MamaG
Prof Stephen SerjeantDo you understand sampling bias? Please boost after voting so the poll can have better statistics
Yes
No
Poll ended at .
Gosh this is doing numbers. I’ve no soundcloud but you may appreciate this very short video tutorial on a related topic that is frequently amplified by online sampling https://youtu.be/yS6LYj-y1HA
How to get straight A’s
Doc Edward Morbius ⭕@stephenserjeant On which point, this is definitely statistically significant:
Doc Edward Morbius ❌ (@[email protected])
Things we didn't do: - Start the fire - Shoot the deputy - Steal the cookies from the cookie jar Things we did: - Tried to fight it - Shot the sheriff - Put the sham in the shama-lama-ding-dong Things we will do: - Survive - Rock you - Walk 500 miles - Walk 500 more Things we won't do: - Get fooled again - Back down - That Things we will never do: - Give you up - Let you down - Run around - Desert you (Oops: - I did it again)
Elenna
Fuzzy Leapfrog
SibrosanIt means that people who are more keen to participate in the poll are more likely to vote "yes"...
Arthur van der Harg@sibrosan @stephenserjeant How can you be sure that it is not the other way around: that people who don’t want to vote “no” are more likely not to know what sampling bias is?
Maarten Schenk 
@stephenserjeant I see what you did there :-)
Juggling With Eggs@stephenserjeant my brain was too foggy to see initially what you did to here...brilliant set up!
DevWouterThere is no way to win, I can either answer “yes” and not boost or not answer and do boost. 🤣😂
J$Winning as in there is no correct answer. So the best solution is not to play.
If one understands sampling bias there is a decent chance their network has a understanding as well and are likely to share it as well while people who don’t understand it are likely to ignore the poll. So skewed results.
Notice the last request: “please share for better statistics”. Which is very cheeky because doing so means we participate in the “self-selection bias”.
Alasdair Allan@stephenserjeant I see what you did there, “…the only way to win is not to play.”
Cdn Curmudgeon@stephenserjeant You need a response labelled "sort of," because I used to know more about it when I was reading about polling and surveys, but I've forgotten much since.
Sisyphus with a Hat
uvok cheetah 🇩🇪
@uvok aaah proof that there is always a relevant xkcd
@stephenserjeant ...confirmation bias? ;)
prinzessinnen_und_raben@stephenserjeant I feel like this toot is trying to tell me something, but I'm not entirely sure 🤔
@stephenserjeant The route to better statistics in this case being other than sampling size 😺
That said: I've been thinking of Doing A Thing on where self-selection polls might actually afford some utility.
Till Buettner@stephenserjeant damn, didn’t think twice.
tatzelbrumm@stephenserjeant
I would really like to forward your poll to the old cat lady downstairs, but she doesn't want to be bothered with such trivialities such as Social Media polls,
and prefers to occupy herself with academic nepotism and
https://en.wikipedia.org/wiki/Fuzzing#Automated_bug_triage
So I'm boosting this on a Fediverse instance dedicated to science, to increase the reach of this poll among science-minded people.
eyebrowsgerri will not comply@stephenserjeant heheh, I see what you did there.
Mootly Obviate
Squeak Doozy@stephenserjeant wow, over 600 people! That's like...*counting on fingers* the whole world! :0
LB Thomas (HAS MOVED)@stephenserjeant
🤣 I may have peed a little.
🤣 I may have peed a little.
Techronic9876@stephenserjeant @AlisP “this is perfectly legit” -Elon Musk
SomersetWhovian 🇺🇦💙@stephenserjeant
Nicely played.
Nicely played.
LPSurge@stephenserjeant - I think so wasn’t a choice so I selected yes.
MikeNM@stephenserjeant @chartier without more answers I can’t make pretty charts to distract from the self selection
JosephusWaggamuffin@stephenserjeant I see what you're doing there. ;-)
The Great Communicator@stephenserjeant there is a wonderful image of a WWII warplane with antiaircraft damage on it that helps explain this
䷰ Xīn Jīn Mèng 新金梦
Lean Sex Sigma 🇮🇪🇫🇮🏳️🌈@stephenserjeant Is this a question about the essence of statistical representation, if you are on Mastodon, please vote.
@Jagesta Well, it’s more a commentary on the futility of social media polls for measuring anything objectively, because while boosts/RTs increase the number of impressions and votes, it’s almost impossible to know whether the audience that saw/reacted to the poll are representative of any larger community. eg: FBPE folk asking about Brexit, then poll boosted by pro-Brexit folk to change the outcome, and result ultimately not informative of anything the original poll was about.
@stephenserjeant I knew it. Well played, sir, well played. My uttermost, and sincere applause for your delivery.
@Jagesta tee hee thank you :)
Brian C. Martinson, PhD
Simon Jerram@stephenserjeant Um... not sure... will people be clicking no who understand it better than some who click yes?
Szymon Sokół 🇵🇱🇪🇺🇺🇦@stephenserjeant this poll lacks the option "I believe I do"…
ceoln
Hilary@stephenserjeant Boosted but not voted because...
It's Just Jenn 🏳️⚧️@stephenserjeant interesting poll. The only way to win is not to play. 😆
Bob VezeauIs that intended as a joke? A self-selected sample, compounded.
@BobVezeau I couldn’t possibly comment
Looks like I’m a little slower than the other responders. 😊
Wennekendonk
Bill Wofford 🖖@stephenserjeant When I took a statistics class, we had to read "How to Lie with Statistics."
Duncan Batey
Lipk
Maquitorf@stephenserjeant I see what you are doing here ;)
johncarneyau
Karl Habermas
Rudi Pfenniger@stephenserjeant "A strange game. The only winning move is not to play."
Okay, would have been better if I set up a bot account to send that reply.
Kagan MacTane (he/him)@stephenserjeant I'm trying so hard to decide whether it's funnier to vote "no" or "yes". 😆