Talk:2494: Flawed Data

2021-08-11T05:25:16Z

172.68.142.147: Added a few reasons "very bad" is so bad and what

For the [[1258: First|first]] time in a very long time I was the [[269: TCMP|first]] to make an attempt at the main explanation. I guess this comic came out very late then? Or just late up on explain xkcd? Seems like the Monday comic first came up on Tuesday in many countries including those in Europe. But guess it was still Monday in the US, at least in the western parts? I hope this is not as bad an attempt as Cueball's research strategies in the last panel :-) --[[User:Kynde|Kynde]] ([[User talk:Kynde|talk]]) 07:05, 27 July 2021 (UTC)
: Isn't it related to a recently published article[https://www.laboratoryequipment.com/577819-AI-Models-to-Analyze-Cancer-Images-Take-Shortcuts-that-Introduce-Bias/ [1]][https://www.nature.com/articles/s41467-021-24698-1 [2]] about bias introduced into AI by humanly-biased data?
::Reports of bias in AI have been in the news for several years. Most notably, facial-recognition systems that are bad at distinguishing faces of black and brown people. [[User:Barmar|Barmar]] ([[User talk:Barmar|talk]]) 13:58, 27 July 2021 (UTC)
:::"On two occasions I have been asked [by members of Parliament], 'Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?' I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question." - Charles Babbage ; note that century and half passed since that quote and people STILL somehow expect computer will be able to reach correct results based on wrong data. -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 17:23, 27 July 2021 (UTC)

This explanation has some good ideas for what these things mean, but it goes into them in excessive detail, which doesn't leave a lot of room for other ideas to be included side-by-side. I think that might be common. I was just thinking that there are a lot of ways extra math is used to produce worse conclusions: as soon as you have to work more to find what is good, occam's razor says you are less likely to be relevant. Similarly there are a lot of ways that AI is used to work with data, but its power greatly surpasses its ability to reflect the underlying meaning of things. For example, the existing data can be extended without being scrapped, and look completely real in every known respect, but that doesn't mean that any new information is included in what is generated, since the only data to work with is what was already there. [[Special:Contributions/108.162.219.98|108.162.219.98]] 16:19, 27 July 2021 (UTC)

There are various techniques in Machine Learning to augment the training data, which can include generating fake data that looks like the real data; one such technique is using {{w|Generative adversarial network}} (GAN).

On first reading, I was thinking the Good approach would be to go out and run new experiments and measurements, incorporating the lessons from their flawed data, to avoid making the same mistakes again. This can be quite expensive, but it is really the only way to increase the validity of the data. Just saying "We can't trust our conclusions," throws away the opportunity to learn from earlier mistakes and come up with better measurements next time. [[User:Nutster|Nutster]] ([[User talk:Nutster|talk]]) 14:38, 28 July 2021 (UTC)

Is this a reference to Biogen? Doing some motivated post hoc subgroup analysis to get Aduhelm approved.

From what I know, the "very bad" approach is becoming common in data science, see the Wikipedia page for {{w|Synthetic_data#Synthetic_data_in_machine_learning}} or, when done on a single feature at a time, {{w|Imputation_(statistics)}}. The reason imputation can be problematic because the data is missing due to some confounding variable, so trying to fill in based on existing values will bias the results. A slightly related example is for class imbalance, where some groups are underrepresented and therefore won't be predicted as accurately as overrepresented groups. Instead of gathering more data, especially more representative data, data scientists will often use something like SMOTE to generate more data. An example of a widely used but frankly bad synthetic dataset is kddcup99. [[Special:Contributions/172.68.142.147|172.68.142.147]] 05:25, 11 August 2021 (UTC)

Talk:1255: Columbus

2021-03-05T19:51:10Z

172.68.142.147:

Megan's version of the story is one big reference to the {{w|Silmarillion}}, in case you're wondering. [[Special:Contributions/100.40.49.22|100.40.49.22]] 06:00, 23 August 2013 (UTC)

I fail to see how the fact scholars and other educated people knew the Earth is round means he couldn't have difficulty getting sponsorship because of that. He wasn't asking scholars for sponsorship, did he? :-) Actually, according to {{w|Christopher_Columbus#Quest_for_support|wikipedia}}, "Columbus presented his plans to Queen Isabella, who, in turn, referred it to a '''committee'''" ... -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 09:14, 23 August 2013 (UTC)

Because it wasn't just scholars - ''everyone'' knew that the world was a sphere. Sailors, for example, took the monumental task of noticing that when objects appeared in the distance, they seemed to "rise up" over the horizon (hence the phrase). For that to happen, the sea (and by extension the rest of the world) had to be curved.
[[Special:Contributions/109.76.209.186|109.76.209.186]] 12:08, 23 August 2013 (UTC)

: Farmers were famous for believing the world was flat, but it might as well just be city prejudice or jokes on farmers behalf. They would anyway be in the worst position to know any better. [[Special:Contributions/62.220.2.194|62.220.2.194]] 12:30, 23 August 2013 (UTC)

:: I was trying to make a joke. According to wikipedia again, it is recorded that the committee denied the request because of distance to Asia, therefore shown much more intelligence that committees tend to have on average. Still, he asked for sponsorship multiple people, which might include some who believed earth is flat. -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 11:07, 24 August 2013 (UTC)

Looking at the moon and at the earth's shadow during a lunar eclipse would probably make many realize the earth is round. [[User:Ghaller825|Ghaller825]] ([[User talk:Ghaller825|talk]]) 12:45, 23 August 2013 (UTC)
:Unless "round" as in "circular", rather than "spherical". A disc-like Earth could give the same effect. A ''non-tidally-locked moon'' would have been an interesting thing for early understanding of the universe, as it would have shown a clearly spherical ball rotating and let the layperson imagine sphericality under their own feet a lot easier in their own childhood, thus flat-earthing would have been culturally invalid, not just lazy/unthinking. Whether or not farmers 'knew'/cared/were-told-by-the-church that the world was flat isn't really relevent on the scale of farming where you need to worry more about localised hills on your land than global curvature on its actual order of magnitude. Of course, in the absence of any other clues you tend to think of everything as flat as your (crudely worked) kitchen tabletop by default. [[Special:Contributions/178.104.103.140|178.104.103.140]] 16:16, 23 August 2013 (UTC)

I am not sure what people knew and what they believed in earlier times. For example: {{w|M-Theory}} says that the space we live in has 11 dimensions. Assuming this is correct, what will people in 500 years say about us? Did we know it or did we not? Could we have expected what will hit us in a couple of years from out of one of the dimensions that we do not visually perceive?
To apply this to the quesion of whether they knew that the world was round: There is a {{w|Deep-sea_exploration#Milestones_of_deep_sea_exploration|story}} about Magellan (who certainly believed that the world was round because he tried to sail around it): He tried to measure the depth of the ocean with a 700m long rope. When the rope failed to reach the bottom, he concluded that the ocean was infinitely deep. Now how can a round object with a finite perimeter have and infinite radius? (I realize that wikipedia does not give any sources for the story and its origin is somewhat obscure, someone translated the story from the German wikipedia in July 2011; in the German wikipedia it had first appeared in 2006, but the story was around on German language websites since at least [http://www.scinexx.de/dossier-detail-40-11.html 2000]; I have no idea where it originally comes from, but it would be interesting to have a look at Magellan's ship's log if it had such a thing.)
[[User:Y4cy|Y4cy]] ([[User talk:Y4cy|talk]]) 13:41, 23 August 2013 (UTC)

:You suppose that the round earth is imbedded in flat 3-dimensional space. If it were’nt, you could easily have infinitely deep oceans. Maybe Magellan was way ahead of his time by thinking in non-Euclidean categories.
:(Explanation for non-mathematicians: Draw a circle – it surely has a finite radius, but if you measure the depth perpendicular to the sheet of paper, you could go infinitely deep. Now apply this to a round sphere and measure perpendicular to the 3D space you put it in.)
:--[[Special:Contributions/188.102.28.80|188.102.28.80]] 09:41, 24 August 2013 (UTC)

::Your example fails. Magellan sailed in ship with keel pointing in the direction of the depth he tried to measure. His success depended on the fact that earth is round IN THAT DIMENSION. Sure, there are geometries where the earth can be round in that dimension AND ocean would still be infinite, but, as you correctly mentioned, they would be non-euclidean, while your example with sheet of paper is (almost) euclidean. Also, dimension which would make possible to measure infinite distances is {{w|Brane cosmology}} - {{w|M-Theory}} would work perfectly well even in case all of those "extra" dimensions would be extremely small. -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 11:07, 24 August 2013 (UTC)

:[http://www.wdl.org/en/item/3082/ Journal of Magellan's Voyage] is an original source (in French) accessible online of this voyage, which could contain this story. Sebastian --[[Special:Contributions/178.26.118.249|178.26.118.249]] 19:36, 24 August 2013 (UTC)

[http://www.glyphweb.com/arda/a/arda.html Arda] was not [http://www.glyphweb.com/arda/b/bentworld.html bent] until the [http://www.glyphweb.com/arda/d/downfallofnumenor.html Downfall of Númenor] in [http://www.glyphweb.com/arda/chronicle.html?startyear=3319&startage=2 S.A. 3319]. When [http://www.glyphweb.com/arda/e/earendil.html Eärendil] sailed into [http://www.glyphweb.com/arda/w/west.html the West] in [http://www.glyphweb.com/arda/chronicle.html?startyear=538&startage=1 F.A. 538] he did so on a topologically flat earth. It was the [http://www.glyphweb.com/arda/i/istari.html Istari], the [http://www.glyphweb.com/arda/g/greyelves.html Sindarin] belatedly answering the [http://www.glyphweb.com/arda/g/greatjourney.html summons of the Valar], [http://www.glyphweb.com/arda/g/galadriel.html Galadriel] of the [http://www.glyphweb.com/arda/n/noldor.html Noldorin], [http://www.glyphweb.com/arda/e/elrond.html Elrond] [http://www.glyphweb.com/arda/h/halfelven.html half-Elven], and the [http://www.glyphweb.com/arda/r/ringbearers.html ring-bearers] of the [http://www.glyphweb.com/arda/t/thirdage.html third age] who took the [http://www.glyphweb.com/arda/s/straightroad.html straight road] to [http://www.glyphweb.com/arda/v/valinor.html Valinor]. --[[User:April_Arcus|April Arcus]] 01:44, 25 August 2013 (UTC)
* Nerrrrrrrrrrrrrrrrrd. :) --[[User:V2Blast|V2Blast]] ([[User talk:V2Blast|talk]]) 07:34, 27 August 2013 (UTC)
: Oh yah, 'cos the rest of the comments/conversation on this page are just soooo hip :P [[User:Orazor|Orazor]] ([[User talk:Orazor|talk]]) 10:11, 30 September 2014 (UTC)

How is the title text related to the title text in 1256? Does Arwen visit the Undying Lands? [[User:Jd2718|Jd2718]] ([[User talk:Jd2718|talk]]) 12:06, 5 September 2013 (UTC)

I'm pretty sure Valar are immune to disease... [[Special:Contributions/199.27.128.150|199.27.128.150]] 22:26, 28 December 2013 (UTC)
:And ''I'm'' pretty sure valar morghulis... wait, what? [[User:Orazor|Orazor]] ([[User talk:Orazor|talk]]) 10:11, 30 September 2014 (UTC)
:Valar, Maiar, and Elves are all disease-immune. Valar and Maiar can actually shed their physical bodies entirely. [[Special:Contributions/108.162.221.40|108.162.221.40]] 13:39, 13 July 2015 (UTC)
While the main inhabitants of the Undying Lands are undying in their own right, it may be that they also confer immortality. As I recall, the Numenorean invasion was based upon that belief. [[User:Magic9mushroom|Magic9mushroom]] ([[User talk:Magic9mushroom|talk]]) 10:38, 10 September 2016 (UTC)

I thought the morning star was Polaris. How did it become the planet Venus?

explain xkcd - User contributions [en]

Talk:2494: Flawed Data

Talk:1255: Columbus