Physics Guy wrote:Skimming through Kass and Raftery 1995 turned out to be easier but less helpful than I thought. I find two points.
1) The association of qualitative terms like "not worth more than a bare mention", "substantial", "strong", etc. for specific ranges of likelihood ratio is indeed discussed in section 3.2 of KR95. This association is NOT used, however, as a rule for assigning quantitative likelihood ratios to subjective assessments of evidence. It's exactly the reverse: KR95 offers the qualitative terms as interpretations that can fairly be made of numerical values in various ranges. There is no suggestion whatever that Bayesian likelihood ratios should ever be restricted to a small set of specific values representing different subjective assessments of evidence strength. That is absolutely turning KR95 on its head. Furthermore KR95 includes the qualitative categories "decisive" or "very strong" for likelihood ratios greater than 100 or 150—with no upper limit. This clearly implies that Bayesian likelihood ratios CANNOT be capped in advance at 50.
2) If the Dales are trying to deflect criticism by citing KR95 then they are simply trying to snow their critics, because KR95 is twenty pages long and only a single column of it deals with anything remotely relevant to the Dales' paper. That single column is the section 3.2 that I mentioned in 1), which invalidates the Dales' basic method of assigning likelihood ratios based on qualitative assessments of evidence. All the rest of KR95 is far more technical. As in, about half of it concerns techniques for numerical integration in higher dimensions. The Dales saying their method is based on KR95 is like first graders claiming that they did their subtraction homework according to Gödel's paper on undecidability. Yeah, nice try, guys.
I pointed this out several pages back... I keep repeating it. They're working Harrold Jeffrey's K table (which is what's being cited in KR95) in reverse, which is completely at odds with its design.
It's worth repeating. The bulk of the paper shows how Bayes is used in several different contexts. None of the examples use "Reverse KR95"
“The ideal subject of totalitarian rule is not the convinced Nazi or the dedicated communist, but people for whom the distinction between fact and fiction, true and false, no longer exists.”
― Hannah Arendt, The Origins of Totalitarianism, 1951
If by reverse you mean the inverse of the LR ratio, the medical papers use both. Their version of the Kass-Raftery and Jeffrey scales is usually captured in a diagnostic tool called Fagan's nomogram.
By reverse, I meant using the suggestive labels to determine LRs as opposed to the other way around.
“The ideal subject of totalitarian rule is not the convinced Nazi or the dedicated communist, but people for whom the distinction between fact and fiction, true and false, no longer exists.”
― Hannah Arendt, The Origins of Totalitarianism, 1951
Bruce E. Dale on May 17, 2019 at 5:54 pm said: Billy, What skeptical prior did you apply to View of the Hebrews being an authentic record of ancient Mesoamerica? Remember, one of the key features of Bayesian analysis is to state your skeptical prior and then see if there is sufficient evidence to overcome the skeptical prior. Bruce
That is absolutely not "one of the key features of Bayesian analysis."
Using bayesian factors allows for the posterior odds to be updated. That update could result in increased, decreased, or unchanged skeptism.
Mr.Dale's hoped-for goal seems to be driving this latest misstatement.
How does a person tell the difference between being skeptical a million to one vs a billion to one? That difference matters in sophistry not decision making. Somewhere in between two minor pieces of evidence lies the entire range of realistic human doubt and certainty.
Lou Midgley 08/20/2020: "...meat wad," and "cockroach" are pithy descriptions of human beings used by gemli? They were not fashioned by Professor Peterson.
LM 11/23/2018: one can explain away the soul of human beings...as...a Meat Unit, to use Professor Peterson's clever derogatory description of gemli's ideology.
Water Dog wrote:I pointed this out several pages back... I keep repeating it. They're working Harrold Jeffrey's K table (which is what's being cited in KR95) in reverse, which is completely at odds with its design.
Yes, section 3.2 in KR95 quotes Jeffrey's table and then offers a modified version of it. I should have mentioned that this is what you'd been saying.
My surprise was that this single half-page discussion of how to interpret likelihood ratios qualitatively was the only item in the twenty-page KR95 review that seemed to have any bearing on the Dales' paper at all. So for the Dales to say they followed the methodology of KR95 was both (a) false, since the Dales actually do the reverse of what KR95 section 3.2 describes, and (b) a blatant attempt at snow, since most of KR95 is technical stuff that plays no role at all in the Dales' paper.
Gadianton wrote:How does a person tell the difference between being skeptical a million to one vs a billion to one? That difference matters in sophistry not decision making. Somewhere in between two minor pieces of evidence lies the entire range of realistic human doubt and certainty.
Yes. That's why there's a limit to my enthusiasm for Bayes. I think the cases must be few in which a proper use of Bayesian inference will give a signficantly different answer from careful but less formal thinking. Bayesian inference is not a seer stone.
Water Dog wrote:I pointed this out several pages back... I keep repeating it. They're working Harrold Jeffrey's K table (which is what's being cited in KR95) in reverse, which is completely at odds with its design.
Yes, section 3.2 in KR95 quotes Jeffrey's table and then offers a modified version of it. I should have mentioned that this is what you'd been saying.
My surprise was that this single half-page discussion of how to interpret likelihood ratios qualitatively was the only item in the twenty-page KR95 review that seemed to have any bearing on the Dales' paper at all. So for the Dales to say they followed the methodology of KR95 was both (a) false, since the Dales actually do the reverse of what KR95 section 3.2 describes, and (b) a blatant attempt at snow, since most of KR95 is technical stuff that plays no role at all in the Dales' paper.
Yes, since like I mentioned, they just list the citation (and sometimes page), like just about everyone else who references the categories. It would be a legit reference except for, as you point out, a) and b).
Then I agree, I haven't seen that anywhere but in the "peer-reviewed" Interpreter.