#sundaycumday pt 2 statistical analysis 😈:
November 10, 2025 at 1:07 AM
#sundaycumday pt 2 statistical analysis 😈:
The "average human touches 1 spiderweb a week" factoid actually just statistical error
World's biggest spiderweb discovered inside 'Sulfur Cave' with 111,000 arachnids living in pitch black.
www.livescience.com/animals/spid...
www.livescience.com/animals/spid...
November 8, 2025 at 7:24 AM
The "average human touches 1 spiderweb a week" factoid actually just statistical error
Here’s another statistic- Mamdani got more votes than the entire population of the truckstop town that Buttigieg was mayor. And that’s the ‘combined statistical area’.
November 8, 2025 at 11:18 PM
Here’s another statistic- Mamdani got more votes than the entire population of the truckstop town that Buttigieg was mayor. And that’s the ‘combined statistical area’.
November 11, 2025 at 7:02 AM
“changes in statistical significance are often not themselves statistically significant. … even large changes in significance levels can correspond to small, nonsignificant changes in the underlying quantities.”
www.tandfonline.com/doi/abs/10.1...
#Statistics
www.tandfonline.com/doi/abs/10.1...
#Statistics
The Difference Between “Significant” and “Not Significant” is not Itself Statistically Significant
It is common to summarize statistical comparisons by declarations of statistical significance or nonsignificance. Here we discuss one problem with such declarations, namely that changes in statisti...
www.tandfonline.com
November 9, 2025 at 12:39 PM
“changes in statistical significance are often not themselves statistically significant. … even large changes in significance levels can correspond to small, nonsignificant changes in the underlying quantities.”
www.tandfonline.com/doi/abs/10.1...
#Statistics
www.tandfonline.com/doi/abs/10.1...
#Statistics
"average person wins 1 fanfest ticket per year" factoid actually just statistical error. average person earns 0 fanfest tickets per year. Fanfest Georg, who lives in cave & wins over 10,000 tickets, is an outlier and should not have been counted
November 10, 2025 at 7:46 PM
"average person wins 1 fanfest ticket per year" factoid actually just statistical error. average person earns 0 fanfest tickets per year. Fanfest Georg, who lives in cave & wins over 10,000 tickets, is an outlier and should not have been counted
I noticed in 2004 that every time Bush was ahead by 4, he’d “opened up a big lead,” but every time Kerry was ahead by 4 it was a “near statistical tie,” and that was one of those “I have seen the source code” moments.
November 8, 2025 at 9:26 PM
I noticed in 2004 that every time Bush was ahead by 4, he’d “opened up a big lead,” but every time Kerry was ahead by 4 it was a “near statistical tie,” and that was one of those “I have seen the source code” moments.
It's a statistical mirage. The 10th percentile spiked because millions of the lowest-paid workers got wiped out of the dataset in 2020. If you delete the lowest rungs of a ladder, the ‘bottom’ suddenly looks higher.
November 10, 2025 at 11:00 AM
It's a statistical mirage. The 10th percentile spiked because millions of the lowest-paid workers got wiped out of the dataset in 2020. If you delete the lowest rungs of a ladder, the ‘bottom’ suddenly looks higher.
Another statistical oddity: Sounders finished the season on a seven-game unbeaten streak. That’s their longest-ever, season-ending unbeaten streak, even including 2016 (3) and 2019 (6) that culminated with winning MLS Cup.
November 10, 2025 at 7:07 PM
Another statistical oddity: Sounders finished the season on a seven-game unbeaten streak. That’s their longest-ever, season-ending unbeaten streak, even including 2016 (3) and 2019 (6) that culminated with winning MLS Cup.
It's trying to beam certain 'statistical graphs' directly into my head whenever I look at it 😭
November 9, 2025 at 7:31 AM
It's trying to beam certain 'statistical graphs' directly into my head whenever I look at it 😭
29/ "We need to see if anyone is engaging in statistical manipulation (quite legal) in their reports to the higher-ups. They're apparently trying to solve the problem of replenishing active units by intensifying the recruitment of civilian contract soldiers...
November 8, 2025 at 9:44 AM
29/ "We need to see if anyone is engaging in statistical manipulation (quite legal) in their reports to the higher-ups. They're apparently trying to solve the problem of replenishing active units by intensifying the recruitment of civilian contract soldiers...
Just randomly happened on this.
From a quick glance this is very good open material on designing statistical maps!
📊
www.e-education.psu.edu/geog486/node...
From a quick glance this is very good open material on designing statistical maps!
📊
www.e-education.psu.edu/geog486/node...
Choosing Symbols for Maps | GEOG 486: Cartography and Visualization
www.e-education.psu.edu
November 10, 2025 at 8:47 AM
Just randomly happened on this.
From a quick glance this is very good open material on designing statistical maps!
📊
www.e-education.psu.edu/geog486/node...
From a quick glance this is very good open material on designing statistical maps!
📊
www.e-education.psu.edu/geog486/node...
The paper was accepted for publication in Computo 🎉
As this is a relatively young journal, I want to share: Computo is the open access journal of the SFDS (French Statistical Society), promoting open source statistical software. The reviewing process was very smooth and helpful! computo-journal.org
As this is a relatively young journal, I want to share: Computo is the open access journal of the SFDS (French Statistical Society), promoting open source statistical software. The reviewing process was very smooth and helpful! computo-journal.org
November 8, 2025 at 2:26 AM
The paper was accepted for publication in Computo 🎉
As this is a relatively young journal, I want to share: Computo is the open access journal of the SFDS (French Statistical Society), promoting open source statistical software. The reviewing process was very smooth and helpful! computo-journal.org
As this is a relatively young journal, I want to share: Computo is the open access journal of the SFDS (French Statistical Society), promoting open source statistical software. The reviewing process was very smooth and helpful! computo-journal.org
"women ruin everything" factoid actually just statistical error. average woman ruins 0 things a year. Maura Quint, who lives in a cave and ruins over 10,000 each day, is an outlier and should not have been counted
November 7, 2025 at 4:07 AM
"women ruin everything" factoid actually just statistical error. average woman ruins 0 things a year. Maura Quint, who lives in a cave and ruins over 10,000 each day, is an outlier and should not have been counted
This is perhaps one my hottest take:s
Any election within, say, 0.1% should be declared a statistical tie and resolved via coin flip.
No recount, no litigation. None of these processes is perfect. Accept the unknowability, admit the indeterminacy, and flip a coin.
Any election within, say, 0.1% should be declared a statistical tie and resolved via coin flip.
No recount, no litigation. None of these processes is perfect. Accept the unknowability, admit the indeterminacy, and flip a coin.
Unreal. As the vote count rolled in, progressive candidate Katie Wilson has overtaken Bruce Harrell by 91 votes for Seattle’s mayor. She is 0.04% ahead after having been down by more than 7 points on election night.
Katie Wilson pulls ahead of Seattle Mayor Bruce Harrell – by 91 votes
www.kuow.org
November 11, 2025 at 2:10 AM
This is perhaps one my hottest take:s
Any election within, say, 0.1% should be declared a statistical tie and resolved via coin flip.
No recount, no litigation. None of these processes is perfect. Accept the unknowability, admit the indeterminacy, and flip a coin.
Any election within, say, 0.1% should be declared a statistical tie and resolved via coin flip.
No recount, no litigation. None of these processes is perfect. Accept the unknowability, admit the indeterminacy, and flip a coin.
Our complaint argues late software changes, testing failures, ballot-handling discrepancies, and concerns of abnormal voting behavior identified with statistical analysis in Cambria, Erie, and Allegheny Counties deprived voters of their right to vote and have their vote counted correctly. (2/3)
November 7, 2025 at 10:26 PM
Our complaint argues late software changes, testing failures, ballot-handling discrepancies, and concerns of abnormal voting behavior identified with statistical analysis in Cambria, Erie, and Allegheny Counties deprived voters of their right to vote and have their vote counted correctly. (2/3)
there is not. it is using a (highly complicated, multidimensional) statistical model to guess the next word in the chain
that is ALL it is doing
that is ALL it CAN do
there is no difference between valid output and hallucination
it can’t search its data, or demonstrate creativity or insight
that is ALL it is doing
that is ALL it CAN do
there is no difference between valid output and hallucination
it can’t search its data, or demonstrate creativity or insight
November 7, 2025 at 12:53 PM
there is not. it is using a (highly complicated, multidimensional) statistical model to guess the next word in the chain
that is ALL it is doing
that is ALL it CAN do
there is no difference between valid output and hallucination
it can’t search its data, or demonstrate creativity or insight
that is ALL it is doing
that is ALL it CAN do
there is no difference between valid output and hallucination
it can’t search its data, or demonstrate creativity or insight
www.nbcnews.com/tech/tech-ne...
According to the study, a significant number of top-tier benchmarks fail to define what exactly they aim to test, concerningly reuse data and testing methods from pre-existing benchmarks, and seldom use reliable statistical methods to compare results between models.
According to the study, a significant number of top-tier benchmarks fail to define what exactly they aim to test, concerningly reuse data and testing methods from pre-existing benchmarks, and seldom use reliable statistical methods to compare results between models.
AI's capabilities may be exaggerated by flawed tests, according to new study
A study from the Oxford Internet Institute analyzed 445 tests used to evaluate AI models.
www.nbcnews.com
November 8, 2025 at 5:56 PM
www.nbcnews.com/tech/tech-ne...
According to the study, a significant number of top-tier benchmarks fail to define what exactly they aim to test, concerningly reuse data and testing methods from pre-existing benchmarks, and seldom use reliable statistical methods to compare results between models.
According to the study, a significant number of top-tier benchmarks fail to define what exactly they aim to test, concerningly reuse data and testing methods from pre-existing benchmarks, and seldom use reliable statistical methods to compare results between models.
BREAKING NEWS IN PENNSYLVANIA!
"In 2024 late software changes, testing failures, ballot-handling discrepancies, & concerns of abnormal voting behavior identified with statistical analysis in Cambria, Erie, and Allegheny Counties deprived voters of their right to have their votes counted correctly"
"In 2024 late software changes, testing failures, ballot-handling discrepancies, & concerns of abnormal voting behavior identified with statistical analysis in Cambria, Erie, and Allegheny Counties deprived voters of their right to have their votes counted correctly"
Pennsylvania Lawsuit Filed | Election Truth Alliance
YouTube video by Election Truth Alliance
youtu.be
November 7, 2025 at 11:26 PM
BREAKING NEWS IN PENNSYLVANIA!
"In 2024 late software changes, testing failures, ballot-handling discrepancies, & concerns of abnormal voting behavior identified with statistical analysis in Cambria, Erie, and Allegheny Counties deprived voters of their right to have their votes counted correctly"
"In 2024 late software changes, testing failures, ballot-handling discrepancies, & concerns of abnormal voting behavior identified with statistical analysis in Cambria, Erie, and Allegheny Counties deprived voters of their right to have their votes counted correctly"
Yeah i got served that ad, it was a “dip” from like 95 -> 93. Statistical noise from degenerate gamblers.
November 4, 2025 at 8:24 PM
Yeah i got served that ad, it was a “dip” from like 95 -> 93. Statistical noise from degenerate gamblers.
there is something wrong with me which requires me to evaluate idle thoughts using the statistical software package R
November 9, 2025 at 5:40 PM
there is something wrong with me which requires me to evaluate idle thoughts using the statistical software package R
fuck having normal luck what if i just became a statistical anomaly and got a yakuman every hand forever has anyone ever considred thsi
November 10, 2025 at 6:06 AM
fuck having normal luck what if i just became a statistical anomaly and got a yakuman every hand forever has anyone ever considred thsi