Spurious correlation #2,961 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of septic tank servicers and sewer pipe cleaners in New York and the second variable is Kerosene used in Falkland Islands. The chart goes from 2003 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of septic tank servicers and sewer pipe cleaners in New York and the second variable is Kerosene used in Falkland Islands. The chart goes from 2003 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As more and more septic tank servicers and sewer pipe cleaners set up shop in New York, the demand for their services skyrocketed. This led to a sudden surge in the use of kerosene-powered equipment and machinery, creating a ripple effect in the kerosene market. As kerosene flew off the shelves in New York to power up all the cleaning operations, suppliers had to source it from far and wide, and somehow, this unexpected kerosene craze even reached the tranquil shores of the Falkland Islands, causing a spike in their kerosene usage. It seems like the connection between cleaning up in the Big Apple and heating things up in the Falkland Islands is smellier than we thought!

^{Show image generation prompt} Model: dalle-3
Prompt: [Symbolism] Generate an image that captures the contrast between urban and remote environments through the use of kerosene, depicting a group of septic tank servicers and sewer pipe cleaners in a New York warehouse discussing and holding containers of kerosene, while in the Falkland Islands, a small group of people construct kerosene lamps using a brochure sent by the New York group as their guide. The image should evoke the sense of shared knowledge and resourcefulness across different locations. 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: The number of septic tank servicers and sewer pipe cleaners in New York and Kerosene used in Falkland Islands. 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: Surrealism Symbolism Voxel art Charcoal Cutsy art illustration
ChatGPT: Symbolism

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 The number of septic tank servicers and sewer pipe cleaners in New York and Kerosene used in Falkland Islands, in the following situation: Because septic tank servicers and sewer pipe cleaners in New York started a kerosene fan club, and their enthusiasm for kerosene manufacture and usage spread all the way to the Falkland Islands!. Keep the description simple.
ChatGPT: In New York, a group of septic tank servicers and sewer pipe cleaners gather in a warehouse, excitedly holding containers of kerosene and discussing its uses. Meanwhile, in the Falkland Islands, a small group of people are seen constructing kerosene lamps using the guidance of a brochure sent by the New York group.

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: [ Symbolism ] and depicting this scene: In New York, a group of septic tank servicers and sewer pipe cleaners gather in a warehouse, excitedly holding containers of kerosene and discussing its uses. Meanwhile, in the Falkland Islands, a small group of people are seen constructing kerosene lamps using the guidance of a brochure sent by the New York group. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [Symbolism] Generate an image that captures the contrast between urban and remote environments through the use of kerosene, depicting a group of septic tank servicers and sewer pipe cleaners in a New York warehouse discussing and holding containers of kerosene, while in the Falkland Islands, a small group of people construct kerosene lamps using a brochure sent by the New York group as their guide. The image should evoke the sense of shared knowledge and resourcefulness across different locations.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in The number of septic tank servicers and sewer pipe cleaners in New York caused Kerosene used in Falkland Islands to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Unearthing the Link: A Septic Search for Kerosene Connections

Journal of Unconventional Combustion Studies

Jan 2024

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

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

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of septic tank servicers and sewer pipe cleaners in New York and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
"Unearthing the Link: A Septic Search for Kerosene Connections"

[[ABSTRACT]]
This study delves into the unexpected interplay between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the distant Falkland Islands. The research team, guided by data from the Bureau of Labor Statistics and the Energy Information Administration, plumbs the depths of this peculiar relationship. With a correlation coefficient of 0.8211035 and an astonishingly low p-value of less than 0.01 during the period from 2003 to 2021, our findings defy expectations and send us on a wild whirl through the world of waste and wick. Join us as we navigate the convoluted conduits of correlation and uncover the surprising ties between seemingly disparate realms in this unorthodox exploration of ecnomic and environmental connections.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the annals of academic research, few topics have sparked as much intrigue as the connection between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the far-flung Falkland Islands. This unlikely pairing of seemingly unrelated phenomena has captivated the minds of scholars and laypeople alike, prompting both skepticism and curiosity in equal measure. As we embark on this academic odyssey, we must brace ourselves for a journey through fecal matter and fossil fuels, where the pathways of waste management and energy consumption intertwine in a most serendipitous manner.
The premise of our investigation may sound more like the setup for a punchline at an academic conference than a legitimate research inquiry. However, our findings, as improbable as they may seem, are as real as that sinking feeling when you realize you've left your hypothesis at home. With a correlation coefficient that refuses to be ignored and a p-value so low it might as well be a limbo stick, the data beckons us to explore the enigmatic relationship between these two seemingly disparate domains.
While the layperson might scratch their head in bemusement, the astute academic recognizes that science often takes us down unexpected avenues, much like taking a wrong turn and stumbling upon a comedy club instead of the library. And so, armed with statistical tools and a healthy sense of humor, we venture forth to unearth the peculiar nexus between the sewage handlers of New York and the illuminating fuel consumption in the remote territories of the Falkland Islands.
With the precision of a surgeon and the curiosity of a cat, we aim to delve into this curious correlation, dissecting the numbers with the vigor of a septic tank being cleaned after a particularly rowdy chili cook-off. Join us, dear reader, as we navigate this labyrinth of unlikely connections, where the mundane and the exotic converge in a manner that could make even the most experienced data analyst do a double take.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith et al. (2008) explored the intricate relationship between sewage handling services and energy consumption patterns in remote regions. Their findings offered tantalizing glimpses into the potential interplay between waste management and fuel usage, laying the groundwork for our own investigation into the fascinating correlation between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the Falkland Islands.

Doe and Jones (2015) further expanded on this line of inquiry, shedding light on the unexpected parallels between waste disposal practices and energy utilization in geographically distinct settings. The intersection of septic tank services and kerosene consumption emerged as an enigma worthy of further exploration, sparking our curiosity and driving the course of our investigation.

The literature on this peculiar topic, while limited, has provided valuable insights into the complex dynamics at play. Moving beyond academic studies, popular books such as "Waste Not, Want Not: A Practical Guide to Septic Systems" by Greenfield (2012) and "Fueling the Falklands: A History of Kerosene Consumption" by Blackwood (2017) have drawn attention to the intersection of waste management and energy needs, offering a glimpse into the broader societal implications of our research focus.

Venturing into the realm of fiction, novels such as "The Septic System Murders" by Reed (2019) and "Island of Illumination" by Bright (2020) have, albeit inadvertently, touched upon themes that resonate with our investigation, albeit wrapped in the cloak of fictional narrative and suspense.

However, in the pursuit of a comprehensive understanding, we cast our net wider, venturing beyond traditional scholarly sources. Engaging in a rather unconventional approach, we gleaned unexpected insights from the most unlikely of places, including the backs of shampoo bottles, where the chemical compositions and ecological impact of cleansing agents unexpectedly surfaced as tangentially relevant to our inquiry. While an unorthodox endeavor, this lighthearted foray into bathroom literature presented quirky perspectives that proved surprisingly thought-provoking.

In further honing our research scope, we recognized the importance of seeking inspiration from diverse sources, no matter how seemingly unrelated or whimsical. After all, sometimes the most unexpected detours lead us to the most illuminating destinations, much like an unplanned adventure that begins with a wrong turn and ends with a eureka moment that leaves even the most stoic researcher chuckling in disbelief.

This exploratory approach, while unconventional, underscores the serendipitous nature of scientific inquiry, reminding us that even in the realms of waste management and energy consumption, the unexpected can often hold the key to unlocking profound insights. With a nod to the unconventional and a wink at the unexpected, we forge ahead in this unorthodox academic quest, propelled by the infectious spirit of intellectual curiosity and the occasional whiff of scatological humor.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of septic tank servicers and sewer pipe cleaners in New York and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Unearthing the Link: A Septic Search for Kerosene Connections"

[[ABSTRACT]]
This study delves into the unexpected interplay between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the distant Falkland Islands. The research team, guided by data from the Bureau of Labor Statistics and the Energy Information Administration, plumbs the depths of this peculiar relationship. With a correlation coefficient of 0.8211035 and an astonishingly low p-value of less than 0.01 during the period from 2003 to 2021, our findings defy expectations and send us on a wild whirl through the world of waste and wick. Join us as we navigate the convoluted conduits of correlation and uncover the surprising ties between seemingly disparate realms in this unorthodox exploration of ecnomic and environmental connections.

[[LITERATURE REVIEW]]
In their seminal work, Smith et al. (2008) explored the intricate relationship between sewage handling services and energy consumption patterns in remote regions. Their findings offered tantalizing glimpses into the potential interplay between waste management and fuel usage, laying the groundwork for our own investigation into the fascinating correlation between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the Falkland Islands.
Doe and Jones (2015) further expanded on this line of inquiry, shedding light on the unexpected parallels between waste disposal practices and energy utilization in geographically distinct settings. The intersection of septic tank services and kerosene consumption emerged as an enigma worthy of further exploration, sparking our curiosity and driving the course of our investigation.
The literature on this peculiar topic, while limited, has provided valuable insights into the complex dynamics at play. Moving beyond academic studies, popular books such as "Waste Not, Want Not: A Practical Guide to Septic Systems" by Greenfield (2012) and "Fueling the Falklands: A History of Kerosene Consumption" by Blackwood (2017) have drawn attention to the intersection of waste management and energy needs, offering a glimpse into the broader societal implications of our research focus.
Venturing into the realm of fiction, novels such as "The Septic System Murders" by Reed (2019) and "Island of Illumination" by Bright (2020) have, albeit inadvertently, touched upon themes that resonate with our investigation, albeit wrapped in the cloak of fictional narrative and suspense.
However, in the pursuit of a comprehensive understanding, we cast our net wider, venturing beyond traditional scholarly sources. Engaging in a rather unconventional approach, we gleaned unexpected insights from the most unlikely of places, including the backs of shampoo bottles, where the chemical compositions and ecological impact of cleansing agents unexpectedly surfaced as tangentially relevant to our inquiry. While an unorthodox endeavor, this lighthearted foray into bathroom literature presented quirky perspectives that proved surprisingly thought-provoking.
In further honing our research scope, we recognized the importance of seeking inspiration from diverse sources, no matter how seemingly unrelated or whimsical. After all, sometimes the most unexpected detours lead us to the most illuminating destinations, much like an unplanned adventure that begins with a wrong turn and ends with a eureka moment that leaves even the most stoic researcher chuckling in disbelief.
This exploratory approach, while unconventional, underscores the serendipitous nature of scientific inquiry, reminding us that even in the realms of waste management and energy consumption, the unexpected can often hold the key to unlocking profound insights. With a nod to the unconventional and a wink at the unexpected, we forge ahead in this unorthodox academic quest, propelled by the infectious spirit of intellectual curiosity and the occasional whiff of scatological humor.

[[RESULTS]]
The results of our intrepid investigation reveal a surprisingly robust correlation between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the Falkland Islands. Our statistical analysis uncovered a correlation coefficient of 0.8211035, indicating a strong positive relationship between these seemingly disparate variables. In the world of statistics, a correlation of this magnitude is akin to finding a treasure map in a pile of old newspapers - both unexpected and potentially rewarding, depending on how much faith you have in buried treasure.
Furthermore, the r-squared value of 0.6742109 indicates that approximately 67.42% of the variation in kerosene consumption in the Falkland Islands can be explained by the number of septic tank servicers and sewer pipe cleaners in New York. This finding suggests that these two phenomena are indeed intertwined, much like the dance of fireflies on a summer evening or the inexplicable friendship between a cat and a dog.
The p-value of less than 0.01 further cemented the significance of our results. In the realm of statistical significance, a p-value of less than 0.01 is like winning the lottery and then finding out your ticket was actually a misprint - it's incredibly unlikely, but when it happens, it's cause for both celebration and a double-take.
Fig. 1 presents a scatterplot illustrating the conspicuous correlation between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the Falkland Islands. The plot showcases the tight relationship between these variables, leaving little room for doubt and plenty of room for contemplation about the interconnectedness of human activities and their environmental impacts.
In conclusion, our findings substantiate a strong and unexpected link between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the Falkland Islands. This unearthing of a peculiar correlation not only adds color to the tapestry of our understanding but also serves as a reminder that in the world of data analysis, strange bedfellows can yield remarkable insights.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study underscore the veritable treasure trove of insights that can be gleaned from the unlikely nexus of septic services and kerosene consumption. It's like stumbling upon a rare gem in the most unexpected of places - an antiquated attic, perhaps, or the depths of a forgotten sock drawer. Our findings not only validate the prior research by Smith et al. and Doe and Jones but also take their implications to a whole new level of impressive, if not downright wacky, significance. The correlation coefficient of 0.8211035, akin to discovering a hidden harmonious melody in cacophonous noise, highlights the unexpectedly tight relationship between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the hitherto unknown annals of the Falkland Islands.

Channeling the eccentric musings of Greenfield's "Waste Not, Want Not," we peer into the labyrinthine depths of waste management and energy utilization, where the elusive threads of connection weave an intricate tapestry of interdependence. Our results support the notion that the disposal of waste in one corner of the world can cast its shadow, or rather its glow, in the seemingly distant surroundings of an island territory. It's akin to the realization that distant echoes can reverberate in unexpected places, much like the resounding impact of a poorly executed joke at a professional conference.

In paying homage to the offbeat insights from "The Septic System Murders" and "Island of Illumination," we're reminded that the seemingly incongruous realms of waste and illumination can indeed share a convoluted, if not downright intertwined, fate. Our findings provide empirical validation for these tangentially relevant works of fiction, emphasizing that reality can be stranger than we could have ever imagined, much like a serendipitous encounter with a long-lost friend while grocery shopping for kale.

And, oh, the shampoo bottle revelations - for all the quirkiness this digression conveyed, it's a testament to the serendipitous nature of scientific inquiry. Who would have thought that a detour through unconventional sources would lead to an enlightening understanding of the interplay between waste management and energy consumption? As unpredictable as the flight path of a startled pigeon, our research demonstrates the value of unorthodox avenues in shedding light on unexpected connections.

In the grand scheme of scholarly pursuit, our unorthodox academic quest has unfurled like a whimsical expedition through uncharted territories, propelled by the infectious spirit of intellectual curiosity and the occasional waft of lighthearted absurdity. Through this pursuit, we've unraveled the hidden, if not downright whimsical, connections between septic services and kerosene consumption, enriching the academic landscape with an unanticipated splash of provoking irreverence.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of septic tank servicers and sewer pipe cleaners in New York and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Unearthing the Link: A Septic Search for Kerosene Connections"

[[ABSTRACT]]
This study delves into the unexpected interplay between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the distant Falkland Islands. The research team, guided by data from the Bureau of Labor Statistics and the Energy Information Administration, plumbs the depths of this peculiar relationship. With a correlation coefficient of 0.8211035 and an astonishingly low p-value of less than 0.01 during the period from 2003 to 2021, our findings defy expectations and send us on a wild whirl through the world of waste and wick. Join us as we navigate the convoluted conduits of correlation and uncover the surprising ties between seemingly disparate realms in this unorthodox exploration of ecnomic and environmental connections.

[[INTRDUCTION]]
In the annals of academic research, few topics have sparked as much intrigue as the connection between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the far-flung Falkland Islands. This unlikely pairing of seemingly unrelated phenomena has captivated the minds of scholars and laypeople alike, prompting both skepticism and curiosity in equal measure. As we embark on this academic odyssey, we must brace ourselves for a journey through fecal matter and fossil fuels, where the pathways of waste management and energy consumption intertwine in a most serendipitous manner.
The premise of our investigation may sound more like the setup for a punchline at an academic conference than a legitimate research inquiry. However, our findings, as improbable as they may seem, are as real as that sinking feeling when you realize you've left your hypothesis at home. With a correlation coefficient that refuses to be ignored and a p-value so low it might as well be a limbo stick, the data beckons us to explore the enigmatic relationship between these two seemingly disparate domains.
While the layperson might scratch their head in bemusement, the astute academic recognizes that science often takes us down unexpected avenues, much like taking a wrong turn and stumbling upon a comedy club instead of the library. And so, armed with statistical tools and a healthy sense of humor, we venture forth to unearth the peculiar nexus between the sewage handlers of New York and the illuminating fuel consumption in the remote territories of the Falkland Islands.
With the precision of a surgeon and the curiosity of a cat, we aim to delve into this curious correlation, dissecting the numbers with the vigor of a septic tank being cleaned after a particularly rowdy chili cook-off. Join us, dear reader, as we navigate this labyrinth of unlikely connections, where the mundane and the exotic converge in a manner that could make even the most experienced data analyst do a double take.

[[RESULTS]]
The results of our intrepid investigation reveal a surprisingly robust correlation between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the Falkland Islands. Our statistical analysis uncovered a correlation coefficient of 0.8211035, indicating a strong positive relationship between these seemingly disparate variables. In the world of statistics, a correlation of this magnitude is akin to finding a treasure map in a pile of old newspapers - both unexpected and potentially rewarding, depending on how much faith you have in buried treasure.
Furthermore, the r-squared value of 0.6742109 indicates that approximately 67.42% of the variation in kerosene consumption in the Falkland Islands can be explained by the number of septic tank servicers and sewer pipe cleaners in New York. This finding suggests that these two phenomena are indeed intertwined, much like the dance of fireflies on a summer evening or the inexplicable friendship between a cat and a dog.
The p-value of less than 0.01 further cemented the significance of our results. In the realm of statistical significance, a p-value of less than 0.01 is like winning the lottery and then finding out your ticket was actually a misprint - it's incredibly unlikely, but when it happens, it's cause for both celebration and a double-take.
Fig. 1 presents a scatterplot illustrating the conspicuous correlation between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the Falkland Islands. The plot showcases the tight relationship between these variables, leaving little room for doubt and plenty of room for contemplation about the interconnectedness of human activities and their environmental impacts.
In conclusion, our findings substantiate a strong and unexpected link between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the Falkland Islands. This unearthing of a peculiar correlation not only adds color to the tapestry of our understanding but also serves as a reminder that in the world of data analysis, strange bedfellows can yield remarkable insights.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In the fecally fortuitous conclusion of our kerosene-soaked odyssey, we have glimpsed the unlikely intertwining of septic tank servicers and sewer pipe cleaners in New York with the illuminating fuel habits of the Falkland Islands. It's the kind of unexpected connection that makes you ponder if someone mixed up the data sets or if statistical algorithms have a secret sense of humor.

With a correlation coefficient resembling a tightly knit family and a p-value so small it could easily hide behind a speck of dust, our findings stand as solid as a well-built septic tank. The r-squared value further cements this relationship, indicating that nearly 68% of kerosene consumption in the Falkland Islands can be traced back to the bustling activity of waste handlers in the Big Apple.

Just as the world thought it had all its p-values in a row, this research comes along and skews the curve with its unexpected twist. It's a reminder that in the realm of science, the most astonishing discoveries often emerge from the unlikeliest of pairings - like finding a diamond ring at the bottom of a sewage treatment plant's pit.

In light of these revelatory findings, it's safe to say that no more research is needed in this area. After all, there's only so much correlation one can handle before it starts to feel like your data has developed a comical streak. So let's savor this wacky revelation and marvel at the whims of statistical fate.

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 Unearthing the Link: A Septic Search for Kerosene Connections. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Unconventional Combustion Studies

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 Unearthing the Link: A Septic Search for Kerosene Connections. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Esoteric Energy Examinations

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 Unearthing the Link: A Septic Search for Kerosene Connections with an abstract of This study delves into the unexpected interplay between the number of septic tank servicers and sewer pipe cleaners in New York and the consumption of kerosene in the distant Falkland Islands. The research team, guided by data from the Bureau of Labor Statistics and the Energy Information Administration, plumbs the depths of this peculiar relationship. With a correlation coefficient of 0.8211035 and an astonishingly low p-value of less than 0.01 during the period from 2003 to 2021, our findings defy expectations and send us on a wild whirl through the world of waste and wick. Join us as we navigate the convoluted conduits of correlation and uncover the surprising ties between seemingly disparate realms in this unorthodox exploration of ecnomic and environmental connections.

ChatGPT:

septic tank servicers, sewer pipe cleaners, New York, consumption of kerosene, Falkland Islands, correlation coefficient, p-value, Bureau of Labor Statistics, Energy Information Administration, waste management, environmental connections, economic connections

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

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

The number of septic tank servicers and sewer pipe cleaners in New York
Detailed data title: BLS estimate of septic tank servicers and sewer pipe cleaners in New York
Source: Bureau of Larbor Statistics
See what else correlates with The number of septic tank servicers and sewer pipe cleaners in New York

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

Correlation r = 0.8211035 (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 = 0.6742109 (Coefficient of determination)
This means 67.4% of the change in the one variable (i.e., Kerosene used in Falkland Islands) is predictable based on the change in the other (i.e., The number of septic tank servicers and sewer pipe cleaners in New York) over the 19 years from 2003 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.6E-5.^Show 0.0000164216236958725940000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.82 in 0.0016% of random cases. Said differently, if you correlated 60,895 random variables^Note You don't actually need 60 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 18 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.59, 0.93 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
The number of septic tank servicers and sewer pipe cleaners in New York (Laborers)	730	720	520	1220	1450	1610	1100	1200	960	990	1070	1070	1470	1410	1620	1560	1570	1110	1440
Kerosene used in Falkland Islands (Million Barrels/Day)	0.0423562	0.0633607	0.0635342	0.0847123	0.0847123	0.0844809	0.0847123	0.0783589	0.0804767	0.0844809	0.0847123	0.0847123	0.095301	0.105601	0.100163	0.10589	0.10589	0.0891857	0.094922

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([730,720,520,1220,1450,1610,1100,1200,960,990,1070,1070,1470,1410,1620,1560,1570,1110,1440,])
array_2 = np.array([0.0423562,0.0633607,0.0635342,0.0847123,0.0847123,0.0844809,0.0847123,0.0783589,0.0804767,0.0844809,0.0847123,0.0847123,0.095301,0.105601,0.100163,0.10589,0.10589,0.0891857,0.094922,])
array_1_name = "The number of septic tank servicers and sewer pipe cleaners in New York"
array_2_name = "Kerosene used in Falkland Islands"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only The number of septic tank servicers and sewer pipe cleaners in New York
Line chart for only Kerosene used in Falkland Islands
AI-generated correlation image
The spurious research paper: Unearthing the Link: A Septic Search for Kerosene Connections

View another random correlation

How fun was this correlation?

Your rating is much appreciated!

Correlation ID: 2961 · Black Variable ID: 12200 · Red Variable ID: 24408


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