about · email me · subscribe
Spurious correlation #2,749 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Number of public school students in 5th grade and the second variable is Number of Lawyers in the United States.  The chart goes from 1990 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the number of 5th graders in public school grows, so does their love for arguments and debates, creating a demand for future lawyers. It's a classic case of multiplication leading to litigation!

Model: dalle-3
Prompt: Generating prompt... Prompt: Generate a photorealistic image of a bustling schoolyard filled with 5th grade students playing dodgeball, while a line of aspiring lawyers-in-training stand prepared, holding stacks of dodgeball-related documents, ready to address any disputes that may arise. The scene should capture the energetic spirit of the game and the focus of the young lawyers, while maintaining a photorealistic style. 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: Number of public school students in 5th grade and Number of Lawyers in the United States. 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: Realistic Brutalism Cyber folk Photorealism Concept art
ChatGPT: Photorealism

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 Number of public school students in 5th grade and Number of Lawyers in the United States, in the following situation: As the number of 5th grade students increased, so did the demand for kids throwing dodgeballs. This led to an abundance of future lawyers specializing in dodgeball-related lawsuits.. Keep the description simple.
ChatGPT: In a bustling schoolyard filled with 5th grade students, a growing number of kids are seen engaging in a spirited game of dodgeball. Amid the action, a line of eager lawyers-in-training form, each holding a stack of dodgeball-related documents, ready to address any disagreements that arise from the game.

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: [ Photorealism ] and depicting this scene: In a bustling schoolyard filled with 5th grade students, a growing number of kids are seen engaging in a spirited game of dodgeball. Amid the action, a line of eager lawyers-in-training form, each holding a stack of dodgeball-related documents, ready to address any disagreements that arise from the game. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generating prompt... Prompt: Generate a photorealistic image of a bustling schoolyard filled with 5th grade students playing dodgeball, while a line of aspiring lawyers-in-training stand prepared, holding stacks of dodgeball-related documents, ready to address any disputes that may arise. The scene should capture the energetic spirit of the game and the focus of the young lawyers, while maintaining a photorealistic style.

*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.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Number of public school students in 5th grade caused Number of Lawyers in the United States to increase.

AI academic paper

(Because p < 0.01)
The ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States

The Journal of Interdisciplinary Mismatch Studies

Jan 2024

Reminder: This paper is AI-generated. Not real!
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 silly researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
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, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Number of public school students in 5th grade and Number of Lawyers in the United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title seem clever.

Your research team used data from National Center for Education Statistics and ABA to assess this nagging question. You found a correlation coefficient of 0.8496229 and p < 0.01 for 1990 to 2022.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States

[[ABSTRACT]]
This paper presents the results of a humorously unexpected investigation into the relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. We employed data from the National Center for Education Statistics and the American Bar Association to unlock the secrets hidden within these seemingly unrelated figures. After rigorous analysis, we discovered a correlation coefficient of 0.8496229 and a p-value less than 0.01 for the years 1990 through 2022. Our findings tickle the brain and challenge conventional assumptions about the interconnectedness of seemingly disparate professions and stages of education. With a touch of statistical whimsy, we reveal an intriguing link that may leave readers in legal wonder.




Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.You draft the introduction 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 introduction section of an academic research paper presenting the findings of the connection between Number of public school students in 5th grade and Number of Lawyers in the United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
The ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States

[[ABSTRACT]]
This paper presents the results of a humorously unexpected investigation into the relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. We employed data from the National Center for Education Statistics and the American Bar Association to unlock the secrets hidden within these seemingly unrelated figures. After rigorous analysis, we discovered a correlation coefficient of 0.8496229 and a p-value less than 0.01 for the years 1990 through 2022. Our findings tickle the brain and challenge conventional assumptions about the interconnectedness of seemingly disparate professions and stages of education. With a touch of statistical whimsy, we reveal an intriguing link that may leave readers in legal wonder.



-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the field of education and law, seemingly unrelated aspects often intertwine in baffling ways, perplexing researchers and beguiling statisticians. In this study, we delve into the interplay between the number of 5th-grade students enrolled in public schools and the abundance of lawyers practicing in the United States. The connection between these two seemingly disparate cohorts tickles the imagination and raises eyebrows, prompting a journey into the quirky realms of statistical analysis and societal dynamics.

While one might assume that the number of 5th-grade students and the quantity of lawyers exist in separate, non-intersecting spheres, the reality begs to differ. Like a magician revealing the mechanics behind a mystifying trick, we aim to unveil the unexpected relationship between these two groups. Our exploration, akin to a whimsical adventure, aims to shed light on an unconventional correlation that challenges traditional notions and leaves the audience in legal wonder.

As we embark on this statistical escapade, we ask the reader to don their analytical spectacles and brace themselves for the unexpected. Through our rigorous data analysis and statistical scrutiny, we invite you to join us in unraveling the enigmatic ties that bind 5th-grade students and lawyers into a thought-provoking statistical dance. In doing so, we set the stage for a lighthearted yet illuminating exploration of the interconnectedness across seemingly unrelated facets of our societal tapestry.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Number of public school students in 5th grade and Number of Lawyers in the United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
The ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States

[[ABSTRACT]]
This paper presents the results of a humorously unexpected investigation into the relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. We employed data from the National Center for Education Statistics and the American Bar Association to unlock the secrets hidden within these seemingly unrelated figures. After rigorous analysis, we discovered a correlation coefficient of 0.8496229 and a p-value less than 0.01 for the years 1990 through 2022. Our findings tickle the brain and challenge conventional assumptions about the interconnectedness of seemingly disparate professions and stages of education. With a touch of statistical whimsy, we reveal an intriguing link that may leave readers in legal wonder.



-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the field of education and law, seemingly unrelated aspects often intertwine in baffling ways, perplexing researchers and beguiling statisticians. In this study, we delve into the interplay between the number of 5th-grade students enrolled in public schools and the abundance of lawyers practicing in the United States. The connection between these two seemingly disparate cohorts tickles the imagination and raises eyebrows, prompting a journey into the quirky realms of statistical analysis and societal dynamics.
While one might assume that the number of 5th-grade students and the quantity of lawyers exist in separate, non-intersecting spheres, the reality begs to differ. Like a magician revealing the mechanics behind a mystifying trick, we aim to unveil the unexpected relationship between these two groups. Our exploration, akin to a whimsical adventure, aims to shed light on an unconventional correlation that challenges traditional notions and leaves the audience in legal wonder.
As we embark on this statistical escapade, we ask the reader to don their analytical spectacles and brace themselves for the unexpected. Through our rigorous data analysis and statistical scrutiny, we invite you to join us in unraveling the enigmatic ties that bind 5th-grade students and lawyers into a thought-provoking statistical dance. In doing so, we set the stage for a lighthearted yet illuminating exploration of the interconnectedness across seemingly unrelated facets of our societal tapestry.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States has intrigued researchers for decades. Smith et al. (2010) delved into the demographic shifts in public school enrollment, while Doe (2015) provided a comprehensive analysis of the legal profession. Both studies, though thorough in their own right, failed to grasp the captivating correlation that this paper seeks to unravel. However, our investigation delves deeper, peering into the intricate web of statistical anomalies and societal quirks that bind these two disparate groups.

Turning to non-fiction works, "Freakonomics" by Steven Levitt and Stephen Dubner offers a fascinating take on unexpected correlations, laying the groundwork for our exploration into the unanticipated link between 5th-grade students and lawyers. In "Outliers" by Malcolm Gladwell, the notion of hidden patterns and connections in society sparks a sense of wonder and curiosity, much like the unexpected relationship we unearth in our study.

On the fictional front, "To Kill a Mockingbird" by Harper Lee and "The Cider House Rules" by John Irving explore legal themes that may indirectly hint at the curious correlation we have stumbled upon. Both works, though not directly related to our topic, lend a whimsical aura to our investigation, much like an unexpected plot twist in the statistical narrative.

Drawing inspiration from the world of board games, the classic game of "Connect Four" serves as a playful metaphor for the interconnectedness we seek to uncover. Just as the colored discs interlock in surprising patterns, our data leads us down a path of discovery that challenges preconceived notions and prompts a playful, if not mischievous, sense of statistical adventure.

In "Lorem and Ipsum: A Statistical Adventure," the authors playfully unravel the enigmatic ties that bind seemingly unrelated facets of our societal tapestry, setting the stage for a lighthearted yet illuminating exploration of the interconnectedness across disparate professions and stages of education. With a touch of statistical whimsy, we invite readers to join us in this quirky journey, as we present our findings that may leave the audience in legal wonder and statistical amusement.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Number of public school students in 5th grade and Number of Lawyers in the United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from National Center for Education Statistics and ABA . You used data from 1990 to 2022

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]]
The ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States

[[ABSTRACT]]
This paper presents the results of a humorously unexpected investigation into the relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. We employed data from the National Center for Education Statistics and the American Bar Association to unlock the secrets hidden within these seemingly unrelated figures. After rigorous analysis, we discovered a correlation coefficient of 0.8496229 and a p-value less than 0.01 for the years 1990 through 2022. Our findings tickle the brain and challenge conventional assumptions about the interconnectedness of seemingly disparate professions and stages of education. With a touch of statistical whimsy, we reveal an intriguing link that may leave readers in legal wonder.



[[INTRODUCTION]]
In the field of education and law, seemingly unrelated aspects often intertwine in baffling ways, perplexing researchers and beguiling statisticians. In this study, we delve into the interplay between the number of 5th-grade students enrolled in public schools and the abundance of lawyers practicing in the United States. The connection between these two seemingly disparate cohorts tickles the imagination and raises eyebrows, prompting a journey into the quirky realms of statistical analysis and societal dynamics.
While one might assume that the number of 5th-grade students and the quantity of lawyers exist in separate, non-intersecting spheres, the reality begs to differ. Like a magician revealing the mechanics behind a mystifying trick, we aim to unveil the unexpected relationship between these two groups. Our exploration, akin to a whimsical adventure, aims to shed light on an unconventional correlation that challenges traditional notions and leaves the audience in legal wonder.
As we embark on this statistical escapade, we ask the reader to don their analytical spectacles and brace themselves for the unexpected. Through our rigorous data analysis and statistical scrutiny, we invite you to join us in unraveling the enigmatic ties that bind 5th-grade students and lawyers into a thought-provoking statistical dance. In doing so, we set the stage for a lighthearted yet illuminating exploration of the interconnectedness across seemingly unrelated facets of our societal tapestry.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

In our delightful endeavor to tease apart the correlation between the number of 5th-grade students and the quantity of lawyers in the United States, we employed a methodological cocktail that blended data collection, statistical analysis, and a dash of whimsical insight. Our data collection process began by gallivanting through the vast landscape of the internet, where we harvested information from the National Center for Education Statistics and the American Bar Association. Our expedition through the digital wilderness proved both exhilarating and informative, akin to a treasure hunt yielding bountiful statistical gems.

The data we collated spanned the years 1990 through 2022, offering a historical tapestry through which we could trace the curious evolution of student populations and legal professionals. With our information securely gathered, we turned to the art of statistical analysis, employing the venerable technique of correlation analysis to discern the intriguing relationship between these unexpected bedfellows.

We petulantly pored over the data, wielding statistical software that titillated our analytical senses and induced harmonious choruses of covariant victories. Through this peculiar dance of statistical inquiry, we calculated the correlation coefficient and p-value with meticulous care, allowing our findings to frolic into the realms of statistical significance and intellectual amusement.

In addition to our numerical escapades, we ventured into the enigmatic kingdom of hypothesis testing, where we subjected our data to rigorous scrutiny, akin to a stern yet lighthearted interrogation. This process, like a courtroom drama with a statistical twist, allowed us to discern the veracity of our correlation, providing a theatrically nuanced backdrop to our statistical revelations.

Our methodology, interweaving serious statistical analyses with a playful spirit of inquiry, encapsulated the essence of our academic pursuit—unlocking the unexpected connections that intertwine the seemingly unrelated realms of public school education and the legal profession. Through this methodological melange, we embarked on a statistical odyssey that offers a delightful blend of intellectual rigor and whimsical insight, revealing a captivating correlation that may raise a chuckle or two among the scholarly audience.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Number of public school students in 5th grade and Number of Lawyers in the United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from National Center for Education Statistics and ABA .

For the time period 1990 to 2022, you found a correlation 0.8496229, r-squared of 0.7218591, 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]]
The ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States

[[ABSTRACT]]
This paper presents the results of a humorously unexpected investigation into the relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. We employed data from the National Center for Education Statistics and the American Bar Association to unlock the secrets hidden within these seemingly unrelated figures. After rigorous analysis, we discovered a correlation coefficient of 0.8496229 and a p-value less than 0.01 for the years 1990 through 2022. Our findings tickle the brain and challenge conventional assumptions about the interconnectedness of seemingly disparate professions and stages of education. With a touch of statistical whimsy, we reveal an intriguing link that may leave readers in legal wonder.



-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the field of education and law, seemingly unrelated aspects often intertwine in baffling ways, perplexing researchers and beguiling statisticians. In this study, we delve into the interplay between the number of 5th-grade students enrolled in public schools and the abundance of lawyers practicing in the United States. The connection between these two seemingly disparate cohorts tickles the imagination and raises eyebrows, prompting a journey into the quirky realms of statistical analysis and societal dynamics.
While one might assume that the number of 5th-grade students and the quantity of lawyers exist in separate, non-intersecting spheres, the reality begs to differ. Like a magician revealing the mechanics behind a mystifying trick, we aim to unveil the unexpected relationship between these two groups. Our exploration, akin to a whimsical adventure, aims to shed light on an unconventional correlation that challenges traditional notions and leaves the audience in legal wonder.
As we embark on this statistical escapade, we ask the reader to don their analytical spectacles and brace themselves for the unexpected. Through our rigorous data analysis and statistical scrutiny, we invite you to join us in unraveling the enigmatic ties that bind 5th-grade students and lawyers into a thought-provoking statistical dance. In doing so, we set the stage for a lighthearted yet illuminating exploration of the interconnectedness across seemingly unrelated facets of our societal tapestry.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our data analysis revealed a striking correlation between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. Over the period from 1990 to 2022, we found a correlation coefficient of 0.8496229, suggesting a strong positive relationship between these two seemingly unrelated variables. The r-squared value of 0.7218591 indicates that approximately 72.19% of the variation in the number of lawyers can be explained by the number of 5th-grade students, providing compelling evidence for their interconnectedness.

Fig. 1 depicts a scatterplot illustrating the robust correlation identified in our analysis, visually capturing the surprising coherence between these disparate cohorts. The plot showcases the enchanting statistical waltz between 5th-grade students and lawyers, inviting viewers to marvel at the unexpected synchronicity.

These findings challenge conventional assumptions and prompt a reevaluation of the invisible threads weaving through our educational and legal landscapes. The statistically significant p-value, less than 0.01, further underscores the substantial nature of the observed relationship, leaving researchers and readers in statistical astonishment.

In unraveling this peculiar correlation, we have unearthed a thought-provoking revelation that tickles the intellect and elicits a whimsical sense of curiosity. It appears that the intricate fabric of our societal tapestry interlaces 5th-grade students and lawyers in a dance of statistical intrigue, inviting us to ponder the enchanting and often humorous connections that underpin our complex world.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Number of public school students in 5th grade and Number of Lawyers in the United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States

[[ABSTRACT]]
This paper presents the results of a humorously unexpected investigation into the relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. We employed data from the National Center for Education Statistics and the American Bar Association to unlock the secrets hidden within these seemingly unrelated figures. After rigorous analysis, we discovered a correlation coefficient of 0.8496229 and a p-value less than 0.01 for the years 1990 through 2022. Our findings tickle the brain and challenge conventional assumptions about the interconnectedness of seemingly disparate professions and stages of education. With a touch of statistical whimsy, we reveal an intriguing link that may leave readers in legal wonder.



[[LITERATURE REVIEW]]
The relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States has intrigued researchers for decades. Smith et al. (2010) delved into the demographic shifts in public school enrollment, while Doe (2015) provided a comprehensive analysis of the legal profession. Both studies, though thorough in their own right, failed to grasp the captivating correlation that this paper seeks to unravel. However, our investigation delves deeper, peering into the intricate web of statistical anomalies and societal quirks that bind these two disparate groups.
Turning to non-fiction works, "Freakonomics" by Steven Levitt and Stephen Dubner offers a fascinating take on unexpected correlations, laying the groundwork for our exploration into the unanticipated link between 5th-grade students and lawyers. In "Outliers" by Malcolm Gladwell, the notion of hidden patterns and connections in society sparks a sense of wonder and curiosity, much like the unexpected relationship we unearth in our study.
On the fictional front, "To Kill a Mockingbird" by Harper Lee and "The Cider House Rules" by John Irving explore legal themes that may indirectly hint at the curious correlation we have stumbled upon. Both works, though not directly related to our topic, lend a whimsical aura to our investigation, much like an unexpected plot twist in the statistical narrative.
Drawing inspiration from the world of board games, the classic game of "Connect Four" serves as a playful metaphor for the interconnectedness we seek to uncover. Just as the colored discs interlock in surprising patterns, our data leads us down a path of discovery that challenges preconceived notions and prompts a playful, if not mischievous, sense of statistical adventure.
In "Lorem and Ipsum: A Statistical Adventure," the authors playfully unravel the enigmatic ties that bind seemingly unrelated facets of our societal tapestry, setting the stage for a lighthearted yet illuminating exploration of the interconnectedness across disparate professions and stages of education. With a touch of statistical whimsy, we invite readers to join us in this quirky journey, as we present our findings that may leave the audience in legal wonder and statistical amusement.

[[RESULTS]]
Our data analysis revealed a striking correlation between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. Over the period from 1990 to 2022, we found a correlation coefficient of 0.8496229, suggesting a strong positive relationship between these two seemingly unrelated variables. The r-squared value of 0.7218591 indicates that approximately 72.19% of the variation in the number of lawyers can be explained by the number of 5th-grade students, providing compelling evidence for their interconnectedness.
Fig. 1 depicts a scatterplot illustrating the robust correlation identified in our analysis, visually capturing the surprising coherence between these disparate cohorts. The plot showcases the enchanting statistical waltz between 5th-grade students and lawyers, inviting viewers to marvel at the unexpected synchronicity.
These findings challenge conventional assumptions and prompt a reevaluation of the invisible threads weaving through our educational and legal landscapes. The statistically significant p-value, less than 0.01, further underscores the substantial nature of the observed relationship, leaving researchers and readers in statistical astonishment.
In unraveling this peculiar correlation, we have unearthed a thought-provoking revelation that tickles the intellect and elicits a whimsical sense of curiosity. It appears that the intricate fabric of our societal tapestry interlaces 5th-grade students and lawyers in a dance of statistical intrigue, inviting us to ponder the enchanting and often humorous connections that underpin our complex world.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our study confirm the unexpected revelation that the number of 5th-grade students in public schools and the quantity of lawyers in the United States are indeed remarkably correlated. Our findings joyously affirm the previously stumbled-upon peculiarities and mysterious statistical dance between these seemingly disparate groups.

The robust correlation coefficient of 0.8496229 mirrors the entwined relationship expounded by Smith et al. (2010) as they delved into the demographic shifts in public school enrollment. Theirs was a journey of discovery akin to unraveling a particularly elusive legal case, and our results provide a gleeful exclamation mark beneath their diligent pursuit.

Coincidentally, the statistical interconnection between 5th-grade students and lawyers seems to echo the musings of Doe (2015), who provided a comprehensive analysis of the legal profession, undoubtedly unaware of our charming discovery. Our study adds an enigmatic footnote to their scholarly prose, revealing a connection as unexpected and intriguing as the twist in a legal thriller.

The whimsical aura lent to our investigation by fictional works such as "To Kill a Mockingbird" by Harper Lee and "The Cider House Rules" by John Irving seems to have foreshadowed the statistical amusement we uncover. Like a curious plot twist in the statistical narrative, our findings prompt a reevaluation of the invisible threads weaving through our educational and legal landscapes, adding a layer of whimsy to the previously solemn analyses within the literature.

Drawing upon inspiration from the game "Connect Four," our findings unfold like a playful metaphor for the interconnectedness we sought to uncover. Just as colored discs interlock in surprising patterns, our data leads us down a path of delightful discovery, further emphasizing the statistical adventure we embarked upon.

Moreover, the compelling evidence of our results is fortified by the substantial nature of the observed relationship, leaving researchers and readers in statistical astonishment, as though they have unexpectedly stumbled upon a legal loophole.

In conclusion, our investigation into the unexpected correlation between 5th-grade students and lawyers has uncovered a lighthearted yet illuminating exploration that challenges conventional assumptions and leaves the audience in legal wonder and statistical amusement. Our findings tickle the intellect and elicit a whimsical sense of curiosity, serving as a testament to the intriguing and often humorous connections that underpin our complex world.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Number of public school students in 5th grade and Number of Lawyers in the United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States

[[ABSTRACT]]
This paper presents the results of a humorously unexpected investigation into the relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. We employed data from the National Center for Education Statistics and the American Bar Association to unlock the secrets hidden within these seemingly unrelated figures. After rigorous analysis, we discovered a correlation coefficient of 0.8496229 and a p-value less than 0.01 for the years 1990 through 2022. Our findings tickle the brain and challenge conventional assumptions about the interconnectedness of seemingly disparate professions and stages of education. With a touch of statistical whimsy, we reveal an intriguing link that may leave readers in legal wonder.



[[INTRDUCTION]]
In the field of education and law, seemingly unrelated aspects often intertwine in baffling ways, perplexing researchers and beguiling statisticians. In this study, we delve into the interplay between the number of 5th-grade students enrolled in public schools and the abundance of lawyers practicing in the United States. The connection between these two seemingly disparate cohorts tickles the imagination and raises eyebrows, prompting a journey into the quirky realms of statistical analysis and societal dynamics.
While one might assume that the number of 5th-grade students and the quantity of lawyers exist in separate, non-intersecting spheres, the reality begs to differ. Like a magician revealing the mechanics behind a mystifying trick, we aim to unveil the unexpected relationship between these two groups. Our exploration, akin to a whimsical adventure, aims to shed light on an unconventional correlation that challenges traditional notions and leaves the audience in legal wonder.
As we embark on this statistical escapade, we ask the reader to don their analytical spectacles and brace themselves for the unexpected. Through our rigorous data analysis and statistical scrutiny, we invite you to join us in unraveling the enigmatic ties that bind 5th-grade students and lawyers into a thought-provoking statistical dance. In doing so, we set the stage for a lighthearted yet illuminating exploration of the interconnectedness across seemingly unrelated facets of our societal tapestry.

[[RESULTS]]
Our data analysis revealed a striking correlation between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. Over the period from 1990 to 2022, we found a correlation coefficient of 0.8496229, suggesting a strong positive relationship between these two seemingly unrelated variables. The r-squared value of 0.7218591 indicates that approximately 72.19% of the variation in the number of lawyers can be explained by the number of 5th-grade students, providing compelling evidence for their interconnectedness.
Fig. 1 depicts a scatterplot illustrating the robust correlation identified in our analysis, visually capturing the surprising coherence between these disparate cohorts. The plot showcases the enchanting statistical waltz between 5th-grade students and lawyers, inviting viewers to marvel at the unexpected synchronicity.
These findings challenge conventional assumptions and prompt a reevaluation of the invisible threads weaving through our educational and legal landscapes. The statistically significant p-value, less than 0.01, further underscores the substantial nature of the observed relationship, leaving researchers and readers in statistical astonishment.
In unraveling this peculiar correlation, we have unearthed a thought-provoking revelation that tickles the intellect and elicits a whimsical sense of curiosity. It appears that the intricate fabric of our societal tapestry interlaces 5th-grade students and lawyers in a dance of statistical intrigue, inviting us to ponder the enchanting and often humorous connections that underpin our complex world.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In this study, we have danced through the labyrinth of statistical analysis to unravel a playful yet thought-provoking correlation between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. The striking correlation coefficient of 0.8496229, akin to a magician's grand reveal, showcases an unexpected harmony between these seemingly unrelated cohorts. The robust r-squared value and statistically significant p-value further emphasize the substantial nature of this delightful revelation, leaving researchers and readers alike in statistical amusement.

Our findings invite a whimsical pondering of the interconnectedness across seemingly disparate facets of our societal tapestry, challenging conventional wisdom and tickling the intellectual fancy. As we lift the curtain on this statistical magic show, we encourage the audience to embrace the surprising coherence between 5th-grade students and lawyers, leaving them in legal wonder and yielding a scholarly chuckle.

It is evident from our findings that no further research in a similar vein is needed, as this study has unfurled the delightful secrets hidden within these curious correlations, leaving behind a trail of statistical delight and academic merriment.


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 ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Interdisciplinary Mismatch 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 ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States. Respond only with the name of a fictional organization.

ChatGPT:

Global Consortium for Child-Lawyer Societal Dynamics


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 ABCs of Connection: Exploring the Correlation Between 5th Grade Students and Lawyers in the United States with an abstract of This paper presents the results of a humorously unexpected investigation into the relationship between the number of 5th-grade students in public schools and the quantity of lawyers in the United States. We employed data from the National Center for Education Statistics and the American Bar Association to unlock the secrets hidden within these seemingly unrelated figures. After rigorous analysis, we discovered a correlation coefficient of 0.8496229 and a p-value less than 0.01 for the years 1990 through 2022. Our findings tickle the brain and challenge conventional assumptions about the interconnectedness of seemingly disparate professions and stages of education. With a touch of statistical whimsy, we reveal an intriguing link that may leave readers in legal wonder.

ChatGPT:

5th grade students, lawyers, correlation, United States, public schools, National Center for Education Statistics, American Bar Association, correlation coefficient, statistical analysis, interconnected professions, education stages

*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

Number of public school students in 5th grade
Detailed data title: 5th grade enrollment in public elementary and secondary schools
Source: National Center for Education Statistics
See what else correlates with Number of public school students in 5th grade

Number of Lawyers in the United States
Detailed data title: The Count of ABA Lawyers in the United States
Source: ABA
See what else correlates with Number of Lawyers in the United States

Correlation r = 0.8496229 (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 = 0.7218591 (Coefficient of determination)
This means 72.2% of the change in the one variable (i.e., Number of Lawyers in the United States) is predictable based on the change in the other (i.e., Number of public school students in 5th grade) over the 33 years from 1990 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.02E-10. 0.0000000004024368375473281000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.85 in 4.02E-8% of random cases. Said differently, if you correlated 2,484,861,988 random variables You don't actually need 2 billion 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 32 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 32 because we have two variables measured over a period of 33 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.

[ 0.71, 0.92 ] 95% correlation confidence interval (using the Fisher z-transformation)
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: 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.
199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Number of public school students in 5th grade (Students)319734032684303325430335045033718803437940345285034575403520100360366037066603726840371147036845403635180363283036018003600090362908036521303717520369912036729803696720371905037328803813740387727038761403801180364629036112303563030
Number of Lawyers in the United States (Lawyers)755694777119799760846036865614896140953260953260985921100044010224601048900104975010586601084500110477011169701143360116212011803901203100122545012452001268010128143013007001312870133596013423801352080132874013279101327010




Why this works

  1. 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.
  2. Lack of causal connection: There is probably 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.
  3. 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 Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. 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([3197340,3268430,3325430,3350450,3371880,3437940,3452850,3457540,3520100,3603660,3706660,3726840,3711470,3684540,3635180,3632830,3601800,3600090,3629080,3652130,3717520,3699120,3672980,3696720,3719050,3732880,3813740,3877270,3876140,3801180,3646290,3611230,3563030,])
array_2 = np.array([755694,777119,799760,846036,865614,896140,953260,953260,985921,1000440,1022460,1048900,1049750,1058660,1084500,1104770,1116970,1143360,1162120,1180390,1203100,1225450,1245200,1268010,1281430,1300700,1312870,1335960,1342380,1352080,1328740,1327910,1327010,])
array_1_name = "Number of public school students in 5th grade"
array_2_name = "Number of Lawyers in the United States"

# 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. 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:


View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!


Correlation ID: 2749 · Black Variable ID: 1302 · Red Variable ID: 542
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0