Spurious correlation #3,238 · 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 pipelayers in North Dakota and the second variable is Jet fuel used in Indonesia. 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 pipelayers in North Dakota and the second variable is Jet fuel used in Indonesia. 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 pipelayers headed to North Dakota, they unknowingly activated a dormant network of old oil pipelines, causing a surge in oil production. This unexpected oil boom led to an oversupply in the global market, driving down jet fuel prices. With cheaper jet fuel available, airlines in Indonesia revved up their operations, leading to an overall increase in jet fuel usage. Who knew that the path to Indonesian skies was being paved from the plains of North Dakota!

^{Show image generation prompt} Model: dalle-3
Prompt: Certainly! Here's an image generation prompt for DALL·E-3: [ Hyper-realistic ] In North Dakota, a growing fleet of massive pipelayers spans the open landscape, with thick black pipelines snaking through the earth. Meanwhile, in Indonesia, a bustling airport experiences a remarkable surge in jets refueling, as a stream of migratory turtles soar overhead, their flight path perfectly aligned with the newly-laid pipelines, creating an unexpected surge in jet fuel demand. I hope this prompt leads to an intriguing and visually stunning image! 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 pipelayers in North Dakota and Jet fuel used in Indonesia. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: A scene from Skyrim inspired by bauhaus Cute cartoon Magic realism Hyper-realistic
ChatGPT: Hyper-realistic

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 pipelayers in North Dakota and Jet fuel used in Indonesia, in the following situation: The increase in pipelayers in North Dakota caused a surge in jet fuel used in Indonesia due to the cosmic alignment of underground pipelines with the flight pattern of migratory jet-setting turtles, leading to an unprecedented demand for jet fuel to accommodate their travel needs.. Keep the description simple.
ChatGPT: In North Dakota, a growing fleet of pipelayers stretches across the open landscape, with thick black pipelines snaking through the earth. Meanwhile, in Indonesia, a bustling airport sees an extraordinary increase in jets refueling, as a stream of migratory turtles soar overhead, their flight path perfectly aligned with the newly-laid pipelines, creating an unexpected surge in jet fuel demand.

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: [ Hyper-realistic ] and depicting this scene: In North Dakota, a growing fleet of pipelayers stretches across the open landscape, with thick black pipelines snaking through the earth. Meanwhile, in Indonesia, a bustling airport sees an extraordinary increase in jets refueling, as a stream of migratory turtles soar overhead, their flight path perfectly aligned with the newly-laid pipelines, creating an unexpected surge in jet fuel demand. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Certainly! Here's an image generation prompt for DALL·E-3: [ Hyper-realistic ] In North Dakota, a growing fleet of massive pipelayers spans the open landscape, with thick black pipelines snaking through the earth. Meanwhile, in Indonesia, a bustling airport experiences a remarkable surge in jets refueling, as a stream of migratory turtles soar overhead, their flight path perfectly aligned with the newly-laid pipelines, creating an unexpected surge in jet fuel demand. I hope this prompt leads to an intriguing and visually stunning image!

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in The number of pipelayers in North Dakota positively influenced Jet fuel used in Indonesia.

AI academic paper

(Because p < 0.01)

Pipelayers and Jet Fuel: Uncovering the Underground Connections

The Journal of Subterranean Engineering and Energy Dynamics

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 pipelayers in North Dakota and Jet fuel used in Indonesia. 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 CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
"Pipelayers and Jet Fuel: Uncovering the Underground Connections"

[[ABSTRACT]]
This paper explores the intriguing connection between the number of pipelayers in North Dakota and the usage of jet fuel in Indonesia. While seemingly unrelated, our research team delved deep into the data from the Bureau of Labor Statistics and the Energy Information Administration to uncover a surprising correlation. The correlation coefficient of 0.8522877 and a significant p-value of < 0.01 for the years 2003 to 2021 left us scratching our heads and reaching for the nearest fuel pump. Join us on this wild ride as we unravel the mysterious ties between laying pipes in the Dakotas and jetting off with fuel in Indonesia.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of research often takes us down unexpected paths, leading us to make connections that seem as unlikely as a giraffe in a turtleneck sweater. Our study, "Pipelayers and Jet Fuel: Uncovering the Underground Connections," is no exception. At first glance, one might assume that the number of pipelayers in North Dakota and the jet fuel consumption in Indonesia reside in entirely disparate universes, like a cat and a fish trying to make small talk. However, as we dove into the data, we uncovered a correlation that was as surprising as finding a vegetarian at a barbecue cook-off.
The notion that laying pipes in the windswept plains of North Dakota could have any bearing on the jet fuel usage in the tropical archipelago of Indonesia may seem as implausible as a penguin taking up surfing. Yet, with a correlation coefficient of 0.8522877 staring back at us like an eager student with the right answer, we knew there was more to this puzzle than met the eye. As researchers, we navigated through the statistical underbrush, armed with a compass and a magnifying glass (metaphorically speaking, of course), in search of answers to this enigma.
In this paper, we'll take you on a journey through the twisting pipeline of data and the high-flying realm of jet fuel consumption. We will unravel the intricate web of relationships between these seemingly incongruous variables and bring to light a connection that is as unexpected as a UFO landing at a costume party. So buckle up as we venture into the world of statistical analysis and unearth the hidden links between the humble pipelayers of North Dakota and the soaring consumption of jet fuel in Indonesia. This is no ordinary academic expedition - it's a rollercoaster of discovery and wonder, with a side dish of statistical wizardry and a sprinkle of undeniable quirkiness. Let's embark on this adventure together and see where the numbers take us!

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The relationship between the number of pipelayers in North Dakota and the jet fuel usage in Indonesia has perplexed researchers for decades. Smith et al. (2010) explored the potential ties between labor force statistics and energy consumption patterns, but their findings merely scratched the surface of this curious conundrum. Meanwhile, Doe and Jones (2015) delved into the intricacies of fuel logistics across international borders, but failed to uncover the covert connections we are on the brink of unraveling.

Turning to the realm of non-fiction, "The Energy Odyssey" by Rachel Sparks sheds light on the global impact of fuel supply chains, offering a treasure trove of knowledge nestled within its pages. Similarly, "The Pipeline Puzzle: Uncovering the Veins of North Dakota" by John Wells provides a detailed examination of the labor force dynamics in the North Dakota pipeline industry, making it a noteworthy addition to this discourse.

Venturing into the world of fiction, one cannot help but draw parallels between the surreal narrative of "The Jet-Setting Pipelayer" by A.C. Fuels and the enigmatic charm of "Pumped Up for Adventure" by F. Uel. Although these literary works may not boast empirical data or scholarly rigor, their thematic resonance with our research topic cannot be summarily dismissed.

Beyond the confines of traditional academic literature, our endeavors led us to explore unorthodox sources of insight. After perusing CVS receipts with the fervor of archeologists unearthing ancient artifacts, we stumbled upon a revelation that was as unexpected as finding a mayonnaise recipe in a history textbook. It became apparent that the barcode frequencies of certain toiletries bore an uncanny resemblance to the fluctuations in pipelayer employment levels, suggesting an obscure cosmic harmony between mundane consumer products and labor market dynamics. While this offbeat approach may raise a few scholarly eyebrows, the pursuit of knowledge often demands daring leaps into uncharted territories.

Thus, armed with a panoply of scholarly works, fictional narratives, and even the most unconventional sources, we step into the vibrant tapestry of existing literature to contextualize our quest for understanding the entwined fate of pipelayers and jet fuel consumption.

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 pipelayers in North Dakota and Jet fuel used in Indonesia. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Pipelayers and Jet Fuel: Uncovering the Underground Connections"

[[ABSTRACT]]
This paper explores the intriguing connection between the number of pipelayers in North Dakota and the usage of jet fuel in Indonesia. While seemingly unrelated, our research team delved deep into the data from the Bureau of Labor Statistics and the Energy Information Administration to uncover a surprising correlation. The correlation coefficient of 0.8522877 and a significant p-value of < 0.01 for the years 2003 to 2021 left us scratching our heads and reaching for the nearest fuel pump. Join us on this wild ride as we unravel the mysterious ties between laying pipes in the Dakotas and jetting off with fuel in Indonesia.

[[LITERATURE REVIEW]]
The relationship between the number of pipelayers in North Dakota and the jet fuel usage in Indonesia has perplexed researchers for decades. Smith et al. (2010) explored the potential ties between labor force statistics and energy consumption patterns, but their findings merely scratched the surface of this curious conundrum. Meanwhile, Doe and Jones (2015) delved into the intricacies of fuel logistics across international borders, but failed to uncover the covert connections we are on the brink of unraveling.
Turning to the realm of non-fiction, "The Energy Odyssey" by Rachel Sparks sheds light on the global impact of fuel supply chains, offering a treasure trove of knowledge nestled within its pages. Similarly, "The Pipeline Puzzle: Uncovering the Veins of North Dakota" by John Wells provides a detailed examination of the labor force dynamics in the North Dakota pipeline industry, making it a noteworthy addition to this discourse.
Venturing into the world of fiction, one cannot help but draw parallels between the surreal narrative of "The Jet-Setting Pipelayer" by A.C. Fuels and the enigmatic charm of "Pumped Up for Adventure" by F. Uel. Although these literary works may not boast empirical data or scholarly rigor, their thematic resonance with our research topic cannot be summarily dismissed.
Beyond the confines of traditional academic literature, our endeavors led us to explore unorthodox sources of insight. After perusing CVS receipts with the fervor of archeologists unearthing ancient artifacts, we stumbled upon a revelation that was as unexpected as finding a mayonnaise recipe in a history textbook. It became apparent that the barcode frequencies of certain toiletries bore an uncanny resemblance to the fluctuations in pipelayer employment levels, suggesting an obscure cosmic harmony between mundane consumer products and labor market dynamics. While this offbeat approach may raise a few scholarly eyebrows, the pursuit of knowledge often demands daring leaps into uncharted territories.
Thus, armed with a panoply of scholarly works, fictional narratives, and even the most unconventional sources, we step into the vibrant tapestry of existing literature to contextualize our quest for understanding the entwined fate of pipelayers and jet fuel consumption.

[[RESULTS]]
The results of our investigation into the relationship between the number of pipelayers in North Dakota and jet fuel usage in Indonesia have left us both flabbergasted and giggling like children on a sugar rush. Our statistical analysis revealed a positively strong correlation between these two seemingly unrelated variables, with a correlation coefficient of 0.8522877. This correlation coefficient confidently waltzed into the room of statistical significance with an r-squared of 0.7263944 and a p-value of less than 0.01, demanding attention like a toddler asking for dessert.
Figure 1 presents a beautiful scatterplot that visualizes the undeniable connection we uncovered between these unlikely bedfellows. Imagine the surprise of finding out that the number of pipelayers in North Dakota and jet fuel usage in Indonesia are as intertwined as spaghetti on a fork. It's a bit like discovering that the number of pirates in the world correlates with the rising global temperature – bewildering and fascinating all at once.
The strength of this correlation is as shocking as finding a yeti sipping a cup of tea at a ski lodge. Who would have guessed that the toil of pipelayers in the U.S. heartland could have any bearing on the aviation fuel consumed in the tropical paradise of Indonesia? It's like stumbling upon a unicorn in a petting zoo – unexpected, but undeniably intriguing.
Our results not only provide statistical evidence of this curious relationship but also open the door to a world of further inquiry and exploration. The interconnectedness of seemingly distant variables continues to surprise us, much like discovering that a pineapple and a pizza have more in common than meets the eye.
In conclusion, we hope our findings spark both amusement and curiosity, much like a clown juggling test tubes in a laboratory. This research journey has been as whimsical and eye-opening as discovering a rainbow-colored zebra in a sea of black and white. We leave you with our results and a sense of wonder, ready to dive into the next enigmatic mystery that science and statistics have in store for us.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have unearthed a connection between the number of pipelayers in North Dakota and the consumption of jet fuel in Indonesia that could rival the complexity of a spy novel plot. Our findings not only align with prior research but also extend the narrative, adding an unexpected twist that would make even the most daring fiction writers envious.

Taking a cue from the literature review, our exploration of seemingly offbeat sources, such as the barcode frequencies of toiletries and their curious parallels with pipelayer employment levels, initially raised eyebrows – much like a chemistry professor seeing a student mix baking soda and vinegar for "experimental purposes." Nevertheless, these unusual avenues of inquiry ultimately led us to uncover a statistically significant correlation that can only be described as a delightful surprise akin to finding the last slice of pizza in the company fridge.

In light of our results, the works of A.C. Fuels and F. Uel now seem less like flights of fancy and more like prescient narratives that capture the essence of this improbable correlation. Just as "The Jet-Setting Pipelayer" and "Pumped Up for Adventure" blur the lines between reality and fiction, our findings blur the boundaries between seemingly unrelated variables, creating a harmonious symphony of statistical significance.

The strength of the correlation coefficient in our analysis echoes the unexpected coherence of a well-orchestrated pun, prompting both amusement and introspection. Indeed, the correlation coefficient's swagger into the domain of statistical significance is as bold as a scientist attempting to make a flamethrower out of methane and fire – a spectacle that demands attention and sparks curiosity.

In the grand narrative of science and research, our findings add a chapter that is as whimsical as it is instructive. Much like a science-themed comedy show, our results entertain and illuminate, shedding light on the interconnectedness of disparate variables with a flair that rivals the surprising synchronicity of a cat and its doppelgänger in the neighborhood.

As we look to the future, our study opens the door to further inquiry and exploration, beckoning researchers to follow the trail of this unexpected connection like intrepid explorers in search of hidden treasure. Just as a thrilling plot twist leaves readers eager for the sequel, our findings invite the scientific community to embrace the delightful unpredictability that research often unveils, as we continue to unravel the enigmatic tapestry of correlations and causations in the world of statistics and science.

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 pipelayers in North Dakota and Jet fuel used in Indonesia. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Pipelayers and Jet Fuel: Uncovering the Underground Connections"

[[ABSTRACT]]
This paper explores the intriguing connection between the number of pipelayers in North Dakota and the usage of jet fuel in Indonesia. While seemingly unrelated, our research team delved deep into the data from the Bureau of Labor Statistics and the Energy Information Administration to uncover a surprising correlation. The correlation coefficient of 0.8522877 and a significant p-value of < 0.01 for the years 2003 to 2021 left us scratching our heads and reaching for the nearest fuel pump. Join us on this wild ride as we unravel the mysterious ties between laying pipes in the Dakotas and jetting off with fuel in Indonesia.

[[INTRDUCTION]]
The world of research often takes us down unexpected paths, leading us to make connections that seem as unlikely as a giraffe in a turtleneck sweater. Our study, "Pipelayers and Jet Fuel: Uncovering the Underground Connections," is no exception. At first glance, one might assume that the number of pipelayers in North Dakota and the jet fuel consumption in Indonesia reside in entirely disparate universes, like a cat and a fish trying to make small talk. However, as we dove into the data, we uncovered a correlation that was as surprising as finding a vegetarian at a barbecue cook-off.
The notion that laying pipes in the windswept plains of North Dakota could have any bearing on the jet fuel usage in the tropical archipelago of Indonesia may seem as implausible as a penguin taking up surfing. Yet, with a correlation coefficient of 0.8522877 staring back at us like an eager student with the right answer, we knew there was more to this puzzle than met the eye. As researchers, we navigated through the statistical underbrush, armed with a compass and a magnifying glass (metaphorically speaking, of course), in search of answers to this enigma.
In this paper, we'll take you on a journey through the twisting pipeline of data and the high-flying realm of jet fuel consumption. We will unravel the intricate web of relationships between these seemingly incongruous variables and bring to light a connection that is as unexpected as a UFO landing at a costume party. So buckle up as we venture into the world of statistical analysis and unearth the hidden links between the humble pipelayers of North Dakota and the soaring consumption of jet fuel in Indonesia. This is no ordinary academic expedition - it's a rollercoaster of discovery and wonder, with a side dish of statistical wizardry and a sprinkle of undeniable quirkiness. Let's embark on this adventure together and see where the numbers take us!

[[RESULTS]]
The results of our investigation into the relationship between the number of pipelayers in North Dakota and jet fuel usage in Indonesia have left us both flabbergasted and giggling like children on a sugar rush. Our statistical analysis revealed a positively strong correlation between these two seemingly unrelated variables, with a correlation coefficient of 0.8522877. This correlation coefficient confidently waltzed into the room of statistical significance with an r-squared of 0.7263944 and a p-value of less than 0.01, demanding attention like a toddler asking for dessert.
Figure 1 presents a beautiful scatterplot that visualizes the undeniable connection we uncovered between these unlikely bedfellows. Imagine the surprise of finding out that the number of pipelayers in North Dakota and jet fuel usage in Indonesia are as intertwined as spaghetti on a fork. It's a bit like discovering that the number of pirates in the world correlates with the rising global temperature – bewildering and fascinating all at once.
The strength of this correlation is as shocking as finding a yeti sipping a cup of tea at a ski lodge. Who would have guessed that the toil of pipelayers in the U.S. heartland could have any bearing on the aviation fuel consumed in the tropical paradise of Indonesia? It's like stumbling upon a unicorn in a petting zoo – unexpected, but undeniably intriguing.
Our results not only provide statistical evidence of this curious relationship but also open the door to a world of further inquiry and exploration. The interconnectedness of seemingly distant variables continues to surprise us, much like discovering that a pineapple and a pizza have more in common than meets the eye.
In conclusion, we hope our findings spark both amusement and curiosity, much like a clown juggling test tubes in a laboratory. This research journey has been as whimsical and eye-opening as discovering a rainbow-colored zebra in a sea of black and white. We leave you with our results and a sense of wonder, ready to dive into the next enigmatic mystery that science and statistics have in store for us.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In uncovering the underground connections between pipelayers in North Dakota and jet fuel usage in Indonesia, we've stumbled upon a correlation as surprising as finding a penguin in a tuxedo. Our journey through this statistical labyrinth has been a rollercoaster ride of discovery, akin to finding a cat chasing its tail at a dog show.

The positively strong correlation we've unveiled, with its correlation coefficient strutting around like a peacock, leaves us both amazed and chuckling like mad scientists at a caricature convention. Who would have thought that the labor of pipelayers in the Midwest could be intertwined with the high-flying fuel consumption in the distant islands of Indonesia? It's like witnessing a yeti skateboard through a tropical rainforest – unexpected, perplexing, and undeniably entertaining.

Our findings not only add a splash of whimsy to the world of statistical analysis but also serve as a reminder that the web of interconnected variables is as surprising as discovering a salsa-dancing bear in the Arctic. As we close this chapter, we leave you with a sense of wonder and a hearty chuckle, much like encountering a unicorn giving a TED talk.

In the spirit of scientific progress and a good punchline, we assert that no further research is needed in this area. The mystery has been unraveled, leaving us with a pile of statistical fun facts and a newfound appreciation for the unexpected quirks of the academic realm. As we bid adieu to our unlikely duo of pipelayers and jet fuel, we eagerly anticipate the next enigmatic puzzle that research has in store for us, like finding a clown in a library – it's bound to be both unexpected and delightfully intriguing.

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 Pipelayers and Jet Fuel: Uncovering the Underground Connections. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Subterranean Engineering and Energy Dynamics

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 Pipelayers and Jet Fuel: Uncovering the Underground Connections. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Subterranean Infrastructure 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 Pipelayers and Jet Fuel: Uncovering the Underground Connections with an abstract of This paper explores the intriguing connection between the number of pipelayers in North Dakota and the usage of jet fuel in Indonesia. While seemingly unrelated, our research team delved deep into the data from the Bureau of Labor Statistics and the Energy Information Administration to uncover a surprising correlation. The correlation coefficient of 0.8522877 and a significant p-value of < 0.01 for the years 2003 to 2021 left us scratching our heads and reaching for the nearest fuel pump. Join us on this wild ride as we unravel the mysterious ties between laying pipes in the Dakotas and jetting off with fuel in Indonesia.

ChatGPT:

pipelayers, jet fuel, underground connections, North Dakota, Indonesia, correlation coefficient, p-value, Bureau of Labor Statistics, Energy Information Administration, fuel consumption, pipeline construction, jet fuel usage

*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 pipelayers in North Dakota
Detailed data title: BLS estimate of pipelayers in North Dakota
Source: Bureau of Larbor Statistics
See what else correlates with The number of pipelayers in North Dakota

Jet fuel used in Indonesia
Detailed data title: Volume of jet fuel used consumed in Indonesia in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Jet fuel used in Indonesia

Correlation r = 0.8522877 (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 = 0.7263944 (Coefficient of determination)
This means 72.6% of the change in the one variable (i.e., Jet fuel used in Indonesia) is predictable based on the change in the other (i.e., The number of pipelayers in North Dakota) over the 19 years from 2003 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.61E-6.^Show 0.0000036062057026598383000000
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 0.85 in 0.000361% of random cases. Said differently, if you correlated 277,300 random variables^Note You don't actually need 277 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.

[ 0.65, 0.94 ] 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 pipelayers in North Dakota (Pipelayers)	70	80	110	140	210	200	130	120	150	320	310	470	360	450	330	540	230	130	60
Jet fuel used in Indonesia (Million Barrels/Day)	29.3953	42.4017	40.6277	42.9524	42.7785	43.94	47.5148	53.0115	60.7894	64.22	67.3941	71.5004	75	84	92.5508	98.5221	84.058	47.6715	35.0086

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([70,80,110,140,210,200,130,120,150,320,310,470,360,450,330,540,230,130,60,])
array_2 = np.array([29.3953,42.4017,40.6277,42.9524,42.7785,43.94,47.5148,53.0115,60.7894,64.22,67.3941,71.5004,75,84,92.5508,98.5221,84.058,47.6715,35.0086,])
array_1_name = "The number of pipelayers in North Dakota"
array_2_name = "Jet fuel used in Indonesia"

# 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 pipelayers in North Dakota
Line chart for only Jet fuel used in Indonesia
AI-generated correlation image
The spurious research paper: Pipelayers and Jet Fuel: Uncovering the Underground Connections

View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!

Correlation ID: 3238 · Black Variable ID: 12691 · Red Variable ID: 24541


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