I work in a place full of statisticians, and we've had to unfortunately have numerous conversations with some of them about the difference between "a decrease" and "a decrease in the rate." Apparently "it's increasing slower" isn't clear enough for some.
Science Memes
Welcome to c/science_memes @ Mander.xyz!
A place for majestic STEMLORD peacocking, as well as memes about the realities of working in a lab.
Rules
- Don't throw mud. Behave like an intellectual and remember the human.
- Keep it rooted (on topic).
- No spam.
- Infographics welcome, get schooled.
This is a science community. We use the Dawkins definition of meme.
Research Committee
Other Mander Communities
Science and Research
Biology and Life Sciences
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- !reptiles and [email protected]
Physical Sciences
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
- [email protected]
Humanities and Social Sciences
Practical and Applied Sciences
- !exercise-and [email protected]
- [email protected]
- !self [email protected]
- [email protected]
- [email protected]
- [email protected]
Memes
Miscellaneous
When my son was about to be born my mother in law caught wind that we didn't plan on circumcising (before researching it I mostly felt it was just strange to do cosmetic surgery on a newborn) but her argument was mostly parroting the 50% reduction in this that and the other disease, missing the fact that it was going from a 0.5% chance to a 0.25% chance, but of course introduced new risks by nature of being a surgery.
Naturally after looking more into it I learned just how bonkers circumcision is so I was far more cemented in my position
The fact that it is even allowed in so-called civilized countries is outrageous. In the US it common because some religious nut was obsessed with children's masturbation.
People got this wrong about inflation as well. In 2020 there was actual deflation, and in 2021 there was very minimal inflation, meaning prices were still largely lower or similar as 2019. Then we saw 9% inflation in 2022. Total inflation in 2024 vs the 2019 benchmark was around 15%. Or 3% average per year, which is barely over the baseline. People just hear 9% inflation, completely missing the fact that this was a YoY number relative to the Trump recession.
And then there was that bogus article that said Argentina had lowered it's inflation to 2% and you find out in the article that's monthly inflation and the yearly figure was like 190%.
In game design, it has to be stated whether it’s multiplicative or additive. Sometimes a logarithmic function is used as well, with increases in efficiency as 1 / ( 1 + bonus ). This allows you to always add more bonus, but there’s diminishing returns.
i wish it was more common to also indicate the precedence of a percentage increase, so that it’s easier to know if i’m dealing with (x + y ) * z or x + (y * z). although that’s admittedly a lot harder to communicate.
hopeful-weirdo just needs to be told to consider what increasing by 500% means and it'll click.
Having two possible outcomes does not mean it's a 50:50 chance.
"So if I aim the arrow at the 1cm square from 100m away and shoot, I either hit it or I don't. So basically I have a 50% chance of hitting it."
The thing with that is that it's actually a useful generalization to make in a lot of scenarios.
If you know nothing about the distinction between two possible outcomes, treating them as equally likely is a helpful tool to continue with the back of the envelope guess. Knowing this path needs 5 coin tosses to go right and this one needs 10 is helpful to approximate which is better.
Your example is obviously outside the realm where you have zero information, so uniform distribution is no longer the reasonable default. But the idea is from a reasonable technique, taken to extremes by someone who doesn't fully get it.
Either I become president, or I don't.
Therefore, the odds of me becoming president is 50%
Brb committing 34 felonies.
Very weird fun fact about arrows/darts and statistics, theres 0% chance of hitting an exact bullseye. You can hit it its possible to throw a perfect bullseye. It just has a probability of zero when mathematically analyzed due to being an infinitesimally small point. Sound like I'm making shit up? Here's the sauce
How can an outcome both be entirely possible and have 0% probability?
Q.E.D
Key word here is "infinitesimally." Of course if you're calculating the odds of hitting something infinitesimally small you're going to get 0. That's just the nature of infinities. It is impossible to hit an infinitesimally small point, but that's not what a human considers to be a "perfect bullseye." There's no paradox here.
Another lesson I the importance of significant digits, a concept I've had to remind many a young (and sometimes an old) engineer about. An interesting idea along similar lines is that 2 + 2 can equal 5 for significantly large values of 2.
What do you mean by significantly large
Depending on how you're rounding, I assume. Standard rounding to whole digits states that 2.4 will round to 2 but 4.8 will round to 5. So 2.4+2.4=4.8 can be reasonably simplified to 2+2=5.
This is part of why it's important to know what your significant digits are, because in this case the tenths digit is a bit load bearing. But, as an example, 2.43 the 3 in the hundredths digit has no bearing on our result and can be rounded or truncated.
My wife, father-in-law and I were playing a board game with my brother-in-law. In this game, we were playing as detectives who have to try to find his character, but each turn he could move in secret in one of several directions. We were a few turns in at one point and he could have been in any of dozens of places at this point. We drove him nuts by saying "he's either in this spot or he's not, it's a 50-50 chance." He kept arguing "I could be in a ton of places! It's not a 50-50 chance!" But we just kept pretending we didn't understand and arguing that there were only two possibilities, he's there or he's not, so it was clearly a 50-50 chance. He got quite angry.
you know, if you watched for tells, that could tilt the probabilities... and I bet with the frustration... he was flashing tells all over the place...
Letters from Whitechapel?
Either that or you buried the lede by failing to mention something rather significant about the hidden character, and you were playing Fury of Dracula. Or my boardgamegeek-fu isn't as strong as I hoped.
Yeah it was Letters from Whitechapel.
Scotland Yard or Letters from Whitechapel?
I love Scotland Yard. We got it for a friend who loves detective stories. Then discovered that it’s a public transit simulator which is even better.
Honestly, Letters From Whitechapel is a better design of the same concept.
For detective story games, Sherlock Holmes Consulting Detective is amazing.
And for public transit games, Bus is the way to go (probably)
Letters from Whitechapel
On the other hand: Half of my lottery tickets were jackpots. I never played and have (1/2 * 0 = ) 0 jackpots.
Difference between increase of x% (old percentage + old percentage * x%)% and increase of x percentage points (old percentage and x)%