Spurious correlation #3,153 · 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 plumbers in Florida and the second variable is University Lecturer salaries in the US. The chart goes from 2009 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 plumbers in Florida and the second variable is University Lecturer salaries in the US. The chart goes from 2009 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of plumbers in Florida rose, so did their expertise in pipe systems. This inadvertently led to a surge in knowledge flow, creating a pressure for universities to keep up. Hence, they had to shell out more money to attract top lecturer talent, causing a rise in lecturer salaries nationwide. It seems like the plumbers were not just great at fixing leaks, but also at creating a pipeline of success for educators.

^{Show image generation prompt} Model: dalle-3
Prompt: Visual prompt: Generate an image capturing the contrast between bustling university lecture halls and overwhelmed plumbers in Florida. The scene should show crowded lecture halls filled with students and lecturers discussing "pipe dreams" expertise, while in contrast, a group of frantic plumbers are shown dealing with a multitude of leaky faucets in various settings across Florida. The image should convey the sense of urgency and demand in both professions, with a spotlight on the dichotomy between the academic setting and the practical, hands-on work of the plumbers. 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 plumbers in Florida and University Lecturer salaries in the US. 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: Minimalism Cutsy art illustration A TIME magazine cover image Low poly Art nouveau
ChatGPT: A TIME magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both The number of plumbers in Florida and University Lecturer salaries in the US, in the following situation: As the number of plumbers in Florida plunged, universities couldn't handle the influx of leaky faucets. This forced them to recruit more lecturers, leading to a hike in their salaries as the demand for "pipe dreams" expertise skyrocketed.. Keep the description simple.
ChatGPT: In Florida, the number of plumbers dwindled, causing a surge in leaky faucets across the state. At the same time, universities across the US were bustling with an increased need for lecturers, evident in the rising demand for "pipe dreams" expertise. This led to a visual scene of busy university lecture halls where lecturers were discussing their expertise, while a group of overwhelmed plumbers struggled to keep up with the influx of leaky faucets in Florida.

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 TIME magazine cover image ] and depicting this scene: In Florida, the number of plumbers dwindled, causing a surge in leaky faucets across the state. At the same time, universities across the US were bustling with an increased need for lecturers, evident in the rising demand for "pipe dreams" expertise. This led to a visual scene of busy university lecture halls where lecturers were discussing their expertise, while a group of overwhelmed plumbers struggled to keep up with the influx of leaky faucets in Florida. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Visual prompt: Generate an image capturing the contrast between bustling university lecture halls and overwhelmed plumbers in Florida. The scene should show crowded lecture halls filled with students and lecturers discussing "pipe dreams" expertise, while in contrast, a group of frantic plumbers are shown dealing with a multitude of leaky faucets in various settings across Florida. The image should convey the sense of urgency and demand in both professions, with a spotlight on the dichotomy between the academic setting and the practical, hands-on work of the plumbers.

*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 plumbers in Florida positively influenced University Lecturer salaries in the US. Include one good pun.

AI academic paper

(Because p < 0.01)

The Pipe Dreams of Academia: A Correlational Study of Plumbers and Professors

The Journal of Interdisciplinary Pipe 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 plumbers in Florida and University Lecturer salaries in the US. 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]]
The Pipe Dreams of Academia: A Correlational Study of Plumbers and Professors

[[ABSTRACT]]
In this paper, we present a seemingly absurd yet curiously connected inquiry into the relationship between the number of plumbers in Florida and the salaries of university lecturers in the US. We employed data from the Bureau of Labor Statistics and the National Center for Education Statistics to unravel the enigmatic ties between these seemingly unrelated professions. Through rigorous analysis, we discovered a statistically significant correlation coefficient of 0.9554005 and p < 0.01 for the years 2009 to 2021, much to our bemusement.

Our findings suggest an unexpectedly strong positive correlation between the two variables, defying traditional expectations. As the number of plumbers in Florida fluctuated, so did the salaries of university lecturers across the US, sending shockwaves through the academic community. While we cannot unequivocally claim causation, the observable relationship between these disparate realms invites further exploration and whimsical contemplation, as we navigate the labyrinthine interconnectedness of society and labor markets. The peculiar links we uncovered between the wrench-wielding workforce and the ivory tower denizens serve as a testament to the delightful unpredictability of scholarly inquiry – a reminder that, in the scholarly pursuit of knowledge, sometimes the most surprising connections emerge from the unlikeliest of places.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the arcane realm of academic research, where erudite scholars delve deep into the annals of data and statistics, there exist phenomena that defy logic and confound expectation. Such is the case with our investigation into the connection between the number of plumbers in Florida and the salaries of university lecturers in the US. On the surface, these two professions may seem as far apart as Jupiter and a clogged drain. However, as we embarked on our analytical escapade, we found ourselves entangled in a web of unexpected correlations and confounding synchronicities.
The pursuit of knowledge often takes us on whimsical journeys, and this particular expedition led us into uncharted territory – where the clang of wrenches meets the echo of academic discourse. What started as an offhand jest during a coffee break swiftly evolved into a full-fledged inquiry, driven by the audacious spirit of scholarly curiosity and a penchant for embracing the absurd.
In this paper, we aim to unravel the peculiar dance between plumbing and pedagogy, forgoing the shackles of convention to explore the enigmatic interplay between labor markets and academic compensation. We dare to peer beyond the surface, where the mortarboard meets the monkey wrench, and where the labyrinthine pathways of economic cause and effect lead us into the most unexpected nooks and crannies of correlation.
Buckle up, dear reader, for our journey will traverse the curious intersections of blue-collar artisanship and ivory tower intellect. As we marinate in the data, we invite you to join us in reveling in the whimsy of scholarly investigation, for in the world of academia, it’s not just the pipes that are full of twists and turns.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The correlation between seemingly unrelated professions has long been a source of academic intrigue and amusement. Smith et al. (2015) delved into the unexpected connections between labor markets and educational economics, shedding light on the interplay of various occupations and their impact on compensation in the educational sector. Similarly, Doe and Jones (2018) explored the intricate web of factors influencing labor market dynamics, uncovering surprising parallels between diverse industries.

As we venture further into the idiosyncratic realm of our inquiry, we encounter a delightful array of literature that tangentially relates to the enigmatic relationship between the number of plumbers in Florida and the salaries of university lecturers in the US. "The Economics of Higher Education" by Johnson and Smith (2017) offers poignant insights into the financial intricacies of academia, though sadly lacking in plumbing references. On the more tangential side, "Fluid Dynamics: A Practical Guide" by Waters (2016) presents itself as an unexpected possibility for unraveling the fluidity of labor market dynamics, albeit with a heavier emphasis on liquids than on vocational pursuits.

Turning to the world of fiction, "A Tale of Two Wrenches" by Charles Dickenstein promises a riveting narrative of vocational vicissitudes and improbable connections, though regrettably devoid of empirical evidence. "The Plumber's Pipedream" by Jane Austopsky, while a captivating title, offers little in terms of scholarly insight but may serve as a source of comic relief in our rigorous pursuit of knowledge.

And now, in a daring departure from convention, we stumbled upon an unorthodox source of insight - the ancient art of divining correlations from mundane fragments of everyday life. After perusing endless scrolls of CVS receipts, we found, to our astonishment, a recurring pattern linking the purchase of drain cleaner in Florida with fluctuations in tenured professor salaries nationwide. While undoubtedly unconventional, this revelatory approach challenges the very essence of conventional scholarly inquiry and demands further contemplation.

In the whimsical tapestry of scholarly exploration, where the threads of knowledge weave together in unpredictable patterns, one cannot help but revel in the delightful absurdity of academic pursuits. As we wade through the scholarly seas, accompanied by the echoing clang of wrenches and the erudite discourse of academia, we must remember that sometimes, the most extraordinary discoveries emerge from the humblest of origins.

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 plumbers in Florida and University Lecturer salaries in the US. 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]]
The Pipe Dreams of Academia: A Correlational Study of Plumbers and Professors

[[ABSTRACT]]
In this paper, we present a seemingly absurd yet curiously connected inquiry into the relationship between the number of plumbers in Florida and the salaries of university lecturers in the US. We employed data from the Bureau of Labor Statistics and the National Center for Education Statistics to unravel the enigmatic ties between these seemingly unrelated professions. Through rigorous analysis, we discovered a statistically significant correlation coefficient of 0.9554005 and p < 0.01 for the years 2009 to 2021, much to our bemusement.

Our findings suggest an unexpectedly strong positive correlation between the two variables, defying traditional expectations. As the number of plumbers in Florida fluctuated, so did the salaries of university lecturers across the US, sending shockwaves through the academic community. While we cannot unequivocally claim causation, the observable relationship between these disparate realms invites further exploration and whimsical contemplation, as we navigate the labyrinthine interconnectedness of society and labor markets. The peculiar links we uncovered between the wrench-wielding workforce and the ivory tower denizens serve as a testament to the delightful unpredictability of scholarly inquiry – a reminder that, in the scholarly pursuit of knowledge, sometimes the most surprising connections emerge from the unlikeliest of places.

[[LITERATURE REVIEW]]
The correlation between seemingly unrelated professions has long been a source of academic intrigue and amusement. Smith et al. (2015) delved into the unexpected connections between labor markets and educational economics, shedding light on the interplay of various occupations and their impact on compensation in the educational sector. Similarly, Doe and Jones (2018) explored the intricate web of factors influencing labor market dynamics, uncovering surprising parallels between diverse industries.
As we venture further into the idiosyncratic realm of our inquiry, we encounter a delightful array of literature that tangentially relates to the enigmatic relationship between the number of plumbers in Florida and the salaries of university lecturers in the US. "The Economics of Higher Education" by Johnson and Smith (2017) offers poignant insights into the financial intricacies of academia, though sadly lacking in plumbing references. On the more tangential side, "Fluid Dynamics: A Practical Guide" by Waters (2016) presents itself as an unexpected possibility for unraveling the fluidity of labor market dynamics, albeit with a heavier emphasis on liquids than on vocational pursuits.
Turning to the world of fiction, "A Tale of Two Wrenches" by Charles Dickenstein promises a riveting narrative of vocational vicissitudes and improbable connections, though regrettably devoid of empirical evidence. "The Plumber's Pipedream" by Jane Austopsky, while a captivating title, offers little in terms of scholarly insight but may serve as a source of comic relief in our rigorous pursuit of knowledge.
And now, in a daring departure from convention, we stumbled upon an unorthodox source of insight - the ancient art of divining correlations from mundane fragments of everyday life. After perusing endless scrolls of CVS receipts, we found, to our astonishment, a recurring pattern linking the purchase of drain cleaner in Florida with fluctuations in tenured professor salaries nationwide. While undoubtedly unconventional, this revelatory approach challenges the very essence of conventional scholarly inquiry and demands further contemplation.
In the whimsical tapestry of scholarly exploration, where the threads of knowledge weave together in unpredictable patterns, one cannot help but revel in the delightful absurdity of academic pursuits. As we wade through the scholarly seas, accompanied by the echoing clang of wrenches and the erudite discourse of academia, we must remember that sometimes, the most extraordinary discoveries emerge from the humblest of origins.

[[RESULTS]]
The statistical analysis revealed a robust and positively fascinating correlation between the number of plumbers in Florida and the salaries of university lecturers in the United States. The correlation coefficient of 0.9554005 startled even the most seasoned researchers, leaving us in disbelief akin to realizing that Pegasus is actually a unifying symbol for both plumbers and professors. The r-squared value of 0.9127901 further reinforced the strength of the relationship, much like a reinforced pipe can withstand the test of time and pressure.
In line with these findings, the p-value of less than 0.01 unequivocally indicated the statistical significance of the relationship, prompting us to boldly proclaim that the connection between these seemingly unrelated professions is more than a mere pipe dream. It’s as tangible as a leaky faucet, dripping with significance and ripe for further investigation.
Our revelatory results challenge conventional wisdom and beckon us to dream of improbable connections – a realization as shocking as finding out that Sigmund Freud moonlighted as a plumber in Vienna. The accompanying scatterplot (Fig. 1), which we present here with bated breath and a twinkle in our eyes, showcases the distinct and undeniable pattern of correlation between the number of plumbers in Florida and university lecturer salaries across the US. It’s as if the fates of these professions were intertwined in a whimsical ballet, pirouetting through the esoteric and capricious world of economic phenomena.
This unforeseen correlation would make even the most seasoned researcher do a double-take, much like spotting a rare albino alligator in a murky bog. We stand both awed and humbled by the revelatory power of data, reminding us that in the scholarly pursuit of knowledge, sometimes the most unexpected connections emerge from the unlikeliest of sources.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

In the immortal words of Robert Frost, "Two roads diverged in a yellow wood, and sorry I could not travel both...but hey, let's see if these roads are correlated somehow!" Our findings have uncorked a Pandora's box of peculiar and whimsical implications, much like discovering that the Loch Ness Monster has been moonlighting as a plumber in the Florida swamps. The results of our study provide solid support for the prior research that ventured into the labyrinthine world of interconnected professions and labor market dynamics.

The unexpectedly strong positive correlation we uncovered between the number of plumbers in Florida and the salaries of university lecturers in the US hearkens back to Smith et al.'s (2015) pioneering examination of the intricate interplay between diverse occupations and their impact on compensation in the education sector. It's as if these two seemingly unrelated realms had been engaged in a clandestine tango across the socio-economic landscape, twirling and dipping in a waltz of statistical significance.

Our results lend credence to the work of Doe and Jones (2018), who delved into the myriad factors influencing labor market dynamics and stumbled upon startling parallels between industries. With a correlation coefficient of 0.9554005 that practically shouts "I'm here to disrupt your conventional assumptions!", our study adds a robust layer of evidence to the web of curiosity surrounding the interconnectedness of labor markets and educational economics.

In a twist that could rival a Shakespearean comedy, our findings stand as a testament to the delightful unpredictability of scholarly inquiry - a reminder that, in the scholarly pursuit of knowledge, sometimes the most surprising connections emerge from the unlikeliest of places. We are left to ponder whether the wages of university lecturers dance to the tune of plumbing fixtures, much like a quirky ballet staged in the unlikeliest of economic theaters.

The tangible link we uncovered between these distinct professions prompts us to consider the significance of this association, which resonates as strongly as a ringing endorsement from the ghost of Thomas Edison. While our study does not offer a causal explanation for this fascinating linkage, it certainly provides a jumping-off point for further exploration into the peculiar and paradoxical interplay of labor markets.

In the end, our study leaves us with more questions than answers, much like discovering that the academic ivory tower and the plumbing industry share a keystone that connects them in surprising and enigmatic ways. It compels us to embrace the delightful absurdity of academic inquiry, where the most improbable connections can unravel in the rigorous pursuit of knowledge. As we navigate the scholarly landscape, we must remain open to the possibility that sometimes, the most extraordinary correlations emerge from the humblest of origins - even if those origins involve a seemingly unremarkable wrench and a lofty professorial salary.

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 plumbers in Florida and University Lecturer salaries in the US. 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]]
The Pipe Dreams of Academia: A Correlational Study of Plumbers and Professors

[[ABSTRACT]]
In this paper, we present a seemingly absurd yet curiously connected inquiry into the relationship between the number of plumbers in Florida and the salaries of university lecturers in the US. We employed data from the Bureau of Labor Statistics and the National Center for Education Statistics to unravel the enigmatic ties between these seemingly unrelated professions. Through rigorous analysis, we discovered a statistically significant correlation coefficient of 0.9554005 and p < 0.01 for the years 2009 to 2021, much to our bemusement.

Our findings suggest an unexpectedly strong positive correlation between the two variables, defying traditional expectations. As the number of plumbers in Florida fluctuated, so did the salaries of university lecturers across the US, sending shockwaves through the academic community. While we cannot unequivocally claim causation, the observable relationship between these disparate realms invites further exploration and whimsical contemplation, as we navigate the labyrinthine interconnectedness of society and labor markets. The peculiar links we uncovered between the wrench-wielding workforce and the ivory tower denizens serve as a testament to the delightful unpredictability of scholarly inquiry – a reminder that, in the scholarly pursuit of knowledge, sometimes the most surprising connections emerge from the unlikeliest of places.

[[INTRDUCTION]]
In the arcane realm of academic research, where erudite scholars delve deep into the annals of data and statistics, there exist phenomena that defy logic and confound expectation. Such is the case with our investigation into the connection between the number of plumbers in Florida and the salaries of university lecturers in the US. On the surface, these two professions may seem as far apart as Jupiter and a clogged drain. However, as we embarked on our analytical escapade, we found ourselves entangled in a web of unexpected correlations and confounding synchronicities.
The pursuit of knowledge often takes us on whimsical journeys, and this particular expedition led us into uncharted territory – where the clang of wrenches meets the echo of academic discourse. What started as an offhand jest during a coffee break swiftly evolved into a full-fledged inquiry, driven by the audacious spirit of scholarly curiosity and a penchant for embracing the absurd.
In this paper, we aim to unravel the peculiar dance between plumbing and pedagogy, forgoing the shackles of convention to explore the enigmatic interplay between labor markets and academic compensation. We dare to peer beyond the surface, where the mortarboard meets the monkey wrench, and where the labyrinthine pathways of economic cause and effect lead us into the most unexpected nooks and crannies of correlation.
Buckle up, dear reader, for our journey will traverse the curious intersections of blue-collar artisanship and ivory tower intellect. As we marinate in the data, we invite you to join us in reveling in the whimsy of scholarly investigation, for in the world of academia, it’s not just the pipes that are full of twists and turns.

[[RESULTS]]
The statistical analysis revealed a robust and positively fascinating correlation between the number of plumbers in Florida and the salaries of university lecturers in the United States. The correlation coefficient of 0.9554005 startled even the most seasoned researchers, leaving us in disbelief akin to realizing that Pegasus is actually a unifying symbol for both plumbers and professors. The r-squared value of 0.9127901 further reinforced the strength of the relationship, much like a reinforced pipe can withstand the test of time and pressure.
In line with these findings, the p-value of less than 0.01 unequivocally indicated the statistical significance of the relationship, prompting us to boldly proclaim that the connection between these seemingly unrelated professions is more than a mere pipe dream. It’s as tangible as a leaky faucet, dripping with significance and ripe for further investigation.
Our revelatory results challenge conventional wisdom and beckon us to dream of improbable connections – a realization as shocking as finding out that Sigmund Freud moonlighted as a plumber in Vienna. The accompanying scatterplot (Fig. 1), which we present here with bated breath and a twinkle in our eyes, showcases the distinct and undeniable pattern of correlation between the number of plumbers in Florida and university lecturer salaries across the US. It’s as if the fates of these professions were intertwined in a whimsical ballet, pirouetting through the esoteric and capricious world of economic phenomena.
This unforeseen correlation would make even the most seasoned researcher do a double-take, much like spotting a rare albino alligator in a murky bog. We stand both awed and humbled by the revelatory power of data, reminding us that in the scholarly pursuit of knowledge, sometimes the most unexpected connections emerge from the unlikeliest of sources.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has revealed a delightfully inconceivable correlation between the number of plumbers in Florida and the salaries of university lecturers in the United States. This unforeseen connection is as surprising as discovering a hidden treasure map in a plumber’s toolbox. The statistical significance of this relationship, with a correlation coefficient akin to finding a golden wrench in the sea of data, challenges traditional paradigms and beckons us to embrace the whimsical waltz of scholarly exploration.

Our findings have opened a Pandora’s toolbox of questions and curiosities, prompting us to ponder the mysterious ways in which the hum of pipe wrenches resonates with the resonance of academic discourse. It’s as if the ghost of Isaac Newton is playfully sending apples and plumbers cascading through the hallowed halls of academia, leaving us with more questions than answers and more laughter than solemn contemplation.

As we peer into the labyrinth of labor markets and scholarly pursuits, we stand at the intersection of perspiration and inspiration, where the rhythm of blue-collar toil seems to harmonize with the symphony of scholarly pursuit. Our study highlights the intriguing interplay between economic phenomena and professional trajectories, reminding us that the world of academic research is as riddled with unexpected connections as a leaky pipe.

In light of these revelatory findings, we boldly assert that no further research is needed in this area. Our work stands as a monument to the capricious dance of data, where the cogs of correlation churn out revelations more surprising than finding a scholarly journal in a plumber’s toolbox. Let us embrace the absurdity of scholarly inquiry and revel in the delightful unpredictability of knowledge, for in the esoteric realm of research, sometimes the most remarkable insights emerge from the unlikeliest of places.

And with that, we leave you to ponder the mysterious synchronicities of scholarly exploration and the gleeful absurdity of uncovering connections where none seemed to exist. As we bid adieu to this confounding cadence of correlations, let us remember that in the scholarly pursuit of knowledge, sometimes it’s the most unexpected findings that prove to be the most enlightening.

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 The Pipe Dreams of Academia: A Correlational Study of Plumbers and Professors. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Interdisciplinary Pipe 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 The Pipe Dreams of Academia: A Correlational Study of Plumbers and Professors. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Interdisciplinary Plumbing 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 The Pipe Dreams of Academia: A Correlational Study of Plumbers and Professors with an abstract of In this paper, we present a seemingly absurd yet curiously connected inquiry into the relationship between the number of plumbers in Florida and the salaries of university lecturers in the US. We employed data from the Bureau of Labor Statistics and the National Center for Education Statistics to unravel the enigmatic ties between these seemingly unrelated professions. Through rigorous analysis, we discovered a statistically significant correlation coefficient of 0.9554005 and p < 0.01 for the years 2009 to 2021, much to our bemusement.
Our findings suggest an unexpectedly strong positive correlation between the two variables, defying traditional expectations. As the number of plumbers in Florida fluctuated, so did the salaries of university lecturers across the US, sending shockwaves through the academic community. While we cannot unequivocally claim causation, the observable relationship between these disparate realms invites further exploration and whimsical contemplation, as we navigate the labyrinthine interconnectedness of society and labor markets. The peculiar links we uncovered between the wrench-wielding workforce and the ivory tower denizens serve as a testament to the delightful unpredictability of scholarly inquiry – a reminder that, in the scholarly pursuit of knowledge, sometimes the most surprising connections emerge from the unlikeliest of places.

ChatGPT:

"plumbers Florida salaries university lecturers," "correlation between plumbers professors," "labor statistics education correlation," "plumbers salaries academic labor market," "unconventional correlations occupations," "unexpected connections workforce academia."

*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 plumbers in Florida
Detailed data title: BLS estimate of plumbers, pipefitters, and steamfitters in Florida
Source: Bureau of Larbor Statistics
See what else correlates with The number of plumbers in Florida

University Lecturer salaries in the US
Detailed data title: Average salary of full-time instructional faculty on 9-month contracts in degree-granting postsecondary institutions, by academic rank of Lecturer
Source: National Center for Education Statistics
See what else correlates with University Lecturer salaries in the US

Correlation r = 0.9554005 (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 = 0.9127901 (Coefficient of determination)
This means 91.3% of the change in the one variable (i.e., University Lecturer salaries in the US) is predictable based on the change in the other (i.e., The number of plumbers in Florida) over the 13 years from 2009 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.6E-7.^Show 0.0000003640559222546552000000
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 0.96 in 3.6E-5% of random cases. Said differently, if you correlated 2,746,831 random variables^Note You don't actually need 2 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 12 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 12 because we have two variables measured over a period of 13 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.

[ 0.85, 0.99 ] 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.

	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
The number of plumbers in Florida (Laborers)	23200	20100	19370	15360	16580	18590	20970	23060	24200	25360	26280	25610	23800
University Lecturer salaries in the US (Salary)	67906	67077	66129	64696	65494	65938	67828	68305	69125	69647	70577	70489	67454

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.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

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([23200,20100,19370,15360,16580,18590,20970,23060,24200,25360,26280,25610,23800,])
array_2 = np.array([67906,67077,66129,64696,65494,65938,67828,68305,69125,69647,70577,70489,67454,])
array_1_name = "The number of plumbers in Florida"
array_2_name = "University Lecturer salaries in the US"

# 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 plumbers in Florida
Line chart for only University Lecturer salaries in the US
AI-generated correlation image
The spurious research paper: The Pipe Dreams of Academia: A Correlational Study of Plumbers and Professors

View another random correlation

How fun was this correlation?

Your rating is stellar!

Correlation ID: 3153 · Black Variable ID: 6614 · Red Variable ID: 1205


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