about · email me · subscribe
Spurious correlation #3,513 · 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 Memphis 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. Small Image
Download png
, svg

AI explanation

A team of highly trained pigeons was deployed to Memphis to combat air pollution by strategically dropping tiny kerosene-absorbing sponges from the sky. Unbeknownst to them, their efforts were so successful that the kerosene molecules, now weighed down by the sponges, decided to take an extended vacation to Peru for some much-needed R&R, leading to a noticeable decrease in kerosene levels. It seems even molecules need a break every now and then! On a serious note, decreased air pollution in Memphis may have indirectly impacted kerosene usage in Peru through a variety of complex environmental and economic factors.

Model: dalle-3
Prompt: Generate an image of a Discovery magazine cover that portrays a serene scene of Memphis with clear skies and reduced factory emissions. Meanwhile, illustrate a contrasting yet heartwarming image of families gathered around a softly lit table in Peru, indicating the decrease in the use of kerosene lamps. Let the cover convey the message of positive environmental changes and improved living conditions through simple, yet impactful, visual storytelling. 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 Memphis 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: Macabre A Discovery magazine cover image a Polaroid photo a funny image macro Futuristic
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 Air pollution in Memphis and Kerosene used in Peru, in the following situation: The decrease in air pollution in Memphis caused kerosene used in Peru to decrease because cleaner air means less need for "burning the midnight oil." With fresher air, Peruvians are feeling more energized and don't need to rely on kerosene for their lamps as much.. Keep the description simple.
ChatGPT: In Memphis, the sky is clear with fewer factory emissions, while in Peru, families are gathered around a warm, softly lit table, as the need for kerosene lamps has decreased.

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 Memphis, the sky is clear with fewer factory emissions, while in Peru, families are gathered around a warm, softly lit table, as the need for kerosene lamps has decreased. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a Discovery magazine cover that portrays a serene scene of Memphis with clear skies and reduced factory emissions. Meanwhile, illustrate a contrasting yet heartwarming image of families gathered around a softly lit table in Peru, indicating the decrease in the use of kerosene lamps. Let the cover convey the message of positive environmental changes and improved living conditions through simple, yet impactful, visual storytelling.

*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.

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

AI academic paper

(Because p < 0.01)
A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey

Journal of Quirky Atmospheric Phenomena

Jan 2024

Reminder: This paper is AI-generated. Not real!
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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.You write titles and abstracts of goofy academic research papers.
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, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air pollution in Memphis and Kerosene used in Peru. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Rhyme words in the title.

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.7342996 and p < 0.01 for 1980 to 2021.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey

[[ABSTRACT]]
A burning question in the realm of environmental research is the potential connection between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru. This study delves into the statistical relationship between these seemingly disparate phenomena and presents some illuminating findings. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, we examined air quality indicators in Memphis and kerosene consumption patterns in Peru from 1980 to 2021.

Our analysis revealed a surprising correlation coefficient of 0.7342996 and a statistically significant p-value of less than 0.01, suggesting a notable association between air pollution in Memphis and kerosene usage in Peru. This unexpected linkage left us both breathless and enlightened. Upon further investigation, it seems that the fumes from kerosene lamps in Peru may be traveling across the globe to influence air quality in Memphis, creating a truly global connection that is nothing short of breathtaking.

We hope this research sheds light on the interconnectedness of environmental factors across different regions, and may spark further inquiries into the global impact of seemingly local practices. As for the dad joke – Did you hear about the kerosene that went to Peru? It had a *lit* time!


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the introduction 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 introduction section of an academic research paper presenting the findings of the connection between Air pollution in Memphis and Kerosene used in Peru. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey

[[ABSTRACT]]
A burning question in the realm of environmental research is the potential connection between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru. This study delves into the statistical relationship between these seemingly disparate phenomena and presents some illuminating findings. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, we examined air quality indicators in Memphis and kerosene consumption patterns in Peru from 1980 to 2021.

Our analysis revealed a surprising correlation coefficient of 0.7342996 and a statistically significant p-value of less than 0.01, suggesting a notable association between air pollution in Memphis and kerosene usage in Peru. This unexpected linkage left us both breathless and enlightened. Upon further investigation, it seems that the fumes from kerosene lamps in Peru may be traveling across the globe to influence air quality in Memphis, creating a truly global connection that is nothing short of breathtaking.

We hope this research sheds light on the interconnectedness of environmental factors across different regions, and may spark further inquiries into the global impact of seemingly local practices. As for the dad joke – Did you hear about the kerosene that went to Peru? It had a *lit* time!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In recent years, the interplay between seemingly disparate environmental factors has piqued the interest of researchers and policymakers alike. One such intriguing connection that has garnered attention is the potential link between air pollution in Memphis, Tennessee, and the utilization of kerosene for household lighting in Peru. This unexpected correlation has sparked a statistical odyssey to unravel the mysteries of how the invisible threads of air quality in one location can be intertwined with the flickering flames of kerosene lamps in a distant land.

This study aims to shed light on this enigmatic relationship by employing rigorous statistical analyses and delving into the depths of environmental data. Our goal is to illuminate the potential influence of kerosene usage in Peru on the air quality in Memphis, and perhaps uncover avenues for mitigating these impacts. As we embark on this statistical journey, we must emphasize the gravity of the matter – both figuratively and statistically.

The statistical association uncovered between air pollution in Memphis and kerosene usage in Peru prompts a reevaluation of the interconnectedness of global environmental influences. This unexpected correlation serves as a wake-up call to the ways in which local practices can have far-reaching effects, akin to the way a joke about kerosene might *ignite* laughter miles away.

As we delve further into our findings, the statistical insights garnered from this research promise to cast a beacon of light on the broader implications of intercontinental environmental interdependence. We hope this study will not only illuminate the statistical relationship between these two seemingly unrelated phenomena but also provide a foundational basis for future inquiries into the global impact of localized environmental practices. In the spirit of shedding light on this statistical odyssey, let us remember that even the most unexpected connections can have a profound impact, much like a well-timed dad joke. Speaking of which, did you hear about the statistician who thought kerosene usage in Peru wouldn't correlate with air pollution in Memphis? He really missed the *spark* of the matter!


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Memphis and Kerosene used in Peru. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey

[[ABSTRACT]]
A burning question in the realm of environmental research is the potential connection between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru. This study delves into the statistical relationship between these seemingly disparate phenomena and presents some illuminating findings. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, we examined air quality indicators in Memphis and kerosene consumption patterns in Peru from 1980 to 2021.

Our analysis revealed a surprising correlation coefficient of 0.7342996 and a statistically significant p-value of less than 0.01, suggesting a notable association between air pollution in Memphis and kerosene usage in Peru. This unexpected linkage left us both breathless and enlightened. Upon further investigation, it seems that the fumes from kerosene lamps in Peru may be traveling across the globe to influence air quality in Memphis, creating a truly global connection that is nothing short of breathtaking.

We hope this research sheds light on the interconnectedness of environmental factors across different regions, and may spark further inquiries into the global impact of seemingly local practices. As for the dad joke – Did you hear about the kerosene that went to Peru? It had a *lit* time!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In recent years, the interplay between seemingly disparate environmental factors has piqued the interest of researchers and policymakers alike. One such intriguing connection that has garnered attention is the potential link between air pollution in Memphis, Tennessee, and the utilization of kerosene for household lighting in Peru. This unexpected correlation has sparked a statistical odyssey to unravel the mysteries of how the invisible threads of air quality in one location can be intertwined with the flickering flames of kerosene lamps in a distant land.
This study aims to shed light on this enigmatic relationship by employing rigorous statistical analyses and delving into the depths of environmental data. Our goal is to illuminate the potential influence of kerosene usage in Peru on the air quality in Memphis, and perhaps uncover avenues for mitigating these impacts. As we embark on this statistical journey, we must emphasize the gravity of the matter – both figuratively and statistically.
The statistical association uncovered between air pollution in Memphis and kerosene usage in Peru prompts a reevaluation of the interconnectedness of global environmental influences. This unexpected correlation serves as a wake-up call to the ways in which local practices can have far-reaching effects, akin to the way a joke about kerosene might *ignite* laughter miles away.
As we delve further into our findings, the statistical insights garnered from this research promise to cast a beacon of light on the broader implications of intercontinental environmental interdependence. We hope this study will not only illuminate the statistical relationship between these two seemingly unrelated phenomena but also provide a foundational basis for future inquiries into the global impact of localized environmental practices. In the spirit of shedding light on this statistical odyssey, let us remember that even the most unexpected connections can have a profound impact, much like a well-timed dad joke. Speaking of which, did you hear about the statistician who thought kerosene usage in Peru wouldn't correlate with air pollution in Memphis? He really missed the *spark* of the matter!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Numerous studies have explored the environmental implications of air pollution and household fuel use, offering valuable insights into their individual impacts. Smith and Doe (2018) investigated the alarming trends of air pollution in urban areas, with a focus on Memphis, Tennessee, while Jones et al. (2020) delved into the nuanced dynamics of kerosene usage in developing regions such as Peru. These serious and reputable studies laid the groundwork for our statistical odyssey, guiding our exploration of the potential linkage between these seemingly disparate phenomena.

However, as we transition into less conventional scholarly works, it is essential to acknowledge the influence of broader literature on environmental interconnectedness. "The Air We Breathe: A Comprehensive Analysis" by Environmental Research Institute provides a comprehensive overview of air quality assessment methodologies, offering a breath of fresh air in the field of environmental research. On the other hand, "Kerosene Illuminations: Cultural and Practical Dimensions" by Energy Dynamics Foundation sheds light on the cultural and practical aspects of kerosene usage, illuminating the multifaceted nature of household fuel practices.

Venturing into more unconventional sources, we encounter "The Great Peruvian Adventure" by A. Lamp, which, although a work of fiction, tantalizingly explores the adventures of a kerosene lamp in rural Peru. Furthermore, "Memphis Mysteries: Air Alchemy" by S. Smog ventures into a fictional realm where air pollution takes on mystical properties, offering an imaginative take on the airborne phenomena in Memphis.

Delving deeper into unexpected connections, the children's show "Dora the Explorer" makes a surprising appearance. In an episode titled "Dora's Environmental Expedition," Dora and Boots learn about air pollution and alternative fuel sources through a whimsical adventure in Memphis, inadvertently stumbling upon a kerosene lamp that hails from Peru. Additionally, the animated series "The Magic School Bus" collaborates with environmental experts to investigate the intercontinental journey of air pollutants and the surprising influence of kerosene emissions on global air quality.

Clearly, the landscape of literature surrounding air pollution in Memphis and kerosene usage in Peru is as varied and seemingly interconnected as the phenomena themselves. As we navigate this amalgam of scholarly works, fictional narratives, and children's media, one can't help but appreciate the unexpected twists and turns that this statistical odyssey has taken. Harkening back to our scholarly pursuits, one is reminded of the gravity and levity with which we approach this research endeavor - much like a well-placed dad joke. Speaking of which, did you hear about the statistician who tried to analyze the correlation between air pollution in Memphis and kerosene usage in Peru? He had to *clear the air* to make sense of the unexpected statistical connection!


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Memphis and Kerosene used in Peru. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey

[[ABSTRACT]]
A burning question in the realm of environmental research is the potential connection between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru. This study delves into the statistical relationship between these seemingly disparate phenomena and presents some illuminating findings. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, we examined air quality indicators in Memphis and kerosene consumption patterns in Peru from 1980 to 2021.

Our analysis revealed a surprising correlation coefficient of 0.7342996 and a statistically significant p-value of less than 0.01, suggesting a notable association between air pollution in Memphis and kerosene usage in Peru. This unexpected linkage left us both breathless and enlightened. Upon further investigation, it seems that the fumes from kerosene lamps in Peru may be traveling across the globe to influence air quality in Memphis, creating a truly global connection that is nothing short of breathtaking.

We hope this research sheds light on the interconnectedness of environmental factors across different regions, and may spark further inquiries into the global impact of seemingly local practices. As for the dad joke – Did you hear about the kerosene that went to Peru? It had a *lit* time!

[[INTRODUCTION]]
In recent years, the interplay between seemingly disparate environmental factors has piqued the interest of researchers and policymakers alike. One such intriguing connection that has garnered attention is the potential link between air pollution in Memphis, Tennessee, and the utilization of kerosene for household lighting in Peru. This unexpected correlation has sparked a statistical odyssey to unravel the mysteries of how the invisible threads of air quality in one location can be intertwined with the flickering flames of kerosene lamps in a distant land.
This study aims to shed light on this enigmatic relationship by employing rigorous statistical analyses and delving into the depths of environmental data. Our goal is to illuminate the potential influence of kerosene usage in Peru on the air quality in Memphis, and perhaps uncover avenues for mitigating these impacts. As we embark on this statistical journey, we must emphasize the gravity of the matter – both figuratively and statistically.
The statistical association uncovered between air pollution in Memphis and kerosene usage in Peru prompts a reevaluation of the interconnectedness of global environmental influences. This unexpected correlation serves as a wake-up call to the ways in which local practices can have far-reaching effects, akin to the way a joke about kerosene might *ignite* laughter miles away.
As we delve further into our findings, the statistical insights garnered from this research promise to cast a beacon of light on the broader implications of intercontinental environmental interdependence. We hope this study will not only illuminate the statistical relationship between these two seemingly unrelated phenomena but also provide a foundational basis for future inquiries into the global impact of localized environmental practices. In the spirit of shedding light on this statistical odyssey, let us remember that even the most unexpected connections can have a profound impact, much like a well-timed dad joke. Speaking of which, did you hear about the statistician who thought kerosene usage in Peru wouldn't correlate with air pollution in Memphis? He really missed the *spark* of the matter!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To embark on our statistical odyssey, we began by acquiring data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), as if we were on an expedition to gather the rarest of statistical artifacts. These data sources provided us with a treasure trove of information spanning from 1980 to 2021, allowing us to peer through the statistical looking glass and delve into the intricate relationship between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru.

Our team of intrepid researchers meticulously conducted data cleaning and transformation, akin to the careful preparation required before setting sail into uncharted statistical waters. This involved wrangling and harmonizing disparate datasets to ensure they were fit for statistical analysis, like taming wild statistical beasts to reveal their underlying patterns and associations. We then performed a series of statistical tests and analyses reminiscent of navigating through statistical mazes with nothing more than a proverbial compass and a keen eye for hidden correlations.

To examine the potential link between air pollution in Memphis and kerosene usage in Peru, we employed various statistical techniques, including bivariate correlation analysis, regression modeling, and time series analysis. Just as an archaeologist carefully brushes away layers of sediment to unveil ancient artifacts, we meticulously sifted through the statistical data to reveal the potential connections between these seemingly disparate environmental factors.

Furthermore, we utilized advanced statistical software, including but not limited to R, Python, and SPSS, to conduct our analyses with precision and rigor. This ensured that our statistical voyage was guided by the latest and most robust tools available, akin to setting sail with a state-of-the-art navigational system to navigate the choppy statistical seas.

As a final step, we subjected our statistical findings to rigorous sensitivity analyses and robustness checks, akin to stress-testing the hull of a statistical ship to ensure its seaworthiness in the face of potential data anomalies and outliers.

Now, as we present our statistical findings, let us remember the age-old statistical adage: "Correlation does not imply causation, but it does waggle its eyebrows suggestively and gesture furtively." The statistical odyssey we embarked on has not only revealed compelling insights but has also underscored the unpredictability and interconnectedness of environmental phenomena across the globe. This serves as a poignant reminder that even the most inconspicuous statistical relationships can *fuel* further inquiry and spark innovative solutions. Speaking of which, did you hear about the statistician who tried to light a lamp with kerosene data? He had a *bright* idea but was cautioned about the potential for statistical significance to go up in *smoke*!


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Memphis and Kerosene used in Peru. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 0.7342996, r-squared of 0.5391960, 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]]
A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey

[[ABSTRACT]]
A burning question in the realm of environmental research is the potential connection between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru. This study delves into the statistical relationship between these seemingly disparate phenomena and presents some illuminating findings. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, we examined air quality indicators in Memphis and kerosene consumption patterns in Peru from 1980 to 2021.

Our analysis revealed a surprising correlation coefficient of 0.7342996 and a statistically significant p-value of less than 0.01, suggesting a notable association between air pollution in Memphis and kerosene usage in Peru. This unexpected linkage left us both breathless and enlightened. Upon further investigation, it seems that the fumes from kerosene lamps in Peru may be traveling across the globe to influence air quality in Memphis, creating a truly global connection that is nothing short of breathtaking.

We hope this research sheds light on the interconnectedness of environmental factors across different regions, and may spark further inquiries into the global impact of seemingly local practices. As for the dad joke – Did you hear about the kerosene that went to Peru? It had a *lit* time!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In recent years, the interplay between seemingly disparate environmental factors has piqued the interest of researchers and policymakers alike. One such intriguing connection that has garnered attention is the potential link between air pollution in Memphis, Tennessee, and the utilization of kerosene for household lighting in Peru. This unexpected correlation has sparked a statistical odyssey to unravel the mysteries of how the invisible threads of air quality in one location can be intertwined with the flickering flames of kerosene lamps in a distant land.
This study aims to shed light on this enigmatic relationship by employing rigorous statistical analyses and delving into the depths of environmental data. Our goal is to illuminate the potential influence of kerosene usage in Peru on the air quality in Memphis, and perhaps uncover avenues for mitigating these impacts. As we embark on this statistical journey, we must emphasize the gravity of the matter – both figuratively and statistically.
The statistical association uncovered between air pollution in Memphis and kerosene usage in Peru prompts a reevaluation of the interconnectedness of global environmental influences. This unexpected correlation serves as a wake-up call to the ways in which local practices can have far-reaching effects, akin to the way a joke about kerosene might *ignite* laughter miles away.
As we delve further into our findings, the statistical insights garnered from this research promise to cast a beacon of light on the broader implications of intercontinental environmental interdependence. We hope this study will not only illuminate the statistical relationship between these two seemingly unrelated phenomena but also provide a foundational basis for future inquiries into the global impact of localized environmental practices. In the spirit of shedding light on this statistical odyssey, let us remember that even the most unexpected connections can have a profound impact, much like a well-timed dad joke. Speaking of which, did you hear about the statistician who thought kerosene usage in Peru wouldn't correlate with air pollution in Memphis? He really missed the *spark* of the matter!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data collected from the Environmental Protection Agency and the Energy Information Administration revealed a notable correlation between air pollution in Memphis and kerosene usage in Peru. The correlation coefficient of 0.7342996 indicates a strong positive relationship between these variables, suggesting that as kerosene usage in Peru increases, air pollution in Memphis tends to follow suit. This unexpected finding truly shines a light on the interconnectedness of seemingly unrelated environmental factors.

The statistically significant p-value of less than 0.01 further supports the observed association, indicating that the likelihood of this correlation occurring purely by chance is extremely low. One might say the odds of this connection being a mere coincidence are as slim as a single hair in a kerosene lamp. *Cue groans*.

The r-squared value of 0.5391960 suggests that approximately 53.92% of the variability in air pollution levels in Memphis can be explained by the variability in kerosene usage in Peru. This statistic reinforces the strength of the relationship between these two factors and underscores the impact of kerosene consumption in Peru on air quality in Memphis.

As promised, the scatterplot (Fig. 1) provides a visual representation of the strong correlation between air pollution in Memphis and kerosene usage in Peru. The plot demonstrates a clear trend, with increasing kerosene usage coinciding with higher levels of air pollution in Memphis. It's as clear as the soot from a kerosene lamp – there's definitely something in the air, and it's not just carbon dioxide!

This statistical evidence not only bolsters our understanding of the interconnectedness of environmental factors across different regions but also raises intriguing questions about the potential global ramifications of seemingly local practices. Let's hope the impact of this research is felt as far and wide as the fumes from a kerosene lamp in Peru. Speaking of which, did you hear about the statistician who loved kerosene lamps? He really knew how to *light up* a room!


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Memphis and Kerosene used in Peru. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey

[[ABSTRACT]]
A burning question in the realm of environmental research is the potential connection between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru. This study delves into the statistical relationship between these seemingly disparate phenomena and presents some illuminating findings. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, we examined air quality indicators in Memphis and kerosene consumption patterns in Peru from 1980 to 2021.

Our analysis revealed a surprising correlation coefficient of 0.7342996 and a statistically significant p-value of less than 0.01, suggesting a notable association between air pollution in Memphis and kerosene usage in Peru. This unexpected linkage left us both breathless and enlightened. Upon further investigation, it seems that the fumes from kerosene lamps in Peru may be traveling across the globe to influence air quality in Memphis, creating a truly global connection that is nothing short of breathtaking.

We hope this research sheds light on the interconnectedness of environmental factors across different regions, and may spark further inquiries into the global impact of seemingly local practices. As for the dad joke – Did you hear about the kerosene that went to Peru? It had a *lit* time!

[[LITERATURE REVIEW]]
Numerous studies have explored the environmental implications of air pollution and household fuel use, offering valuable insights into their individual impacts. Smith and Doe (2018) investigated the alarming trends of air pollution in urban areas, with a focus on Memphis, Tennessee, while Jones et al. (2020) delved into the nuanced dynamics of kerosene usage in developing regions such as Peru. These serious and reputable studies laid the groundwork for our statistical odyssey, guiding our exploration of the potential linkage between these seemingly disparate phenomena.
However, as we transition into less conventional scholarly works, it is essential to acknowledge the influence of broader literature on environmental interconnectedness. "The Air We Breathe: A Comprehensive Analysis" by Environmental Research Institute provides a comprehensive overview of air quality assessment methodologies, offering a breath of fresh air in the field of environmental research. On the other hand, "Kerosene Illuminations: Cultural and Practical Dimensions" by Energy Dynamics Foundation sheds light on the cultural and practical aspects of kerosene usage, illuminating the multifaceted nature of household fuel practices.
Venturing into more unconventional sources, we encounter "The Great Peruvian Adventure" by A. Lamp, which, although a work of fiction, tantalizingly explores the adventures of a kerosene lamp in rural Peru. Furthermore, "Memphis Mysteries: Air Alchemy" by S. Smog ventures into a fictional realm where air pollution takes on mystical properties, offering an imaginative take on the airborne phenomena in Memphis.
Delving deeper into unexpected connections, the children's show "Dora the Explorer" makes a surprising appearance. In an episode titled "Dora's Environmental Expedition," Dora and Boots learn about air pollution and alternative fuel sources through a whimsical adventure in Memphis, inadvertently stumbling upon a kerosene lamp that hails from Peru. Additionally, the animated series "The Magic School Bus" collaborates with environmental experts to investigate the intercontinental journey of air pollutants and the surprising influence of kerosene emissions on global air quality.
Clearly, the landscape of literature surrounding air pollution in Memphis and kerosene usage in Peru is as varied and seemingly interconnected as the phenomena themselves. As we navigate this amalgam of scholarly works, fictional narratives, and children's media, one can't help but appreciate the unexpected twists and turns that this statistical odyssey has taken. Harkening back to our scholarly pursuits, one is reminded of the gravity and levity with which we approach this research endeavor - much like a well-placed dad joke. Speaking of which, did you hear about the statistician who tried to analyze the correlation between air pollution in Memphis and kerosene usage in Peru? He had to *clear the air* to make sense of the unexpected statistical connection!

[[RESULTS]]
The analysis of the data collected from the Environmental Protection Agency and the Energy Information Administration revealed a notable correlation between air pollution in Memphis and kerosene usage in Peru. The correlation coefficient of 0.7342996 indicates a strong positive relationship between these variables, suggesting that as kerosene usage in Peru increases, air pollution in Memphis tends to follow suit. This unexpected finding truly shines a light on the interconnectedness of seemingly unrelated environmental factors.
The statistically significant p-value of less than 0.01 further supports the observed association, indicating that the likelihood of this correlation occurring purely by chance is extremely low. One might say the odds of this connection being a mere coincidence are as slim as a single hair in a kerosene lamp. *Cue groans*.
The r-squared value of 0.5391960 suggests that approximately 53.92% of the variability in air pollution levels in Memphis can be explained by the variability in kerosene usage in Peru. This statistic reinforces the strength of the relationship between these two factors and underscores the impact of kerosene consumption in Peru on air quality in Memphis.
As promised, the scatterplot (Fig. 1) provides a visual representation of the strong correlation between air pollution in Memphis and kerosene usage in Peru. The plot demonstrates a clear trend, with increasing kerosene usage coinciding with higher levels of air pollution in Memphis. It's as clear as the soot from a kerosene lamp – there's definitely something in the air, and it's not just carbon dioxide!
This statistical evidence not only bolsters our understanding of the interconnectedness of environmental factors across different regions but also raises intriguing questions about the potential global ramifications of seemingly local practices. Let's hope the impact of this research is felt as far and wide as the fumes from a kerosene lamp in Peru. Speaking of which, did you hear about the statistician who loved kerosene lamps? He really knew how to *light up* a room!

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of this study lend credence to the hypothesis positing a link between air pollution in Memphis and the use of kerosene for household lighting in Peru. The substantial correlation coefficient of 0.7342996 and the statistically significant p-value of less than 0.01 provide compelling evidence for the association between these seemingly unrelated phenomena. This unexpected linkage underscores the interconnectedness of environmental factors across disparate geographical locations and raises intriguing questions about the global reach of local practices.

Our findings align with prior research that has laid the groundwork for understanding the individual impacts of air pollution and household fuel use. Notably, the works of Smith and Doe (2018), which focused on urban air pollution in Memphis, and Jones et al. (2020), which delved into kerosene usage in developing regions such as Peru, have provided valuable insights that are complemented and enriched by our investigation. Moreover, the whimsical narrative explored in "The Great Peruvian Adventure" by A. Lamp, despite being a work of fiction, inexplicably resonates with our statistically grounded findings, shedding light on the potential transcontinental journey of kerosene fumes.

The r-squared value of 0.5391960 indicates that approximately 53.92% of the variability in air pollution levels in Memphis can be attributed to the variability in kerosene usage in Peru. This statistical evidence underscores the substantial influence of kerosene consumption in Peru on the air quality in Memphis, elucidating the magnitude of this unexpected connection.

In addition to affirming the previous literature's implications, our study has unearthed a truly global connection that extends beyond geographic boundaries, as the fumes from kerosene lamps in Peru appear to traverse across the globe to influence air quality in Memphis. This revelation is nothing short of breathtaking and emphasizes the importance of considering the far-reaching consequences of seemingly local practices.

While our research has serious implications for understanding the global impact of environmental phenomena, it also highlights the unexpected twists and turns that statistical inquiry can unveil. This ongoing pursuit of knowledge, much like the journey of a kerosene lamp traveling from Peru to Memphis, has its share of both rigorous analysis and serendipitous discovery. It is in this blend of scientific rigor and unexpected connections that the true beauty of statistical investigation lies. Speaking of unexpected connections, did you hear about the statistician who loved air pollution research? He found it absolutely *breathtaking*!


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Memphis and Kerosene used in Peru. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey

[[ABSTRACT]]
A burning question in the realm of environmental research is the potential connection between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru. This study delves into the statistical relationship between these seemingly disparate phenomena and presents some illuminating findings. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, we examined air quality indicators in Memphis and kerosene consumption patterns in Peru from 1980 to 2021.

Our analysis revealed a surprising correlation coefficient of 0.7342996 and a statistically significant p-value of less than 0.01, suggesting a notable association between air pollution in Memphis and kerosene usage in Peru. This unexpected linkage left us both breathless and enlightened. Upon further investigation, it seems that the fumes from kerosene lamps in Peru may be traveling across the globe to influence air quality in Memphis, creating a truly global connection that is nothing short of breathtaking.

We hope this research sheds light on the interconnectedness of environmental factors across different regions, and may spark further inquiries into the global impact of seemingly local practices. As for the dad joke – Did you hear about the kerosene that went to Peru? It had a *lit* time!

[[INTRDUCTION]]
In recent years, the interplay between seemingly disparate environmental factors has piqued the interest of researchers and policymakers alike. One such intriguing connection that has garnered attention is the potential link between air pollution in Memphis, Tennessee, and the utilization of kerosene for household lighting in Peru. This unexpected correlation has sparked a statistical odyssey to unravel the mysteries of how the invisible threads of air quality in one location can be intertwined with the flickering flames of kerosene lamps in a distant land.
This study aims to shed light on this enigmatic relationship by employing rigorous statistical analyses and delving into the depths of environmental data. Our goal is to illuminate the potential influence of kerosene usage in Peru on the air quality in Memphis, and perhaps uncover avenues for mitigating these impacts. As we embark on this statistical journey, we must emphasize the gravity of the matter – both figuratively and statistically.
The statistical association uncovered between air pollution in Memphis and kerosene usage in Peru prompts a reevaluation of the interconnectedness of global environmental influences. This unexpected correlation serves as a wake-up call to the ways in which local practices can have far-reaching effects, akin to the way a joke about kerosene might *ignite* laughter miles away.
As we delve further into our findings, the statistical insights garnered from this research promise to cast a beacon of light on the broader implications of intercontinental environmental interdependence. We hope this study will not only illuminate the statistical relationship between these two seemingly unrelated phenomena but also provide a foundational basis for future inquiries into the global impact of localized environmental practices. In the spirit of shedding light on this statistical odyssey, let us remember that even the most unexpected connections can have a profound impact, much like a well-timed dad joke. Speaking of which, did you hear about the statistician who thought kerosene usage in Peru wouldn't correlate with air pollution in Memphis? He really missed the *spark* of the matter!

[[RESULTS]]
The analysis of the data collected from the Environmental Protection Agency and the Energy Information Administration revealed a notable correlation between air pollution in Memphis and kerosene usage in Peru. The correlation coefficient of 0.7342996 indicates a strong positive relationship between these variables, suggesting that as kerosene usage in Peru increases, air pollution in Memphis tends to follow suit. This unexpected finding truly shines a light on the interconnectedness of seemingly unrelated environmental factors.
The statistically significant p-value of less than 0.01 further supports the observed association, indicating that the likelihood of this correlation occurring purely by chance is extremely low. One might say the odds of this connection being a mere coincidence are as slim as a single hair in a kerosene lamp. *Cue groans*.
The r-squared value of 0.5391960 suggests that approximately 53.92% of the variability in air pollution levels in Memphis can be explained by the variability in kerosene usage in Peru. This statistic reinforces the strength of the relationship between these two factors and underscores the impact of kerosene consumption in Peru on air quality in Memphis.
As promised, the scatterplot (Fig. 1) provides a visual representation of the strong correlation between air pollution in Memphis and kerosene usage in Peru. The plot demonstrates a clear trend, with increasing kerosene usage coinciding with higher levels of air pollution in Memphis. It's as clear as the soot from a kerosene lamp – there's definitely something in the air, and it's not just carbon dioxide!
This statistical evidence not only bolsters our understanding of the interconnectedness of environmental factors across different regions but also raises intriguing questions about the potential global ramifications of seemingly local practices. Let's hope the impact of this research is felt as far and wide as the fumes from a kerosene lamp in Peru. Speaking of which, did you hear about the statistician who loved kerosene lamps? He really knew how to *light up* a room!

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our statistical odyssey has led us to uncover a remarkable connection between air pollution in Memphis and kerosene usage in Peru. The strong correlation coefficient and the statistically significant p-value not only illuminate this unexpected linkage but also highlight the far-reaching impacts of seemingly local practices on global environmental phenomena. It's as if the fumes from a kerosene lamp in Peru have taken on a life of their own, embarking on a journey across continents to influence air quality in Memphis. One might say these fumes have truly mastered the art of *air travel*.

The r-squared value further emphasizes the substantial influence of kerosene consumption in Peru on air quality in Memphis, indicating that over half of the variability in air pollution levels can be attributed to variations in kerosene usage. It's like a statistical symphony, with the fluctuations in kerosene consumption composing the melody of Memphis's air quality. Not to mention, the scatterplot provides a clear visual representation of this relationship, demonstrating a trend as unmistakable as the smell of a kerosene lamp on a dark night.

Our findings serve as a clarion call for further exploration of the intricate web of intercontinental environmental interdependence. It seems that what happens in Peru doesn't just stay in Peru – it travels through statistical pathways and exerts its influence on air quality thousands of miles away. However, this also means that our research has shed light on a significant piece of the environmental puzzle. Future studies should continue to explore the global ripple effects of seemingly local practices. At the end of the day, the connection between air pollution in Memphis and kerosene usage in Peru is as real as the groans after a good dad joke.

In light of these findings, we boldly assert that no more research is needed in this area. The statistical evidence stands as solid as a well-built kerosene lamp. It's time to let this statistical odyssey rest and bask in the *glow* of our illuminating discoveries.


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 A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Atmospheric Phenomena


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 A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Enigmatic Atmospheric Phenomena Discovery (SEAPD)


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 A Tale of Air in Memphis and Kerosene in Peru: A Statistical Odyssey with an abstract of A burning question in the realm of environmental research is the potential connection between air pollution in Memphis, Tennessee, and the use of kerosene for household lighting in Peru. This study delves into the statistical relationship between these seemingly disparate phenomena and presents some illuminating findings. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, we examined air quality indicators in Memphis and kerosene consumption patterns in Peru from 1980 to 2021.
Our analysis revealed a surprising correlation coefficient of 0.7342996 and a statistically significant p-value of less than 0.01, suggesting a notable association between air pollution in Memphis and kerosene usage in Peru. This unexpected linkage left us both breathless and enlightened. Upon further investigation, it seems that the fumes from kerosene lamps in Peru may be traveling across the globe to influence air quality in Memphis, creating a truly global connection that is nothing short of breathtaking.
We hope this research sheds light on the interconnectedness of environmental factors across different regions, and may spark further inquiries into the global impact of seemingly local practices. As for the dad joke – Did you hear about the kerosene that went to Peru? It had a *lit* time!

ChatGPT:

air pollution, Memphis, Tennessee, kerosene, household lighting, Peru, statistical analysis, environmental research, correlation coefficient, air quality indicators, kerosene consumption, global impact, environmental factors, interconnectedness

*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 Memphis
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Memphis, TN-MS-AR
Source: Environmental Protection Agency
See what else correlates with Air pollution in Memphis

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 = 0.7342996 (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 = 0.5391960 (Coefficient of determination)
This means 53.9% 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 Memphis) over the 42 years from 1980 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.1E-8. 0.0000000312033950989835240000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. 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 0.73 in 3.1E-6% of random cases. Said differently, if you correlated 32,047,795 random variables You don't actually need 32 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, 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.

[ 0.55, 0.85 ] 95% correlation confidence interval (using the Fisher z-transformation)
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: 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.
198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021
Air pollution in Memphis (Bad air quality days)7.92354.657532.465754.931512.185793.287674.931514.1095911.47541.643845.479452.191783.005463.561642.191784.931514.644814.657537.397269.04116.284153.287674.383562.465750.5464483.561642.191781.369860.81967200.5479451.643842.185790000.2732240.2739730.27397300.2732240
Kerosene used in Peru (Million Barrels/Day)18.608219.167919.02817.34917.768817.4891922221816156.91513141414141414.044914.888214.951710.80086.842954.426221.778961.164790.971531.524821.418931.397751.034891.143621.24951110.7821370.4127950.06517810.04345210.0434521




Why this works

  1. 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.
  2. Lack of causal connection: There is probably 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.
  3. 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 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. 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([7.9235,4.65753,2.46575,4.93151,2.18579,3.28767,4.93151,4.10959,11.4754,1.64384,5.47945,2.19178,3.00546,3.56164,2.19178,4.93151,4.64481,4.65753,7.39726,9.0411,6.28415,3.28767,4.38356,2.46575,0.546448,3.56164,2.19178,1.36986,0.819672,0,0.547945,1.64384,2.18579,0,0,0,0.273224,0.273973,0.273973,0,0.273224,0,])
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 Memphis"
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. 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:


View another random correlation

How fun was this correlation?

Big thanks for reviewing!


Correlation ID: 3513 · Black Variable ID: 20884 · Red Variable ID: 24811
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0