Spurious correlation #1,823 · 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 library assistants in North Dakota and the second variable is Petroluem consumption in Norway. The chart goes from 2003 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of library assistants in North Dakota and the second variable is Petroluem consumption in Norway. The chart goes from 2003 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of library assistants in North Dakota dwindled, so too did their ability to shelve books efficiently. Unbeknownst to many, North Dakota library assistants were the unsung heroes of the "Library of Unnecessary Knowledge." This ripple effect led to a drastic decrease in the production of obscure Norwegian oil consumption manuals, thus lowering Norway's overall need for petroleum. With fewer librarian-led quests for unconventional information, Norway found innovative ways to reduce their reliance on oil, opting instead for eco-friendly alternatives like herring grease and fermented lingonberry juice to power their vehicles. It seems that in the global saga of knowledge and petroleum, the plot thickens in the most unexpected and overdue ways!

^{Show image generation prompt} Model: dalle-3
Prompt: [A photo-realistic image] Create an image of a cozy library in North Dakota, with warm lighting and shelves filled with books. Show a team of diligent library assistants sorting books and helping patrons. Also depict a scene across the ocean in Norway, where a fleet of cars and trucks travels through the scenic countryside, fueled by petroleum. The image should capture the contrast between the tranquil library and the bustling activity of the vehicles in the Norwegian landscape. Let the lighting in the library be inviting, and the vehicles in Norway should be depicted against a picturesque natural backdrop. 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 library assistants in North Dakota and Petroluem consumption in Norway. 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: Woodblock painting A photo-realistic image Glitch art Data cyber art Cyber folk
ChatGPT: A photo-realistic 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 library assistants in North Dakota and Petroluem consumption in Norway together. Keep the description simple.
ChatGPT: In a cozy library in North Dakota, a team of diligent library assistants is busy sorting books and helping patrons. Meanwhile, across the ocean in Norway, a fleet of cars and trucks is fueled by petroleum, traversing the scenic countryside.

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 photo-realistic image ] and depicting this scene: In a cozy library in North Dakota, a team of diligent library assistants is busy sorting books and helping patrons. Meanwhile, across the ocean in Norway, a fleet of cars and trucks is fueled by petroleum, traversing the scenic countryside. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [A photo-realistic image] Create an image of a cozy library in North Dakota, with warm lighting and shelves filled with books. Show a team of diligent library assistants sorting books and helping patrons. Also depict a scene across the ocean in Norway, where a fleet of cars and trucks travels through the scenic countryside, fueled by petroleum. The image should capture the contrast between the tranquil library and the bustling activity of the vehicles in the Norwegian landscape. Let the lighting in the library be inviting, and the vehicles in Norway should be depicted against a picturesque natural backdrop.

*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 a decrease in The number of library assistants in North Dakota caused Petroluem consumption in Norway to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)

More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway

The International Journal of Quirky Connections

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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of library assistants in North Dakota and Petroluem consumption in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then 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]]
More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway

[[ABSTRACT]]
This study explores the peculiar relationship between the number of library assistants in North Dakota and petroleum consumption in Norway. Using data from the Bureau of Labor Statistics and the Energy Information Administration, a correlation coefficient of 0.7012281 and p < 0.01 was calculated for the period spanning 2003 to 2021. Despite the geographical and cultural gulf between the two regions, the results suggest a surprising linkage – as unexpected as finding a book on anti-gravity! This paper delves into the statistical analysis and potential explanations for this correlation, shedding light on the mysterious interplay between seemingly unrelated factors. After all, who would have thought that lugging books and guzzling gas could be intertwined?

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The enigma of seemingly unrelated phenomena interwoven throughout the fabric of our world never ceases to amaze. From the peculiar mating habits of anglerfish to the confounding correlation between the number of library assistants in North Dakota and petroleum consumption in Norway, the mysteries of science and statistics continue to pique our curiosity. As Albert Einstein famously quipped, "The most beautiful thing we can experience is the mysterious. It is the source of all true art and science – and dad jokes."
In the annals of scientific inquiry, unexpected connections have often yielded profound insight and revelation. Just as the discovery of penicillin was stumbled upon by Sir Alexander Fleming in a happy accident, the unearthing of this peculiar relationship between library assistants and petroleum consumption invites us to contemplate the seemingly disparate forces at play. It's a bit like finding a rare book nestled among a sea of paperbacks - surprising, yet utterly captivating!
The present study endeavors to unravel this conundrum, peering through the lens of rigorous statistical analysis to examine the linkage between these two divergent variables. With an exploratory spirit reminiscent of Lewis and Clark embarking on their expedition, we venture into uncharted territory to shed light on this unexpected correlation. After all, as researchers, we are no strangers to navigating the labyrinth of data, much like a librarian deftly guiding patrons through the maze of bookshelves.
As we embark on this intellectual journey, we are reminded of the words of J.R.R. Tolkien, who aptly observed, "Not all those who wander are lost." In the realm of scientific exploration, our journey may take us down unexpected paths, but the insights garnered along the way have the potential to illuminate hidden truths. So, buckle up as we delve into the curious case of more library assistants and more petrol phesants - and prepare for the statistical twists and turns that lie ahead!

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The previous research on the correlation between the number of library assistants in North Dakota and petroleum consumption in Norway has been scant, to say the least. In "Smith et al.'s" comprehensive study, no discernible link was found between these two variables, leaving the scientific community scratching their heads in perplexity. However, recent findings by "Doe" and "Jones" have hinted at a potential association, sparking renewed interest in this quirky connection. Despite the lack of consensus, the relationship between library assistants and petrol consumption remains as enigmatic as a book that mysteriously appears on your shelf overnight.

Real-life economics and energy consumption books such as "Energy Economics" by Peter Zweifel and "Sustainable Energy – Without the Hot Air" by David J.C. MacKay have delved into the complexities of petroleum consumption, shedding light on the intricate web of factors influencing this phenomenon. On the other hand, fictional works such as "The Library Book" by Susan Orlean and "The Shadow of the Wind" by Carlos Ruiz Zafón have alluded to the mystique surrounding libraries and books, offering a narrative lens through which to view the peculiar relationship at hand. Perhaps the intertwining of library assistants and petrol consumption is as improbable as finding a tome of ancient wisdom hidden within the stacks of your local library.

One particularly unconventional source of insight emerged during the course of this literature review, as the researchers stumbled upon a series of obscure fiction novels purportedly authored by a collective of gasoline-loving pheasants. Although their literary merit is questionable, these books, with titles like "The Pheasant and the Pump" and "Fueling Feathers: A Petrol Pheasant's Tale," offered an unexpected perspective on the intersection of avian interests and energy consumption. While their credibility is dubious at best, these texts provided a whimsical reminder of the unexpected places one's academic pursuits may lead – akin to stumbling upon a dad joke in the footnotes of a scholarly article.

As the literature review draws to a close, the authors are left with more questions than answers, much like a reader perusing an unfinished mystery novel. The bizarre yet tantalizing connection between library assistants in North Dakota and petroleum consumption in Norway continues to defy conventional expectations, beckoning further investigation and perhaps a lighthearted chuckle or two along the way. After all, in the unpredictable realm of academic inquiry, one must always be prepared for the unexpected – much like a well-timed dad joke in the midst of a scholarly discourse.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of library assistants in North Dakota and Petroluem consumption in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Energy Information Administration . You used data from 2003 to 2021

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway

[[ABSTRACT]]
This study explores the peculiar relationship between the number of library assistants in North Dakota and petroleum consumption in Norway. Using data from the Bureau of Labor Statistics and the Energy Information Administration, a correlation coefficient of 0.7012281 and p < 0.01 was calculated for the period spanning 2003 to 2021. Despite the geographical and cultural gulf between the two regions, the results suggest a surprising linkage – as unexpected as finding a book on anti-gravity! This paper delves into the statistical analysis and potential explanations for this correlation, shedding light on the mysterious interplay between seemingly unrelated factors. After all, who would have thought that lugging books and guzzling gas could be intertwined?

[[INTRODUCTION]]
The enigma of seemingly unrelated phenomena interwoven throughout the fabric of our world never ceases to amaze. From the peculiar mating habits of anglerfish to the confounding correlation between the number of library assistants in North Dakota and petroleum consumption in Norway, the mysteries of science and statistics continue to pique our curiosity. As Albert Einstein famously quipped, "The most beautiful thing we can experience is the mysterious. It is the source of all true art and science – and dad jokes."
In the annals of scientific inquiry, unexpected connections have often yielded profound insight and revelation. Just as the discovery of penicillin was stumbled upon by Sir Alexander Fleming in a happy accident, the unearthing of this peculiar relationship between library assistants and petroleum consumption invites us to contemplate the seemingly disparate forces at play. It's a bit like finding a rare book nestled among a sea of paperbacks - surprising, yet utterly captivating!
The present study endeavors to unravel this conundrum, peering through the lens of rigorous statistical analysis to examine the linkage between these two divergent variables. With an exploratory spirit reminiscent of Lewis and Clark embarking on their expedition, we venture into uncharted territory to shed light on this unexpected correlation. After all, as researchers, we are no strangers to navigating the labyrinth of data, much like a librarian deftly guiding patrons through the maze of bookshelves.
As we embark on this intellectual journey, we are reminded of the words of J.R.R. Tolkien, who aptly observed, "Not all those who wander are lost." In the realm of scientific exploration, our journey may take us down unexpected paths, but the insights garnered along the way have the potential to illuminate hidden truths. So, buckle up as we delve into the curious case of more library assistants and more petrol phesants - and prepare for the statistical twists and turns that lie ahead!

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

In order to investigate the curious correlation between the number of library assistants in North Dakota and petroleum consumption in Norway, a comprehensive and systematic methodology was employed. The data used in this study was primarily sourced from the Bureau of Labor Statistics and the Energy Information Administration, covering the period from 2003 to 2021. The selection of these sources was based on their extensive coverage and reliability, ensuring that the data used for analysis was as robust as a well-constructed statistical model.

Once the data was gathered, the research team engaged in a painstaking process of data scrubbing and cleaning, akin to the meticulous care a librarian might take in cataloging books. This involved identifying and rectifying any anomalies or inconsistencies in the datasets, ensuring that the statistical analyses were based on accurate and reliable information. After all, just like a good book, the data needed to be in pristine condition to yield meaningful insights.

With the cleaned datasets in hand, the next step involved the calculation of correlation coefficients and statistical significance tests. The correlation coefficient, which quantifies the strength and direction of the relationship between the number of library assistants in North Dakota and petroleum consumption in Norway, was determined using rigorous statistical methods. The P-value, indicating the probability of obtaining the observed results by chance, was also calculated to assess the significance of the correlation. This statistical analysis was conducted with precision and care, much like a surgeon wielding a scalpel in the realm of data.

Furthermore, to ensure that the results were not influenced by extraneous variables or spurious correlations, a series of robustness checks and sensitivity analyses were performed. This involved examining the stability of the relationship between the two variables under various scenarios and conditions, akin to stress-testing a scientific hypothesis. After all, just as a librarian might employ different reference sources to cross-verify information, our research sought to validate the relationship between library assistants and petrol phesants from all angles.

Finally, the findings of the statistical analyses were subjected to thorough peer review and validation, drawing upon the expertise of fellow researchers and statisticians. This rigorous scrutiny and critique aimed to bolster the robustness and reliability of the results, akin to the rigors of academic peer review. After all, every good hypothesis benefits from a bit of healthy skepticism and scrutiny, much like a clever joke improved with a bit of friendly banter.

In summary, the methodology employed in this study combined meticulous data collection, rigorous statistical analysis, and stringent validation processes, equipping us to delve into the enigmatic correlation between the number of library assistants in North Dakota and petroleum consumption in Norway. As we journeyed through this scientific expedition, we remained ever mindful that in the grand symphony of statistical inquiry, even the most unexpected correlations can strike a harmonious chord – much like a dad joke that catches us by surprise.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between The number of library assistants in North Dakota and Petroluem consumption in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Energy Information Administration .

For the time period 2003 to 2021, you found a correlation 0.7012281, r-squared of 0.4917209, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway

[[ABSTRACT]]
This study explores the peculiar relationship between the number of library assistants in North Dakota and petroleum consumption in Norway. Using data from the Bureau of Labor Statistics and the Energy Information Administration, a correlation coefficient of 0.7012281 and p < 0.01 was calculated for the period spanning 2003 to 2021. Despite the geographical and cultural gulf between the two regions, the results suggest a surprising linkage – as unexpected as finding a book on anti-gravity! This paper delves into the statistical analysis and potential explanations for this correlation, shedding light on the mysterious interplay between seemingly unrelated factors. After all, who would have thought that lugging books and guzzling gas could be intertwined?

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The enigma of seemingly unrelated phenomena interwoven throughout the fabric of our world never ceases to amaze. From the peculiar mating habits of anglerfish to the confounding correlation between the number of library assistants in North Dakota and petroleum consumption in Norway, the mysteries of science and statistics continue to pique our curiosity. As Albert Einstein famously quipped, "The most beautiful thing we can experience is the mysterious. It is the source of all true art and science – and dad jokes."
In the annals of scientific inquiry, unexpected connections have often yielded profound insight and revelation. Just as the discovery of penicillin was stumbled upon by Sir Alexander Fleming in a happy accident, the unearthing of this peculiar relationship between library assistants and petroleum consumption invites us to contemplate the seemingly disparate forces at play. It's a bit like finding a rare book nestled among a sea of paperbacks - surprising, yet utterly captivating!
The present study endeavors to unravel this conundrum, peering through the lens of rigorous statistical analysis to examine the linkage between these two divergent variables. With an exploratory spirit reminiscent of Lewis and Clark embarking on their expedition, we venture into uncharted territory to shed light on this unexpected correlation. After all, as researchers, we are no strangers to navigating the labyrinth of data, much like a librarian deftly guiding patrons through the maze of bookshelves.
As we embark on this intellectual journey, we are reminded of the words of J.R.R. Tolkien, who aptly observed, "Not all those who wander are lost." In the realm of scientific exploration, our journey may take us down unexpected paths, but the insights garnered along the way have the potential to illuminate hidden truths. So, buckle up as we delve into the curious case of more library assistants and more petrol phesants - and prepare for the statistical twists and turns that lie ahead!

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis revealed a strong positive correlation between the number of library assistants in North Dakota and petroleum consumption in Norway, with a correlation coefficient of 0.7012281 and an r-squared value of 0.4917209. The p-value was found to be less than 0.01, indicating a statistically significant relationship between the two variables. It seems that as the number of library assistants in North Dakota increased, so did the petrol consumption in Norway. It's almost as if the books were whispering to the petrol pumps across the ocean, saying "fill 'er up!"

(Fig. 1) presents a scatterplot illustrating this unexpected connection. The plot unmistakably depicts a positive linear relationship between the two variables, leaving little room for doubt about the strength of their association. It’s a relationship as clear as a well-written library due date slip!

The findings of this study support the notion that seemingly unrelated factors can indeed exhibit intriguing connections. Just as the equation for the correlation coefficient unveils hidden associations, our research endeavors to unravel the mystery behind this unusual pairing. Who would have thought that the bustling activity of library assistants in North Dakota could coincide with the fuel-hungry habits of Norway? It’s as surprising as finding a book on shipbuilding in a landlocked library!

The statistical significance of this correlation paves the way for further exploration into the underlying mechanisms at play. As researchers, we revel in the uncovering of such enigmatic linkages, much like uncovering the solution to a particularly vexing crossword puzzle. The intricacies of statistical analysis often reveal unexpected patterns, and this study serves as a testament to the significance of rigorous inquiry in unearthing the unlikeliest of associations.

These findings provoke contemplation on the intricate web of interconnections that permeate our world, reminding us that, just like books on a shelf, the elements of our reality are bound to be intricately linked in ways we may not initially perceive. After all, as the saying goes, "When in doubt, go to the library" – even if you need to fuel up along the way!

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of library assistants in North Dakota and Petroluem consumption in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway

[[ABSTRACT]]
This study explores the peculiar relationship between the number of library assistants in North Dakota and petroleum consumption in Norway. Using data from the Bureau of Labor Statistics and the Energy Information Administration, a correlation coefficient of 0.7012281 and p < 0.01 was calculated for the period spanning 2003 to 2021. Despite the geographical and cultural gulf between the two regions, the results suggest a surprising linkage – as unexpected as finding a book on anti-gravity! This paper delves into the statistical analysis and potential explanations for this correlation, shedding light on the mysterious interplay between seemingly unrelated factors. After all, who would have thought that lugging books and guzzling gas could be intertwined?

[[LITERATURE REVIEW]]
The previous research on the correlation between the number of library assistants in North Dakota and petroleum consumption in Norway has been scant, to say the least. In "Smith et al.'s" comprehensive study, no discernible link was found between these two variables, leaving the scientific community scratching their heads in perplexity. However, recent findings by "Doe" and "Jones" have hinted at a potential association, sparking renewed interest in this quirky connection. Despite the lack of consensus, the relationship between library assistants and petrol consumption remains as enigmatic as a book that mysteriously appears on your shelf overnight.
Real-life economics and energy consumption books such as "Energy Economics" by Peter Zweifel and "Sustainable Energy – Without the Hot Air" by David J.C. MacKay have delved into the complexities of petroleum consumption, shedding light on the intricate web of factors influencing this phenomenon. On the other hand, fictional works such as "The Library Book" by Susan Orlean and "The Shadow of the Wind" by Carlos Ruiz Zafón have alluded to the mystique surrounding libraries and books, offering a narrative lens through which to view the peculiar relationship at hand. Perhaps the intertwining of library assistants and petrol consumption is as improbable as finding a tome of ancient wisdom hidden within the stacks of your local library.
One particularly unconventional source of insight emerged during the course of this literature review, as the researchers stumbled upon a series of obscure fiction novels purportedly authored by a collective of gasoline-loving pheasants. Although their literary merit is questionable, these books, with titles like "The Pheasant and the Pump" and "Fueling Feathers: A Petrol Pheasant's Tale," offered an unexpected perspective on the intersection of avian interests and energy consumption. While their credibility is dubious at best, these texts provided a whimsical reminder of the unexpected places one's academic pursuits may lead – akin to stumbling upon a dad joke in the footnotes of a scholarly article.
As the literature review draws to a close, the authors are left with more questions than answers, much like a reader perusing an unfinished mystery novel. The bizarre yet tantalizing connection between library assistants in North Dakota and petroleum consumption in Norway continues to defy conventional expectations, beckoning further investigation and perhaps a lighthearted chuckle or two along the way. After all, in the unpredictable realm of academic inquiry, one must always be prepared for the unexpected – much like a well-timed dad joke in the midst of a scholarly discourse.

[[RESULTS]]
The analysis revealed a strong positive correlation between the number of library assistants in North Dakota and petroleum consumption in Norway, with a correlation coefficient of 0.7012281 and an r-squared value of 0.4917209. The p-value was found to be less than 0.01, indicating a statistically significant relationship between the two variables. It seems that as the number of library assistants in North Dakota increased, so did the petrol consumption in Norway. It's almost as if the books were whispering to the petrol pumps across the ocean, saying "fill 'er up!"
(Fig. 1) presents a scatterplot illustrating this unexpected connection. The plot unmistakably depicts a positive linear relationship between the two variables, leaving little room for doubt about the strength of their association. It’s a relationship as clear as a well-written library due date slip!
The findings of this study support the notion that seemingly unrelated factors can indeed exhibit intriguing connections. Just as the equation for the correlation coefficient unveils hidden associations, our research endeavors to unravel the mystery behind this unusual pairing. Who would have thought that the bustling activity of library assistants in North Dakota could coincide with the fuel-hungry habits of Norway? It’s as surprising as finding a book on shipbuilding in a landlocked library!
The statistical significance of this correlation paves the way for further exploration into the underlying mechanisms at play. As researchers, we revel in the uncovering of such enigmatic linkages, much like uncovering the solution to a particularly vexing crossword puzzle. The intricacies of statistical analysis often reveal unexpected patterns, and this study serves as a testament to the significance of rigorous inquiry in unearthing the unlikeliest of associations.
These findings provoke contemplation on the intricate web of interconnections that permeate our world, reminding us that, just like books on a shelf, the elements of our reality are bound to be intricately linked in ways we may not initially perceive. After all, as the saying goes, "When in doubt, go to the library" – even if you need to fuel up along the way!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study have shed light on the unexpected relationship between the number of library assistants in North Dakota and petroleum consumption in Norway. The robust positive correlation observed between these variables, as supported by the statistical analysis, challenges conventional wisdom and underscores the intricate nature of empirical associations. It’s as if the research data was whispering a punchline about the quirky pair of library assistants and petroleum consumption across the academic universe!

The outcomes of this investigation align with the recent hints at a potential association between library assistants and petrol consumption found in the work of "Doe" and "Jones," further confirming the validity and significance of exploring this intriguing phenomenon. The interplay between these seemingly unrelated variables, while as far-fetched as a book mysteriously appearing on your shelf overnight, has undoubtedly captured the imagination of the scholarly community.

Considering the contextual backdrop of the enigmatic relationship between library assistants and petrol consumption, our study not only affirms the previously scant conclusions on this theme but also surpasses them, much like a particularly victorious pun in scientific literature. It's a connection as clear as a well-understood research hypothesis!

These unexpected findings stimulate contemplation on the interrelatedness of seemingly disparate facets of our world and underscore the boundless potential for discovery in the realm of scientific inquiry. The statistical significance of the observed correlation serves as a testament to the immortal allure of unraveling unexpected patterns and connections, resembling the satisfaction of solving a particularly cryptic crossword puzzle.

In conclusion, the results of this investigation not only validate the phenomenon of a peculiar connection between library assistants in North Dakota and petroleum consumption in Norway but also propel the scientific community into a realm of boundless curiosity, rife with potential unexpected twists and whimsical associations. After all, who would have thought that the activities of library assistants and the petrol preferences of Norway could be as intertwined as a series of well-placed dad jokes in the otherwise serious fabric of academic discourse?

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of library assistants in North Dakota and Petroluem consumption in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway

[[ABSTRACT]]
This study explores the peculiar relationship between the number of library assistants in North Dakota and petroleum consumption in Norway. Using data from the Bureau of Labor Statistics and the Energy Information Administration, a correlation coefficient of 0.7012281 and p < 0.01 was calculated for the period spanning 2003 to 2021. Despite the geographical and cultural gulf between the two regions, the results suggest a surprising linkage – as unexpected as finding a book on anti-gravity! This paper delves into the statistical analysis and potential explanations for this correlation, shedding light on the mysterious interplay between seemingly unrelated factors. After all, who would have thought that lugging books and guzzling gas could be intertwined?

[[INTRDUCTION]]
The enigma of seemingly unrelated phenomena interwoven throughout the fabric of our world never ceases to amaze. From the peculiar mating habits of anglerfish to the confounding correlation between the number of library assistants in North Dakota and petroleum consumption in Norway, the mysteries of science and statistics continue to pique our curiosity. As Albert Einstein famously quipped, "The most beautiful thing we can experience is the mysterious. It is the source of all true art and science – and dad jokes."
In the annals of scientific inquiry, unexpected connections have often yielded profound insight and revelation. Just as the discovery of penicillin was stumbled upon by Sir Alexander Fleming in a happy accident, the unearthing of this peculiar relationship between library assistants and petroleum consumption invites us to contemplate the seemingly disparate forces at play. It's a bit like finding a rare book nestled among a sea of paperbacks - surprising, yet utterly captivating!
The present study endeavors to unravel this conundrum, peering through the lens of rigorous statistical analysis to examine the linkage between these two divergent variables. With an exploratory spirit reminiscent of Lewis and Clark embarking on their expedition, we venture into uncharted territory to shed light on this unexpected correlation. After all, as researchers, we are no strangers to navigating the labyrinth of data, much like a librarian deftly guiding patrons through the maze of bookshelves.
As we embark on this intellectual journey, we are reminded of the words of J.R.R. Tolkien, who aptly observed, "Not all those who wander are lost." In the realm of scientific exploration, our journey may take us down unexpected paths, but the insights garnered along the way have the potential to illuminate hidden truths. So, buckle up as we delve into the curious case of more library assistants and more petrol phesants - and prepare for the statistical twists and turns that lie ahead!

[[RESULTS]]
The analysis revealed a strong positive correlation between the number of library assistants in North Dakota and petroleum consumption in Norway, with a correlation coefficient of 0.7012281 and an r-squared value of 0.4917209. The p-value was found to be less than 0.01, indicating a statistically significant relationship between the two variables. It seems that as the number of library assistants in North Dakota increased, so did the petrol consumption in Norway. It's almost as if the books were whispering to the petrol pumps across the ocean, saying "fill 'er up!"
(Fig. 1) presents a scatterplot illustrating this unexpected connection. The plot unmistakably depicts a positive linear relationship between the two variables, leaving little room for doubt about the strength of their association. It’s a relationship as clear as a well-written library due date slip!
The findings of this study support the notion that seemingly unrelated factors can indeed exhibit intriguing connections. Just as the equation for the correlation coefficient unveils hidden associations, our research endeavors to unravel the mystery behind this unusual pairing. Who would have thought that the bustling activity of library assistants in North Dakota could coincide with the fuel-hungry habits of Norway? It’s as surprising as finding a book on shipbuilding in a landlocked library!
The statistical significance of this correlation paves the way for further exploration into the underlying mechanisms at play. As researchers, we revel in the uncovering of such enigmatic linkages, much like uncovering the solution to a particularly vexing crossword puzzle. The intricacies of statistical analysis often reveal unexpected patterns, and this study serves as a testament to the significance of rigorous inquiry in unearthing the unlikeliest of associations.
These findings provoke contemplation on the intricate web of interconnections that permeate our world, reminding us that, just like books on a shelf, the elements of our reality are bound to be intricately linked in ways we may not initially perceive. After all, as the saying goes, "When in doubt, go to the library" – even if you need to fuel up along the way!

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the findings of this study provide compelling evidence of a robust correlation between the number of library assistants in North Dakota and petroleum consumption in Norway. The positive linear relationship uncovered suggests a surprising linkage that is as unexpected as finding a book on "the history of oil spills" next to a gallon of motor oil - truly a tale of serendipity! The statistical significance of this correlation serves as a testament to the power of rigorous inquiry in uncovering the unlikeliest of associations, much like unexpectedly discovering a book on Scandinavian oil drilling techniques in the library archives!

The implications of this peculiar connection prompt contemplation on the vast and intricate web of interconnections that permeate our world, much like the intricate maze of library shelves. It's a bit like stumbling upon a well-hidden section on 'petroleum engineering for penguins' when browsing through the library's catalog - an utterly surprising but undoubtedly fascinating discovery!

Given the unexpected nature of this correlation, it seems that there is more at play than meets the eye. The enigmatic interplay between these seemingly unrelated variables is a reminder that, in the realm of scientific inquiry and statistical analysis, the most unassuming factors may hold the key to unraveling complex phenomena. It's like searching for a book on "fish behavior in petroleum-rich environments" and realizing that the library assistant holds the answer!

In light of these findings, it appears that no further investigations are needed in this area. The unexpected and statistically significant association between library assistants in North Dakota and petroleum consumption in Norway offers a fascinating glimpse into the intricate dance of interrelated variables. It's as if the data itself is whispering, "No need to check out any more books on this topic - this correlation is as clear as the Dewey Decimal System!"

Therefore, we assert that this research provides a compelling contribution to the scientific community. It's akin to finding the missing puzzle piece in a complex jigsaw - unexpected, satisfying, and worthy of admiration. After all, as the age-old saying goes, "A good research finding is like a fine wine - it gets better with statistical significance!"

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 More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Quirky Connections

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 More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Cryptic Sociological 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 More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway with an abstract of This study explores the peculiar relationship between the number of library assistants in North Dakota and petroleum consumption in Norway. Using data from the Bureau of Labor Statistics and the Energy Information Administration, a correlation coefficient of 0.7012281 and p < 0.01 was calculated for the period spanning 2003 to 2021. Despite the geographical and cultural gulf between the two regions, the results suggest a surprising linkage – as unexpected as finding a book on anti-gravity! This paper delves into the statistical analysis and potential explanations for this correlation, shedding light on the mysterious interplay between seemingly unrelated factors. After all, who would have thought that lugging books and guzzling gas could be intertwined?

ChatGPT:

North Dakota, library assistants, petroleum consumption, Norway, correlation coefficient, Bureau of Labor Statistics, Energy Information Administration, statistical analysis, geographical linkage, cultural linkage, interplay, unrelated factors

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

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

The number of library assistants in North Dakota
Detailed data title: BLS estimate of library assistants, clerical in North Dakota
Source: Bureau of Larbor Statistics
See what else correlates with The number of library assistants in North Dakota

Petroluem consumption in Norway
Detailed data title: Volume of petroluem consumption consumed in Norway in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Petroluem consumption in Norway

Correlation r = 0.7012281 (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 = 0.4917209 (Coefficient of determination)
This means 49.2% of the change in the one variable (i.e., Petroluem consumption in Norway) is predictable based on the change in the other (i.e., The number of library assistants in North Dakota) over the 19 years from 2003 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00082.^Show 0.0008223903822050845000000000
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 0.7 in 0.082% of random cases. Said differently, if you correlated 1,216 random variables^Note Which I absolutely did.
with the same 18 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.36, 0.88 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
The number of library assistants in North Dakota (Laborers)	130	70	100	130	190	130	90	70	120	100	120	90	110	110	170	150	100	40	90
Petroluem consumption in Norway (Million Barrels/Day)	230.079	217.503	221.701	227.2	238.362	223.352	222.888	233.323	227.545	226.877	230.707	226.896	232.397	229.648	236.882	242.499	235.03	217.694	222.397

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([130,70,100,130,190,130,90,70,120,100,120,90,110,110,170,150,100,40,90,])
array_2 = np.array([230.079,217.503,221.701,227.2,238.362,223.352,222.888,233.323,227.545,226.877,230.707,226.896,232.397,229.648,236.882,242.499,235.03,217.694,222.397,])
array_1_name = "The number of library assistants in North Dakota"
array_2_name = "Petroluem consumption in Norway"

# 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 library assistants in North Dakota
Line chart for only Petroluem consumption in Norway
AI-generated correlation image
The spurious research paper: More Library Assistants, More Petrol Pheasants: A Strange Connection Between North Dakota and Norway

View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!

Correlation ID: 1823 · Black Variable ID: 12671 · Red Variable ID: 24778


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