Pages

Tuesday, November 07, 2006

Ridiculing the ridiculous

BILL CURRY SAID:

Steve’s Quote: Permit my to my own back-of-the-envelop calculation. Assuming that there were about 6 billion people alive today, there’s only a one-in-six billion chance that Bill Curry even exists.

“Steve, I think this comment indicates a fundamental misunderstanding of Bayesian inference. But here is a chance for you to prove me wrong. Let’s use a more numerically extreme example.”

I see no reason to prefer your example over mine. I chose the example I did because it’s the way that Michael Martin reasons in chapter 2 of TET (pp50-51), where the more specific the claim, the lower the initial probability.

Be definition, the existence of Bill Curry is a contingent, one-in-six-billion event.

What prior probability would you assign to this event? And how would you probabilify the evidence needed to overcome this presumption to the contrary?

“Please answer these questions.”

I posed a number of questions in the previous post for you to answer, which you’ve chosen to ignore.

“In my opinion, you subject your opponents to a lot of ridicule, but the ridicule may be worth it if I am going to learn something from you. At this point, I am unconvinced that you are making a reasonable effort to understand my position or Bayesian inference in general. Your behavior is very surprising if one thinks that the Holy Spirit is working in your life.”

Well, now, let’s see. According to my pneumatology, the Holy Spirit is the author of the Bible. And the Bible ridicules the enemies of the faith.

Indeed, there’s even a literary genre which raises ridicule to an art form, viz. the taunt-song. Taunt-songs are pure ridicule from start to finish.

“I certainly hope I and my own children can refrain from ridiculing those they disagree with as you regularly do here.”

1.While your teaching your children not to ridicule those they disagree with, you might also teach them not to make exaggerating claims about those they disagree with.

I don’t ridicule everyone I disagree with. To take the most recent example, I’ve had several exchanges with the interlocutor in which I refrained from any ridicule.

I have a very logical rule of thumb about this: ridiculous positions merit ridicule.

2.I treat you exactly the way you treat the Bible.

“It seems to me that you are mischaracterizing what the author is saying here. The author is indicating that Bayesian analysis is not applicable for assessing the question of miracles in general (Hume’s argument in particular), with which I agree. In principle Bayes’ Theorem could be used to support particular miracle claims. But the author did not make the case that Bayesian inference cannot be used to assess a particular miracle claim. The author may or may not believe that, but this quote doesn’t strongly support the idea that Bayesian inference is not a useful tool for such assessments.”

You’re attempting to change the subject. Why doesn’t that surprise me?

His point is that one cannot bring Bayesean analysis to bear until certain preliminary, metahistorical questions have been addressed—questions which fall outside the scope of Bayesean analysis.

And, among other glaring omissions, it’s this preliminary step which you (and your brother) are attempting to sneak past customs.

“If you are interested in a valid assessment I hope that you would. I have attempted to make my argument as scrutable as possible. I would welcome you doing the same. If you would like, I could email you or Jason the MS Excel spreadsheet I used so you could use that as a template for your inferential argument for the resurrection. Of course, if you want to obfuscate the issues as much as possible, this would not help you achieve your goals.”

My “inferential” argument is contained in my review of the ET. I think it would be a little difficult to reformat my 480 page review to fit into the confines of an Excel spreadsheet, but perhaps you can offer me some technical pointers on that exercise.

I said: Curry doesn’t bother to interact with Stephen T. Davis’ criticisms of Bayesean theory in this context.”

Curry said: “Because MacKay and Jaynes (both books published in 2003) have successfully defended Bayesian inference to my satisfaction. Some of the criticism that you have offered have been variants of the Hempel paradox which has been answered as early as 1967 by I. J. Good, according to Jaynes.”

Notice how Bill Curry always plays a bait-and-switch game by jumping from the general to the specific or vice versa without constructing a stepwise bridge from one to the other.

Even if Bayesean probability theory were generally sound, that’s irrelevant to the specific issue at hand.

“I disagree with some of the number’s Martin used as well, but I would agree with Davis that ‘I have said little thus far about the way Martin uses Bayes's Theorem, which by and large is beyond reproach, at least until he starts supplying actual values.’”

Same bait-and-switch. Ignore his specific criticisms.

“I think my a priori assessment for the initial plausibility is quite reasonable.”

Even if that were true, it’s a huge leap of logic to jump from “quite reasonable” to putting numbers on this or that with a certain decimal expansion.

“Pagan miracle claims vastly outnumber miracle claims in the gospels and far exceed the number of miracles observed today.”

This is an assertion, not an argument. And I’d add that the gospels are not the only sample. There are Biblical miracles generally, exclusive of the gospels.

“This fact in conjunction with the fact that there is a great deal of known fraud in religious writing gives me to think that my a priori expectation of miracles is quite reasonable.”

There’s a great deal of known fraud in secular writings as well.

“To quote MacKay “you can’t do inference – or data compression – without making assumptions.” I have tried to make my assumptions clear, will you?”

Once again, making your assumptions clear or being “quite reasonable” (even if that were true) affords you absolutely no concrete justification for the actual numbers you brandish.

Citing books on the general topic of Bayesean probability theory is irrelevant to how you yourself generate the specific probability values for these specific events.

This is one of the crucial steps which you always leave out. You tell us what your operating assumptions are, and you give us your results, but everything in-between is missing.

Curry’s blackbox. And he keeps it under lock-and-key because there’s nothing inside—except for maybe a stale ham sandwich or a gerbil on a wheel.

So there is the lack of detailed argumentation for your operating assumptions, along with any detailed argumentation for the process by which you actually probabilify these events.

That’s not Bayesean inference. That’s Bayesean rhetoric. Using a few gee-whiz catchphrases, along with the pseudo-precisionistic figures you pull out of your hat to stick onto your results, is a phony show of exactitude. This isn’t rigor—this is rigmarole.

8 comments:

  1. :::YAWN!!!:::


    P.S. Why didn't you ever answer the question that was posed to you about your 'real job?'

    ReplyDelete
  2. Perhaps because you atheists are too lazy to even read his profile.

    ReplyDelete
  3. Steve's profile says "writer" for occupation.

    See, I can read.

    However, I'm not an atheist. I'm not sure why the t-bloggers are so quick to assign that label to people that make comments that aren't gushy gooey "Go Calvin" comments.

    For the record, my occupation is "worker."

    ReplyDelete
  4. You can read, and yet you apparently don't want to make the effort to read past the first line.

    Keep reading. Second line of the body text under 'About me.'

    ReplyDelete
  5. Bill,

    Given Steve's demonstrated infantile grasp of what would be considered an obvious concept to any first year student of probability and statistics (see pages 41-42 in "ThisJoyful Eastertide” and the correction by anonymous in the “Cooking the Books” thread), I think your wasting your time trying to get him to interact in any kind of intelligent way with your arguments.

    ReplyDelete
  6. You're right, PMS. Bill and I discussed this over the phone last night. Bill is sometimes hopeful that people here will come to understand him, but I told him to post only if there's a chance that a response from Steve would include something that he could learn from. Do not post in hopes that Steve will actually come to understand something. He will not. And we are also both aware that when you do venture to post here as a skeptic you will be called names, insulted, ridiculed, and generally attacked personally, as per the biblical example. So you have to decide if that is worth the price.

    ReplyDelete
  7. Steve,

    I am not sure that I understand your point of your example. Assuming that there were about 6 billion people alive today, there’s only a one-in-six billion chance that Bill Curry even exists.

    Are you saying that 1) this is an example of Bayesian inference and 2) this shows the absurdity of Bayesian methods applied to everyday reasoning? Would it be helpful if I recast your argument in what I think are more proper Bayesian terms?

    One reason that I was reluctant to use your example is that the hypothesis space seems ambiguous. Why would you say the there is a one-in-six billion chance that Bill Curry event exits? There are a lot of humans named Bill Curry that are not me. There are even more none human things that are not me (the Orion nebula, the Homestead Act of 1862, the number 42). It seems to me that your example gives a lot opportunity for misunderstanding, so I presented an example that I though would provide more clarity.

    I am will to try and discuss this in accord with the advice found in 1 Peter 1:17 and 1 Peter 3:9-16 with regard to respect and honoring everyone, but it is your call.

    ReplyDelete
  8. I think Steve believes he is on to something profound, but he’s really only recycling a sophomoric false paradox.

    If one million people play the lottery, each participant obviously has a one in a million chance of winning, but, just as obviously, the odds that SOMEONE will win is 1/1.

    Let’s say Mr. X wins the cash. What Steve is doing would be analogous to someone claiming the near impossibility that that participant X actually won the cash since his chances were, after all, only 1 in a million (even as lucky Mr. X cashes in his big fat check, quits his job, and retires to a beach side resort in Cabo).

    Probability applies when we are elucidating the likelihood of a particular outcome, not after a particular outcome has obtained, since, by that time, the distribution of probabilities we applied beforehand has collapsed to singularity (or better yet, a certainty).

    Hate to state the obvious; it’s just that Steve really seems to have his head in the clouds on this one…or maybe he just needs to clarify his point a wee bit more.

    ReplyDelete