I can live with this. Can you? — javra

Yep.

See the musings added to the previous post. You've got me rethinking my reply to Un.

Is there a problem?

Given your rudeness and ridicule, why should I respond to your posts? Your worldview strikes me as sophistic bullshit.

As in the rock intended to start the avalanche that happened by intending to pursue gravitational paths of less resistance down the mountain just so? — javra

That'd be more a "how" than a "why" - how the avalanche started rather than why.

Why questions all presuppose purpose — javra

Yep.

What's proposed is causation not as an external “thing to be explained” but as a feature of our ongoing engagement with the world. Saying that causes are unreal would be a misrepresentation. Pushing the trolly causes it to move, hence it's true that pushing the trolly caused its movement. That's not an antirealist ploy.

Added:

The reason why leaves flutter is not because the wind so wills it. Lest we loose track of what are poetic truths and what is objectively real. — javra

Reconsidering, "Why did the leaves flutter - because the wind blew them" presumes neither intent nor purpose. Fair point.

Davidson treats intentions as causal, after all. I'll give @unenlightened's post some more thought.

Why did the wind blow? - because of areas of differing atmospheric pressures.
Why were there differing areas of atmospheric pressures? - because of solar heating on a rotation earth.
Why was there solar heating on a rotation earth...

Each of these presents a broader description.

Do we end with "because godswill" or perhaps "Becasue triadic thingumies"?

My point is that: 1) we can draw some conclusions based on the information that IS available; 2) some conclusions are more reasonable than others; 3) (obviously) it's contingent upon the information being correct. — Relativist

Is the argument that abduction can be used to pick out which theories are conspiracy theories? Then what counts as a conspiracy theory is which "conclusions are more reasonable than others"; but a conspiracy theorist may just insist that the conspiracy is the more reasonable conclusion.

Hence Melina Tsapos' conspiracy definition dilemma.

Yes, and there's plenty more here to unpack. "Why" questions presume intent, in some aspect, and so all that goes with intentionality.

Again, it would be very odd, wouldn't it, if a sceptic about causality proposed causal relationships to explain what causes are. I think the best way of understanding this is by comparison with Wittgenstein's exasperated "This is what I do." — Ludwig V

That nicely frames the incipient circularity in explaining causation in terms of evolution. To make use of evolutionary explanations, we are already talking in terms of causation. It's not mistaken, so much as unsatisfactory.

"This is what I do." — Ludwig V

This is where we might sidestep Wittgenstein and invoke Davidson. We might overcome Hume's passive observation using something like Davidson's interactive process of interpretation; which is itself a development from Wittgenstein's language games. We sidestep the circularity problem by seeing causation not as something to be explained only by invoking causal mechanisms but as something continuously enacted and interpreted in practice.

Added, for @javra: And that is an evolved practice.

Let's see what @Ludwig V says, but it's clear Hume rejected the Aristotelian idea of causation, replacing it with habit and custom.

This is what I at first took T Clark to be saying, here:

My conclusion - identifying one element as the cause of another depends on where you look. What constitutes the cause is a matter of convention, not fact. It works when you can isolate the elements of the phenomena you are studying at from their environments... e.g. if I push the grocery cart it moves. — T Clark

But perhaps not.

, a compelling line of thought. Good stuff.

Ludwig rightly emphasizes that Hume rejects the idea of causation as a metaphysical reality. For Hume, causation is instead an aspect of our psychology: the association of impressions and ideas through “custom or habit.”

Javra agrees, and adds that these customs or habits may arise from the evolutionary inheritance of predispositions and behaviours via genotypes.

I would like to add that causal expositions can also be understood as a language game—an activity we perform in the world, using words to describe patterns and decide what to do next. In this sense, Hume’s “customs or habits” can be seen as a precursor to Wittgenstein’s “language games.” On this view, causes are not waiting out there in the world to be discovered; they are part and parcel of the way we interact with the world. This need not conflict with Javra’s account, but can complement it: our evolved predispositions may make us disposed to engage in these language games, generating causal explanations as part of practical life.

Thus, the focus shifts from grand metaphysical schemes to the practical question of how we act and respond to patterns in our experience.

Pathetic.

"My daddy's a policeman..."

We may have different notions of abduction. — Janus

That's part of the problem... the idea is equivocal.

Any way, back to the insults and misrepresentations from our friends.

Not even close. — apokrisis

Yep. On this we agree.

You've put up a few posts, to which I have not replied. That's becasue they appear to be addressing something very different to what I have actually said. That is what happens when everything must be shoehorned into Peirce's variant of Hegelian dialectic.

You want that symmetry be explanatory because it’s a necessary structure. The question remains as to whether that structure is in the world or in the description. Is symmetry foundational to the world, or foundational to our descriptions? Is it that the world just gets on with whatever it is doing, while we construct descriptions of symmetry?

But from Davidson, we might see that this very juxtaposition is fraught with presumption. I see you as working inside a conceptual scheme that is itself a false construction. The whole picture you’re working with — of structure vs correlation, complementary limits, systems logic — is already suspect, or atl least already a construct.

We continue to talk past each other. There may be room for some form of reconciliation, since both Pierce and Davidson make use of holism. For Pierce there is a deep division between dialectic opposites that is healed by holism. For Davidson, that deep division is not there in the beginning - it's holism all the way down.

You wish for metaphysical explanations; but such explanations are inseparable from myth, not explanations so much as further descriptions and just-so stories. Your reading the necessary structure of the world into symmetry, into your complementary extremes, is not explanatory so much as more description. Meaning is not going to be found in the structure of the world, but is constructed by what we do with our language inside that world.

But there's a difference in our methodological dispositions that may be irreconcilable. I have an allergy to explanations of everything. I think complete explanations are completely wrong. So I'll leave you to your mythologising, and muddle along.

A philosopher worthy of attention in regard to conspiracy theories is Melina Tsapos.

Maybe start with Who is a Conspiracy Theorist?, in which she sets out some of the conceptual problems involved. It includes a video abstract.

Tsapos points out that on the common definition, we are all conspiracy theorists; yet few self identify as such (the problem of self identification). Also, if the class of conspiracy theorists includes almost everyone, then that class becomes useless as an analytic tool (the problem of theoretical fruitfulness). The term is either used merely rhetorically, in which case it is an example of "othering"; or it "collapse into already well-established concepts within cognitive psychology, thus failing the differentiation test for being a valuable addition to our conceptual toolbox."

A simplistic account of conspiracy theories as failing to apply abduction "correctly" begs for an explanation of what a "correct" application of abduction is; which remains problematic.

I'm reading "Against Method" — Relativist

Good. Feyerabend is mistaken, but in interesting ways. Perhaps the most important aspect of his writing is his drawing attention to how the normatively inherent in scientific work is not algorithmic; the "best" hypothesis is not found using a fixed procedure; it’s lived and worked out within a community.

Perhaps we might continue when your finished.

Well, why not aim for the best explanation one can think of? — Janus

Go right ahead. Just don't conclude that such an explanation is true, which is what is needed if we are to overcome Hume's objection.

I take explanations to answer question of "why" — javra

This was a side-kick at Aristotle's causes. Perhaps for Aristotle "fire is hot" is a description, but "fire is hot because heat is its essential nature" is an explanation. The explanation gives the cause. Elsewhere I've argued against causes, for various reasons.

Here, Aristotle hasn't noticed that "fire is hot because heat is its essential nature" says no more than that fire is hot because fire is hot.

So I'm raising the question - can we distinguish between a description and an explanation? My suspicion is that explanations are descriptions in a border context. Explanations might appear to invoking metaphysical causes, but I suspect this is an illusion.

Nothing more nor less than creating explanatory hypotheses. I'm not seeing the difficulty you are apparently having with the idea. — Janus

If that's all it is, then fine. Add the word "best" - "creating the best explanatory hypotheses" - and it falls apart.

So where you say

There are not innumerable possible plausible explanations. — Janus

"plausible" adds the normative element that lets confirmation bias in. We can now reject all the explanations we take as implausible.

But further, in the context of this thread, do you take abduction as helping answer Hume's scepticism?

Besides, the point remains, gravity can serve as an explanation. — javra

I'll accept that, if you will accept that the explanation is no more than a more usable description. :wink:

Ok, so what is it?

Laws appeal to symmetries. So they are grounded in mathematical logic. — apokrisis

Noether’s theorem links symmetries to conservation laws - is that were you would go? Isn't describing things in terms of symmetry still describing them?

"For every action there is an opposite and equal reaction" is interpreted as "momentum is conserved" which in turn is understood as "the Universe is symmetrical in space, hence momentum is conserved".


Bigger and bigger descriptions. Still descriptions. Awesome descriptions.

"be-cause of gravity" — javra

:wink:

And is that better than "Be-cause it is the will of the Flying Spaghetti Monster"?

I think not. What makes gravity a better account is F=Gm₁m₂/r².

It's what we do that counts, the use to which we can put the theory, and F=Gm₁m₂/r² is much more useable than "Because it is the will of the Flying Spaghetti Monster".

I've brought up conspiracy theories, and argued that it is irrational to embrace them - based on abdduction. — Relativist

Seems to me you missed the argument. Oh well.

Let's look at conspiracy theories. The classic analysis for my eye comes from Watkins, in his Confirmable and Influential Metaphysics. Watkins was a disciple and defender of of Popper.

In the paper, Watkins points out that some hypotheses are neither confirmable nor falsifiable. Such hypotheses have the logical form of an uncircumscribed existential statement - one in which nothing is said about where or when the item in question occurs. This is the logical structure of many conspiracy theories.

Let's look at an example. The government is hiding evidence of alien landings. This asserts the existence of some thing - alien landings - but nothing is said here about where or when. However the government responds, it is open to the believer to maintain their position. If they open area 51 to inspection, the theorist can say that the evidence has been moved elsewhere. If they deny that there is any evidence, that reinforces the idea of a conspiracy.

Where is abduction here?

Is it irrational to embrace conspiracy theories? Consider MKUltra, the Tuskegee Syphilis Study or Watergate. These were conspiracy theories until the time and place of the incidents were fixed.

It is not irrational to believe in conspiracies.

Good stuff.

entertaining Aristotelian notions... — javra

...happens a lot more then it perhaps ought, around these fora. A favourite grump of mine.

But if I may advocate for the devil, let's look at gravity. It's the force of attraction between two masses, and explains all sorts of things, from balls falling to the motion of satellites... or does it describe that motion - that the motion depends on the combined mass and the square of the distance between the bodies... is that an explanation of what happens, or a description?

But gravity is the curvature of space-time! There's an explanation. Only that curvature is itself a mathematical description, one that as you note is incompatible with the other half of physics, which describes things in very different terms.

So we get to this:

We then use the notion of gravity to explain why an object thrown up into thin air will always come back down to earth... — javra

Does it explain why? Or does it just detail the description of the motion?

Now my point would be that it doesn't matter. What we get is a brilliant and useful way of working out what will happen - description or explanation, be damned.

there's a lot in that, a fair bit of it being quite agreeable, some less so.

Here's, I think, the first use of "abduction" in this thread:

Here's how I approach it: some explanation is needed for the constant conjunction of past regularities. I judge that the "inference to best explanation" for this is that there exist laws of nature that necessitate this behavior. Inferring a best explanation is rational - it's a form of abductive reasoning. — Relativist

Leaving aside why there must be such an explanation, a careful look will show that "abduction" doesn't provide such an explanation. "Inference to best explanation" is utterly hollow, until one sets out what a best explanation is. Further, is the mooted "natural law" an explanation of what happens, or just a description - "for every action there is an opposite and equal reaction" sets out what happens; does it explain what happens?

It's apparent that many here think "abduction" provides an explanation, tricking themselves into not taking Hume seriously. Science does not gain its force from deduction, induction, or abduction.
Laws are descriptions, not explanations. What matters is the communal practice of testing, contesting, revising. “Abduction” just papers over the real philosophical problem (Hume’s), instead of answering it.

So there's good reason to question the use of abduction hereabouts.

Well, much appreciated. Kind of you to say.

Perhaps, but given it's abstruseness, I'm not sure we should even grant that.

Sure, science involves hunches, guesses, paradigm shifts — all the messiness Feyerabend loved. But dignifying that by calling it “abduction” is a mistake. To reduce the process to some syllogism like “C is surprising, A would explain C, so maybe A” is a derogation of what actually happens in science. And crucially, none of this rescues us from Hume’s problem. Surviving falsification, or being the most elegant hypothesis, does not make a theory more true. What drives science is not a special logic, but the interplay of criticism, communal testing, and background certainties.

What is central to the scientific method of the empirical sciences (in contrast to what some term “the science of mathematics” and such, which have no such method) is communal verification via empirical means (aka, peer review and replicability of test results) that falsifiable hypotheses are not in fact false and, thereby, are likely to be true. — javra

This is a simple logical truth - a hypotheses being unfalsified does not make it more likely to be true. On this we agree. We could take a Bayesian approach to selecting amongst competing hypotheses, but note well that this is not adopting induction. There is a world of difference between an hypothesis being unfalsified and it's being more likely than other hypotheses. Popper’s point was exactly that: science isn’t about confirming hypotheses through accumulation of positive cases (which falls afoul of Hume’s problem of induction), but about weeding them out through falsification. A hypothesis standing unrefuted is not “more true,” it’s just “not yet eliminated.”

A very large part of The Logic of Scientific Discovery is a frequentist defence of falsification. The probability of a universal law (e.g., "all swans are white") is always zero in the strict mathematical sense, because it makes infinitely many claims about unobserved cases. The case he made was the defence of a statistical definition of the corroboration of an hypothesis that survives a sever attemtp at falsification. But this could not be made to fly.

The problems were many, but the Duhem–Quine problem is central. An hypotheses is never tested in isolation, but in unison with a vast array of other hypotheses, each of which might account for any falsification. Lakatos’ research programmes, Kuhn’s paradigms, and Bayesian epistemology all tried to capture what Popper’s model missed.

As with all trial-and-error heuristics, most abductions are bound to be wrong. Yes, of course. Notwithstanding, for any paradigm shift to ever occur one must first conceive of a new paradigm from outside the boundaries of the old that better accounts for the known data. This will not be a process of deduction, nor will it typically be one of induction (generalization from particulars, for example), but instead will typically commence with what we in retrospect will then likely claim to be a flash of insight, as per the Eureka moment; this then yet being abduction. One which happens to eventually produce a better understanding regarding what is by newly devised deductions and inductions, which yet pivot on the given roundabout abduction. But again, without being falsifiable, it will not be science (not of the empirical kind). — javra

Nice. But is it right, or even fair, to lump all this together and call it "abduction", and then to set it out in some gross oversimplification such as

The surprising fact, C, is observed.
But if A were true, C would be a matter of course.
Hence, there is reason to suspect that A is true. — SEP article

As I said to @Relativist, that is surely a derogation of science.

And then that further point, to relate this back to 's OP: abduction, in any of it's many guises, does not solve Hume's problem of induction.

From what I know of Feyerabend, he appears to be discussing the creative processes of scientists — Relativist

His work is a bit broader than just that. His classic formulation, "anything goes", is of course mistaken; but the interesting bit is how it is mistaken - what it is that restricts which ideas are considered scientific and which are not.

Of course scientists are creative. Calling there creativity "abduction" and locking it down to Peirce's simplistic schema is denigrating that creativity. Positing abduction as a response to Hume's scepticism is piling obfuscation on top of misunderstanding.

The activities in which scientists engage are not algorithmic, not mechanical. Those accounts of scientific method that set it out as such do science a disservice.

Please, disagree.

Science is a human enterprise, and as such is communal. A picture of how science works must include the social aspects, looking at the communication between scientists. Competing theories may have a shared reference, although since before Feyerabend and Kuhn it has been understood that those references are themselves embedded in theory. The sociology of science is not the whole story, but it is a part of the story.

Go back to your OP

Hume concluded that fundamental beliefs, such as the existence of an external world or the existence of the self, are not rationally justifiable but are legitimate because they are the result of experience and custom. — JuanZu

More recent developments in Philosophy show us how experience and custom are themselves grounded in the community in which we live. To doubt requires a background of presumed certainty. Those fundamental beliefs are what enable doubt.

Again, science is not just a social enterprise, but it is in part a social enterprise.

What we can take from Hume is that induction has not been validated. Our beliefs in what are loosely called the external world or the existence of the self are not deduced from first principles, nor inducted from some finite set of observations, but presumed as the background against which our enterprises - including science - can occur.

Abduction is worse. The SEP notes that Peirce’s conception of abduction shifts over his long career, making it hard to pin down a coherent, stable doctrine. Peirce apparently thought abduction was about inventing hypotheses, not justifying them; and so is nothing more than conjecturing. The schematic form he offers, mentioned previously, amounts to adopting an idea one already has - hence my somewhat hyperbolic accusation of confirmation bias. What is certain is that abduction is no improvement on induction, and certainly cannot overcome Hume's objections.

A neat example that supports the hypothesis that "abduction" - understood as accepting the best hypothesis - is central to scientific method. That's what confirmation bias entails. Popper taught us to look also for examples that run counter to our expectations - to look for falsifications. Let's do that.

I gave the example of the comparison between the Copernican and Ptolemaic systems, above. The first renderings of the Copernican system were at best no simpler or more accurate than those of the then quite well developed Ptolemaic account.

Brownian motion was noticed in pollen grains in 1827. For decades, it was accounted for as at first evidence of a vital force in the pollen, then when it was demonstrated in non-organic particles, as evidence of eddies in the fluid. It wasn't until Einstein provided a statistical analysis of Brownian Motion as the result of collisions with other particles that it was linked to molecular theory - the maths made Brownian motion a testable, quantitative prediction of molecular theory. Feyerabend pointed out that the acceptance of this explanation is thus theory-laden, dependent on the availability of a mathematical interpretation in order to allow empirical confirmation.

Bringing this back to your post, what this shows is that what counts as providing the greater explanatory power is dependent on the ad hoc and auxiliary hypotheses employed. There is no simple way to compare competing hypotheses, since each hypothesis brings with it a differing account of what observation is relevant.

The surprising fact, Brownian motion, is observed.
But if there are eddies in the fluid, Then Brownian motion would be a matter of course.
Hence, there is reason to suspect that there are eddies in the fluid.

Abduction here leads away from the better answer!


Considering relativity again, the procession of Mercury was explained by an otherwise unseen additional planet - which was even named "Vulcan". It had to exist, becasue it was the best explanation for the observed phenomena - exactly in line with Abduction:

The surprising fact, the procession of Mercury, is observed.
But if Vulcan were true, the procession of Mercury would be a matter of course.
Hence, there is reason to suspect that Vulcan exists.

But this abduction was mistaken!

What these examples show is not just that abduction is sometimes mistaken, but that it leads to a lack of progress, and that other, wildly differing background assumptions are instead needed to progress our understanding.

Notice that in each case, abduction leads to the confirmation of the accepted paradigm, where what was needed was a change to that very paradigm. Abduction as a counterproductive process.

A nod to @Joshs.

If a conclusion were "determined" (not underdetermined) it would be a deduction- a conclusion that follows necessarily.

Of course, as you said, deduction would be preferred, but in real life (including science) we rarely have sufficient information to make a deduction. But there is often sufficient information to support some hypotheses more than others. — Relativist

Quite right. We need pay close attention to that last bit. We may indeed support one hypotheses over another, but the "why" cannot be based solely on information - there must also be a preference. A mere list of facts is insufficient to decide between competing hypotheses.

That's again the problem with abduction - it doesn't set out why we should prefer one hypotheses amongst the many.

See the examples from Feyerabend given in my reply to @Janus, just above. An examination of the history of science shows that it does not follow the supposed prescription you provide; and indeed, that scientific progress is dependent on breaking those conventions.

The point I would press here is again that what makes science work is not a series of logical rules, but a group of sociological rules. It's not a special type of logic - induction or abduction - that makes science effective, but the open interplay between scientists.

...it should involve actively trying to falsify current accepted belief and theory and attempting to find better, more comprehensive hypotheses. — Janus

Should. But should it?

We have before us quite different notions of abduction. Sometimes it is talked of as the process of forming an hypothesis. We know that, for any set of observations, there are innumerable possible explanations. Simply having available a range of hypotheses is insufficient. We must choose between them.

In the supplement, Peirce's version of abduction is taken from this quote:

The surprising fact, C, is observed.
But if A were true, C would be a matter of course.
Hence, there is reason to suspect that A is true. — SEP article

In reality, we do not have just A - we have alternate hypotheses, each of which explains C. And we have the possibility that C is incorrect. C is also theory laden - observations dependent on our prior presumptions as to what it is we are observing.

We are never in a position to say that this hypothesis is categorically better than that one.

So the SEP account brings in ABD1:

Given evidence E and candidate explanations H1,…, Hn of E, infer the truth of that Hi which best explains E. — SEP article

And to the problem of which hypothesis is best. Abduction does not tell us. It instead brings in the auxiliaries of simplicity and coherence, aesthetic preferences that remain unclarified within the context of abduction. So again, abduction amounts to choosing the hypothesis that looks good to you.

Feyerabend examines examples in detail, such as the tower argument, early telescopic observations, or Brownian motion, to show that science often progresses by insisting on an explanation that is not the simplest or most complete. An example - Copernicus's heliocentric model was both less accurate and more complex than the Ptolemaic alternative. The Copernican case showed that the heliocentric theory was adopted despite not being more accurate, and actually being more complex, contradicting the idea that science always progresses by choosing simpler, more predictive theories.

One example amongst many.

Now Feyerabend used such examples to show that science does not conform to the model proposed by Popper - that falsification, while useful, is very far from the full story. The case is even worse with Abduction, which remains ill-defined and obscure.

Science in real life is much, much messier than the descriptions given by Popper or Peirce. And you are right that the SEP article does not set out the notion of abduction well - but we need add that, that is a problem for abduction, it remains ill defined. The term papers over the issues of method, rather than explicating them.

My own view is of science as a social phenomenon rather than a logical one. There is no firm method that underpins the practice of science, but rather a set of attitudes that involve openness to criticism, open discussion, join examination of evidence, collaboration - the basic liberal attitudes of which we are so in need.

This is perhaps the point of intersection between myself and .

—to repeat, they should be consistent with current scientific theory and understanding. If you want to call that confirmation bias, then you'd better apply that judgement to the whole of science. — Janus

Well, yes -

Second, abduction misses the paradigm-dependence of hypothesis generation. — Joshs

Conformation of the current scientific theory. Feyerabend would have a party here.

Abduction entails drawing a non-necessary inference from a set of data (intended to be all available, relevant data), that consists of an explanatory hypothesis for that data - one that is deemed to explain the data better* than alternatives. — Relativist

Cool. Nice and clean. Good stuff.

A few issues.

"Better" - an improvement on "best", but suffering the same ambiguity. If abduction is going to tell us which of the innumerable possible explanatory hypotheses to choose, then we need more than an asterisk and a deference. We need the basis for that choice. Otherwise abduction falls to underdetermination, to the Duhem–Quine problem.

Whence normatively? Deductions are preferred when valid. Inductions are preferred on the basis of Bayesian statistics. What of abduction? If it is statistical success, then isn't it just anther name for induction? If it's some pragmatic or parsimonious, isn't that just an appeal to aesthetics? to what you prefer?

So it comes down to how you cash out better/superior.

And hence my original point, that whatever criteria you choose, you are subsequently just reinforcing that choice.

Same here. To general disgust and annoyance. It's still large enough to make a difference, and the point - that labour may be divorced from government revenue by policy - stands.

you really haven’t given a validation of abduction. If you really believe that the whole of abduction is just brainstorming, then you’re missing quite a bit. Check out the SEP article perhaps.

Pretty much. Abduction was perhaps an attempt to form an algorithmic method for science, back in the days when such things were thought important. Where you are presumably coming to this from a phenomenal logical perspective, mine is more to do with the approaches of Popper, Quine and eventually Fayerabend. Perhaps what we have in common is the rejection of algorithmic processes.

That's not what was said. But if you can set out what you think abduction is, and how it works, just go ahead and do so.

I don't think anyone here can. I think folk have been told that what they are doing is abduction, but not looked to see what that meant; and when they do look, they will see the idea is hollow.

Show how I am mistaken.