For those interested, Netflix has a new documentary out about the case: https://youtu.be/9r8LG_lCbac
Seth_Goldin
Karma: 172
I’m going to try to make it.
Sorry I missed this. I’ll try to attend the next one. I suggest Capital City Brewery at Metro Center.
I recommend a related essay by Hayek, “Competition as a Discovery Procedure.”
This is a fallacious amphiboly, so it’s deductively wrong. There’s no need to even bring up induction here, and Bayesian inference is for induction. It’s a category error to criticize that Bayesian inference doesn’t apply. It would be like asking Bayesian inference to cook me dinner.
David Friedman laments another misuse of frequentism.
I know this is an old thread, but for any people just now reading it, I thought I’d pass along this bizarre development.
There is no such thing as absolute certainty, but there is assurance sufficient for the purposes of human life.
John Stuart Mill, On Liberty
He seems to have understood that 0 and 1 are not probabilities.
Yeah, that would be great, but I can’t do it; I don’t have the technical background, so I hereby delegate the task to someone else willing to write it up.
In A Technical Explanation of Technical Explanation, Eliezer writes,
You should only assign a calibrated confidence of 98% if you’re confident enough that you think you could answer a hundred similar questions, of equal difficulty, one after the other, each independent from the others, and be wrong, on average, about twice. We’ll keep track of how often you’re right, over time, and if it turns out that when you say “90% sure” you’re right about 7 times out of 10, then we’ll say you’re poorly calibrated.
...
What we mean by “probability” is that if you utter the words “two percent probability” on fifty independent occasions, it better not happen more than once
...
If you say “98% probable” a thousand times, and you are surprised only five times, we still ding you for poor calibration. You’re allocating too much probability mass to the possibility that you’re wrong. You should say “99.5% probable” to maximize your score. The scoring rule rewards accurate calibration, encouraging neither humility nor arrogance.
So I have a question. Is this not an endorsement of frequentism? I don’t think I understand fully, but isn’t counting the instances of the event exactly frequentist methodology? How could this be Bayesian?
Cool paper: When Did Bayesian Inference Become “Bayesian”?
http://ba.stat.cmu.edu/journal/2006/vol01/issue01/fienberg.pdf
This is an excellent diagnosis, and those are excellent suggestions for really learning the material.
“If you can’t explain it simply, you don’t understand it well enough.” Albert Einstein
This relates well to my earlier frustration about the cop-out of vaguely appealing to life experience in an argument, without actually explaining anything.
I’m a little late to this game, but I spent over an hour, maybe two, comparing the information from the two websites. I had known nothing previously about the case.
My answers: 1: 0.05; 2: 0.05; 3: 0.95; 4: 0.65
So, I feel pretty vindicated. This was a great complement to Kaj Sotala’s post on Bayesianism. With his post in mind, as I was considering this case, I assigned probabilities to the existence of an orgy gone wrong as against one rape and murder from one person. There is strong Bayesian evidence for Guédé′s guilt, but it’s exceedingly weak for Sollecito and Knox. This has really helped the idea of Bayesianism “click” for me.
komponisto, your reasoning is wonderfully thorough and sound. I can corroborate that I deliberately found myself “shutting the voice out” concerning the activity with the mop. You have a great explanation, overall. These two posts of yours are in the running for my all-time favorites.
Noted, thanks.
I know you two are joking, but I will take this opportunity to point out that I really do appreciate the culture of humility on Less Wrong. It’s Yudkowsky’s eighth virtue. I am aware of my profound ignorance as a mere 22-year-old undergrad.
Alternatively, is this a plea for the Skinnerian, egalitarian abolition of honorifics, as from Walden Two?
Well, I am an undergrad right now, at least for a couple more months.
You really should read Taleb; you can probably start with The Black Swan. His terms for these are “Mediocristan,” domains that are described by Gaussian distributions, and “Extremistan,” domains that are described by power laws.