Timeline for Bayes' Theorem and Science
Current License: CC BY-SA 4.0
24 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 17, 2023 at 5:23 | comment | added | Gerald | phenomenologically* | |
| Jan 17, 2023 at 5:21 | comment | added | Gerald | That is merely meant to be explanatory. Most hypotheses which feature entities called "non-physical" or the like often imply that it should be possible to affect the world in very specific ways that are not generally observed. In laboratory conditions most of these explanations offer no additional explanation other than "I don't know" or "that's not how my hypothesis explains these observations". Souls definitely exist until you try to weigh them. Demons definitely exist until antibiotics and medicine offer better explanations. | |
| Jan 17, 2023 at 5:16 | comment | added | Gerald | Occam's razor is mostly an aesthetic tool for preferring one hypothesis over another when both fit the data equally. Atoms and quantum particles are more preferable than fairies and demons because it is simpler. It is entirely possible to arbitrarily construct hypotheses of fairies and demons that make the same predictions. If you do, then phenologically they are identical explanations where you have just decided to call electrons demons and protons fairies. If the alternative offers identical predictions, but requires more complicated explanations, then Occam's razor says to exclude it. | |
| Jan 17, 2023 at 5:07 | comment | added | Hudjefa | @Gerald, gracias for the guidance. At my level of understanding, a given set of observation squares with multiple hypotheses H1, H2, H3, ..., Hn. Now to make a choice. I hear that Occam's razor is a handy tool. In short, I'd need to use a combo - Bayes' theorem + the novacula occami. | |
| Jan 17, 2023 at 5:01 | comment | added | Gerald | @AgentSmith, the broader and more accurate explanations require you to read and understand a statistics textbook. "Truth" is context dependent. For example the concept of a data fit is much broader and more technical than I explained. | |
| Jan 17, 2023 at 4:35 | comment | added | Hudjefa | @Gerald, gracias. So if a hypothesis H is said to be x% true, it means it explains/fits x% of the observations? What true is in Bayes' theorem is not the same true in it is true that the Eiffel tower is in Paris, France. If H accords with all the observations, it seems, H is true in the same sense as the Eiffel tower is in Paris, France. | |
| Jan 17, 2023 at 2:58 | comment | added | Gerald | @AgentSmith, In general scientific hypotheses make specific claims about specific phenomena and make measurable claims about outcomes and results of experiments. Non-scientific hypotheses either don't make specific claims, don't make measurable claims, or cannot be applied to experiment. | |
| Jan 17, 2023 at 2:54 | comment | added | Gerald | @AgentSmith, "how does 90% true differ from 100% true in terms of truth?" Statistically this means out of all observed data, the hypothesis fits 100%/90%/50% of the data. Adding more data to the dataset gives more opportunities for a given hypothesis to establish that it does not fit all the data. A "True" hypothesis will fit 100% of the data no matter the size of the data set. Half-true statements fit half the data. Untrue (false) hypotheses fit none or almost no data. Also quantum theory is not statistics. I highly recommend Griffiths Introduction to Quantum Mechanics to learn the basics | |
| Jan 16, 2023 at 5:46 | vote | accept | Hudjefa | ||
| Jan 9, 2023 at 17:51 | comment | added | Hudjefa | @MarcoOcram, says "I have a PhD in quantum theory." You're kidding, right? | |
| Jan 9, 2023 at 17:21 | comment | added | Professor Sushing | @AgentSmith I can't because it is not meaningful to do so. | |
| Jan 9, 2023 at 15:55 | comment | added | Hudjefa | @MarcoOcram, the phraseology I've employed here is taken verbatim from a Wikipedia article on Bayes' theorem. The mathematical expression P(H/E) reads the probability that hypothesis H is true given the evidence E. This is standard interpretation, not my personal point of view. Hence the question. A book on logic contains the exact same interpretation of P(H/E). If you think a hypothesis needn't be true or false in binary sense then explain to me the meaning of Einstein's theory (which was once a hypothesis) is 90% true. | |
| Jan 9, 2023 at 15:22 | comment | added | Professor Sushing | @AgentSmith you are talking at cross purposes again, by assuming H is a logical proposition which must be true or false, whereas we had been talking of H as a scientific hypothesis which need not be true or false in a binary sense. | |
| Jan 9, 2023 at 12:26 | comment | added | Hudjefa | A proposition is true/false i.e. it is either 100% true or 100% false; there's no grey zone between true and false unless you're using some version of fuzzy logic which I've only heard of but never applied. | |
| Jan 9, 2023 at 12:16 | comment | added | Professor Sushing | @AgentSmith but even then, do you mean 90% likely to be 100% true? The probability can be quantified, but the extent to which something is true may be harder to quantify. | |
| Jan 9, 2023 at 11:48 | comment | added | Hudjefa | @MarcoOcram, I'm not saying H is 90% true, I'm saying H is 90% likely to be true. | |
| Jan 9, 2023 at 11:30 | comment | added | Professor Sushing | @AgentSmith I'm not sure truth may be meaningfully quantified in quite the way you are imagining. | |
| Jan 9, 2023 at 9:13 | comment | added | Hudjefa | I had the same idea, but how does 90% true differ from 100% true in terms of truth? | |
| Jan 9, 2023 at 7:20 | comment | added | Professor Sushing | @AgentSmith in that sense of the word true, there are degrees of truth. We used to consider Newton's law of gravitation to be correct until Einstein came up with a truer model. | |
| Jan 9, 2023 at 5:40 | comment | added | Hudjefa | Agreed, but then what's the meaning of P(H/E) where H is a scientific hypothesis and E is evidence for that hypothesis? You made a good suggestion - interpret true as being "in accord with the facts" but then, as I brought to yer attention, all hypotheses (there's always more than one) are "in accord with the facts". | |
| Jan 8, 2023 at 23:31 | comment | added | Frank | @AgentSmith I think we should give up on using the word "true". I don't think science really needs it anyway. Science provides "models that fit with observation", as you say. That's enough. It's a mistake to drag science into making it say that some things are "true", except, as Marco says, in the sense that they are "truthful" to observation as far as we know. Again, that's enough. I really think we should not try to find "truth" or use the word "truth". | |
| Jan 8, 2023 at 20:10 | vote | accept | Hudjefa | ||
| Jan 8, 2023 at 20:13 | |||||
| Jan 8, 2023 at 20:10 | comment | added | Hudjefa | An interesting obaervation. You, I believe, hit the bullseye mon ami. However, you do admit that there are two very different meanings of truth at play here. What about the fact that all other contender hypotheses are also "in accord" with the facts? | |
| Jan 8, 2023 at 17:32 | history | answered | Professor Sushing | CC BY-SA 4.0 |