Spurious correlation #2,578 · 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 British American Tobacco p.l.c.'s stock price (BTI). The chart goes from 2003 to 2022, 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 British American Tobacco p.l.c.'s stock price (BTI). The chart goes from 2003 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the demand for pipelayers in North Dakota rose, so did the need for pipes and pipe-related products. This unexpected pipe boom led to a surge in tobacco pipe sales, including those fancy Sherlock Holmes-style ones. As British American Tobacco p.l.c. saw their tobacco pipe division rake in the profits, investors were drawn to the smokin' hot potential for growth, causing BTI's stock price to soar like a smoke ring in the wind. Looks like the pipelayers weren't the only ones laying down the pipeline for success!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image that depicts a breathtaking landscape in North Dakota, where fields are filled with busy pipelayers working on constructing new pipelines. The scene should be vibrant and dynamic, showcasing the movement and energy of the worksite. The focus should be on the pipelines being constructed, with attention to detail on the machinery and workers. The image should also convey an atmosphere of industry and progress, capturing the essence of the increased activity in the area. 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 British American Tobacco p.l.c.'s stock price (BTI). 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: Psychedelic Celtic art A photo-realistic image Hyper-realistic A scene from Skyrim
ChatGPT: A scene from Skyrim

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 British American Tobacco p.l.c.'s stock price (BTI), in the following situation: The spike in pipelayers led to more "smokin' hot" construction projects, igniting a surge in demand for cigarettes, thus boosting BTI's stock price. As the number of pipelayers "fueled" economic growth, investors saw BTI as a "pipe dream" for profits, causing the stock price to "flare up" like a freshly lit cigarette.. Keep the description simple.
ChatGPT: In North Dakota, the fields are bustling with a fleet of pipelayers, busy constructing new pipelines. The increased activity has sparked a surge in demand for cigarettes, leading to a significant rise in British American Tobacco p.l.c.'s stock price (BTI). Investors are seeing the stock as a "pipe dream" for profits, causing it to "flare up" like a freshly lit cigarette.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A scene from Skyrim ] and depicting this scene: In North Dakota, the fields are bustling with a fleet of pipelayers, busy constructing new pipelines. The increased activity has sparked a surge in demand for cigarettes, leading to a significant rise in British American Tobacco p.l.c.'s stock price (BTI). Investors are seeing the stock as a "pipe dream" for profits, causing it to "flare up" like a freshly lit cigarette. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that depicts a breathtaking landscape in North Dakota, where fields are filled with busy pipelayers working on constructing new pipelines. The scene should be vibrant and dynamic, showcasing the movement and energy of the worksite. The focus should be on the pipelines being constructed, with attention to detail on the machinery and workers. The image should also convey an atmosphere of industry and progress, capturing the essence of the increased activity in the area.

*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 pipelayers in North Dakota caused British American Tobacco p.l.c.'s stock price (BTI) to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

Pipelayers in North Dakota and Puffing on BTI: A Peculiar Partnership

The Journal of Unconventional Collaborations

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 British American Tobacco p.l.c.'s stock price (BTI). 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 in North Dakota and Puffing on BTI: A Peculiar Partnership

[[ABSTRACT]]
In this scholarly exploration, we dive into the unlikely connection between the number of pipelayers in North Dakota and the stock price of British American Tobacco p.l.c. (BTI). While one might expect tobacco sales to go up in smoke alongside pipeline activity, our research paints a different picture. Utilizing data from the Bureau of Labor Statistics and LSEG Analytics (Refinitiv), we delved into the numbers from 2003 to 2022 to uncover the correlation coefficient of 0.8491579, with a significant p-value of less than 0.01.

Our findings reveal a surprising link between these seemingly unrelated variables, leaving us to ponder whether the puffing and laying have been secretly in cahoots all along. Could it be that as the pipes go down, BTI stock prices also rise, blowing smoke in the face of conventional wisdom? Join us as we unravel this curiously convoluted connection and light the way for further investigations into the whimsical world of inter-industry correlations.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Imagine a world where the number of pipelayers in the heart of North Dakota has a peculiar dance with the stock price of British American Tobacco p.l.c. (BTI). One might expect these two to be as closely related as a fish and a bicycle, but as we delved into the depths of this connection, we were met with a revelation more surprising than finding a unicorn in a cornfield.
In this era of big data, we researchers are often tasked with unraveling the mysteries of the universe, but few mysteries are as perplexing and unexpected as the one we are about to reveal. It's as if Sherlock Holmes were called in to investigate the enigmatic partnership of pipelayers and puffing.
As we embark on this scholarly journey of discovery, let us first acknowledge the raised eyebrows and quizzical looks that our topic might incite. After all, what could the labor force of pipeline construction possibly have to do with the performance of a multinational tobacco company’s stocks? It's like trying to find a connection between cats and the consumption of cabbage – seemingly unrelated, yet here we are, determined to shine a light on this shadowy alliance.
So, dear reader, buckle up for a whimsical ride through the wacky world of statistics and correlation. We assure you that by the end of this paper, you will be as wide-eyed as a rabbit in a carrot patch, and you may just find yourself pondering the mysteries of the stock market and industrial activity with the same boggled mind that contemplates the existence of dodo birds and disco music - truly a head-scratcher for the ages.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.," the authors find a dire shortage of academic studies linking the number of pipelayers in North Dakota to the stock price of British American Tobacco p.l.c. (BTI). This gap in the literature provides us with the perfect opportunity to indulge in some academically sanctioned wild goose chasing.

Building on the previous work of Doe et al., who managed to draw correlations between snowfall in Antarctica and the sales of flip-flops in the Caribbean, we set out to venture into uncharted territory where pipelines and tobacco intertwine like spaghetti on a fork. But fear not, dear reader, for we are equipped not only with data and statistical methods, but also with an ample supply of puns and humor.

To bolster our exploration, we turn to non-fiction books that have delved into the world of strange connections and unpredictable phenomena. "Freakonomics" by Steven D. Levitt and Stephen J. Dubner serves as our guiding light, illuminating the unanticipated relationships that underpin seemingly unrelated concepts. From there, we take a leap into the realms of probability and chance with "The Black Swan" by Nassim Nicholas Taleb, preparing ourselves for the unexpected twists and turns that await us in this eccentric endeavor.

But as we journey deeper into the literature, we cannot help but borrow a page from the unexpected partners playbook. Consider "Pride and Prejudice" by Jane Austen and "Moby-Dick" by Herman Melville – two timeless works offering indirect insights into the unconventional connections we seek to uncover. Much like the unconventional union of Elizabeth Bennet and Mr. Darcy, and the entwined destinies of Captain Ahab and his hunt for the elusive whale, we are about to embark on a quest where the unexpected takes center stage.

Now, as we descend further into the rabbit hole of our literature review, we must confess – in the pursuit of knowledge, we have perused sources that could be considered, well, unconventional. Yes, we are talking about the extensive and highly revealing data found on CVS receipts! It turns out, amidst the mundane purchases of toothpaste and potato chips, lies a treasure trove of industry overlaps and consumer behaviors that could send even the most seasoned researcher down a path of bewildering revelations.

With this wealth of literary and not-so-literary resources at our disposal, we are primed to confront the conundrum of pipelayers and puffing in the enthralling context of BTI's stock performance. Let the journey through the absurd and the unexpected commence – for who knows what delightful surprises await us as we navigate this eccentric landscape of academic inquiry.

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 British American Tobacco p.l.c.'s stock price (BTI). 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]]
Pipelayers in North Dakota and Puffing on BTI: A Peculiar Partnership

[[ABSTRACT]]
In this scholarly exploration, we dive into the unlikely connection between the number of pipelayers in North Dakota and the stock price of British American Tobacco p.l.c. (BTI). While one might expect tobacco sales to go up in smoke alongside pipeline activity, our research paints a different picture. Utilizing data from the Bureau of Labor Statistics and LSEG Analytics (Refinitiv), we delved into the numbers from 2003 to 2022 to uncover the correlation coefficient of 0.8491579, with a significant p-value of less than 0.01.

Our findings reveal a surprising link between these seemingly unrelated variables, leaving us to ponder whether the puffing and laying have been secretly in cahoots all along. Could it be that as the pipes go down, BTI stock prices also rise, blowing smoke in the face of conventional wisdom? Join us as we unravel this curiously convoluted connection and light the way for further investigations into the whimsical world of inter-industry correlations.

[[LITERATURE REVIEW]]
In "Smith et al.," the authors find a dire shortage of academic studies linking the number of pipelayers in North Dakota to the stock price of British American Tobacco p.l.c. (BTI). This gap in the literature provides us with the perfect opportunity to indulge in some academically sanctioned wild goose chasing.
Building on the previous work of Doe et al., who managed to draw correlations between snowfall in Antarctica and the sales of flip-flops in the Caribbean, we set out to venture into uncharted territory where pipelines and tobacco intertwine like spaghetti on a fork. But fear not, dear reader, for we are equipped not only with data and statistical methods, but also with an ample supply of puns and humor.
To bolster our exploration, we turn to non-fiction books that have delved into the world of strange connections and unpredictable phenomena. "Freakonomics" by Steven D. Levitt and Stephen J. Dubner serves as our guiding light, illuminating the unanticipated relationships that underpin seemingly unrelated concepts. From there, we take a leap into the realms of probability and chance with "The Black Swan" by Nassim Nicholas Taleb, preparing ourselves for the unexpected twists and turns that await us in this eccentric endeavor.
But as we journey deeper into the literature, we cannot help but borrow a page from the unexpected partners playbook. Consider "Pride and Prejudice" by Jane Austen and "Moby-Dick" by Herman Melville – two timeless works offering indirect insights into the unconventional connections we seek to uncover. Much like the unconventional union of Elizabeth Bennet and Mr. Darcy, and the entwined destinies of Captain Ahab and his hunt for the elusive whale, we are about to embark on a quest where the unexpected takes center stage.
Now, as we descend further into the rabbit hole of our literature review, we must confess – in the pursuit of knowledge, we have perused sources that could be considered, well, unconventional. Yes, we are talking about the extensive and highly revealing data found on CVS receipts! It turns out, amidst the mundane purchases of toothpaste and potato chips, lies a treasure trove of industry overlaps and consumer behaviors that could send even the most seasoned researcher down a path of bewildering revelations.
With this wealth of literary and not-so-literary resources at our disposal, we are primed to confront the conundrum of pipelayers and puffing in the enthralling context of BTI's stock performance. Let the journey through the absurd and the unexpected commence – for who knows what delightful surprises await us as we navigate this eccentric landscape of academic inquiry.

[[RESULTS]]
Our analysis of the data spanning from 2003 to 2022 has produced some eyebrow-raising findings. The correlation coefficient between the number of pipelayers in North Dakota and the stock price of British American Tobacco p.l.c. (BTI) came in at a surprising 0.8491579. This strong positive correlation astounded us more than finding a kangaroo in a coffee shop, especially given the seemingly independent nature of these two entities.
In addition, the calculated r-squared value of 0.7210692 further solidifies the strength of this association. It’s as if the pipelayers and BTI stock prices have been partners in crime all along, defying the odds and materializing a connection more puzzling than a Rubik's cube made of spaghetti.
Even more astonishing, the p-value of less than 0.01 confidently asserts the statistical significance of this relationship. It’s as if the data itself is tapping us on the shoulder, whispering, "You better believe it, buddy!"
As depicted in Fig. 1, our scatterplot showcases the undeniable connection between the number of pipelayers in North Dakota and BTI stock prices. The data points practically form a perfect heart shape, as if these two variables were destined to be a match made in statistical heaven.
This unexpected revelation has left us marveling at the mysterious dance between pipelayers and puffing, with more questions than answers. Could it be that as the pipelayers labor away, they are unintentionally adding fuel to the fire of BTI stock prices, sculpting an unexpected narrative that defies the logic of market forces?
These findings undoubtedly set the stage for further investigation into the enigmatic kinship of seemingly unrelated industries, reminding us once again that the world of statistics is filled with surprises stranger than fiction and more peculiar than a platypus wearing a top hat.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have unveiled an intriguing connection between the number of pipelayers in North Dakota and the stock price of British American Tobacco p.l.c. (BTI), sparking more excitement than a group of mathematicians finding the square root of a negative number. Our findings not only confirm but also shed new light on the prior research, leaving us with a cloud of curiosity thicker than cigar smoke on a windless day.

Drawing from the literature review, where we dabbled in the bizarro world of unexpected correlations, our results stand as a testament to the unlikeliest of bedfellows. Just as Doe et al. unearthed the unlikely link between snowfall in Antarctica and flip-flop sales in the Caribbean, our discovery of the strong positive correlation between pipelayers and BTI stock prices solidifies the reality that in the realm of statistical relationships, truth can indeed be stranger than fiction. It is as if the universe has a penchant for orchestrating cosmic jokes, reminiscent of a Shakespearean comedy with a statistical twist.

Furthermore, our findings can be seen as a nod to the principles espoused in "Freakonomics" and "The Black Swan," where the unexpected is not just acknowledged but celebrated. Our results stand as a tangible example of the unpredictable nature of correlations, reinforcing the notion that the world of data analysis is a playground for the whimsical and the counterintuitive. It’s as if we've stumbled into a carnival of statistical oddities, where the merry-go-round of correlations and causations spins in directions we never thought possible.

In the context of our results, it seems that the confluence of pipelayers and BTI stock prices is more than just a statistical anomaly – it’s a testament to the enigmatic tapestry of inter-industry relationships. Just as Elizabeth Bennet and Mr. Darcy found themselves drawn together against all odds, so too have pipelayers and tobacco stocks seemingly intertwined their fate in a dance of statistical serendipity.

As we contemplate the implications of our findings, the quirky world of academic inquiry continues to surprise us. Our results raise questions about the underlying mechanisms driving this unexpected correlation, reminding us that the pursuit of understanding often leads us down paths more winding than a labyrinth made of pretzels.

In conclusion, our study has not only added a peculiar puzzle piece to the mosaic of economic relationships but has also reinforced the notion that in the realm of statistics, the extraordinary often lurks behind the facade of the ordinary. It’s as if we've stumbled upon a treasure map hidden in the most unlikely of places – a reminder that in the world of data analysis, the unexpected is not just a possibility but a promise waiting to be unraveled.

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 British American Tobacco p.l.c.'s stock price (BTI). 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]]
Pipelayers in North Dakota and Puffing on BTI: A Peculiar Partnership

[[ABSTRACT]]
In this scholarly exploration, we dive into the unlikely connection between the number of pipelayers in North Dakota and the stock price of British American Tobacco p.l.c. (BTI). While one might expect tobacco sales to go up in smoke alongside pipeline activity, our research paints a different picture. Utilizing data from the Bureau of Labor Statistics and LSEG Analytics (Refinitiv), we delved into the numbers from 2003 to 2022 to uncover the correlation coefficient of 0.8491579, with a significant p-value of less than 0.01.

Our findings reveal a surprising link between these seemingly unrelated variables, leaving us to ponder whether the puffing and laying have been secretly in cahoots all along. Could it be that as the pipes go down, BTI stock prices also rise, blowing smoke in the face of conventional wisdom? Join us as we unravel this curiously convoluted connection and light the way for further investigations into the whimsical world of inter-industry correlations.

[[INTRDUCTION]]
Imagine a world where the number of pipelayers in the heart of North Dakota has a peculiar dance with the stock price of British American Tobacco p.l.c. (BTI). One might expect these two to be as closely related as a fish and a bicycle, but as we delved into the depths of this connection, we were met with a revelation more surprising than finding a unicorn in a cornfield.
In this era of big data, we researchers are often tasked with unraveling the mysteries of the universe, but few mysteries are as perplexing and unexpected as the one we are about to reveal. It's as if Sherlock Holmes were called in to investigate the enigmatic partnership of pipelayers and puffing.
As we embark on this scholarly journey of discovery, let us first acknowledge the raised eyebrows and quizzical looks that our topic might incite. After all, what could the labor force of pipeline construction possibly have to do with the performance of a multinational tobacco company’s stocks? It's like trying to find a connection between cats and the consumption of cabbage – seemingly unrelated, yet here we are, determined to shine a light on this shadowy alliance.
So, dear reader, buckle up for a whimsical ride through the wacky world of statistics and correlation. We assure you that by the end of this paper, you will be as wide-eyed as a rabbit in a carrot patch, and you may just find yourself pondering the mysteries of the stock market and industrial activity with the same boggled mind that contemplates the existence of dodo birds and disco music - truly a head-scratcher for the ages.

[[RESULTS]]
Our analysis of the data spanning from 2003 to 2022 has produced some eyebrow-raising findings. The correlation coefficient between the number of pipelayers in North Dakota and the stock price of British American Tobacco p.l.c. (BTI) came in at a surprising 0.8491579. This strong positive correlation astounded us more than finding a kangaroo in a coffee shop, especially given the seemingly independent nature of these two entities.
In addition, the calculated r-squared value of 0.7210692 further solidifies the strength of this association. It’s as if the pipelayers and BTI stock prices have been partners in crime all along, defying the odds and materializing a connection more puzzling than a Rubik's cube made of spaghetti.
Even more astonishing, the p-value of less than 0.01 confidently asserts the statistical significance of this relationship. It’s as if the data itself is tapping us on the shoulder, whispering, "You better believe it, buddy!"
As depicted in Fig. 1, our scatterplot showcases the undeniable connection between the number of pipelayers in North Dakota and BTI stock prices. The data points practically form a perfect heart shape, as if these two variables were destined to be a match made in statistical heaven.
This unexpected revelation has left us marveling at the mysterious dance between pipelayers and puffing, with more questions than answers. Could it be that as the pipelayers labor away, they are unintentionally adding fuel to the fire of BTI stock prices, sculpting an unexpected narrative that defies the logic of market forces?
These findings undoubtedly set the stage for further investigation into the enigmatic kinship of seemingly unrelated industries, reminding us once again that the world of statistics is filled with surprises stranger than fiction and more peculiar than a platypus wearing a top hat.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

Our scholarly expedition into the eccentric entanglement of pipelayers and puffing on BTI has left us scratching our heads more vigorously than a gang of curious monkeys trying to solve a Rubik's Cube. Unveiling a correlation coefficient of 0.8491579 and an r-squared value of 0.7210692, we can confidently say that these variables are as intertwined as spaghetti on a fork – it's a tangled mess, but undeniably connected.

The statistical significance of this relationship, with a p-value of less than 0.01, is like a neon sign flashing "Surprise!" in the face of conventional wisdom. It seems as though the data itself is orchestrating a grand, unexpected reveal, akin to a magician pulling a kangaroo out of a top hat.

As we wrap up our investigation, we are left pondering the curious coalescence of these industries. It's like discovering a secret society of synchronized swimmers in a bathtub – a baffling and delightful revelation.

In conclusion, our findings suggest that as the pipelines lay, so do the foundations for BTI stock prices to rise. It's a partnership more surprising than a penguin doing the tango, leaving us with a sense of bewilderment and an ample supply of questions without answers.

In the grand scheme of scholarly pursuits, the enigmatic kinship of pipelayers and puffing on BTI poses more riddles than a Sphinx on a Sudoku puzzle. Therefore, we assert that further research in this domain would be as futile as trying to teach a fish to ride a bicycle – a comical endeavor with little prospect of substantial gain.

In this peculiar partnership between pipelayers and puffing, we bid adieu with the realization that the realm of statistics is as capricious and comically confounding as a three-ring circus operated by cats. No more research is needed in this wacky world of inter-industry correlations!

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 in North Dakota and Puffing on BTI: A Peculiar Partnership. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unconventional Collaborations

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 in North Dakota and Puffing on BTI: A Peculiar Partnership. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Unconventional 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 in North Dakota and Puffing on BTI: A Peculiar Partnership with an abstract of In this scholarly exploration, we dive into the unlikely connection between the number of pipelayers in North Dakota and the stock price of British American Tobacco p.l.c. (BTI). While one might expect tobacco sales to go up in smoke alongside pipeline activity, our research paints a different picture. Utilizing data from the Bureau of Labor Statistics and LSEG Analytics (Refinitiv), we delved into the numbers from 2003 to 2022 to uncover the correlation coefficient of 0.8491579, with a significant p-value of less than 0.01.
Our findings reveal a surprising link between these seemingly unrelated variables, leaving us to ponder whether the puffing and laying have been secretly in cahoots all along. Could it be that as the pipes go down, BTI stock prices also rise, blowing smoke in the face of conventional wisdom? Join us as we unravel this curiously convoluted connection and light the way for further investigations into the whimsical world of inter-industry correlations.

ChatGPT:

pipelayers, North Dakota, British American Tobacco, BTI, correlation, stock price, tobacco sales, pipeline activity, Bureau of Labor Statistics, LSEG Analytics, Refinitiv, correlation coefficient, p-value, inter-industry correlations

*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

British American Tobacco p.l.c.'s stock price (BTI)
Detailed data title: Opening price of British American Tobacco p.l.c. (BTI) on the first trading day of the year
Source: LSEG Analytics (Refinitiv)
Additional Info: ^{See full details} Via Microsoft Excel Stockhistory function

See what else correlates with British American Tobacco p.l.c.'s stock price (BTI)

Correlation r = 0.8491579 (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 = 0.7210692 (Coefficient of determination)
This means 72.1% of the change in the one variable (i.e., British American Tobacco p.l.c.'s stock price (BTI)) is predictable based on the change in the other (i.e., The number of pipelayers in North Dakota) over the 20 years from 2003 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.2E-6.^Show 0.0000021912449923860844000000
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 0.00022% of random cases. Said differently, if you correlated 456,362 random variables^Note You don't actually need 456 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 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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	2022
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	190
British American Tobacco p.l.c.'s stock price (BTI) (Stock price)	9.98	13.78	17.35	22.74	29.03	39.05	26.51	32.52	38.81	47.59	50.64	53.12	53.55	54.69	56.58	67.71	31.23	42.94	37.92	37.52

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([70,80,110,140,210,200,130,120,150,320,310,470,360,450,330,540,230,130,60,190,])
array_2 = np.array([9.98,13.78,17.35,22.74,29.03,39.05,26.51,32.52,38.81,47.59,50.64,53.12,53.55,54.69,56.58,67.71,31.23,42.94,37.92,37.52,])
array_1_name = "The number of pipelayers in North Dakota"
array_2_name = "British American Tobacco p.l.c.'s stock price (BTI)"

# 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 British American Tobacco p.l.c.'s stock price (BTI)
AI-generated correlation image
The spurious research paper: Pipelayers in North Dakota and Puffing on BTI: A Peculiar Partnership

View another random correlation

How fun was this correlation?

Cheers to you for rating this correlation!

Correlation ID: 2578 · Black Variable ID: 12691 · Red Variable ID: 1666


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