out your neck too much.
Identity generally. You're right, it's loose phrasing on my part. Most philosophers working in the area seem to think probability is degrees of belief, and the probability calculus is a normative constraint on them.
Subjective theories of probability are popular, yes, but there are lots of problems with them! (For one, they can't account for the use of probability theory in statistical mechanics and quantum mechanics.)
A total layman. But I have also noticed that the word priors seems to be vogue. However, from my layman’s perspective the difference between belief and a prior is prior has the connotation of “starting place.” And belief does not. It makes sense to build on a belief and it makes sense to come to a belief. But with prior, while it makes sense to build on one’s priors, it seems to make less sense to “come to a prior”
So I guess my question is what would be the appropriate word for “starting place” when it comes to the drafting of an argument?
I guess the way I use priors is less as a gloss for belief and more as a gloss for assumption. So the things I am not going to defend but rather build on.
I think it's very important for understanding yourself and your reasoning to realize that your beliefs are the assumptions you make and the things that you build on in further reasoning, whether you defend them or not.
I'm curious what the "specific way" and "specific mindset" are that allow disagreements to be understood and received properly?
I'll actually grant a little more than Matt here, I do think that some people, some times, use "prior" to convey something like belief + orientation toward as a preliminary position. But I believe you've given the primary reason it's lately used in your reply.
The main reason people should stop saying, "That confirms my priors," is because it doesn't even make any sense. Any evidence you get at all should change your prior probability, unless you've gotten pieces of evidence that weigh both for and against the hypothesis and perfectly cancel each other out, in which case the net effect is no evidence. So it's by definition impossible to "confirm your priors": If your prior stayed the same, then you got no net evidence either way, and if you got evidence that confirms something, you should necessarily update your priors.
As you say in the article, what people really mean by "confirm my priors" is "confirm my beliefs." That can be done by simply finding evidence that weighs in favor of the hypotheses you already thought were more likely. This will make you more confident in your beliefs, but that's not the same thing as being more confident in your priors. By definition, becoming more confident in your beliefs means that you no longer agree with your old prior. People are just using the word "prior" wrong - to represent a proposition that you hold a binary attitude of belief or nonbelief towards, rather than to describe a degree of confidence in a proposition.
As a side note, I think the SMBC comic is wrong. The entire point of Bayesianism as a philosophy is to make you less confident in your beliefs by treating them as non-binary judgements that change over time, rather than just thinking in terms of "this claim is true/false," which tends to make people overconfident. And the Bayesians that I know of, Nate Silver among them, actually succeed at this and tend not to render overconfident judgements. They also don't pretend to use math unless they actually are doing the math. Meanwhile, other pundits tend to produce very overconfident judgements. To be fair, though, I might have a biased sample that includes a lot of Bayesians who do it right, rather than the ones who misuse Bayesian reasoning.
This is very silly. You don't subscribe to Bayesianism, so obviously *you* shouldn't say priors. Lots of people have different beliefs, so they do.
Was that really worth a post? Did this make a useful contribution to discourse? Why not just argue against Bayesianism, instead of this snarky 'you're not Nate Silver', shaming people for speaking in a way that more precisely communicates their beliefs?
You're not Nate Silver, so you shouldn't try to improve the way you talk and reason about things in the way that he does. You shouldn't try to reason in a quantitative way, because that would be "pretending to do math", and no doubt, implicitly, *pretentious*.
I can't fathom why Bentham's Bulldog liked this, inflicting upon me the substack version of bullying nerds because they care about stuff.
Good article overall, but the use of priors and Bayesian reasoning is downstream of the rationalism community rather than Nate Silver
Sure, but I think Silver made it go mainstream.
So saying 'don't say priors because you're not Nate Silver' wouldn't make much sense then?
I thought it was Nate - lemme go update my priors
In thee political arena that’s fair
I'm pretty sure this article started as an anger towards jargon (literally an abbreviation for person's *prior beliefs* , Wiki "Klayman and Ha used Bayesian probability and information theory as their standard of hypothesis-testing, rather than the falsificationism used by Wason. According to these ideas, each answer to a question yields a different amount of information, which depends on the person's *prior beliefs.* ") which then bent its way into "I don't like these people, so they are Subjective Bayesians that don't even care about combatting this little thing called Confirmation Bias so I won't look at each X post and see it's all self-deprecating humor, and also overstep and say the elusive actual Subjective Bayesian in the Smbc comic does no math, rather than less math."
"If this sounds a bit silly, that’s because it is."
It actually sounds completely reasonable.
I think saying "prior" sounds cool and smart and stylish, so I will continue to do so and celebrate those who feel similarly
Belief is expectation of predictive accuracy. Prior does not require actionability,, only the weighted tendency. And it's always in context of new information, which belief is not. The terms stand as pragmatically distinct.
Whether they're being misused is a separate question.
Thanks for playing #wordgames.
No
I think "belief" often implies certainty. Eg "I believe the Earth is a sphere" or "I believe there's no God."
So "prior" simply gets at the idea of "I figure this thing is true but with only low to medium confidence".
Seems like perfectly reasonable language usage to me.
It's worth noting that people working in philosophy of probability, in my experience, generally think probability tracks degrees of belief. Some of them may be objective Bayesians, but this is still compatiable with priors talk.
So I don't think talking about priors is really sticking out your neck too much.
What do you mean "probability *tracks* degrees of belief?" Is that tracking identity, causal regulation, normative regulation, or what?
Identity generally. You're right, it's loose phrasing on my part. Most philosophers working in the area seem to think probability is degrees of belief, and the probability calculus is a normative constraint on them.
Subjective theories of probability are popular, yes, but there are lots of problems with them! (For one, they can't account for the use of probability theory in statistical mechanics and quantum mechanics.)
When intelligence is the highest attribute, people will fake intelligence any way they can.
I’m always delighted to conversate on it.
https://substack.com/profile/214294422-kaiser-basileus/note/c-238138081
A total layman. But I have also noticed that the word priors seems to be vogue. However, from my layman’s perspective the difference between belief and a prior is prior has the connotation of “starting place.” And belief does not. It makes sense to build on a belief and it makes sense to come to a belief. But with prior, while it makes sense to build on one’s priors, it seems to make less sense to “come to a prior”
Your priors today are the beliefs you came to yesterday.
So I guess my question is what would be the appropriate word for “starting place” when it comes to the drafting of an argument?
I guess the way I use priors is less as a gloss for belief and more as a gloss for assumption. So the things I am not going to defend but rather build on.
I think it's very important for understanding yourself and your reasoning to realize that your beliefs are the assumptions you make and the things that you build on in further reasoning, whether you defend them or not.
Why not just say "beliefs" in that situation?
In other words: it communicates useful information. Matt doesn't like that, because he disagrees with the beliefs that the word implies.
I wish he'd just said that.
I'm curious what the "specific way" and "specific mindset" are that allow disagreements to be understood and received properly?
I'll actually grant a little more than Matt here, I do think that some people, some times, use "prior" to convey something like belief + orientation toward as a preliminary position. But I believe you've given the primary reason it's lately used in your reply.