Spurious correlation #2,224 · 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 Canton, Ohio and the second variable is NASA's budget as a percentage of the total US Federal Budget. The chart goes from 1980 to 2023, 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 Canton, Ohio and the second variable is NASA's budget as a percentage of the total US Federal Budget. The chart goes from 1980 to 2023, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As air pollution in Canton, Ohio increased, residents took to the skies with their own homemade oxygen tanks, leading to a surge in amateur space exploration. This newfound interest in reaching for the stars prompted NASA to receive additional funding, propelling their budget to new heights. It seems the smog in Canton wasn't just full of particulate matter, but also of stellar aspirations!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image showing a polluted skyline of Canton, Ohio, shrouded in smog and haze. In the background, a sign bears NASA's budget as a minuscule fraction of the US Federal Budget, emphasizing the stark contrast between the two. The atmosphere is filled with a sense of environmental disparity and the impactful insignificance of space exploration in comparison to the broader federal budget. 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: Poor air quality in Canton, Ohio and NASA's budget as a percentage of the total US Federal Budget. 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: A black-and-white newspaper illustration Futuristic Glitch art Sci-fi fantacy A Discovery magazine cover image
ChatGPT: A Discovery magazine cover image

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 Poor air quality in Canton, Ohio and NASA's budget as a percentage of the total US Federal Budget together. Keep the description simple.
ChatGPT: In Canton, Ohio, the sky is filled with smog and haze, making it difficult to see the NASA budget sign in the distance. The sign shows NASA's budget as a tiny fraction of the total US Federal Budget, underscoring the stark contrast between the two variables.

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 Discovery magazine cover image ] and depicting this scene: In Canton, Ohio, the sky is filled with smog and haze, making it difficult to see the NASA budget sign in the distance. The sign shows NASA's budget as a tiny fraction of the total US Federal Budget, underscoring the stark contrast between the two variables. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image showing a polluted skyline of Canton, Ohio, shrouded in smog and haze. In the background, a sign bears NASA's budget as a minuscule fraction of the US Federal Budget, emphasizing the stark contrast between the two. The atmosphere is filled with a sense of environmental disparity and the impactful insignificance of space exploration in comparison to the broader federal budget.

*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 increases in Air pollution in Canton, Ohio positively influenced NASA's budget as a percentage of the total US Federal Budget. Include one good pun.

AI academic paper

(Because p < 0.01)

NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget

The Journal of Space Policy and Environmental Science

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 Canton, Ohio and NASA's budget as a percentage of the total US Federal Budget. Make lots of jokes, goofy observations, and puns.

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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
"NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget"

[[ABSTRACT]]
This paper delves into the peculiar relationship between air pollution in Canton, Ohio, and the fluctuations in NASA's budget as a percentage of the total US Federal Budget. While one may find it as surprising as finding a rocket in one's backyard, our research team has strived to unravel this bizarre correlation. Utilizing data from the Environmental Protection Agency and Planetary.org, we conducted a rigorous analysis from 1980 to 2023. The results revealed a correlation coefficient of 0.6215913 and p < 0.01, indicating a significant relationship. Our findings may leave readers gasping for clean air, but further investigations are necessary to comprehend the truly cosmic forces at play in this entangled tale of air pollution and space budgets.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of environmental quality and government spending may seem as unlikely as a Martian invasion, but our research aims to explore the unexpected connection between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget. While the idea of space exploration and air pollution in a small Ohio city may sound as mismatched as a rocket in a rose garden, our investigation seeks to shed light on this puzzling correlation.
The allocation of funds for space exploration, like a spaceship hurtling through the cosmos, is a complex and dynamic process. Similarly, the environmental conditions in Canton, Ohio, such as air pollution levels, are subject to numerous factors and influences. Combining these two seemingly disparate elements into a single analysis may appear as incongruous as a telescope at a smoggy skyline.
Nevertheless, in the spirit of scientific inquiry, we sought to undertake a rigorous examination of the relationship between these variables. Our investigation covers a time span from 1980 to 2023, allowing for a comprehensive analysis of historical trends and patterns. By bringing together data from the Environmental Protection Agency and Planetary.org, we conducted a thorough examination to determine the nature of the association between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget.
We recognize that this research may raise eyebrows and elicit skeptical reactions, much like the discovery of a lunar rover parked in a suburban driveway. However, our findings revealed a correlation coefficient of 0.6215913, with a significant p-value of less than 0.01, indicating an intriguing and statistically robust relationship. This unexpected connection between terrestrial air quality and celestial spending warrants further investigation to unravel the underlying mechanisms at play.
As we embark on this cosmic journey of analysis, we invite readers to join us in exploring the unusual intersection of environmental pollution and space funding. While our findings may prompt double takes and raised eyebrows, they provide an intriguing glimpse into the intertwined forces shaping our earthly and extraterrestrial domains.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith and Doe (2010)," the authors find that air pollution has numerous adverse effects on human health and the environment. The study highlights the detrimental impact of particulate matter and nitrogen dioxide emissions on respiratory health, cardiovascular function, and overall well-being. Furthermore, "Jones et al. (2015)" underscore the economic ramifications of air pollution, demonstrating its association with higher healthcare costs and reduced labor productivity.

Turning to the realm of government spending, "Economic Perspectives on Space" by Johnson and Parker (2018) offers a comprehensive analysis of budget allocation for space exploration. The authors discuss the intricate budgetary dynamics and the competing priorities that influence funding decisions for NASA and related programs. Additionally, "The Politics of Planetary Spending" by Adams and Rodriguez (2016) delves into the political factors shaping the allocation of resources for space initiatives, shedding light on the complexities of federal budgetary processes.

Expanding our purview to fictional works, the acclaimed novel "The Martian" by Andy Weir weaves a captivating tale of survival and ingenuity on the red planet. Though a work of fiction, the narrative provides a compelling exploration of the challenges and triumphs of space exploration. Likewise, "The Hitchhiker's Guide to the Galaxy" by Douglas Adams humorously navigates the whimsical intricacies of intergalactic travel and cosmic exploration in a delightful, tongue-in-cheek manner.

Venturing into the realm of unconventional sources, the researchers undertook an exhaustive examination of various literature forms, including the back labels of household cleaning products and the packaging of canned goods. While such unconventional sources may elicit raised eyebrows, they provided a surprisingly enlightening glimpse into the linguistic and marketing strategies surrounding everyday consumer goods. These eclectic sources, though unconventional, offered unexpected insights and a refreshing departure from traditional academic texts.

In the pursuit of understanding the connection between air pollution in Canton, Ohio, and NASA's budget allocation, the integration of diverse literary sources has provided a nuanced and multifaceted perspective. This confluence of serious studies, fictional narratives, and unorthodox sources has contributed to a rich and vibrant tapestry of insights, paving the way for a uniquely holistic exploration of the subject matter.

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 methodology 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 methodology section of an academic research paper presenting the findings of the connection between Air pollution in Canton, Ohio and NASA's budget as a percentage of the total US Federal Budget. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Planetary.org . You used data from 1980 to 2023

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget"

[[ABSTRACT]]
This paper delves into the peculiar relationship between air pollution in Canton, Ohio, and the fluctuations in NASA's budget as a percentage of the total US Federal Budget. While one may find it as surprising as finding a rocket in one's backyard, our research team has strived to unravel this bizarre correlation. Utilizing data from the Environmental Protection Agency and Planetary.org, we conducted a rigorous analysis from 1980 to 2023. The results revealed a correlation coefficient of 0.6215913 and p < 0.01, indicating a significant relationship. Our findings may leave readers gasping for clean air, but further investigations are necessary to comprehend the truly cosmic forces at play in this entangled tale of air pollution and space budgets.

[[INTRODUCTION]]
The intersection of environmental quality and government spending may seem as unlikely as a Martian invasion, but our research aims to explore the unexpected connection between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget. While the idea of space exploration and air pollution in a small Ohio city may sound as mismatched as a rocket in a rose garden, our investigation seeks to shed light on this puzzling correlation.
The allocation of funds for space exploration, like a spaceship hurtling through the cosmos, is a complex and dynamic process. Similarly, the environmental conditions in Canton, Ohio, such as air pollution levels, are subject to numerous factors and influences. Combining these two seemingly disparate elements into a single analysis may appear as incongruous as a telescope at a smoggy skyline.
Nevertheless, in the spirit of scientific inquiry, we sought to undertake a rigorous examination of the relationship between these variables. Our investigation covers a time span from 1980 to 2023, allowing for a comprehensive analysis of historical trends and patterns. By bringing together data from the Environmental Protection Agency and Planetary.org, we conducted a thorough examination to determine the nature of the association between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget.
We recognize that this research may raise eyebrows and elicit skeptical reactions, much like the discovery of a lunar rover parked in a suburban driveway. However, our findings revealed a correlation coefficient of 0.6215913, with a significant p-value of less than 0.01, indicating an intriguing and statistically robust relationship. This unexpected connection between terrestrial air quality and celestial spending warrants further investigation to unravel the underlying mechanisms at play.
As we embark on this cosmic journey of analysis, we invite readers to join us in exploring the unusual intersection of environmental pollution and space funding. While our findings may prompt double takes and raised eyebrows, they provide an intriguing glimpse into the intertwined forces shaping our earthly and extraterrestrial domains.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To probe the curious correlation between air pollution in Canton, Ohio, and the budget allocation for NASA as a percentage of the total US Federal Budget, our research conducted a comprehensive data collection and analysis spanning the years 1980 to 2023. The initial phase of our methodology included a survey of existing literature on air quality, space exploration funding, and any tangentially related subjects, reminiscent of a cosmic scavenger hunt for scholarly insights.

Following this, data from the Environmental Protection Agency regarding air pollution levels in Canton, Ohio, were gathered, providing a firsthand glimpse into the atmospheric conditions of this quaint midwestern city. The acquisition of these data involved navigating through multiple online databases and interfaces, akin to exploring a dense meteorite field in search of precious cosmic debris.

Concurrently, information on NASA's budget as a percentage of the total US Federal Budget was sourced from Planetary.org, representing a quest through the virtual cosmos to collect the artifacts of celestial expenditure. The diligent curation of budgetary data across the decades mirrors the meticulous cataloging of stars in a distant galaxy, as our research team navigated through financial reports and historical documents to construct a comprehensive dataset.

The next stage of our methodology involved employing advanced statistical techniques, including regression analysis and time series modeling, to unravel the relationship between air pollution levels in Canton, Ohio, and NASA's budget allocation. Through the application of these analytical tools, we sought to elucidate whether the observed correlation represents a genuine cosmic phenomenon or merely a statistical mirage, akin to distinguishing between a murky nebula and a distant galaxy.

Furthermore, to mitigate the potential influence of confounding variables, such as economic fluctuations and policy changes, we utilized multivariate regression models with robustness checks, resembling the strategic deployment of planetary shields to defend against extraneous cosmic forces.

Finally, the findings of our analysis were subjected to rigorous validation and sensitivity testing, ensuring that the observed relationship between air pollution in Canton, Ohio, and NASA's budget allocation withstands the scrutiny of scientific inquiry. This validation process encompasses a comprehensive assessment of alternative model specifications and diagnostic tests, akin to scrutinizing the stability of a newly discovered celestial body amidst a sea of cosmic phenomena.

In summary, our methodology is akin to embarking on an astronomical expedition, navigating through the scientific cosmos to unearth the hidden connections between earthly air quality and celestial funding. Through a blend of data collection, statistical analysis, and rigorous validation, our research seeks to shed light on this perplexing link, guiding readers through a journey that transcends the boundaries of terrestrial and celestial realms.

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 Canton, Ohio and NASA's budget as a percentage of the total US Federal Budget. Make lots of jokes, goofy observations, and puns.

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]]
"NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget"

[[ABSTRACT]]
This paper delves into the peculiar relationship between air pollution in Canton, Ohio, and the fluctuations in NASA's budget as a percentage of the total US Federal Budget. While one may find it as surprising as finding a rocket in one's backyard, our research team has strived to unravel this bizarre correlation. Utilizing data from the Environmental Protection Agency and Planetary.org, we conducted a rigorous analysis from 1980 to 2023. The results revealed a correlation coefficient of 0.6215913 and p < 0.01, indicating a significant relationship. Our findings may leave readers gasping for clean air, but further investigations are necessary to comprehend the truly cosmic forces at play in this entangled tale of air pollution and space budgets.

[[LITERATURE REVIEW]]
In "Smith and Doe (2010)," the authors find that air pollution has numerous adverse effects on human health and the environment. The study highlights the detrimental impact of particulate matter and nitrogen dioxide emissions on respiratory health, cardiovascular function, and overall well-being. Furthermore, "Jones et al. (2015)" underscore the economic ramifications of air pollution, demonstrating its association with higher healthcare costs and reduced labor productivity.
Turning to the realm of government spending, "Economic Perspectives on Space" by Johnson and Parker (2018) offers a comprehensive analysis of budget allocation for space exploration. The authors discuss the intricate budgetary dynamics and the competing priorities that influence funding decisions for NASA and related programs. Additionally, "The Politics of Planetary Spending" by Adams and Rodriguez (2016) delves into the political factors shaping the allocation of resources for space initiatives, shedding light on the complexities of federal budgetary processes.
Expanding our purview to fictional works, the acclaimed novel "The Martian" by Andy Weir weaves a captivating tale of survival and ingenuity on the red planet. Though a work of fiction, the narrative provides a compelling exploration of the challenges and triumphs of space exploration. Likewise, "The Hitchhiker's Guide to the Galaxy" by Douglas Adams humorously navigates the whimsical intricacies of intergalactic travel and cosmic exploration in a delightful, tongue-in-cheek manner.
Venturing into the realm of unconventional sources, the researchers undertook an exhaustive examination of various literature forms, including the back labels of household cleaning products and the packaging of canned goods. While such unconventional sources may elicit raised eyebrows, they provided a surprisingly enlightening glimpse into the linguistic and marketing strategies surrounding everyday consumer goods. These eclectic sources, though unconventional, offered unexpected insights and a refreshing departure from traditional academic texts.
In the pursuit of understanding the connection between air pollution in Canton, Ohio, and NASA's budget allocation, the integration of diverse literary sources has provided a nuanced and multifaceted perspective. This confluence of serious studies, fictional narratives, and unorthodox sources has contributed to a rich and vibrant tapestry of insights, paving the way for a uniquely holistic exploration of the subject matter.

[[RESULTS]]
The data analysis revealed a correlation coefficient of 0.6215913, indicating a moderate positive relationship between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget. This surprising correlation may be as unexpected as finding a shooting star on a cloudy night. The coefficient of determination (r-squared) of 0.3863757 indicates that approximately 38.64% of the variability in NASA's budget as a percentage of the total US Federal Budget can be explained by variations in air pollution levels in Canton, Ohio. The p-value of less than 0.01 suggests that this relationship is statistically significant, leaving researchers scratching their heads more vigorously than a cat on a scratching post.
The scatterplot (Fig. 1) illustrates the strong correlation between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget. This unexpected connection may prompt reactions akin to seeing a UFO in the sky or a rocket in a recycling bin, but the results stand as a testament to the fascinatingly intricate web of factors that influence government spending in the cosmos and environmental conditions on Earth.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have underscored the peculiar and somewhat confounding correlation between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget. Just as Andy Weir's protagonist in "The Martian" faced unexpected challenges on the red planet, our research has unveiled an unforeseen relationship that may leave many scratching their heads more vigorously than a cat on a scratching post.

Our findings align with prior research on the adverse effects of air pollution on human health and the environment, as highlighted by Smith and Doe (2010). The detrimental impact of particulate matter and nitrogen dioxide emissions on respiratory health and overall well-being serves as a backdrop to our investigation. Additionally, the economic ramifications of air pollution, as demonstrated by Jones et al. (2015), set the stage for understanding the broader implications of environmental conditions on government spending.

In the realm of budget allocation for space exploration, the work of Johnson and Parker (2018) and the insights presented by Adams and Rodriguez (2016) provide valuable context for our findings. The intricate dynamics and political factors shaping the allocation of resources for space initiatives shed light on the complexities of federal budgetary processes, which play a significant role in our exploration of the correlation between air pollution and NASA's budget.

Furthermore, the integration of fictional narratives, such as "The Martian" by Andy Weir and "The Hitchhiker's Guide to the Galaxy" by Douglas Adams, along with unconventional sources, has contributed to a rich and vibrant tapestry of insights that complement our analysis. While these sources may prompt raised eyebrows, they have offered unexpected perspectives and a refreshing departure from traditional academic texts, enriching our understanding of the complex interplay between environmental conditions and government spending in the cosmic realm.

The moderate positive relationship revealed by our analysis, with a correlation coefficient of 0.6215913 and a statistically significant p-value, further supports the entangled tale of air pollution and space budgets. The results stand as a testament to the intricate web of factors that influence government spending and environmental conditions, sparking contemplation as profound as pondering the mysteries of the cosmos.

As the cosmic dance between air pollution in Canton, Ohio, and NASA's budget unfolds, our study opens avenues for further exploration into the cosmic forces at play, beckoning researchers to delve deeper into this enigmatic connection. Just as astronauts navigate the cosmos, our research endeavors to navigate the unexpected connections between terrestrial environmental conditions and celestial budgetary decisions, paving the way for a truly out-of-this-world understanding of this captivating correlation.

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 Canton, Ohio and NASA's budget as a percentage of the total US Federal Budget. Make lots of jokes, goofy observations, and puns.

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]]
"NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget"

[[ABSTRACT]]
This paper delves into the peculiar relationship between air pollution in Canton, Ohio, and the fluctuations in NASA's budget as a percentage of the total US Federal Budget. While one may find it as surprising as finding a rocket in one's backyard, our research team has strived to unravel this bizarre correlation. Utilizing data from the Environmental Protection Agency and Planetary.org, we conducted a rigorous analysis from 1980 to 2023. The results revealed a correlation coefficient of 0.6215913 and p < 0.01, indicating a significant relationship. Our findings may leave readers gasping for clean air, but further investigations are necessary to comprehend the truly cosmic forces at play in this entangled tale of air pollution and space budgets.

[[INTRDUCTION]]
The intersection of environmental quality and government spending may seem as unlikely as a Martian invasion, but our research aims to explore the unexpected connection between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget. While the idea of space exploration and air pollution in a small Ohio city may sound as mismatched as a rocket in a rose garden, our investigation seeks to shed light on this puzzling correlation.
The allocation of funds for space exploration, like a spaceship hurtling through the cosmos, is a complex and dynamic process. Similarly, the environmental conditions in Canton, Ohio, such as air pollution levels, are subject to numerous factors and influences. Combining these two seemingly disparate elements into a single analysis may appear as incongruous as a telescope at a smoggy skyline.
Nevertheless, in the spirit of scientific inquiry, we sought to undertake a rigorous examination of the relationship between these variables. Our investigation covers a time span from 1980 to 2023, allowing for a comprehensive analysis of historical trends and patterns. By bringing together data from the Environmental Protection Agency and Planetary.org, we conducted a thorough examination to determine the nature of the association between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget.
We recognize that this research may raise eyebrows and elicit skeptical reactions, much like the discovery of a lunar rover parked in a suburban driveway. However, our findings revealed a correlation coefficient of 0.6215913, with a significant p-value of less than 0.01, indicating an intriguing and statistically robust relationship. This unexpected connection between terrestrial air quality and celestial spending warrants further investigation to unravel the underlying mechanisms at play.
As we embark on this cosmic journey of analysis, we invite readers to join us in exploring the unusual intersection of environmental pollution and space funding. While our findings may prompt double takes and raised eyebrows, they provide an intriguing glimpse into the intertwined forces shaping our earthly and extraterrestrial domains.

[[RESULTS]]
The data analysis revealed a correlation coefficient of 0.6215913, indicating a moderate positive relationship between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget. This surprising correlation may be as unexpected as finding a shooting star on a cloudy night. The coefficient of determination (r-squared) of 0.3863757 indicates that approximately 38.64% of the variability in NASA's budget as a percentage of the total US Federal Budget can be explained by variations in air pollution levels in Canton, Ohio. The p-value of less than 0.01 suggests that this relationship is statistically significant, leaving researchers scratching their heads more vigorously than a cat on a scratching post.
The scatterplot (Fig. 1) illustrates the strong correlation between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget. This unexpected connection may prompt reactions akin to seeing a UFO in the sky or a rocket in a recycling bin, but the results stand as a testament to the fascinatingly intricate web of factors that influence government spending in the cosmos and environmental conditions on Earth.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the relationship between air pollution in Canton, Ohio, and NASA's budget as a percentage of the total US Federal Budget is as perplexing as an astronaut trying to navigate through a maze of zero gravity. The moderate positive correlation uncovered in our analysis has left us more puzzled than a chimpanzee trying to solve a Rubik's cube.

The noteworthy correlation coefficient of 0.6215913 and the eye-poppingly significant p-value of less than 0.01 have made us contemplate the cosmic implications of these findings more deeply than a black hole absorbing matter. If we were to take this relationship at face value, one could jest that "NASA's budget is truly out of this world, influenced by the very air we breathe in Canton, Ohio."

As amusing as this connection may be, it behooves us to recognize that correlation does not imply causation, and there could be other celestial forces at play. While our findings unveil a correlation that may be as unexpected as spotting a shooting star in broad daylight, additional research is warranted to disentangle the cosmic ballet of air pollution and space budgets.

In the spirit of scientific inquiry, we declare that further exploration of this unlikely correlation risks sending researchers on a wild goose chase across the Milky Way. Hence, we assert, with the confidence of a seasoned astronomer identifying a star, that no more investigation is needed in this area.

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 NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Space Policy and Environmental Science

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 NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quantitative Environmental Economics and Space Policy (SQEESP)

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 NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget with an abstract of This paper delves into the peculiar relationship between air pollution in Canton, Ohio, and the fluctuations in NASA's budget as a percentage of the total US Federal Budget. While one may find it as surprising as finding a rocket in one's backyard, our research team has strived to unravel this bizarre correlation. Utilizing data from the Environmental Protection Agency and Planetary.org, we conducted a rigorous analysis from 1980 to 2023. The results revealed a correlation coefficient of 0.6215913 and p < 0.01, indicating a significant relationship. Our findings may leave readers gasping for clean air, but further investigations are necessary to comprehend the truly cosmic forces at play in this entangled tale of air pollution and space budgets.

ChatGPT:

NASA budget, air pollution, correlation, budget analysis, federal budget allocation, environmental impact, Canton Ohio, NASA funding, air quality, pollution data, EPA 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 Canton, Ohio
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Canton-Massillon, OH
Source: Environmental Protection Agency
See what else correlates with Air pollution in Canton, Ohio

NASA's budget as a percentage of the total US Federal Budget
Source: Planetary.org
See what else correlates with NASA's budget as a percentage of the total US Federal Budget

Correlation r = 0.6215913 (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 = 0.3863757 (Coefficient of determination)
This means 38.6% of the change in the one variable (i.e., NASA's budget as a percentage of the total US Federal Budget) is predictable based on the change in the other (i.e., Air pollution in Canton, Ohio) over the 44 years from 1980 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.7E-6.^Show 0.0000066936877669412290000000
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 0.62 in 0.00067% of random cases. Said differently, if you correlated 149,394 random variables^Note You don't actually need 149 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 43 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 43 because we have two variables measured over a period of 44 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.

[ 0.4, 0.78 ] 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.

	1980	1981	1982	1983	1984	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Air pollution in Canton, Ohio (Bad air quality days)	2.7933	2.1978	3.56164	4.93151	1.36612	1.64384	1.10497	4.6832	8.96359	1.66205	1.91781	4.93151	1.64384	3.57143	1.09589	3.56164	1.36612	0.824176	4.10959	3.0137	1.36986	2.73973	4.93151	1.36986	0.273973	1.10803	0.292398	1.97183	0	0	0.273973	0.547945	0.273224	0	0	0	0	0	0	0	0	0	0	1.23457
NASA's budget as a percentage of the total US Federal Budget (Percent of Federal Budget)	0.84	0.82	0.83	0.85	0.83	0.77	0.75	0.76	0.85	0.96	0.99	1.05	1.01	1.01	0.94	0.88	0.89	0.9	0.86	0.8	0.75	0.76	0.72	0.68	0.66	0.63	0.57	0.58	0.6	0.54	0.55	0.49	0.49	0.49	0.49	0.5	0.49	0.47	0.48	0.48	0.35	0.33	0.41	0.44

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.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

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([2.7933,2.1978,3.56164,4.93151,1.36612,1.64384,1.10497,4.6832,8.96359,1.66205,1.91781,4.93151,1.64384,3.57143,1.09589,3.56164,1.36612,0.824176,4.10959,3.0137,1.36986,2.73973,4.93151,1.36986,0.273973,1.10803,0.292398,1.97183,0,0,0.273973,0.547945,0.273224,0,0,0,0,0,0,0,0,0,0,1.23457,])
array_2 = np.array([0.84,0.82,0.83,0.85,0.83,0.77,0.75,0.76,0.85,0.96,0.99,1.05,1.01,1.01,0.94,0.88,0.89,0.9,0.86,0.8,0.75,0.76,0.72,0.68,0.66,0.63,0.57,0.58,0.6,0.54,0.55,0.49,0.49,0.49,0.49,0.5,0.49,0.47,0.48,0.48,0.35,0.33,0.41,0.44,])
array_1_name = "Air pollution in Canton, Ohio"
array_2_name = "NASA's budget as a percentage of the total US Federal Budget"

# 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 Canton, Ohio
Line chart for only NASA's budget as a percentage of the total US Federal Budget
AI-generated correlation image
The spurious research paper: NASA's Budget: A Breath of Fresh Air or a Polluted Connection? Analyzing the Relationship Between Air Pollution in Canton, Ohio and NASA's Budget as a Percentage of the Total US Federal Budget

View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!

Correlation ID: 2224 · Black Variable ID: 20404 · Red Variable ID: 1084


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