Spurious correlation #3,879 · 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 Milwaukee and the second variable is Kerosene used in Peru. The chart goes from 1980 to 2021, 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 Milwaukee and the second variable is Kerosene used in Peru. The chart goes from 1980 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

When air pollution decreased in Milwaukee, it created a ripple effect of environmental conscientiousness. This led to a global decrease in the demand for kerosene, thereby impacting production and distribution. Additionally, the newfound fresh air in Milwaukee somehow altered the atmospheric conditions in Peru, making kerosene a less appealing lighting option. It's as if Mother Nature said, "Hey, let's switch to solar power, amigos!"

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Generate an image of a futuristic cityscape with heavy smog covering Milwaukee's skyline. In the sky, geese are seen flying off course, dropping kerosene canisters as they migrate. Meanwhile, in a rural area of Peru, depict locals looking up in surprise as the unexpected canisters fall from the sky, raising concern about the impact of kerosene usage. The image should capture the contrast between the futuristic city and the natural landscape, conveying a sense of environmental imbalance and human intervention. 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 Milwaukee and Kerosene used in Peru. 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: Magic realism Pop art Cyber folk Futuristic Futuristic
ChatGPT: Futuristic

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 Milwaukee and Kerosene used in Peru, in the following situation: Because the increased air pollution in Milwaukee altered the migratory patterns of geese, causing them to fly off course and inadvertently drop kerosene canisters in Peru during their annual migration.. Keep the description simple.
ChatGPT: In the sky above Milwaukee, geese fly off course due to the thick smog, dropping kerosene canisters as they migrate. In Peru, locals look up in surprise as the unexpected canisters fall from the sky, causing concern about the impact of kerosene usage.

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: [ Futuristic ] and depicting this scene: In the sky above Milwaukee, geese fly off course due to the thick smog, dropping kerosene canisters as they migrate. In Peru, locals look up in surprise as the unexpected canisters fall from the sky, causing concern about the impact of kerosene usage. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image of a futuristic cityscape with heavy smog covering Milwaukee's skyline. In the sky, geese are seen flying off course, dropping kerosene canisters as they migrate. Meanwhile, in a rural area of Peru, depict locals looking up in surprise as the unexpected canisters fall from the sky, raising concern about the impact of kerosene usage. The image should capture the contrast between the futuristic city and the natural landscape, conveying a sense of environmental imbalance and human intervention.

*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 Milwaukee caused Kerosene used in Peru to decrease.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog

The Journal of Absurd Atmospheric Analysis

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 Milwaukee and Kerosene used in Peru. 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 name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog

[[ABSTRACT]]
This study hilariously investigates the potential link between air pollution levels in Milwaukee, Wisconsin, and the use of kerosene for lighting in Peru. Using data from the Environmental Protection Agency and the Energy Information Administration, our research team conducted a thorough analysis spanning from 1980 to 2021. Surprisingly, we discovered a correlation coefficient of 0.7583268 and p < 0.01, indicating a significant relationship between the two seemingly unrelated phenomena. Our findings suggest that while one may be choking on smog in Milwaukee, another might be lighting up the night with kerosene in Peru, all contributing to a larger-than-expected trend in global air pollution. These results highlight the need for further investigation into the interconnectedness of environmental factors and the potential for unexpected connections to emerge, much like comical punchlines in an academic research paper.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world is full of unexpected connections and correlations, much like finding a sock without a pair in the laundry or stumbling upon a pun in a serious academic paper. In the realm of environmental factors, the relationship between air pollution in one part of the world and the use of kerosene for lighting in another might seem as peculiar as a penguin in a desert. However, as we delve into the comical correlation between Milwaukee's smog and Peru's kerosene fog, we aim to shed light on this unanticipated connection and examine the potential implications for global air quality.
Air pollution has long been a topic of concern, casting a shadow over the health and well-being of urban populations. Milwaukee, Wisconsin, known for its cheese and beer, also harbors its fair share of smog, contributing to the atmospheric haze and respiratory difficulties of its inhabitants. On the other side of the globe, in the high-altitude regions of Peru, kerosene lamps have been providing illumination but also emitting their own cloud of pollutants, creating a fog of their own kind. The juxtaposition of these two seemingly disparate phenomena has sparked our curiosity and prompted us to investigate whether there might be a relationship more substantial than a whimsical quip at a research conference.
Join us on this academic adventure as we untangle the threads of air pollution in Milwaukee and the use of kerosene in Peru, perhaps uncovering a connection as surprising as finding a dollar in the pocket of old jeans. Through rigorous analysis and statistical scrutiny, we aim to bring clarity to this comical correlation and provide insights that may guide future research and policy efforts towards a fresher, cleaner global atmosphere.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Smith and Jones (2005) conducted a comprehensive study on the air pollution levels in urban areas, highlighting the significant impact of industrial emissions and vehicular traffic on atmospheric quality. Meanwhile, Doe et al. (2010) investigated the use of kerosene for lighting in rural households, emphasizing the implications for indoor air pollution and respiratory health.

Venturing beyond the world of academic journals, "The Omnivore's Dilemma" by Michael Pollan offers insights into the environmental consequences of modern agricultural practices, shedding light on the interconnectedness of human activities and atmospheric conditions. Additionally, "The Lorax" by Dr. Seuss delves into the consequences of environmental degradation, albeit in a whimsical and fantastical manner.

As we explore the comical correlation between air pollution in Milwaukee and the use of kerosene in Peru, our research team has delved into the intriguing realm of television for further insights. "Breaking Bad" provides a dramatic portrayal of illicit activities involving chemicals, whereas "The Great British Bake Off" offers a lighthearted counterbalance with its focus on culinary pursuits.

The unexpected parallels and intersecting themes in these diverse sources have inspired our approach to this investigation, highlighting the potential for unconventional connections to emerge, much like stumbling upon a punchline in the midst of academic rigor.

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 Milwaukee and Kerosene used in Peru. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration . You used data from 1980 to 2021

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]]
The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog

[[ABSTRACT]]
This study hilariously investigates the potential link between air pollution levels in Milwaukee, Wisconsin, and the use of kerosene for lighting in Peru. Using data from the Environmental Protection Agency and the Energy Information Administration, our research team conducted a thorough analysis spanning from 1980 to 2021. Surprisingly, we discovered a correlation coefficient of 0.7583268 and p < 0.01, indicating a significant relationship between the two seemingly unrelated phenomena. Our findings suggest that while one may be choking on smog in Milwaukee, another might be lighting up the night with kerosene in Peru, all contributing to a larger-than-expected trend in global air pollution. These results highlight the need for further investigation into the interconnectedness of environmental factors and the potential for unexpected connections to emerge, much like comical punchlines in an academic research paper.

[[INTRODUCTION]]
The world is full of unexpected connections and correlations, much like finding a sock without a pair in the laundry or stumbling upon a pun in a serious academic paper. In the realm of environmental factors, the relationship between air pollution in one part of the world and the use of kerosene for lighting in another might seem as peculiar as a penguin in a desert. However, as we delve into the comical correlation between Milwaukee's smog and Peru's kerosene fog, we aim to shed light on this unanticipated connection and examine the potential implications for global air quality.
Air pollution has long been a topic of concern, casting a shadow over the health and well-being of urban populations. Milwaukee, Wisconsin, known for its cheese and beer, also harbors its fair share of smog, contributing to the atmospheric haze and respiratory difficulties of its inhabitants. On the other side of the globe, in the high-altitude regions of Peru, kerosene lamps have been providing illumination but also emitting their own cloud of pollutants, creating a fog of their own kind. The juxtaposition of these two seemingly disparate phenomena has sparked our curiosity and prompted us to investigate whether there might be a relationship more substantial than a whimsical quip at a research conference.
Join us on this academic adventure as we untangle the threads of air pollution in Milwaukee and the use of kerosene in Peru, perhaps uncovering a connection as surprising as finding a dollar in the pocket of old jeans. Through rigorous analysis and statistical scrutiny, we aim to bring clarity to this comical correlation and provide insights that may guide future research and policy efforts towards a fresher, cleaner global atmosphere.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data for this comically correlated study was gathered from sources as diverse as finding a carrot in the refrigerator and spotting a unicorn in a field. However, the bulk of the information was extracted from the Environmental Protection Agency and the Energy Information Administration, akin to mining for gold in an expansive data landscape. The time span for data collection extended from 1980 to 2021, allowing for a comprehensive analysis of the trends and patterns in air pollution levels in Milwaukee and kerosene usage in Peru.

Variable Selection:
A multitude of variables was considered for inclusion in this investigation, ranging from the density of cheese stands in Milwaukee to the number of llama sightings in Peru. However, after meticulous consideration, the focus settled on key air pollution indicators in Milwaukee, such as particulate matter and ozone levels, and the consumption of kerosene for lighting purposes in Peru. These variables were chosen for their relevance and potential impact on the overall study, like selecting the perfect punchline for a joke.

Statistical Analysis:
The data underwent a rigorous statistical examination, much like subjecting a joke to various punchline trials to determine its comedic potential. Correlation coefficients and p-values were calculated to ascertain the strength and significance of the relationship between air pollution in Milwaukee and kerosene use in Peru. The use of Pearson's correlation coefficient and regression analysis provided a solid foundation for evaluating this unlikely connection, akin to employing a well-crafted setup to deliver a satisfying punchline.

Control Variables:
To ensure that the comical correlation between Milwaukee’s smog and Peru's kerosene fog was not confounded by extraneous factors, control variables were introduced into the analysis. These included socio-economic indicators, urbanization trends, and meteorological conditions, much like introducing unexpected characters into a comedic storyline. The inclusion of control variables aimed to tease apart the distinct contributions of air pollution in one location and kerosene usage in another, much like unravelling the layers of a humorous anecdote.

Sensitivity Analysis:
Sensitivity analyses were performed to assess the robustness of the findings, akin to testing a joke with different audiences to gauge its universal appeal. Various model specifications and outlier treatments were explored to ensure that the observed comical correlation persisted across different analytical approaches. This exhaustive scrutiny aimed to confirm the reliability and validity of the results, much like trying out different comedic timings for a punchline.

Ethical Considerations:
In conducting this research, ethical considerations were paramount, matching the gravity of delivering a punchline at an appropriate moment. The privacy and integrity of the data sources were rigorously upheld, and the findings were presented with the utmost honesty and transparency, akin to delivering a candid comedic performance. The dissemination of the results followed ethical guidelines, ensuring that the humor of this unexpected connection did not overshadow the serious implications for environmental and public health policies.

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 results section of an academic research paper. You speak in the past tense (you found...).
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 results section of an academic research paper presenting the findings of the connection between Air pollution in Milwaukee and Kerosene used in Peru. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration .

For the time period 1980 to 2021, you found a correlation 0.7583268, r-squared of 0.5750595, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog

[[ABSTRACT]]
This study hilariously investigates the potential link between air pollution levels in Milwaukee, Wisconsin, and the use of kerosene for lighting in Peru. Using data from the Environmental Protection Agency and the Energy Information Administration, our research team conducted a thorough analysis spanning from 1980 to 2021. Surprisingly, we discovered a correlation coefficient of 0.7583268 and p < 0.01, indicating a significant relationship between the two seemingly unrelated phenomena. Our findings suggest that while one may be choking on smog in Milwaukee, another might be lighting up the night with kerosene in Peru, all contributing to a larger-than-expected trend in global air pollution. These results highlight the need for further investigation into the interconnectedness of environmental factors and the potential for unexpected connections to emerge, much like comical punchlines in an academic research paper.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The world is full of unexpected connections and correlations, much like finding a sock without a pair in the laundry or stumbling upon a pun in a serious academic paper. In the realm of environmental factors, the relationship between air pollution in one part of the world and the use of kerosene for lighting in another might seem as peculiar as a penguin in a desert. However, as we delve into the comical correlation between Milwaukee's smog and Peru's kerosene fog, we aim to shed light on this unanticipated connection and examine the potential implications for global air quality.
Air pollution has long been a topic of concern, casting a shadow over the health and well-being of urban populations. Milwaukee, Wisconsin, known for its cheese and beer, also harbors its fair share of smog, contributing to the atmospheric haze and respiratory difficulties of its inhabitants. On the other side of the globe, in the high-altitude regions of Peru, kerosene lamps have been providing illumination but also emitting their own cloud of pollutants, creating a fog of their own kind. The juxtaposition of these two seemingly disparate phenomena has sparked our curiosity and prompted us to investigate whether there might be a relationship more substantial than a whimsical quip at a research conference.
Join us on this academic adventure as we untangle the threads of air pollution in Milwaukee and the use of kerosene in Peru, perhaps uncovering a connection as surprising as finding a dollar in the pocket of old jeans. Through rigorous analysis and statistical scrutiny, we aim to bring clarity to this comical correlation and provide insights that may guide future research and policy efforts towards a fresher, cleaner global atmosphere.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The data analysis revealed a striking correlation coefficient of 0.7583268 between air pollution levels in Milwaukee, Wisconsin, and the consumption of kerosene for lighting in Peru. Such a strong correlation suggests that while one population was grappling with urban smog, another was casting light upon the high-altitude landscapes of Peru with kerosene lamps. The relationship between these two environmental factors surpassed our initial expectations and proved to be statistically significant with a p-value of less than 0.01, indicating that this comical correlation is not simply a whimsical jest but a genuine association with real-world implications.

The squared correlation coefficient (r-squared) of 0.5750595 further underscores the robustness of the relationship between air pollution in Milwaukee and kerosene usage in Peru. This signifies that approximately 57.51% of the variability in air pollution levels in Milwaukee can be explained by the variability in kerosene consumption in Peru, a surprising finding that serves as a poignant reminder of the interconnected nature of global environmental phenomena. This correlation, much like a clever punchline, highlights the unexpected link between seemingly disparate factors and calls for further investigation into the mechanisms underlying this comedic connection.

Additionally, a scatterplot (Fig. 1) visually depicts the compelling correlation between air pollution in Milwaukee and kerosene usage in Peru, providing a clear and visually engaging representation of this unlikely relationship. The scatterplot serves as a friendly reminder that, much like the unpredictability of a well-timed joke, the world of environmental research is filled with delightful surprises and unexpected connections, waiting to be explored and understood in all their comical glory.

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 Milwaukee and Kerosene used in Peru. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog

[[ABSTRACT]]
This study hilariously investigates the potential link between air pollution levels in Milwaukee, Wisconsin, and the use of kerosene for lighting in Peru. Using data from the Environmental Protection Agency and the Energy Information Administration, our research team conducted a thorough analysis spanning from 1980 to 2021. Surprisingly, we discovered a correlation coefficient of 0.7583268 and p < 0.01, indicating a significant relationship between the two seemingly unrelated phenomena. Our findings suggest that while one may be choking on smog in Milwaukee, another might be lighting up the night with kerosene in Peru, all contributing to a larger-than-expected trend in global air pollution. These results highlight the need for further investigation into the interconnectedness of environmental factors and the potential for unexpected connections to emerge, much like comical punchlines in an academic research paper.

[[LITERATURE REVIEW]]
Smith and Jones (2005) conducted a comprehensive study on the air pollution levels in urban areas, highlighting the significant impact of industrial emissions and vehicular traffic on atmospheric quality. Meanwhile, Doe et al. (2010) investigated the use of kerosene for lighting in rural households, emphasizing the implications for indoor air pollution and respiratory health.
Venturing beyond the world of academic journals, "The Omnivore's Dilemma" by Michael Pollan offers insights into the environmental consequences of modern agricultural practices, shedding light on the interconnectedness of human activities and atmospheric conditions. Additionally, "The Lorax" by Dr. Seuss delves into the consequences of environmental degradation, albeit in a whimsical and fantastical manner.
As we explore the comical correlation between air pollution in Milwaukee and the use of kerosene in Peru, our research team has delved into the intriguing realm of television for further insights. "Breaking Bad" provides a dramatic portrayal of illicit activities involving chemicals, whereas "The Great British Bake Off" offers a lighthearted counterbalance with its focus on culinary pursuits.
The unexpected parallels and intersecting themes in these diverse sources have inspired our approach to this investigation, highlighting the potential for unconventional connections to emerge, much like stumbling upon a punchline in the midst of academic rigor.

[[RESULTS]]
The data analysis revealed a striking correlation coefficient of 0.7583268 between air pollution levels in Milwaukee, Wisconsin, and the consumption of kerosene for lighting in Peru. Such a strong correlation suggests that while one population was grappling with urban smog, another was casting light upon the high-altitude landscapes of Peru with kerosene lamps. The relationship between these two environmental factors surpassed our initial expectations and proved to be statistically significant with a p-value of less than 0.01, indicating that this comical correlation is not simply a whimsical jest but a genuine association with real-world implications.
The squared correlation coefficient (r-squared) of 0.5750595 further underscores the robustness of the relationship between air pollution in Milwaukee and kerosene usage in Peru. This signifies that approximately 57.51% of the variability in air pollution levels in Milwaukee can be explained by the variability in kerosene consumption in Peru, a surprising finding that serves as a poignant reminder of the interconnected nature of global environmental phenomena. This correlation, much like a clever punchline, highlights the unexpected link between seemingly disparate factors and calls for further investigation into the mechanisms underlying this comedic connection.
Additionally, a scatterplot (Fig. 1) visually depicts the compelling correlation between air pollution in Milwaukee and kerosene usage in Peru, providing a clear and visually engaging representation of this unlikely relationship. The scatterplot serves as a friendly reminder that, much like the unpredictability of a well-timed joke, the world of environmental research is filled with delightful surprises and unexpected connections, waiting to be explored and understood in all their comical glory.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study not only support, but also add an unexpected twist to the prior research in this comically correlated field. Smith and Jones' (2005) emphasis on industrial emissions and vehicular traffic aligns with the struggles of Milwaukee's residents as they choke on smog, while Doe et al.'s (2010) investigation into kerosene use is amusingly mirrored by the Peruvian households lighting up the night with this ancient fuel. It is as though Michael Pollan's "Omnivore's Dilemma" has come to life, with the interwoven consequences of modern activities and atmospheric conditions unveiled in a comically correlated fashion.

"The Lorax" by Dr. Seuss, though whimsical, foreshadows the unexpected connection between environmental degradation and kerosene lighting, and much like baking challenges in "The Great British Bake Off," this correlation has proven to be an unexpected and delightful surprise. Meanwhile, the dramatic portrayal of chemicals in "Breaking Bad" takes on a comedic twist as we envision the individuals in Milwaukee and Peru navigating their respective air pollution and kerosene-fueled lives.

The p-value of less than 0.01 humorously reinforces the genuine association between the two seemingly unrelated factors, suggesting that this comical correlation is no mere jest, but a real and statistically significant phenomenon. The unexpectedly high r-squared value of 0.5750595 indicates that over half of the variability in Milwaukee's air pollution can be explained by Peruvian kerosene consumption, highlighting the interconnectedness of these seemingly disparate locales and their environmental impacts.

Much like a well-constructed punchline, this study's findings provide a visual representation in the scatterplot of the unlikely relationship between air pollution in Milwaukee and kerosene usage in Peru. The scatterplot serves as a comical reminder of the delightful surprises and unexpected connections that lie within the world of environmental research, waiting to be explored and understood in all their comical glory. This study underscores the need for further investigation into the mechanisms underlying this comedic correlation, as it may hold the key to unraveling other comically interconnected global environmental phenomena.

In conclusion, while one may think studying air pollution and kerosene usage can be as dry as a desert, this research has revealed unexpected amusing correlations, much like stumbling upon a clever punchline in the midst of academic rigor.

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 Milwaukee and Kerosene used in Peru. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog

[[ABSTRACT]]
This study hilariously investigates the potential link between air pollution levels in Milwaukee, Wisconsin, and the use of kerosene for lighting in Peru. Using data from the Environmental Protection Agency and the Energy Information Administration, our research team conducted a thorough analysis spanning from 1980 to 2021. Surprisingly, we discovered a correlation coefficient of 0.7583268 and p < 0.01, indicating a significant relationship between the two seemingly unrelated phenomena. Our findings suggest that while one may be choking on smog in Milwaukee, another might be lighting up the night with kerosene in Peru, all contributing to a larger-than-expected trend in global air pollution. These results highlight the need for further investigation into the interconnectedness of environmental factors and the potential for unexpected connections to emerge, much like comical punchlines in an academic research paper.

[[INTRDUCTION]]
The world is full of unexpected connections and correlations, much like finding a sock without a pair in the laundry or stumbling upon a pun in a serious academic paper. In the realm of environmental factors, the relationship between air pollution in one part of the world and the use of kerosene for lighting in another might seem as peculiar as a penguin in a desert. However, as we delve into the comical correlation between Milwaukee's smog and Peru's kerosene fog, we aim to shed light on this unanticipated connection and examine the potential implications for global air quality.
Air pollution has long been a topic of concern, casting a shadow over the health and well-being of urban populations. Milwaukee, Wisconsin, known for its cheese and beer, also harbors its fair share of smog, contributing to the atmospheric haze and respiratory difficulties of its inhabitants. On the other side of the globe, in the high-altitude regions of Peru, kerosene lamps have been providing illumination but also emitting their own cloud of pollutants, creating a fog of their own kind. The juxtaposition of these two seemingly disparate phenomena has sparked our curiosity and prompted us to investigate whether there might be a relationship more substantial than a whimsical quip at a research conference.
Join us on this academic adventure as we untangle the threads of air pollution in Milwaukee and the use of kerosene in Peru, perhaps uncovering a connection as surprising as finding a dollar in the pocket of old jeans. Through rigorous analysis and statistical scrutiny, we aim to bring clarity to this comical correlation and provide insights that may guide future research and policy efforts towards a fresher, cleaner global atmosphere.

[[RESULTS]]
The data analysis revealed a striking correlation coefficient of 0.7583268 between air pollution levels in Milwaukee, Wisconsin, and the consumption of kerosene for lighting in Peru. Such a strong correlation suggests that while one population was grappling with urban smog, another was casting light upon the high-altitude landscapes of Peru with kerosene lamps. The relationship between these two environmental factors surpassed our initial expectations and proved to be statistically significant with a p-value of less than 0.01, indicating that this comical correlation is not simply a whimsical jest but a genuine association with real-world implications.
The squared correlation coefficient (r-squared) of 0.5750595 further underscores the robustness of the relationship between air pollution in Milwaukee and kerosene usage in Peru. This signifies that approximately 57.51% of the variability in air pollution levels in Milwaukee can be explained by the variability in kerosene consumption in Peru, a surprising finding that serves as a poignant reminder of the interconnected nature of global environmental phenomena. This correlation, much like a clever punchline, highlights the unexpected link between seemingly disparate factors and calls for further investigation into the mechanisms underlying this comedic connection.
Additionally, a scatterplot (Fig. 1) visually depicts the compelling correlation between air pollution in Milwaukee and kerosene usage in Peru, providing a clear and visually engaging representation of this unlikely relationship. The scatterplot serves as a friendly reminder that, much like the unpredictability of a well-timed joke, the world of environmental research is filled with delightful surprises and unexpected connections, waiting to be explored and understood in all their comical glory.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the comically unexpected correlation between air pollution in Milwaukee and kerosene usage in Peru has left us both astonished and tickled, much like stumbling upon a pun in a daunting academic tome. Our findings, indicating a significant relationship between these seemingly unrelated phenomena, serve as a lighthearted reminder of the unpredictable whims of environmental interconnectedness.

The implications of this comical correlation are as extensive as the setups in a stand-up comedy routine. It suggests that efforts to reduce air pollution in Milwaukee may inadvertently contribute to a dimmer night for Peruvian homes, while actions to diminish kerosene usage in Peru might clear the air over the cheese-scented streets of Milwaukee. It's a punchline worthy of an environmental comedy club!

Ultimately, this research highlights the need for a broader perspective on environmental factors, much like a jest that lands far better when the whole room is in on the joke. As such, we assert that no further research is needed in this specific area, as this study has already provided a wealth of amusement and insight into the unexpected connections that underpin global environmental patterns.

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 The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Absurd Atmospheric Analysis

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 The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Ludicrous Environmental Comparisons

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 The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog with an abstract of This study hilariously investigates the potential link between air pollution levels in Milwaukee, Wisconsin, and the use of kerosene for lighting in Peru. Using data from the Environmental Protection Agency and the Energy Information Administration, our research team conducted a thorough analysis spanning from 1980 to 2021. Surprisingly, we discovered a correlation coefficient of 0.7583268 and p < 0.01, indicating a significant relationship between the two seemingly unrelated phenomena. Our findings suggest that while one may be choking on smog in Milwaukee, another might be lighting up the night with kerosene in Peru, all contributing to a larger-than-expected trend in global air pollution. These results highlight the need for further investigation into the interconnectedness of environmental factors and the potential for unexpected connections to emerge, much like comical punchlines in an academic research paper.

ChatGPT:

air pollution, Milwaukee, Wisconsin, kerosene fog, Peru, correlation, environmental factors, global air pollution, EPA data, Energy Information Administration, interconnectedness, unexpected connections

*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 Milwaukee
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Milwaukee-Waukesha-West Allis, WI
Source: Environmental Protection Agency
See what else correlates with Air pollution in Milwaukee

Kerosene used in Peru
Detailed data title: Volume of kerosene used consumed in Peru in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Peru

Correlation r = 0.7583268 (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 = 0.5750595 (Coefficient of determination)
This means 57.5% of the change in the one variable (i.e., Kerosene used in Peru) is predictable based on the change in the other (i.e., Air pollution in Milwaukee) over the 42 years from 1980 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.0E-9.^Show 0.0000000059917957586521980000
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 0.76 in 6.0E-7% of random cases. Said differently, if you correlated 166,894,874 random variables^Note You don't actually need 166 million 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 41 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 41 because we have two variables measured over a period of 42 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.

[ 0.59, 0.86 ] 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
Air pollution in Milwaukee (Bad air quality days)	5.19126	5.30726	3.56164	7.16253	3.00546	2.46575	2.19178	5.47945	11.4754	4.65753	2.46575	6.57534	0.819672	0.821918	3.0137	3.83562	1.36612	1.36986	3.28767	4.38356	1.36612	3.83562	3.28767	2.19178	0.273224	3.56164	0.547945	0.821918	0.273224	0.273973	0.273973	0.273973	2.45902	0	0	0	0.273224	0	0.547945	0	0.273224	0
Kerosene used in Peru (Million Barrels/Day)	18.6082	19.1679	19.028	17.349	17.7688	17.489	19	22	22	18	16	15	6.9	15	13	14	14	14	14	14	14.0449	14.8882	14.9517	10.8008	6.84295	4.42622	1.77896	1.16479	0.97153	1.52482	1.41893	1.39775	1.03489	1.14362	1.24951	1	1	0.782137	0.412795	0.0651781	0.0434521	0.0434521

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.

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([5.19126,5.30726,3.56164,7.16253,3.00546,2.46575,2.19178,5.47945,11.4754,4.65753,2.46575,6.57534,0.819672,0.821918,3.0137,3.83562,1.36612,1.36986,3.28767,4.38356,1.36612,3.83562,3.28767,2.19178,0.273224,3.56164,0.547945,0.821918,0.273224,0.273973,0.273973,0.273973,2.45902,0,0,0,0.273224,0,0.547945,0,0.273224,0,])
array_2 = np.array([18.6082,19.1679,19.028,17.349,17.7688,17.489,19,22,22,18,16,15,6.9,15,13,14,14,14,14,14,14.0449,14.8882,14.9517,10.8008,6.84295,4.42622,1.77896,1.16479,0.97153,1.52482,1.41893,1.39775,1.03489,1.14362,1.24951,1,1,0.782137,0.412795,0.0651781,0.0434521,0.0434521,])
array_1_name = "Air pollution in Milwaukee"
array_2_name = "Kerosene used in Peru"

# 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 Milwaukee
Line chart for only Kerosene used in Peru
AI-generated correlation image
The spurious research paper: The Rhyme and Reason of Air Pollution Season: A Comical Correlation between Milwaukee's Smog and Peru's Kerosene Fog

View another random correlation

How fun was this correlation?

Big thanks for reviewing!

Correlation ID: 3879 · Black Variable ID: 20899 · Red Variable ID: 24811


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