Spurious correlation #5,030 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Bucyrus, Ohio and the second variable is Career regular season goals scored by Sidney Crosby. The chart goes from 2002 to 2010, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Bucyrus, Ohio and the second variable is Career regular season goals scored by Sidney Crosby. The chart goes from 2002 to 2010, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the air quality improved in Bucyrus, Ohio, it meant there were fewer airborne distractions. This inadvertently led to Sidney Crosby feeling less "air-ritated" on the ice. With cleaner air, he just couldn't generate the same level of goal-scoring "momentum." So, the correlation here is as clear as the now pristine Bucyrus air - fresher air in the city somehow led to a bit of a scoring drought for Sidney Crosby.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of an ice rink in Bucyrus, Ohio, with the sky above reflecting the cleaner air. Show Sidney Crosby in his hockey gear looking slightly puzzled or frustrated as he skates on the ice. A comet or shooting star streaks across the sky, subtly hinting at the unexpected link between the improved air quality and Crosby's goal-scoring abilities. The image should have a humorous and lighthearted tone, suitable for sharing on Reddit. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Air pollution in Bucyrus, Ohio and Career regular season goals scored by Sidney Crosby. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Cubism a funny image you would see on reddit a meme Futuristic Low poly
ChatGPT: a funny image you would see on reddit

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air pollution in Bucyrus, Ohio and Career regular season goals scored by Sidney Crosby, in the following situation: As the air quality improved in Bucyrus, Ohio, it meant there were fewer airborne distractions. This inadvertently led to Sidney Crosby feeling less "air-ritated" on the ice. With cleaner air, he just couldn't generate the same level of goal-scoring "momentum." So, the correlation here is as clear as the now pristine Bucyrus air - fresher air in the city somehow led to a bit of a scoring drought for Sidney Crosby.. Keep the description simple.
ChatGPT: In Bucyrus, Ohio, the air is finally clearing up, with fewer pollutants marring the skies. Meanwhile, on the ice rink, Sidney Crosby seems slightly unsettled, unable to find the back of the net as frequently as before. The cleaner air in Bucyrus inadvertently seems to have affected Crosby's goal-scoring prowess, creating an unexpected connection between air quality and his performance.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ a funny image you would see on reddit ] and depicting this scene: In Bucyrus, Ohio, the air is finally clearing up, with fewer pollutants marring the skies. Meanwhile, on the ice rink, Sidney Crosby seems slightly unsettled, unable to find the back of the net as frequently as before. The cleaner air in Bucyrus inadvertently seems to have affected Crosby's goal-scoring prowess, creating an unexpected connection between air quality and his performance. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of an ice rink in Bucyrus, Ohio, with the sky above reflecting the cleaner air. Show Sidney Crosby in his hockey gear looking slightly puzzled or frustrated as he skates on the ice. A comet or shooting star streaks across the sky, subtly hinting at the unexpected link between the improved air quality and Crosby's goal-scoring abilities. The image should have a humorous and lighthearted tone, suitable for sharing on Reddit.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Air pollution in Bucyrus, Ohio caused Career regular season goals scored by Sidney Crosby to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Bothering Bucyrus: A Biomass of Air Pollution and Crosby's Career Goals

The Journal of Ecological Entanglements

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Bucyrus, Ohio and Career regular season goals scored by Sidney Crosby. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Bothering Bucyrus: A Biomass of Air Pollution and Crosby's Career Goals

[[ABSTRACT]]
Air pollution is a pervasive issue with potential impacts on both human health and the environment. In this paper, we sought to investigate the unusual and seemingly unrelated correlation between air pollution in Bucyrus, Ohio, and the career regular season goals scored by the eminent ice hockey player, Sidney Crosby. Drawing data from the Environmental Protection Agency's Air Quality System and the National Hockey League statistics, we analyzed the air pollution levels in Bucyrus and Sidney Crosby's career regular season goals from 2002 to 2010. The correlation coefficient was calculated to be an astonishing 0.8049148, with a p-value less than 0.01, indicating a statistically robust relationship between these two seemingly distant variables.

Despite the apparent absurdity of the connection at first glance, our findings suggest that there may be a whimsical link between air pollution and Sidney Crosby's performance on the ice. The study's results are a breath of fresh air for hockey enthusiasts and environmentalists alike, shedding light on the potential far-reaching effects of air quality on unexpected arenas.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Air pollution is a concerning issue with ramifications far beyond what meets the eye. However, what happens when it intersects with the world of ice hockey, specifically, the career regular season goals scored by Sidney Crosby? It may sound like a punchline to a bad joke, but it turns out, there's much more to this peculiar association than meets the ice.
Pollution and hockey may seem like an odd couple, but our research indicates otherwise. It's almost as unexpected as finding ice in a hockey rink! But the data don't lie, and our findings provide an intriguing glimpse into the possibility of a connection between air quality in Bucyrus, Ohio, and Sidney Crosby's goal-scoring prowess.
The relationship between air pollution and Crosby's career regular season goals adds a whole new meaning to the term "air quality." It's as if the proverbial "it's in the air" has taken on a literal significance. But before we delve into the delightfully unexpected link between puck and pollution, let's examine the prevailing literature on air pollution and its potential impacts. This exploration will lay the groundwork for unraveling the enigma of Crosby's goals and particulate matter.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The relationship between air pollution and Sidney Crosby's career regular season goals is as unexpected as finding a polar bear in a snowstorm, yet the existing body of literature on air pollution provides valuable insight into potential connections that may seem flimsy at first blush. In "Smith et al.," the authors find that air pollution can have adverse effects on respiratory health, cardiovascular function, and overall well-being. This serves as the baseline for understanding the potential impact of air pollution on seemingly unrelated domains.

As we delve deeper, "Doe" explores the far-reaching repercussions of air pollution on environmental quality and public health, emphasizing the need for stringent measures to mitigate its deleterious effects. The extent of air pollution's impact, as established by these studies, is nothing to sneeze at.

Additionally, "Jones" outlines the intricate interplay between air pollution and climatic changes, underscoring the pervasive nature of its consequences. The far-reaching impact of air pollution extends to realms beyond the human experience, implicating ecosystems and natural habitats. It would seem that air pollution has more tentacles than a certain cephalopod in a popular animated series.

Quite like the air quality in a bustling city, these findings are dense - but fear not! The journey through our literature review will soon take an unexpected turn. As we transition to related sources, it is worth noting the influence of non-fiction works such as "The Air We Breathe" by Andrea Barrett and "Choked" by Beth Gardiner, which offer detailed accounts of the detrimental effects of air pollution on human health and the environment.

In a fictional vein, "The Polluted Puck" by J. K. Rowling and "The Ozone Offense" by J.R.R. Tolkien, while not rooted in factual events, intriguingly capture the imagination about potential connections between pollution and unexpected arenas. These fictional works add a whimsical touch to our exploration, much like finding a joke in a scholarly manuscript.

And now, turning our attention to more unconventional sources, we wade into the realm of childhood nostalgia with observations from "Captain Planet" and "The Magic School Bus." Although these may seem lighthearted at first glance, they inadvertently provide early exposure to environmental issues, which may have influenced the path of future research in unexpected ways.

In the grand scheme of air pollution's influence, these seemingly disparate works contribute to the whimsical tapestry of our scholarly investigation, offering an unexpected mix of scholarly depth and lighthearted exploration.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Bucyrus, Ohio and Career regular season goals scored by Sidney Crosby. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
Bothering Bucyrus: A Biomass of Air Pollution and Crosby's Career Goals

[[ABSTRACT]]
Air pollution is a pervasive issue with potential impacts on both human health and the environment. In this paper, we sought to investigate the unusual and seemingly unrelated correlation between air pollution in Bucyrus, Ohio, and the career regular season goals scored by the eminent ice hockey player, Sidney Crosby. Drawing data from the Environmental Protection Agency's Air Quality System and the National Hockey League statistics, we analyzed the air pollution levels in Bucyrus and Sidney Crosby's career regular season goals from 2002 to 2010. The correlation coefficient was calculated to be an astonishing 0.8049148, with a p-value less than 0.01, indicating a statistically robust relationship between these two seemingly distant variables.

Despite the apparent absurdity of the connection at first glance, our findings suggest that there may be a whimsical link between air pollution and Sidney Crosby's performance on the ice. The study's results are a breath of fresh air for hockey enthusiasts and environmentalists alike, shedding light on the potential far-reaching effects of air quality on unexpected arenas.

[[LITERATURE REVIEW]]
The relationship between air pollution and Sidney Crosby's career regular season goals is as unexpected as finding a polar bear in a snowstorm, yet the existing body of literature on air pollution provides valuable insight into potential connections that may seem flimsy at first blush. In "Smith et al.," the authors find that air pollution can have adverse effects on respiratory health, cardiovascular function, and overall well-being. This serves as the baseline for understanding the potential impact of air pollution on seemingly unrelated domains.
As we delve deeper, "Doe" explores the far-reaching repercussions of air pollution on environmental quality and public health, emphasizing the need for stringent measures to mitigate its deleterious effects. The extent of air pollution's impact, as established by these studies, is nothing to sneeze at.
Additionally, "Jones" outlines the intricate interplay between air pollution and climatic changes, underscoring the pervasive nature of its consequences. The far-reaching impact of air pollution extends to realms beyond the human experience, implicating ecosystems and natural habitats. It would seem that air pollution has more tentacles than a certain cephalopod in a popular animated series.
Quite like the air quality in a bustling city, these findings are dense - but fear not! The journey through our literature review will soon take an unexpected turn. As we transition to related sources, it is worth noting the influence of non-fiction works such as "The Air We Breathe" by Andrea Barrett and "Choked" by Beth Gardiner, which offer detailed accounts of the detrimental effects of air pollution on human health and the environment.
In a fictional vein, "The Polluted Puck" by J. K. Rowling and "The Ozone Offense" by J.R.R. Tolkien, while not rooted in factual events, intriguingly capture the imagination about potential connections between pollution and unexpected arenas. These fictional works add a whimsical touch to our exploration, much like finding a joke in a scholarly manuscript.
And now, turning our attention to more unconventional sources, we wade into the realm of childhood nostalgia with observations from "Captain Planet" and "The Magic School Bus." Although these may seem lighthearted at first glance, they inadvertently provide early exposure to environmental issues, which may have influenced the path of future research in unexpected ways.
In the grand scheme of air pollution's influence, these seemingly disparate works contribute to the whimsical tapestry of our scholarly investigation, offering an unexpected mix of scholarly depth and lighthearted exploration.

[[RESULTS]]
The results of the analysis between air pollution in Bucyrus, Ohio, and Sidney Crosby's career regular season goals from 2002 to 2010 revealed a surprisingly strong positive correlation, much like the bond between a hockey player and their favorite stick. The correlation coefficient of 0.8049148 suggests a robust relationship between these seemingly unrelated variables, highlighting a connection as seamless as a well-executed power play.
Furthermore, the high value of the coefficient of determination (r-squared = 0.6478878) indicates that approximately 64.8% of the variability in Sidney Crosby's career regular season goals can be explained by the variation in air pollution levels in Bucyrus, Ohio. This finding is as solid as a well-aimed slap shot on goal.
The statistical significance of the relationship was confirmed by a p-value of less than 0.01, indicating that the likelihood of observing such a strong correlation due to random chance is lower than the probability of a puck magically appearing in the net on its own. This result underscores the undeniable link between air pollution in Bucyrus and Sidney Crosby's scoring performance, leaving researchers and hockey fans alike in awe, much like witnessing a hat trick.
As shown in Fig. 1, the scatterplot further illustrates the marked association between air pollution levels in Bucyrus and Sidney Crosby's career regular season goals. The points on the plot align so closely, they could be mistaken for the precision of a Zamboni on freshly resurfaced ice.
Overall, our findings point to an unexpectedly strong and statistically significant relationship between air pollution in Bucyrus, Ohio, and Sidney Crosby's career regular season goals, offering a fascinating new perspective on the potential influences of air quality on athletic performance and leaving us all pondering the whimsical and wondrous ways in which the world of ice hockey and environmental conditions intertwine.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The unexpected connection between air pollution in Bucyrus and Sidney Crosby's career regular season goals has yielded astonishing results, leaving us with as many questions as a goalie facing a penalty shot. As we reflect on the correlation coefficient of 0.8049148, it becomes evident that there is more than meets the eye in the realm of environmental influences on athletic performance. This finding underscores the need to consider a broader array of factors, much like considering the full strength of a team on the ice rather than fixating solely on individual players.

Our results align with prior research on the overarching impact of air pollution, adding a fresh twist to the established body of literature. Just as a well-executed slap shot can catch an opponent off guard, the relationship between air pollution and athletic performance has emerged as a surprise twist in the ongoing narrative of environmental influences. The existing literature, which outlines the far-reaching repercussions of air pollution on human health, environmental quality, and climatic changes, offers a sturdy foundation for our unexpected discovery. It is quite like finding a hidden gem in a seemingly ordinary stretch of ice.

Indeed, our findings breathe new life into the discussion of how air quality may interlace with the performance of athletes in various sports arenas. The statistical significance of the relationship, with a p-value of less than 0.01, reinforces the notion that the impact of air pollution on unexpected domains may be as tangible as the feeling of lacing up one's skates for a game. In a similar vein, a dad joke could be as unavoidable as a penalty in a high-stakes match.

As we navigate this uncharted territory of environmental impact on athletic achievement, it is imperative to approach this whimsical discovery with cautious optimism, akin to cautiously plotting the path to the opponent's net during a power play. While our findings reflect a remarkable association between air pollution in Bucyrus and Sidney Crosby's goal-scoring prowess, there remains much to unravel about the underlying mechanisms driving this correlation, much like the anticipation before a game-winning goal in overtime.

In summary, our study has unfurled an unexpected chapter in the intricate tale of environmental influences, interspersed with unexpected humorous moments akin to a well-timed moment of levity on the ice. It is clear that the realm of air pollution's impact extends beyond the realms of traditional understanding, adding a fresh layer to the conversation and demonstrating that unexpected correlations can be as delightful as a perfectly executed one-timer.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Bucyrus, Ohio and Career regular season goals scored by Sidney Crosby. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Bothering Bucyrus: A Biomass of Air Pollution and Crosby's Career Goals

[[ABSTRACT]]
Air pollution is a pervasive issue with potential impacts on both human health and the environment. In this paper, we sought to investigate the unusual and seemingly unrelated correlation between air pollution in Bucyrus, Ohio, and the career regular season goals scored by the eminent ice hockey player, Sidney Crosby. Drawing data from the Environmental Protection Agency's Air Quality System and the National Hockey League statistics, we analyzed the air pollution levels in Bucyrus and Sidney Crosby's career regular season goals from 2002 to 2010. The correlation coefficient was calculated to be an astonishing 0.8049148, with a p-value less than 0.01, indicating a statistically robust relationship between these two seemingly distant variables.

Despite the apparent absurdity of the connection at first glance, our findings suggest that there may be a whimsical link between air pollution and Sidney Crosby's performance on the ice. The study's results are a breath of fresh air for hockey enthusiasts and environmentalists alike, shedding light on the potential far-reaching effects of air quality on unexpected arenas.

[[INTRDUCTION]]
Air pollution is a concerning issue with ramifications far beyond what meets the eye. However, what happens when it intersects with the world of ice hockey, specifically, the career regular season goals scored by Sidney Crosby? It may sound like a punchline to a bad joke, but it turns out, there's much more to this peculiar association than meets the ice.
Pollution and hockey may seem like an odd couple, but our research indicates otherwise. It's almost as unexpected as finding ice in a hockey rink! But the data don't lie, and our findings provide an intriguing glimpse into the possibility of a connection between air quality in Bucyrus, Ohio, and Sidney Crosby's goal-scoring prowess.
The relationship between air pollution and Crosby's career regular season goals adds a whole new meaning to the term "air quality." It's as if the proverbial "it's in the air" has taken on a literal significance. But before we delve into the delightfully unexpected link between puck and pollution, let's examine the prevailing literature on air pollution and its potential impacts. This exploration will lay the groundwork for unraveling the enigma of Crosby's goals and particulate matter.

[[RESULTS]]
The results of the analysis between air pollution in Bucyrus, Ohio, and Sidney Crosby's career regular season goals from 2002 to 2010 revealed a surprisingly strong positive correlation, much like the bond between a hockey player and their favorite stick. The correlation coefficient of 0.8049148 suggests a robust relationship between these seemingly unrelated variables, highlighting a connection as seamless as a well-executed power play.
Furthermore, the high value of the coefficient of determination (r-squared = 0.6478878) indicates that approximately 64.8% of the variability in Sidney Crosby's career regular season goals can be explained by the variation in air pollution levels in Bucyrus, Ohio. This finding is as solid as a well-aimed slap shot on goal.
The statistical significance of the relationship was confirmed by a p-value of less than 0.01, indicating that the likelihood of observing such a strong correlation due to random chance is lower than the probability of a puck magically appearing in the net on its own. This result underscores the undeniable link between air pollution in Bucyrus and Sidney Crosby's scoring performance, leaving researchers and hockey fans alike in awe, much like witnessing a hat trick.
As shown in Fig. 1, the scatterplot further illustrates the marked association between air pollution levels in Bucyrus and Sidney Crosby's career regular season goals. The points on the plot align so closely, they could be mistaken for the precision of a Zamboni on freshly resurfaced ice.
Overall, our findings point to an unexpectedly strong and statistically significant relationship between air pollution in Bucyrus, Ohio, and Sidney Crosby's career regular season goals, offering a fascinating new perspective on the potential influences of air quality on athletic performance and leaving us all pondering the whimsical and wondrous ways in which the world of ice hockey and environmental conditions intertwine.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has uncovered a delightful and unexpected relationship between air pollution in Bucyrus, Ohio, and Sidney Crosby's career regular season goals. It seems that air pollution may not only affect human health and the environment but also the precision and finesse of a talented hockey player. It's as if poor air quality is the penalty box, and Sidney Crosby's goals are the power play – they just can't seem to stay apart!

Our findings serve as a gentle reminder that sometimes the most seemingly unrelated factors can be surprisingly intertwined, much like the unbreakable bond between a player and their hockey stick. It's a bit like finding out that a Zamboni driver moonlights as an air quality monitor – unexpected, but undeniably linked!

While our results may seem like a slap shot from left field, they bring a breath of fresh air to the world of sports and environmental research. It's a bit like discovering that hockey pucks are made of recycled air – it's all connected in ways we never imagined!

Given the whimsical nature of our findings, it is clear that no further research is warranted in this area. It seems that the peculiar relationship between air pollution in Bucyrus, Ohio, and Sidney Crosby's career regular season goals has been adequately explored and illuminated. There's no need to belabor the point – this research has put the puck in the net, and it's time to celebrate this surprising discovery with a well-deserved victory lap on the ice!

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited Bothering Bucyrus: A Biomass of Air Pollution and Crosby's Career Goals. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Ecological Entanglements

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Bothering Bucyrus: A Biomass of Air Pollution and Crosby's Career Goals. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Environmental Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Bothering Bucyrus: A Biomass of Air Pollution and Crosby's Career Goals with an abstract of Air pollution is a pervasive issue with potential impacts on both human health and the environment. In this paper, we sought to investigate the unusual and seemingly unrelated correlation between air pollution in Bucyrus, Ohio, and the career regular season goals scored by the eminent ice hockey player, Sidney Crosby. Drawing data from the Environmental Protection Agency's Air Quality System and the National Hockey League statistics, we analyzed the air pollution levels in Bucyrus and Sidney Crosby's career regular season goals from 2002 to 2010. The correlation coefficient was calculated to be an astonishing 0.8049148, with a p-value less than 0.01, indicating a statistically robust relationship between these two seemingly distant variables.
Despite the apparent absurdity of the connection at first glance, our findings suggest that there may be a whimsical link between air pollution and Sidney Crosby's performance on the ice. The study's results are a breath of fresh air for hockey enthusiasts and environmentalists alike, shedding light on the potential far-reaching effects of air quality on unexpected arenas.

ChatGPT:

air pollution, Bucyrus, Ohio, Sidney Crosby, ice hockey, career regular season goals, environmental impact, correlation, data analysis, Environmental Protection Agency, Air Quality System, National Hockey League statistics

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

Air pollution in Bucyrus, Ohio
Detailed data title: Percentage of days with moderate or worse air quality in Bucyrus, OH
Source: Environmental Protection Agency
See what else correlates with Air pollution in Bucyrus, Ohio

Career regular season goals scored by Sidney Crosby
Source: NHL
See what else correlates with Career regular season goals scored by Sidney Crosby

Correlation r = 0.8049148 (Pearson correlation coefficient)
Correlation is a measure of how much the variables move together. If it is 0.99, when one goes up the other goes up. If it is 0.02, the connection is very weak or non-existent. If it is -0.99, then when one goes up the other goes down. If it is 1.00, you probably messed up your correlation function.

r² = 0.6478878 (Coefficient of determination)
This means 64.8% of the change in the one variable (i.e., Career regular season goals scored by Sidney Crosby) is predictable based on the change in the other (i.e., Air pollution in Bucyrus, Ohio) over the 9 years from 2002 through 2010.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0089.^Show 0.0088704386704833230000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.8 in 0.89% of random cases. Said differently, if you correlated 113 random variables^Note Which I absolutely did.
with the same 8 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 8 because we have two variables measured over a period of 9 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.3, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!

All values for the years included above: ^Note If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2002	2003	2004	2005	2006	2007	2008	2009	2010
Air pollution in Bucyrus, Ohio (Bad air quality days)	0.267218	0.21727	0.138889	0.222222	0.171014	0.157895	0.177143	0.0957747	0.175
Career regular season goals scored by Sidney Crosby (Goals scored)	95	72	56	78	47	36	24	33	55

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.267218,0.21727,0.138889,0.222222,0.171014,0.157895,0.177143,0.0957747,0.175,])
array_2 = np.array([95,72,56,78,47,36,24,33,55,])
array_1_name = "Air pollution in Bucyrus, Ohio"
array_2_name = "Career regular season goals scored by Sidney Crosby"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Air pollution in Bucyrus, Ohio
Line chart for only Career regular season goals scored by Sidney Crosby
AI-generated correlation image
The spurious research paper: Bothering Bucyrus: A Biomass of Air Pollution and Crosby's Career Goals

View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!

Correlation ID: 5030 · Black Variable ID: 22165 · Red Variable ID: 348


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: