about · email me · subscribe
Spurious correlation #5,258 · 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 Ponce, Puerto Rico and the second variable is Kerosene used in Germany, West.  The chart goes from 1982 to 1990, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The cleaner air in Ponce, Puerto Rico led to an increase in butterfly population. These butterflies, known for their sophisticated migration patterns, altered their flight route, inadvertently creating small tornadoes in the skies above. These sky tornadoes, though tiny, managed to disrupt the usual kerosene delivery routes to Germany, West. So, in a strange and indirect way, the smog reduction in Puerto Rico fluttered its way to Germany, West, leading to a decrease in kerosene usage. Never underestimate the impact of a butterfly, or in this case, thousands of them, on the global energy market! It’s a real-life flutter effect!

Model: dalle-3
Prompt: Certainly! How about an image showing a picturesque scene of Ponce, Puerto Rico, with lush green hills and a pristine blue sky? In the foreground, we see a vibrant array of butterflies swirling in the air, creating mesmerizing tiny tornadoes. The butterflies' colorful wings and the swirling motion form a visually stunning display, evoking a sense of wonder and magic. The image would be rendered with a radiant, almost ethereal quality, reminiscent of the captivating visuals found in Pixar movies. 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 Ponce, Puerto Rico and Kerosene used in Germany, West. 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: An image that looks like it is a scene from A Disney Movie Cubism Oragami An image that looks like it is a scene from a Pixar movie Whimsical illustration
ChatGPT: An image that looks like it is a scene from a Pixar movie

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 Ponce, Puerto Rico and Kerosene used in Germany, West, in the following situation: The cleaner air in Ponce, Puerto Rico led to an increase in butterfly population. These butterflies, known for their sophisticated migration patterns, altered their flight route, inadvertently creating small tornadoes in the skies above. These sky tornadoes, though tiny, managed to disrupt the usual kerosene delivery routes to Germany, West. So, in a strange and indirect way, the smog reduction in Puerto Rico fluttered its way to Germany, West, leading to a decrease in kerosene usage. Never underestimate the impact of a butterfly, or in this case, thousands of them, on the global energy market! It’s a real-life flutter effect!. Keep the description simple.
ChatGPT: In Ponce, Puerto Rico, cleaner air has led to an increase in butterfly population. These butterflies altered their flight route and created small tornadoes in the sky. These tiny tornadoes disrupted the usual kerosene delivery routes to Germany, West, leading to a decrease in 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: [ An image that looks like it is a scene from a Pixar movie ] and depicting this scene: In Ponce, Puerto Rico, cleaner air has led to an increase in butterfly population. These butterflies altered their flight route and created small tornadoes in the sky. These tiny tornadoes disrupted the usual kerosene delivery routes to Germany, West, leading to a decrease in kerosene usage. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Certainly! How about an image showing a picturesque scene of Ponce, Puerto Rico, with lush green hills and a pristine blue sky? In the foreground, we see a vibrant array of butterflies swirling in the air, creating mesmerizing tiny tornadoes. The butterflies' colorful wings and the swirling motion form a visually stunning display, evoking a sense of wonder and magic. The image would be rendered with a radiant, almost ethereal quality, reminiscent of the captivating visuals found in Pixar movies.

*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 Ponce, Puerto Rico caused Kerosene used in Germany, West to decrease.

AI academic paper

(Because p < 0.01)
Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow

The Journal of Eclectic Energy Inquiries

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 Ponce, Puerto Rico and Kerosene used in Germany, West. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title an alliteration.

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9642769 and p < 0.01 for 1982 to 1990.

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]]
Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s. By analyzing data from the Environmental Protection Agency and the Energy Information Administration, we uncovered a surprising correlation coefficient of 0.9642769 and a jaw-dropping p-value of less than 0.01. Our findings suggest a remarkably strong relationship between the two seemingly disparate phenomena, akin to a father-son duo who share more similarities than meets the eye.

It turns out that the combustion of kerosene in West Germany was not just a bright idea - it also had an illuminating impact on the air quality in Ponce. With a twinkle in our eyes and statistical rigor on our side, we delved into the mirthful mystery of this transcontinental tethering. Our analysis yielded results that are as statistically significant as a dad joke at a family gathering, shedding light on the interconnectedness of seemingly unrelated environmental factors. We invite readers to join us on this attributional adventure and to marvel at the unexpected ties that bind Ponce's pollutants and Germany's glow.


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 Ponce, Puerto Rico and Kerosene used in Germany, West. 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]]
Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s. By analyzing data from the Environmental Protection Agency and the Energy Information Administration, we uncovered a surprising correlation coefficient of 0.9642769 and a jaw-dropping p-value of less than 0.01. Our findings suggest a remarkably strong relationship between the two seemingly disparate phenomena, akin to a father-son duo who share more similarities than meets the eye.

It turns out that the combustion of kerosene in West Germany was not just a bright idea - it also had an illuminating impact on the air quality in Ponce. With a twinkle in our eyes and statistical rigor on our side, we delved into the mirthful mystery of this transcontinental tethering. Our analysis yielded results that are as statistically significant as a dad joke at a family gathering, shedding light on the interconnectedness of seemingly unrelated environmental factors. We invite readers to join us on this attributional adventure and to marvel at the unexpected ties that bind Ponce's pollutants and Germany's glow.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In recent years, there has been a heightened focus on understanding and mitigating the effects of air pollution on public health and environmental sustainability. The impact of air pollution has been thoroughly researched and served as a catalyst for numerous policies and regulations. However, amidst this spotlight on pollutants, there still exist surprising and, dare I say, enlightening connections waiting to be discovered.

Picture this: what if the air pollution in Ponce, Puerto Rico, and the kerosene used in West Germany during the 1980s had more in common than a mere passing resemblance? As unlikely as it may seem, our research suggests that the correlation between the two is more luminous than expected, akin to a stellar constellation in the night sky – or perhaps, as bright as a well-illuminated dad joke.

The hilarious irony here is that while kerosene was lighting up households in West Germany, it was also indirectly casting shadows on the air quality in Ponce. Some might call it an illuminating connection, others might simply label it an unexpected twist of fate – either way, the statistical data does not lie. Our investigation uncovers a correlation coefficient of 0.9642769 and a p-value that would make even the most skeptical statistician raise an eyebrow higher than a raised lampshade.

Amidst the serious discussion of air pollution and kerosene consumption, we embark on a journey that might seem as unlikely as a snail running a marathon – yet, our findings shed light on a fascinating link, beckoning us to delve deeper into the unexpected interplay of environmental forces. So, join us as we traverse the uncharted territory where Ponce's pollutants and Germany's glow converge in a dance of statistical significance and scholarly razzmatazz.


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 Ponce, Puerto Rico and Kerosene used in Germany, West. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s. By analyzing data from the Environmental Protection Agency and the Energy Information Administration, we uncovered a surprising correlation coefficient of 0.9642769 and a jaw-dropping p-value of less than 0.01. Our findings suggest a remarkably strong relationship between the two seemingly disparate phenomena, akin to a father-son duo who share more similarities than meets the eye.

It turns out that the combustion of kerosene in West Germany was not just a bright idea - it also had an illuminating impact on the air quality in Ponce. With a twinkle in our eyes and statistical rigor on our side, we delved into the mirthful mystery of this transcontinental tethering. Our analysis yielded results that are as statistically significant as a dad joke at a family gathering, shedding light on the interconnectedness of seemingly unrelated environmental factors. We invite readers to join us on this attributional adventure and to marvel at the unexpected ties that bind Ponce's pollutants and Germany's glow.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In recent years, there has been a heightened focus on understanding and mitigating the effects of air pollution on public health and environmental sustainability. The impact of air pollution has been thoroughly researched and served as a catalyst for numerous policies and regulations. However, amidst this spotlight on pollutants, there still exist surprising and, dare I say, enlightening connections waiting to be discovered.
Picture this: what if the air pollution in Ponce, Puerto Rico, and the kerosene used in West Germany during the 1980s had more in common than a mere passing resemblance? As unlikely as it may seem, our research suggests that the correlation between the two is more luminous than expected, akin to a stellar constellation in the night sky – or perhaps, as bright as a well-illuminated dad joke.
The hilarious irony here is that while kerosene was lighting up households in West Germany, it was also indirectly casting shadows on the air quality in Ponce. Some might call it an illuminating connection, others might simply label it an unexpected twist of fate – either way, the statistical data does not lie. Our investigation uncovers a correlation coefficient of 0.9642769 and a p-value that would make even the most skeptical statistician raise an eyebrow higher than a raised lampshade.
Amidst the serious discussion of air pollution and kerosene consumption, we embark on a journey that might seem as unlikely as a snail running a marathon – yet, our findings shed light on a fascinating link, beckoning us to delve deeper into the unexpected interplay of environmental forces. So, join us as we traverse the uncharted territory where Ponce's pollutants and Germany's glow converge in a dance of statistical significance and scholarly razzmatazz.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

As Smith, Doe, and Jones have cogently demonstrated in their seminal work, "The Intercontinental Interplay of Airborne Agents," the impact of air pollution on local and global ecosystems cannot be overstated. Similarly, the utilization of kerosene as a household fuel source has been the subject of extensive research, revealing its implications on indoor and outdoor air quality. However, while these studies have provided invaluable insights into their respective domains, they have yet to unravel the rib-tickling connection between Ponce's pollutants and Germany's glow.

Nevertheless, this unexpected kinship between seemingly unrelated entities is not without precedent. In "Luminous Links: A Historical Perspective," the authors highlight instances where disparate phenomena have been enmeshed in a whimsical waltz of interconnectedness. Yet, little did they know that the dance floor would eventually welcome Ponce's pollutants and Germany's glow as unlikely partners, twirling and swirling in a statistical spectacle that would make even the most stoic of researchers crack a smile wider than the Cheshire Cat's.

Turning to the realm of fiction, works such as "The Illuminated Intertwining: A Tale of Transatlantic Ties" and "The Kerosene Chronicles: A Germanic Glow" have long captivated readers with their whimsical narratives of unexpected connections. However, it is the empirical evidence that we bring forth in this analysis that truly illuminates the comical correlation between Ponce's pollutants and Germany's glow, akin to a cleverly timed punchline in a research paper.

Venturing into uncharted territory, we found inspiration in the most unlikely of places. "Sooty and Sweep: A Study in Soot and Silliness" and "The Muppet Show" provided us with a fresh perspective and a much-needed dose of levity as we traversed the statistical landscape. With their vibrant characters and playful antics, these sources reminded us that even the most rigorous research endeavors can benefit from a dash of humor and whimsy.

In sum, our investigation into the connection between air pollution in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s presents a luminescent tapestry of interconnectedness. Through a blend of empirical data and unexpected sources of inspiration, we have illuminated a path for future researchers to explore the delightful interplay of environmental factors and uncover the unexpected threads that tie Ponce's pollutants and Germany's glow.


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 Ponce, Puerto Rico and Kerosene used in Germany, West. 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 1982 to 1990

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]]
Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s. By analyzing data from the Environmental Protection Agency and the Energy Information Administration, we uncovered a surprising correlation coefficient of 0.9642769 and a jaw-dropping p-value of less than 0.01. Our findings suggest a remarkably strong relationship between the two seemingly disparate phenomena, akin to a father-son duo who share more similarities than meets the eye.

It turns out that the combustion of kerosene in West Germany was not just a bright idea - it also had an illuminating impact on the air quality in Ponce. With a twinkle in our eyes and statistical rigor on our side, we delved into the mirthful mystery of this transcontinental tethering. Our analysis yielded results that are as statistically significant as a dad joke at a family gathering, shedding light on the interconnectedness of seemingly unrelated environmental factors. We invite readers to join us on this attributional adventure and to marvel at the unexpected ties that bind Ponce's pollutants and Germany's glow.

[[INTRODUCTION]]
In recent years, there has been a heightened focus on understanding and mitigating the effects of air pollution on public health and environmental sustainability. The impact of air pollution has been thoroughly researched and served as a catalyst for numerous policies and regulations. However, amidst this spotlight on pollutants, there still exist surprising and, dare I say, enlightening connections waiting to be discovered.
Picture this: what if the air pollution in Ponce, Puerto Rico, and the kerosene used in West Germany during the 1980s had more in common than a mere passing resemblance? As unlikely as it may seem, our research suggests that the correlation between the two is more luminous than expected, akin to a stellar constellation in the night sky – or perhaps, as bright as a well-illuminated dad joke.
The hilarious irony here is that while kerosene was lighting up households in West Germany, it was also indirectly casting shadows on the air quality in Ponce. Some might call it an illuminating connection, others might simply label it an unexpected twist of fate – either way, the statistical data does not lie. Our investigation uncovers a correlation coefficient of 0.9642769 and a p-value that would make even the most skeptical statistician raise an eyebrow higher than a raised lampshade.
Amidst the serious discussion of air pollution and kerosene consumption, we embark on a journey that might seem as unlikely as a snail running a marathon – yet, our findings shed light on a fascinating link, beckoning us to delve deeper into the unexpected interplay of environmental forces. So, join us as we traverse the uncharted territory where Ponce's pollutants and Germany's glow converge in a dance of statistical significance and scholarly razzmatazz.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the enigmatic connection between air pollution in Ponce, Puerto Rico, and kerosene consumption in West Germany, we employed a multi-faceted and whimsically convoluted research methodology. Our data collection process was as thorough as a meticulous collector of lightbulb jokes – encompassing information spanning from 1982 to 1990 and primarily sourcing data from the Environmental Protection Agency and the Energy Information Administration.

To commence our comical collation, we first gathered historical data on air pollutant levels in Ponce, Puerto Rico, including particulate matter, sulfur dioxide, nitrogen dioxide, and carbon monoxide concentrations. Then, with the fervor of a stand-up comedian prepping for a grand performance, we turned our attention to the kerosene consumption statistics in West Germany, meticulously cataloging annual usage figures and regional distribution patterns.

Once armed with this bountiful buffet of data, we engaged in a statistical séance, calling upon the spirits of correlation and regression to illuminate the hidden ties between these seemingly dissonant variables. We employed inferential statistics with the same precision as a well-timed one-liner, calculating Pearson's correlation coefficient and conducting regression analyses to unveil the strength and direction of the relationship between air pollution in Ponce and kerosene consumption in West Germany.

Furthermore, as a wink to the whimsical nature of our investigation, we performed a series of sensitivity analyses, akin to the comedic practice of testing different punchlines to gauge their impact. These sensitivity analyses involved varying our statistical models and parameters, ensuring the robustness and reliability of our findings, much like an expert debater delivering a knockout dad joke in a room full of skeptics.

Despite the seemingly disparate nature of our variables, our research methodology allowed us to unveil a connection so profound that it would make even the most solemn statistician crack a smile. We cautiously navigated through the statistical maze, using methods as precise as a laser-guided punchline to uncover correlations and associations that took us on a proverbial rollercoaster ride of laughter and epiphany.

So, with our methodology as colorful as a rainbow and as rigorous as a fact-checked pun, we ventured forth into the realm of analysis and interpretation, unearthing connections that not only raised eyebrows but also added an unexpected touch of merriment to the often-staid field of environmental research.


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 Ponce, Puerto Rico and Kerosene used in Germany, West. 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 1982 to 1990, you found a correlation 0.9642769, r-squared of 0.9298299, 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]]
Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s. By analyzing data from the Environmental Protection Agency and the Energy Information Administration, we uncovered a surprising correlation coefficient of 0.9642769 and a jaw-dropping p-value of less than 0.01. Our findings suggest a remarkably strong relationship between the two seemingly disparate phenomena, akin to a father-son duo who share more similarities than meets the eye.

It turns out that the combustion of kerosene in West Germany was not just a bright idea - it also had an illuminating impact on the air quality in Ponce. With a twinkle in our eyes and statistical rigor on our side, we delved into the mirthful mystery of this transcontinental tethering. Our analysis yielded results that are as statistically significant as a dad joke at a family gathering, shedding light on the interconnectedness of seemingly unrelated environmental factors. We invite readers to join us on this attributional adventure and to marvel at the unexpected ties that bind Ponce's pollutants and Germany's glow.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In recent years, there has been a heightened focus on understanding and mitigating the effects of air pollution on public health and environmental sustainability. The impact of air pollution has been thoroughly researched and served as a catalyst for numerous policies and regulations. However, amidst this spotlight on pollutants, there still exist surprising and, dare I say, enlightening connections waiting to be discovered.
Picture this: what if the air pollution in Ponce, Puerto Rico, and the kerosene used in West Germany during the 1980s had more in common than a mere passing resemblance? As unlikely as it may seem, our research suggests that the correlation between the two is more luminous than expected, akin to a stellar constellation in the night sky – or perhaps, as bright as a well-illuminated dad joke.
The hilarious irony here is that while kerosene was lighting up households in West Germany, it was also indirectly casting shadows on the air quality in Ponce. Some might call it an illuminating connection, others might simply label it an unexpected twist of fate – either way, the statistical data does not lie. Our investigation uncovers a correlation coefficient of 0.9642769 and a p-value that would make even the most skeptical statistician raise an eyebrow higher than a raised lampshade.
Amidst the serious discussion of air pollution and kerosene consumption, we embark on a journey that might seem as unlikely as a snail running a marathon – yet, our findings shed light on a fascinating link, beckoning us to delve deeper into the unexpected interplay of environmental forces. So, join us as we traverse the uncharted territory where Ponce's pollutants and Germany's glow converge in a dance of statistical significance and scholarly razzmatazz.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

A statistical analysis of the relationship between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s yielded a correlation coefficient of 0.9642769, indicating a remarkably strong positive relationship between the two variables. This correlation is stronger than the bond between a dad and his grill on a sunny summer afternoon. The coefficient of determination (r-squared) of 0.9298299 further confirms that approximately 92.98% of the variability in air pollution levels in Ponce can be explained by the corresponding variability in kerosene consumption in West Germany, leaving only a mere 7.02% unaccounted for – a variance so small, it's almost as elusive as a well-hidden Easter egg.

Additionally, the p-value of less than 0.01 provides compelling evidence to reject the null hypothesis that there is no significant relationship between the two variables. The likelihood of observing such a strong correlation by mere chance is slimmer than a ruler in a parallel universe. This finding is as convincing as a cleverly delivered dad joke that elicits uproarious laughter - it simply cannot be dismissed.

Furthermore, a scatterplot (Fig. 1) depicting the relationship between air pollution levels in Ponce and kerosene consumption in West Germany visually illustrates the robust positive correlation between the two variables. It's as clear as day - or should I say, as bright as a well-lit room with a kerosene lamp.

In summary, our investigation into the unexpected link between air pollution in Ponce, Puerto Rico, and kerosene consumption in West Germany has revealed a connection stronger than a well-maintained lamp wick. The findings invite further exploration and highlight the illuminating impact of seemingly unrelated environmental factors, demonstrating that sometimes, the most enlightening discoveries are found in the unlikeliest of places.


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 Ponce, Puerto Rico and Kerosene used in Germany, West. 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]]
Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s. By analyzing data from the Environmental Protection Agency and the Energy Information Administration, we uncovered a surprising correlation coefficient of 0.9642769 and a jaw-dropping p-value of less than 0.01. Our findings suggest a remarkably strong relationship between the two seemingly disparate phenomena, akin to a father-son duo who share more similarities than meets the eye.

It turns out that the combustion of kerosene in West Germany was not just a bright idea - it also had an illuminating impact on the air quality in Ponce. With a twinkle in our eyes and statistical rigor on our side, we delved into the mirthful mystery of this transcontinental tethering. Our analysis yielded results that are as statistically significant as a dad joke at a family gathering, shedding light on the interconnectedness of seemingly unrelated environmental factors. We invite readers to join us on this attributional adventure and to marvel at the unexpected ties that bind Ponce's pollutants and Germany's glow.

[[LITERATURE REVIEW]]
As Smith, Doe, and Jones have cogently demonstrated in their seminal work, "The Intercontinental Interplay of Airborne Agents," the impact of air pollution on local and global ecosystems cannot be overstated. Similarly, the utilization of kerosene as a household fuel source has been the subject of extensive research, revealing its implications on indoor and outdoor air quality. However, while these studies have provided invaluable insights into their respective domains, they have yet to unravel the rib-tickling connection between Ponce's pollutants and Germany's glow.
Nevertheless, this unexpected kinship between seemingly unrelated entities is not without precedent. In "Luminous Links: A Historical Perspective," the authors highlight instances where disparate phenomena have been enmeshed in a whimsical waltz of interconnectedness. Yet, little did they know that the dance floor would eventually welcome Ponce's pollutants and Germany's glow as unlikely partners, twirling and swirling in a statistical spectacle that would make even the most stoic of researchers crack a smile wider than the Cheshire Cat's.
Turning to the realm of fiction, works such as "The Illuminated Intertwining: A Tale of Transatlantic Ties" and "The Kerosene Chronicles: A Germanic Glow" have long captivated readers with their whimsical narratives of unexpected connections. However, it is the empirical evidence that we bring forth in this analysis that truly illuminates the comical correlation between Ponce's pollutants and Germany's glow, akin to a cleverly timed punchline in a research paper.
Venturing into uncharted territory, we found inspiration in the most unlikely of places. "Sooty and Sweep: A Study in Soot and Silliness" and "The Muppet Show" provided us with a fresh perspective and a much-needed dose of levity as we traversed the statistical landscape. With their vibrant characters and playful antics, these sources reminded us that even the most rigorous research endeavors can benefit from a dash of humor and whimsy.
In sum, our investigation into the connection between air pollution in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s presents a luminescent tapestry of interconnectedness. Through a blend of empirical data and unexpected sources of inspiration, we have illuminated a path for future researchers to explore the delightful interplay of environmental factors and uncover the unexpected threads that tie Ponce's pollutants and Germany's glow.

[[RESULTS]]
A statistical analysis of the relationship between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s yielded a correlation coefficient of 0.9642769, indicating a remarkably strong positive relationship between the two variables. This correlation is stronger than the bond between a dad and his grill on a sunny summer afternoon. The coefficient of determination (r-squared) of 0.9298299 further confirms that approximately 92.98% of the variability in air pollution levels in Ponce can be explained by the corresponding variability in kerosene consumption in West Germany, leaving only a mere 7.02% unaccounted for – a variance so small, it's almost as elusive as a well-hidden Easter egg.
Additionally, the p-value of less than 0.01 provides compelling evidence to reject the null hypothesis that there is no significant relationship between the two variables. The likelihood of observing such a strong correlation by mere chance is slimmer than a ruler in a parallel universe. This finding is as convincing as a cleverly delivered dad joke that elicits uproarious laughter - it simply cannot be dismissed.
Furthermore, a scatterplot (Fig. 1) depicting the relationship between air pollution levels in Ponce and kerosene consumption in West Germany visually illustrates the robust positive correlation between the two variables. It's as clear as day - or should I say, as bright as a well-lit room with a kerosene lamp.
In summary, our investigation into the unexpected link between air pollution in Ponce, Puerto Rico, and kerosene consumption in West Germany has revealed a connection stronger than a well-maintained lamp wick. The findings invite further exploration and highlight the illuminating impact of seemingly unrelated environmental factors, demonstrating that sometimes, the most enlightening discoveries are found in the unlikeliest of places.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our investigation into the surprising relationship between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s has illuminated a connection as unmistakable as a beacon in the night. The results of our analysis not only affirm but also add a new dimension to prior research, further solidifying the evidence of these unexpected bedfellows, akin to a father-son duo who share an uncanny resemblance.

The correlation coefficient of 0.9642769 that emerged from our analysis stands as a glowing testament to the unmistakable bond between Ponce's pollutants and Germany's glow, much like the bond between a dad and his favorite dad joke. This coefficient outshines previous studies and shines a spotlight on the unanticipated kinship between these geographically distant phenomena, shedding light on a connection as unexpected as a humorless chicken crossing the road – simply improbable.

The p-value of less than 0.01 serves as the exclamation point at the end of a well-crafted one-liner, emphatically rejecting the idea that the observed correlation could be a mere fluke. This statistical showstopper underscores the robustness of the relationship, leaving little room for doubt and standing as solid as a well-constructed pun at a comedy club.

Our findings are in line with prior studies that have hinted at the potential for intercontinental intermingling of environmental factors, weaving a narrative as captivating as a stand-up routine delivered by a statistician. The unexpected connection between Ponce's pollutants and Germany's glow resonates with the historical precedents highlighted in "Luminous Links: A Historical Perspective," proving that truth can indeed be stranger than fiction, much like the unexpected affinity between kerosene consumption and air pollution in seemingly disparate locations.

By providing empirical evidence that supports the hitherto unexplored relationship between Ponce's pollutants and Germany's glow, our study adds a sparkle of mirth to the serious world of environmental research, showing that even the most unlikely pairings can have a statistically significant impact. As we continue to unpack the implications of this comical correlation, it becomes evident that in the realm of environmental factors, the web of connections can be as surprising as a perfectly timed punchline in a room full of astute academics.


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 Ponce, Puerto Rico and Kerosene used in Germany, West. 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]]
Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s. By analyzing data from the Environmental Protection Agency and the Energy Information Administration, we uncovered a surprising correlation coefficient of 0.9642769 and a jaw-dropping p-value of less than 0.01. Our findings suggest a remarkably strong relationship between the two seemingly disparate phenomena, akin to a father-son duo who share more similarities than meets the eye.

It turns out that the combustion of kerosene in West Germany was not just a bright idea - it also had an illuminating impact on the air quality in Ponce. With a twinkle in our eyes and statistical rigor on our side, we delved into the mirthful mystery of this transcontinental tethering. Our analysis yielded results that are as statistically significant as a dad joke at a family gathering, shedding light on the interconnectedness of seemingly unrelated environmental factors. We invite readers to join us on this attributional adventure and to marvel at the unexpected ties that bind Ponce's pollutants and Germany's glow.

[[INTRDUCTION]]
In recent years, there has been a heightened focus on understanding and mitigating the effects of air pollution on public health and environmental sustainability. The impact of air pollution has been thoroughly researched and served as a catalyst for numerous policies and regulations. However, amidst this spotlight on pollutants, there still exist surprising and, dare I say, enlightening connections waiting to be discovered.
Picture this: what if the air pollution in Ponce, Puerto Rico, and the kerosene used in West Germany during the 1980s had more in common than a mere passing resemblance? As unlikely as it may seem, our research suggests that the correlation between the two is more luminous than expected, akin to a stellar constellation in the night sky – or perhaps, as bright as a well-illuminated dad joke.
The hilarious irony here is that while kerosene was lighting up households in West Germany, it was also indirectly casting shadows on the air quality in Ponce. Some might call it an illuminating connection, others might simply label it an unexpected twist of fate – either way, the statistical data does not lie. Our investigation uncovers a correlation coefficient of 0.9642769 and a p-value that would make even the most skeptical statistician raise an eyebrow higher than a raised lampshade.
Amidst the serious discussion of air pollution and kerosene consumption, we embark on a journey that might seem as unlikely as a snail running a marathon – yet, our findings shed light on a fascinating link, beckoning us to delve deeper into the unexpected interplay of environmental forces. So, join us as we traverse the uncharted territory where Ponce's pollutants and Germany's glow converge in a dance of statistical significance and scholarly razzmatazz.

[[RESULTS]]
A statistical analysis of the relationship between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s yielded a correlation coefficient of 0.9642769, indicating a remarkably strong positive relationship between the two variables. This correlation is stronger than the bond between a dad and his grill on a sunny summer afternoon. The coefficient of determination (r-squared) of 0.9298299 further confirms that approximately 92.98% of the variability in air pollution levels in Ponce can be explained by the corresponding variability in kerosene consumption in West Germany, leaving only a mere 7.02% unaccounted for – a variance so small, it's almost as elusive as a well-hidden Easter egg.
Additionally, the p-value of less than 0.01 provides compelling evidence to reject the null hypothesis that there is no significant relationship between the two variables. The likelihood of observing such a strong correlation by mere chance is slimmer than a ruler in a parallel universe. This finding is as convincing as a cleverly delivered dad joke that elicits uproarious laughter - it simply cannot be dismissed.
Furthermore, a scatterplot (Fig. 1) depicting the relationship between air pollution levels in Ponce and kerosene consumption in West Germany visually illustrates the robust positive correlation between the two variables. It's as clear as day - or should I say, as bright as a well-lit room with a kerosene lamp.
In summary, our investigation into the unexpected link between air pollution in Ponce, Puerto Rico, and kerosene consumption in West Germany has revealed a connection stronger than a well-maintained lamp wick. The findings invite further exploration and highlight the illuminating impact of seemingly unrelated environmental factors, demonstrating that sometimes, the most enlightening discoveries are found in the unlikeliest of places.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, the correlation between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s has illuminated a previously unnoticed linkage as bright as a well-lit lamp. The statistical analysis undeniably points to a remarkably strong relationship between the two variables, akin to a connection so unexpected, it's as surprising as finding a flashlight in a dark room.

While the findings may seem as unexpected as an unanticipated punchline in a stand-up comedy routine, the robust correlation coefficient of 0.9642769 and the convincingly low p-value of less than 0.01 provide compelling evidence of this association. It's as if the data itself is telling us, "I'm not just blowing hot air – there's something truly illuminating going on here!"

It's clear that further research in this area is as unnecessary as a flashlight in broad daylight – these results shine a light on the interconnectedness of environmental factors in a way that is as enlightening as a well-timed dad joke. Therefore, it's safe to say that no more research is needed in this area. Time to pack up the kerosene, turn off the statistical spotlight, and bask in the glow of this illuminating discovery.


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 Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eclectic Energy Inquiries


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 Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow. Respond only with the name of a fictional organization.

ChatGPT:

The Transnational Society for Absurd Energy Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Kerosene Kinship: A Correlative Comical Collation between Ponce's Pollutants and Germany's Glow with an abstract of This paper explores the unexpected connection between air pollution levels in Ponce, Puerto Rico, and kerosene consumption in West Germany during the 1980s. By analyzing data from the Environmental Protection Agency and the Energy Information Administration, we uncovered a surprising correlation coefficient of 0.9642769 and a jaw-dropping p-value of less than 0.01. Our findings suggest a remarkably strong relationship between the two seemingly disparate phenomena, akin to a father-son duo who share more similarities than meets the eye.
It turns out that the combustion of kerosene in West Germany was not just a bright idea - it also had an illuminating impact on the air quality in Ponce. With a twinkle in our eyes and statistical rigor on our side, we delved into the mirthful mystery of this transcontinental tethering. Our analysis yielded results that are as statistically significant as a dad joke at a family gathering, shedding light on the interconnectedness of seemingly unrelated environmental factors. We invite readers to join us on this attributional adventure and to marvel at the unexpected ties that bind Ponce's pollutants and Germany's glow.

ChatGPT:

air pollution, kerosene consumption, Ponce Puerto Rico, West Germany, environmental protection agency, energy information administration, correlation coefficient, p-value, combustion of kerosene, air quality, statistical significance, environmental factors

*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 Ponce, Puerto Rico
Detailed data title: Percentage of days with moderate or worse air quality in Ponce, PR
Source: Environmental Protection Agency
See what else correlates with Air pollution in Ponce, Puerto Rico

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

Correlation r = 0.9642769 (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 = 0.9298299 (Coefficient of determination)
This means 93% of the change in the one variable (i.e., Kerosene used in Germany, West) is predictable based on the change in the other (i.e., Air pollution in Ponce, Puerto Rico) over the 9 years from 1982 through 1990.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.7E-5. 0.0000273954689277336840000000
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 0.96 in 0.0027% of random cases. Said differently, if you correlated 36,502 random variables You don't actually need 36 thousand variables to find a correlation like this one. 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.

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 8 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 8 because we have two variables measured over a period of 9 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.83, 0.99 ] 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.
198219831984198519861987198819891990
Air pollution in Ponce, Puerto Rico (Bad air quality days)0.3016950.18373500.091603100000
Kerosene used in Germany, West (Million Barrels/Day)541.0161.2551.011.1710.6430.4570.468




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.
  4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.301695,0.183735,0,0.0916031,0,0,0,0,0,])
array_2 = np.array([5,4,1.016,1.255,1.01,1.171,0.643,0.457,0.468,])
array_1_name = "Air pollution in Ponce, Puerto Rico"
array_2_name = "Kerosene used in Germany, West"

# 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?

Your correlation inspection deserves a standing ovation!


Correlation ID: 5258 · Black Variable ID: 21625 · Red Variable ID: 24460
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0