• neomac
    1.4k
    I'm entailing that you are a troll.
  • Bartricks
    6k
    I am entailing that you don't know what words mean.

    Tell me, Neomac, when someone says "correlation does not imply causation" what do you think they mean? Do you think they mean that it does not entail it, or that it does not imply it?

    Psst: it's the latter. And it is false. Yes? It's false. It DOES imply it.

    It doesn't ENTAIL it.

    It does IMPLY it.
  • invizzy
    149


    Such a statement about causation would be the formal ‘entail’ sense of the word. One would only really use imply as a synonym for‘suggest’ if a PERSON was doing the implying, not when state of affairs implies something.
  • Bartricks
    6k
    Yeah, okaaay.

    You know as well as I do that you meant by imply, imply - that is, suggest. And that's what everyone else means when they say 'correlation does not imply causation'. And they're wrong. It does imply it.
  • creativesoul
    11.9k
    In each and every case of causation there is a correlation between cause and effect/affect.
  • invizzy
    149
    You know as well as I do that you meant by imply, imply - that is, suggestBartricks



    I'm not sure which of my uses of 'imply' you're referring to, but it doesn't matter as I've been very consistent in using it as a synonym for 'entails'. That's because I / we are talking about correlation implying something. Correlation isn't a person so it can't be said to imply something in the 'suggest' sense of the word, it implies in the formal 'entails' sense.

    I can absolutely tell you that correlation does not imply causation because a standard reading of that claim would tell us all correlations are instances of causation. I know you don't believe that, so I must insist you switch to a standard use of the words: suggest for when people imply and entails for when states of affairs imply.
  • invizzy
    149
    I wonder if it is more likely you are the only one with a new insight about correlations (that correlation implies causation) or that you are using 'implies' in a non-standard way and actually agree with everybody?
  • Banno
    24.8k
    From the article cited in the OP as "the main source material discussed"

    Usage and meaning of "imply"

    In casual use, the word "implies" loosely means suggests, rather than requires. However, in logic, the technical use of the word "implies" means "is a sufficient condition for." [3] That is the meaning intended by statisticians when they say causation is not certain. Indeed, p implies q has the technical meaning of the material conditional: if p then q symbolized as p → q. That is, "if circumstance p is true, then q follows." In that sense, it is always correct to say "Correlation does not imply causation."

    If there is causation, there is correlation but also a sequence in time from cause to effect, a plausible mechanism, and sometimes common and intermediate causes. Correlation is often used to infer causation because it is a necessary condition, but it is not a sufficient condition.

    @Bartricks's having a lend of you all. Stop feeding him.
  • Jamal
    9.6k
    implies1 = suggests
    implies2 = entails (to use the terminology being used in the thread so far)

    It is precisely because correlation implies1 causation that it's important to keep in mind that correlation does not imply2 causation. It's not banal, as Bartricks has claimed.

    By the way, and roughly speaking, I think implication in logic is something that happens within statements (if then), whereas entailment happens within arguments, that is, between sets of statements and a conclusion.

    Don't waste your time with Bartricks.
  • neomac
    1.4k
    It is precisely because correlation implies1 causation that it's important to keep in mind that correlation does not imply2 causation. It's not banal, as Bartricks has claimed.Jamal

    I'd agree (except that "implies2" != "entails" see below)

    By the way, and roughly speaking, I think implication in logic is something that happens within statements (if then), whereas entailment happens within arguments, that is, between sets of statements and a conclusion.Jamal

    I agree on that too, but I would elaborate further as follows. The notion of "entailment" has broadly to do with semantics, while "implication" in formal logic is just a certain type of truth-functional operator (namely expressing a certain combination of truth conditions as in the "material conditional"). So when we deduce a conclusion from some premises (like in propositional logic by using logical connectors like "if/then", "and", "not", "or", etc.), one can claim the conclusion is "entailed" by the premises, when the truth-functional meaning of the logical connectors (independently from the actual/full meaning of the terms they combine) ensures the truth of the conclusion. In conclusion, while the "entailment" expresses a semantic link between terms, "implication" doesn't express any such link.
  • Real Gone Cat
    346


    Yup. Been making the same point, difference being I ... <hangs head in shame> ... never read the entire OP, so never clicked the link.
  • Real Gone Cat
    346
    By the way, and roughly speaking, I think implication in logic is something that happens within statements (if then), whereas entailment happens within arguments, that is, between sets of statements and a conclusion.Jamal

    Pretty much in agreement, but I think you're splitting hairs a bit finely here. The statement carries within it the modus ponens argument. [Isn't modus ponens just one row of its truth table?]

    Unless you're reserving "implies" for the form of the argument, and "entails" for an instantiation. (Still too delicate for my tastes.)
  • invizzy
    149
    Thanks for the advice @Jamal I might leave this convo here. It’s been instructive though, my philosophy education is a bit piecemeal so now I feel better educated on the word ‘implies’. Cheers all!
  • Benj96
    2.3k
    Ah, now please complete your post with a short paragraph telling us what (a) cause is. Back when we all had paper dictionaries, cause took up a lot of column inches because it's not-so-simple. For present purpose, that you or I might agree with or subsequently adjust or refine, what do you say it is?tim wood

    Why say many words when a few will do just fine

    Alas, 'tis the power of condensing information with big impact into a little box".
  • Real Gone Cat
    346
    ... and including this cat personBartricks

    Hahaha. Almost missed this one.

    This cat person has feelings, you know. Your callous dismissal wounds me. Cannot cat people bleed?

    From now on, I would prefer if you referred to me as Mr. Real Gone Cat. We are not friends, sir. Good day.
  • Bartricks
    6k
    I never said anything that implied - sorry, entailed - we are friends.

    And you can refer to me as Dr Bartricks.

    Correlation, let's remember, does imply causation.

    It doesn't entail it.

    It does imply it.
123Next
bold
italic
underline
strike
code
quote
ulist
image
url
mention
reveal
youtube
tweet
Add a Comment