about · email me · subscribe
Spurious correlation #4,982 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Republican Presidential candidate in Kentucky and the second variable is Number of Lawyers in the United States.  The chart goes from 1989 to 2020, and the two variables track closely in value over that time. Small Image

AI explanation

It's simple: as the votes for the Republican Presidential candidate in Kentucky increased, so did the LegalElection representation across the nation. It seems like the candidates were all vying for the popular vote, and the spike in legal matters just can't be de-baited! It's a case of campaign litigation leading to an influx of legal professionals - talk about a vote of confidence in the law!

Model: dalle-3
Prompt: Prompt: Generate an image in the style of symbolism depicting the correlation between the Republican Presidential candidate's votes in Kentucky and the increasing number of lawyers in the United States. In the scene, show Kentucky's map with a rising bar or indicator under the Republican candidate's votes, and across the entire United States, depict a steadily rising bar or indicator representing the growing number of lawyers. Keep the visual depiction simple, without including any words or speech bubbles. 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: Votes for the Republican Presidential candidate in Kentucky 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: A photo-realistic image Cubism Futuristic Scalar art Symbolism
ChatGPT: Symbolism

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 Votes for the Republican Presidential candidate in Kentucky and Number of Lawyers in the United States, in the following situation: It's simple: as the votes for the Republican Presidential candidate in Kentucky increased, so did the LegalElection representation across the nation. It seems like the candidates were all vying for the popular vote, and the spike in legal matters just can't be de-baited! It's a case of campaign litigation leading to an influx of legal professionals - talk about a vote of confidence in the law!. Keep the description simple.
ChatGPT: As the Votes for the Republican Presidential candidate in Kentucky increased, so did the number of Lawyers in the United States. The scene shows Kentucky's map with growing numbers under the Republican candidate, while across the entire United States, the figure indicating the growing number of lawyers steadily rises alongside it.

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: [ Symbolism ] and depicting this scene: As the Votes for the Republican Presidential candidate in Kentucky increased, so did the number of Lawyers in the United States. The scene shows Kentucky's map with growing numbers under the Republican candidate, while across the entire United States, the figure indicating the growing number of lawyers steadily rises alongside it. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image in the style of symbolism depicting the correlation between the Republican Presidential candidate's votes in Kentucky and the increasing number of lawyers in the United States. In the scene, show Kentucky's map with a rising bar or indicator under the Republican candidate's votes, and across the entire United States, depict a steadily rising bar or indicator representing the growing number of lawyers. Keep the visual depiction simple, without including any words or speech bubbles.

*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 Votes for the Republican Presidential candidate in Kentucky caused Number of Lawyers in the United States to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
The Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States

The Journal of Political Pachyderms

Jan 2024
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 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 Votes for the Republican Presidential candidate in Kentucky and Number of Lawyers in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title seem clever.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and ABA to assess this nagging question. You found a correlation coefficient of 0.9143842 and p < 0.01 for 1989 to 2020.

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 Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States

[[ABSTRACT]]
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. In this study, we delve into the compelling relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Drawing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, our analysis spanning from 1989 to 2020 unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01.

The results of this study raise eyebrows and prompt lively discussions, much like a lawyer grilling a witness on the stand. We discovered that as the number of Republican votes in the Bluegrass State sways, so does the number of legal practitioners across the nation, showcasing a connection as tight-knit as a judge's gavel. This surprising association invokes an age-old question: are lawyers and conservative votes like peanut butter and jelly, seemingly unrelated but undeniably inseparable?

While the causality behind this correlation remains enigmatic, the findings of this research serve as a testament to the uncanny intertwining of legal and political realms. As we unravel the quirkiness of this phenomenon, let us remember that even in the world of statistics, correlation does not necessarily imply causation – much like how having a lot of papers on the desk doesn't make one a stationery expert. This study stands as a testament to the unyielding potential for unexpected connections in the labyrinthine corridors of data, where just like laws and jokes, patterns sometimes come out of left field.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Votes for the Republican Presidential candidate in Kentucky and Number of Lawyers in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
The Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States

[[ABSTRACT]]
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. In this study, we delve into the compelling relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Drawing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, our analysis spanning from 1989 to 2020 unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01.

The results of this study raise eyebrows and prompt lively discussions, much like a lawyer grilling a witness on the stand. We discovered that as the number of Republican votes in the Bluegrass State sways, so does the number of legal practitioners across the nation, showcasing a connection as tight-knit as a judge's gavel. This surprising association invokes an age-old question: are lawyers and conservative votes like peanut butter and jelly, seemingly unrelated but undeniably inseparable?

While the causality behind this correlation remains enigmatic, the findings of this research serve as a testament to the uncanny intertwining of legal and political realms. As we unravel the quirkiness of this phenomenon, let us remember that even in the world of statistics, correlation does not necessarily imply causation – much like how having a lot of papers on the desk doesn't make one a stationery expert. This study stands as a testament to the unyielding potential for unexpected connections in the labyrinthine corridors of data, where just like laws and jokes, patterns sometimes come out of left field.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Introduction

Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. From courtrooms to Capitol Hill, the intertwining of law and politics has intrigued scholars and armchair analysts alike. In this study, we set out to explore a curious connection that has emerged from the annals of electoral history— the correlation between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States.

This surprising link between votive preferences and legal practitioners has raised eyebrows and piqued the interest of many, much like the expression on a judge's face when a lawyer walks into court wearing an outlandishly colorful tie. One might say it's a tale as old as judicial robes themselves – the constant dance of power dynamics and legal representation, set against the backdrop of electoral tides. Perhaps lawyers and Republican votes are not as unrelated as they appear, much like how a lawyer's briefcase is never truly empty, always carrying the weight of evidence and caffeine.

Our exploration of this correlation drew from robust datasets, including information from the MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, ensuring that our statistical scrutiny was as rigorous as a lawyer's cross-examination. The results of our analysis, spanning from 1989 to 2020, unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01. Such a close correlation beckons one to ask: have lawyers and Republican votes formed an unspoken alliance as unbreakable as the bond between a client and their retainer?

As we dive deeper into this fascinating correlation, it is crucial to remember that correlation does not imply causation – a principle as fundamental as the gavel's role in a courtroom. While we navigate the intriguing link between legal practitioners and electoral preferences, let's keep in mind that just because a lawyer tells a good joke doesn't mean they should quit their day job. The unexpected connections we uncover serve as a reminder that the depths of data can often conceal astonishing relationships, much like how a lawyer's argument can sometimes turn a case on its head.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Votes for the Republican Presidential candidate in Kentucky and Number of Lawyers in the United States. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
The Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States

[[ABSTRACT]]
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. In this study, we delve into the compelling relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Drawing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, our analysis spanning from 1989 to 2020 unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01.

The results of this study raise eyebrows and prompt lively discussions, much like a lawyer grilling a witness on the stand. We discovered that as the number of Republican votes in the Bluegrass State sways, so does the number of legal practitioners across the nation, showcasing a connection as tight-knit as a judge's gavel. This surprising association invokes an age-old question: are lawyers and conservative votes like peanut butter and jelly, seemingly unrelated but undeniably inseparable?

While the causality behind this correlation remains enigmatic, the findings of this research serve as a testament to the uncanny intertwining of legal and political realms. As we unravel the quirkiness of this phenomenon, let us remember that even in the world of statistics, correlation does not necessarily imply causation – much like how having a lot of papers on the desk doesn't make one a stationery expert. This study stands as a testament to the unyielding potential for unexpected connections in the labyrinthine corridors of data, where just like laws and jokes, patterns sometimes come out of left field.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. From courtrooms to Capitol Hill, the intertwining of law and politics has intrigued scholars and armchair analysts alike. In this study, we set out to explore a curious connection that has emerged from the annals of electoral history— the correlation between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States.
This surprising link between votive preferences and legal practitioners has raised eyebrows and piqued the interest of many, much like the expression on a judge's face when a lawyer walks into court wearing an outlandishly colorful tie. One might say it's a tale as old as judicial robes themselves – the constant dance of power dynamics and legal representation, set against the backdrop of electoral tides. Perhaps lawyers and Republican votes are not as unrelated as they appear, much like how a lawyer's briefcase is never truly empty, always carrying the weight of evidence and caffeine.
Our exploration of this correlation drew from robust datasets, including information from the MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, ensuring that our statistical scrutiny was as rigorous as a lawyer's cross-examination. The results of our analysis, spanning from 1989 to 2020, unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01. Such a close correlation beckons one to ask: have lawyers and Republican votes formed an unspoken alliance as unbreakable as the bond between a client and their retainer?
As we dive deeper into this fascinating correlation, it is crucial to remember that correlation does not imply causation – a principle as fundamental as the gavel's role in a courtroom. While we navigate the intriguing link between legal practitioners and electoral preferences, let's keep in mind that just because a lawyer tells a good joke doesn't mean they should quit their day job. The unexpected connections we uncover serve as a reminder that the depths of data can often conceal astonishing relationships, much like how a lawyer's argument can sometimes turn a case on its head.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

A multitude of studies have delved into the intricate relationship between politics and legal professions, seeking to unravel the enigmatic ties binding these seemingly distinct domains. Smith et al. (2015) have extensively examined the regional variations in lawyer density and political affiliations, shedding light on the divergent trends observed across different states. Similarly, Doe and Jones (2017) explored the influence of political landscapes on legal career trajectories, elucidating the nuanced interplay between ideological leanings and professional pursuits. However, amidst these scholarly endeavors, one correlation persists like a lawyer's persistent argument in court – the intriguing alignment between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States.

It is fascinating to note the gravity of this correlation, which has captured the attention of researchers and enthusiasts alike, much like how a good lawyer captivates an audience in the courtroom. The link between these seemingly disparate entities prompts contemplation akin to pondering the paradox of legal jargon – often convoluted and yet unmistakably influential. Past studies have provided valuable insights into the regional distribution of legal practitioners and their political proclivities, but none have plumbed the depths of this unique relationship quite like our current endeavor. This correlation presents itself as an enigma wrapped in a mystery, much like a lawyer's bafflingly complex billable hours.

Turning to the broader landscape of literature, non-fiction works such as "The Legal Profession in America" (Adams, 2019) and "The Political Puzzle: Lawyers and the Electoral Process" (Brown, 2018) have offered illuminating perspectives on the intersection of law and politics, furnishing a rich tapestry of insights that contextualize our present investigation. Yet, as we embark on this scholarly odyssey, it is crucial to acknowledge the influence of fictitious narratives that, albeit fictional, offer surprisingly relevant parallels to our topic. Works such as "The Firm" (Grisham, 1991) and "Presumed Innocent" (Turow, 1987) not only entertain readers with legal dramas, but also inadvertently capture the essence of the intricate dance between legal professionals and political undercurrents. Similarly, board games such as "Lawyer Up: The Courtroom Game" and "Campaign Manager: The Political Strategy Game" serve as playful reminders of the intertwining realms we seek to explore. After all, what's a study on lawyers and Republican votes without a play on words, or at least a Monopoly reference?

In closing, our literature review illuminates the path paved by prior research, while adding a dash of levity befitting the enigmatic correlation we endeavor to untangle. From serious scholarly work to fictional tales and whimsical games, the entwined domains of law and politics continue to captivate our collective imagination, much like an unexpected punchline in a courtroom—surprising, yet remarkably fitting.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Votes for the Republican Presidential candidate in Kentucky and Number of Lawyers in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and ABA . You used data from 1989 to 2020

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 Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States

[[ABSTRACT]]
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. In this study, we delve into the compelling relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Drawing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, our analysis spanning from 1989 to 2020 unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01.

The results of this study raise eyebrows and prompt lively discussions, much like a lawyer grilling a witness on the stand. We discovered that as the number of Republican votes in the Bluegrass State sways, so does the number of legal practitioners across the nation, showcasing a connection as tight-knit as a judge's gavel. This surprising association invokes an age-old question: are lawyers and conservative votes like peanut butter and jelly, seemingly unrelated but undeniably inseparable?

While the causality behind this correlation remains enigmatic, the findings of this research serve as a testament to the uncanny intertwining of legal and political realms. As we unravel the quirkiness of this phenomenon, let us remember that even in the world of statistics, correlation does not necessarily imply causation – much like how having a lot of papers on the desk doesn't make one a stationery expert. This study stands as a testament to the unyielding potential for unexpected connections in the labyrinthine corridors of data, where just like laws and jokes, patterns sometimes come out of left field.

[[INTRODUCTION]]
Introduction
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. From courtrooms to Capitol Hill, the intertwining of law and politics has intrigued scholars and armchair analysts alike. In this study, we set out to explore a curious connection that has emerged from the annals of electoral history— the correlation between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States.
This surprising link between votive preferences and legal practitioners has raised eyebrows and piqued the interest of many, much like the expression on a judge's face when a lawyer walks into court wearing an outlandishly colorful tie. One might say it's a tale as old as judicial robes themselves – the constant dance of power dynamics and legal representation, set against the backdrop of electoral tides. Perhaps lawyers and Republican votes are not as unrelated as they appear, much like how a lawyer's briefcase is never truly empty, always carrying the weight of evidence and caffeine.
Our exploration of this correlation drew from robust datasets, including information from the MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, ensuring that our statistical scrutiny was as rigorous as a lawyer's cross-examination. The results of our analysis, spanning from 1989 to 2020, unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01. Such a close correlation beckons one to ask: have lawyers and Republican votes formed an unspoken alliance as unbreakable as the bond between a client and their retainer?
As we dive deeper into this fascinating correlation, it is crucial to remember that correlation does not imply causation – a principle as fundamental as the gavel's role in a courtroom. While we navigate the intriguing link between legal practitioners and electoral preferences, let's keep in mind that just because a lawyer tells a good joke doesn't mean they should quit their day job. The unexpected connections we uncover serve as a reminder that the depths of data can often conceal astonishing relationships, much like how a lawyer's argument can sometimes turn a case on its head.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic connection between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States, we embarked on a methodological quest as intricate as deciphering a complex legal statute. Our journey began with the collection and curation of extensive datasets from 1989 to 2020, akin to building a compelling case by gathering substantial evidence – though in our case, the evidence was statistics and not eyewitness accounts.

We sourced our data primarily from reputable repositories such as the MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association. With the diligence of a lawyer sifting through case precedents, we combed through these datasets to ensure a comprehensive representation of voting patterns and legal practitioners over the years. Much like the discovery of a substantial legal loophole, our pursuit was marked by meticulous attention to detail and thoroughness in data selection.

Our analytical approach was as rigorous as a seasoned prosecutor preparing for a high-stakes trial. We embarked on a statistical odyssey, employing a combination of regression analysis and time series modeling to examine the relationship between Republican votes in Kentucky and the nationwide count of lawyers. Through these analytical lenses, we sought to illuminate the nuances of the correlation, much like a seasoned litigator sheds light on the intricacies of a complex case.

Furthermore, to ascertain the robustness and reliability of our findings, our methodology entailed intricate sensitivity analyses, akin to scrutinizing witness testimonies for inconsistencies. These analyses encompassed rigorous checks for autocorrelation, heteroscedasticity, and other potential confounding variables, ensuring that our conclusions were as sound as a judge's ruling.

Finally, in our approach to uncover this intriguing correlation, we employed state-of-the-art statistical software, navigating its complexities with the dexterity of a seasoned legal practitioner maneuvering through a labyrinthine legal code. This allowed for precise and efficient modeling, akin to the finesse of a well-crafted legal argument.

As we reflect on the diverse facets of our methodology, it becomes evident that our pursuit of understanding the relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States was as intricate and multifaceted as a complex legal case. Much like the art of law, our methodology encapsulates the fusion of meticulousness, precision, and analytical rigor, demonstrating that the pursuit of evidence-driven insights can be as compelling as a well-crafted legal argument.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Votes for the Republican Presidential candidate in Kentucky and Number of Lawyers in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and ABA .

For the time period 1989 to 2020, you found a correlation 0.9143842, r-squared of 0.8360984, 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 Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States

[[ABSTRACT]]
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. In this study, we delve into the compelling relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Drawing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, our analysis spanning from 1989 to 2020 unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01.

The results of this study raise eyebrows and prompt lively discussions, much like a lawyer grilling a witness on the stand. We discovered that as the number of Republican votes in the Bluegrass State sways, so does the number of legal practitioners across the nation, showcasing a connection as tight-knit as a judge's gavel. This surprising association invokes an age-old question: are lawyers and conservative votes like peanut butter and jelly, seemingly unrelated but undeniably inseparable?

While the causality behind this correlation remains enigmatic, the findings of this research serve as a testament to the uncanny intertwining of legal and political realms. As we unravel the quirkiness of this phenomenon, let us remember that even in the world of statistics, correlation does not necessarily imply causation – much like how having a lot of papers on the desk doesn't make one a stationery expert. This study stands as a testament to the unyielding potential for unexpected connections in the labyrinthine corridors of data, where just like laws and jokes, patterns sometimes come out of left field.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. From courtrooms to Capitol Hill, the intertwining of law and politics has intrigued scholars and armchair analysts alike. In this study, we set out to explore a curious connection that has emerged from the annals of electoral history— the correlation between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States.
This surprising link between votive preferences and legal practitioners has raised eyebrows and piqued the interest of many, much like the expression on a judge's face when a lawyer walks into court wearing an outlandishly colorful tie. One might say it's a tale as old as judicial robes themselves – the constant dance of power dynamics and legal representation, set against the backdrop of electoral tides. Perhaps lawyers and Republican votes are not as unrelated as they appear, much like how a lawyer's briefcase is never truly empty, always carrying the weight of evidence and caffeine.
Our exploration of this correlation drew from robust datasets, including information from the MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, ensuring that our statistical scrutiny was as rigorous as a lawyer's cross-examination. The results of our analysis, spanning from 1989 to 2020, unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01. Such a close correlation beckons one to ask: have lawyers and Republican votes formed an unspoken alliance as unbreakable as the bond between a client and their retainer?
As we dive deeper into this fascinating correlation, it is crucial to remember that correlation does not imply causation – a principle as fundamental as the gavel's role in a courtroom. While we navigate the intriguing link between legal practitioners and electoral preferences, let's keep in mind that just because a lawyer tells a good joke doesn't mean they should quit their day job. The unexpected connections we uncover serve as a reminder that the depths of data can often conceal astonishing relationships, much like how a lawyer's argument can sometimes turn a case on its head.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis revealed a strong and statistically significant correlation between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Over the period from 1989 to 2020, the correlation coefficient stood at 0.9143842 and the R-squared value at 0.8360984, both of which were found to be significant at p < 0.01. These findings suggest that as the votes for the Republican presidential candidate in Kentucky fluctuated, there was a corresponding fluctuation in the number of lawyers across the nation, laying the groundwork for further exploration into this unexpected association.

In Figure 1, the scatterplot visually illustrates the remarkable correlation between the two variables. It demonstrates a clear trend, akin to a well-prepared legal argument leaving little room for doubt. The figure presents a compelling visual representation of this intriguing relationship, prompting contemplation much like a lawyer preparing for a closing statement.

Now for a lawyer joke: Why don't lawyers ever go to the beach? Cats keep trying to bury them in the sand!

This unexpected correlation prompts vibrant discussions and invites further inquiry into the underlying mechanisms at play. While the precise causality remains cloaked in mystery, these findings underscore the intriguing interplay between political preferences and the legal profession, much like a legal brief unraveling the nuances of a complex case.

The uncanny alignment between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States introduces a thought-provoking dimension to the intersection of law and politics, much like how unexpected evidence can turn a trial on its head. As we continue to unravel the enigma of this correlation, it is crucial to bear in mind that correlation does not imply causation – a fundamental principle as unshakeable as the steadfastness of legal precedent. Just as a lawyer's argument can sway a jury, these findings emphasize the powerful impact of seemingly unrelated variables coming together in the labyrinth of data, much like an unexpected witness testimony dramatically altering the course of a trial.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Votes for the Republican Presidential candidate in Kentucky and Number of Lawyers in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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 Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States

[[ABSTRACT]]
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. In this study, we delve into the compelling relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Drawing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, our analysis spanning from 1989 to 2020 unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01.

The results of this study raise eyebrows and prompt lively discussions, much like a lawyer grilling a witness on the stand. We discovered that as the number of Republican votes in the Bluegrass State sways, so does the number of legal practitioners across the nation, showcasing a connection as tight-knit as a judge's gavel. This surprising association invokes an age-old question: are lawyers and conservative votes like peanut butter and jelly, seemingly unrelated but undeniably inseparable?

While the causality behind this correlation remains enigmatic, the findings of this research serve as a testament to the uncanny intertwining of legal and political realms. As we unravel the quirkiness of this phenomenon, let us remember that even in the world of statistics, correlation does not necessarily imply causation – much like how having a lot of papers on the desk doesn't make one a stationery expert. This study stands as a testament to the unyielding potential for unexpected connections in the labyrinthine corridors of data, where just like laws and jokes, patterns sometimes come out of left field.

[[LITERATURE REVIEW]]
A multitude of studies have delved into the intricate relationship between politics and legal professions, seeking to unravel the enigmatic ties binding these seemingly distinct domains. Smith et al. (2015) have extensively examined the regional variations in lawyer density and political affiliations, shedding light on the divergent trends observed across different states. Similarly, Doe and Jones (2017) explored the influence of political landscapes on legal career trajectories, elucidating the nuanced interplay between ideological leanings and professional pursuits. However, amidst these scholarly endeavors, one correlation persists like a lawyer's persistent argument in court – the intriguing alignment between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States.
It is fascinating to note the gravity of this correlation, which has captured the attention of researchers and enthusiasts alike, much like how a good lawyer captivates an audience in the courtroom. The link between these seemingly disparate entities prompts contemplation akin to pondering the paradox of legal jargon – often convoluted and yet unmistakably influential. Past studies have provided valuable insights into the regional distribution of legal practitioners and their political proclivities, but none have plumbed the depths of this unique relationship quite like our current endeavor. This correlation presents itself as an enigma wrapped in a mystery, much like a lawyer's bafflingly complex billable hours.
Turning to the broader landscape of literature, non-fiction works such as "The Legal Profession in America" (Adams, 2019) and "The Political Puzzle: Lawyers and the Electoral Process" (Brown, 2018) have offered illuminating perspectives on the intersection of law and politics, furnishing a rich tapestry of insights that contextualize our present investigation. Yet, as we embark on this scholarly odyssey, it is crucial to acknowledge the influence of fictitious narratives that, albeit fictional, offer surprisingly relevant parallels to our topic. Works such as "The Firm" (Grisham, 1991) and "Presumed Innocent" (Turow, 1987) not only entertain readers with legal dramas, but also inadvertently capture the essence of the intricate dance between legal professionals and political undercurrents. Similarly, board games such as "Lawyer Up: The Courtroom Game" and "Campaign Manager: The Political Strategy Game" serve as playful reminders of the intertwining realms we seek to explore. After all, what's a study on lawyers and Republican votes without a play on words, or at least a Monopoly reference?
In closing, our literature review illuminates the path paved by prior research, while adding a dash of levity befitting the enigmatic correlation we endeavor to untangle. From serious scholarly work to fictional tales and whimsical games, the entwined domains of law and politics continue to captivate our collective imagination, much like an unexpected punchline in a courtroom—surprising, yet remarkably fitting.

[[RESULTS]]
The statistical analysis revealed a strong and statistically significant correlation between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Over the period from 1989 to 2020, the correlation coefficient stood at 0.9143842 and the R-squared value at 0.8360984, both of which were found to be significant at p < 0.01. These findings suggest that as the votes for the Republican presidential candidate in Kentucky fluctuated, there was a corresponding fluctuation in the number of lawyers across the nation, laying the groundwork for further exploration into this unexpected association.
In Figure 1, the scatterplot visually illustrates the remarkable correlation between the two variables. It demonstrates a clear trend, akin to a well-prepared legal argument leaving little room for doubt. The figure presents a compelling visual representation of this intriguing relationship, prompting contemplation much like a lawyer preparing for a closing statement.
Now for a lawyer joke: Why don't lawyers ever go to the beach? Cats keep trying to bury them in the sand!
This unexpected correlation prompts vibrant discussions and invites further inquiry into the underlying mechanisms at play. While the precise causality remains cloaked in mystery, these findings underscore the intriguing interplay between political preferences and the legal profession, much like a legal brief unraveling the nuances of a complex case.
The uncanny alignment between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States introduces a thought-provoking dimension to the intersection of law and politics, much like how unexpected evidence can turn a trial on its head. As we continue to unravel the enigma of this correlation, it is crucial to bear in mind that correlation does not imply causation – a fundamental principle as unshakeable as the steadfastness of legal precedent. Just as a lawyer's argument can sway a jury, these findings emphasize the powerful impact of seemingly unrelated variables coming together in the labyrinth of data, much like an unexpected witness testimony dramatically altering the course of a trial.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The remarkable correlation unveiled in this study bolstered and extended prior research, reinforcing the compelling interplay between political leanings and the legal landscape, akin to the synergy between a skilled attorney and a well-crafted argument. The findings align with Smith et al. (2015) and Doe and Jones (2017), who explored the intricate relationship between political affiliations and the distribution of lawyers, further solidifying the notion that regional variations in votes for the Republican presidential candidate are indeed linked to the density of legal practitioners nationwide.

Now, for a witty interjection: What do you call a lawyer who doesn't chase ambulances? Retired.

These results not only accentuate the robustness of the observed correlation but also underline its pervasive nature, permeating the fabric of legal and political landscapes much like a memorable quip in a riveting courtroom drama. The seemingly incongruous connection between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States echoes the paradoxical nature of legal doctrines, where unexpected juxtapositions often reveal profound insights, much like how a lawyer's seemingly unrelated testimony can pivot a case.

Building upon the intriguing alignment between these variables, the present study weaves a narrative that reinforces the notion that as the political tides ebb and flow, so do the patterns of legal practitioners, mirroring the tenacity of a skilled lawyer's pursuit of justice. These findings evoke a sense of curiosity and stimulate further explorations, engendering discussions as lively as a courtroom debate, much like the playful banter between legal adversaries seeking the truth.

In a manner reflective of a tapestry woven from diverse threads, this research upholds the noteworthy juxtaposition presented in the literature review, uniting the gravity of serious scholarly works with the playful undertones of fiction and games to illuminate the multifaceted nature of the relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. This scholarly pursuit aptly captures the inherent charm of navigating the nebulous corridors of data, where correlations emerge as unexpectedly as a well-timed punchline.

Stay tuned for the conclusion!


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Votes for the Republican Presidential candidate in Kentucky and Number of Lawyers in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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 Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States

[[ABSTRACT]]
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. In this study, we delve into the compelling relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Drawing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, our analysis spanning from 1989 to 2020 unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01.

The results of this study raise eyebrows and prompt lively discussions, much like a lawyer grilling a witness on the stand. We discovered that as the number of Republican votes in the Bluegrass State sways, so does the number of legal practitioners across the nation, showcasing a connection as tight-knit as a judge's gavel. This surprising association invokes an age-old question: are lawyers and conservative votes like peanut butter and jelly, seemingly unrelated but undeniably inseparable?

While the causality behind this correlation remains enigmatic, the findings of this research serve as a testament to the uncanny intertwining of legal and political realms. As we unravel the quirkiness of this phenomenon, let us remember that even in the world of statistics, correlation does not necessarily imply causation – much like how having a lot of papers on the desk doesn't make one a stationery expert. This study stands as a testament to the unyielding potential for unexpected connections in the labyrinthine corridors of data, where just like laws and jokes, patterns sometimes come out of left field.

[[INTRDUCTION]]
Introduction
Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. From courtrooms to Capitol Hill, the intertwining of law and politics has intrigued scholars and armchair analysts alike. In this study, we set out to explore a curious connection that has emerged from the annals of electoral history— the correlation between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States.
This surprising link between votive preferences and legal practitioners has raised eyebrows and piqued the interest of many, much like the expression on a judge's face when a lawyer walks into court wearing an outlandishly colorful tie. One might say it's a tale as old as judicial robes themselves – the constant dance of power dynamics and legal representation, set against the backdrop of electoral tides. Perhaps lawyers and Republican votes are not as unrelated as they appear, much like how a lawyer's briefcase is never truly empty, always carrying the weight of evidence and caffeine.
Our exploration of this correlation drew from robust datasets, including information from the MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, ensuring that our statistical scrutiny was as rigorous as a lawyer's cross-examination. The results of our analysis, spanning from 1989 to 2020, unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01. Such a close correlation beckons one to ask: have lawyers and Republican votes formed an unspoken alliance as unbreakable as the bond between a client and their retainer?
As we dive deeper into this fascinating correlation, it is crucial to remember that correlation does not imply causation – a principle as fundamental as the gavel's role in a courtroom. While we navigate the intriguing link between legal practitioners and electoral preferences, let's keep in mind that just because a lawyer tells a good joke doesn't mean they should quit their day job. The unexpected connections we uncover serve as a reminder that the depths of data can often conceal astonishing relationships, much like how a lawyer's argument can sometimes turn a case on its head.

[[RESULTS]]
The statistical analysis revealed a strong and statistically significant correlation between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Over the period from 1989 to 2020, the correlation coefficient stood at 0.9143842 and the R-squared value at 0.8360984, both of which were found to be significant at p < 0.01. These findings suggest that as the votes for the Republican presidential candidate in Kentucky fluctuated, there was a corresponding fluctuation in the number of lawyers across the nation, laying the groundwork for further exploration into this unexpected association.
In Figure 1, the scatterplot visually illustrates the remarkable correlation between the two variables. It demonstrates a clear trend, akin to a well-prepared legal argument leaving little room for doubt. The figure presents a compelling visual representation of this intriguing relationship, prompting contemplation much like a lawyer preparing for a closing statement.
Now for a lawyer joke: Why don't lawyers ever go to the beach? Cats keep trying to bury them in the sand!
This unexpected correlation prompts vibrant discussions and invites further inquiry into the underlying mechanisms at play. While the precise causality remains cloaked in mystery, these findings underscore the intriguing interplay between political preferences and the legal profession, much like a legal brief unraveling the nuances of a complex case.
The uncanny alignment between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States introduces a thought-provoking dimension to the intersection of law and politics, much like how unexpected evidence can turn a trial on its head. As we continue to unravel the enigma of this correlation, it is crucial to bear in mind that correlation does not imply causation – a fundamental principle as unshakeable as the steadfastness of legal precedent. Just as a lawyer's argument can sway a jury, these findings emphasize the powerful impact of seemingly unrelated variables coming together in the labyrinth of data, much like an unexpected witness testimony dramatically altering the course of a trial.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has shed light on the curious relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. The robust statistical analysis uncovered a remarkably strong correlation, akin to a client and their attorney – seemingly distinct entities, yet undeniably connected. This association, much like a legal argument, leaves little room for doubt, with a correlation coefficient of 0.9143842 and a p-value less than 0.01, showcasing a bond as unbreakable as the unwavering allegiance between lawyers and their trusty briefcases.

Now, for a lawyer joke: Why did the scarecrow become a successful lawyer? Because he was outstanding in his field!

The scatterplot visually emphasizes the tight-knit relationship between these variables, much like how a well-crafted case builds the foundation for a compelling argument in court. These results prompt lively discussions and highlight the intriguing interplay of legal landscapes and political preferences, much like how a surprising twist in a legal drama captivates the audience.

No more research is needed in this area.


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 Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Pachyderms


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 Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Legalistics and Political Pachyderm Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Elephant in the Courtroom: Exploring the Correlation Between Votes for the Republican Presidential Candidate in Kentucky and the Number of Lawyers in the United States with an abstract of Legal landscapes and political arenas have long been the subjects of scrutiny, often yielding intriguing correlations and captivating insights. In this study, we delve into the compelling relationship between votes for the Republican presidential candidate in Kentucky and the number of lawyers in the United States. Drawing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Bar Association, our analysis spanning from 1989 to 2020 unearthed a remarkable correlation coefficient of 0.9143842 with a p-value less than 0.01.
The results of this study raise eyebrows and prompt lively discussions, much like a lawyer grilling a witness on the stand. We discovered that as the number of Republican votes in the Bluegrass State sways, so does the number of legal practitioners across the nation, showcasing a connection as tight-knit as a judge's gavel. This surprising association invokes an age-old question: are lawyers and conservative votes like peanut butter and jelly, seemingly unrelated but undeniably inseparable?
While the causality behind this correlation remains enigmatic, the findings of this research serve as a testament to the uncanny intertwining of legal and political realms. As we unravel the quirkiness of this phenomenon, let us remember that even in the world of statistics, correlation does not necessarily imply causation – much like how having a lot of papers on the desk doesn't make one a stationery expert. This study stands as a testament to the unyielding potential for unexpected connections in the labyrinthine corridors of data, where just like laws and jokes, patterns sometimes come out of left field.

ChatGPT:

Republican presidential candidate, Kentucky, lawyers in the United States, correlation, MIT Election Data and Science Lab, Harvard Dataverse, American Bar Association, correlation coefficient, causality, legal and political realms, statistics, causation, unexpected connections, data analysis

*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

Votes for the Republican Presidential candidate in Kentucky
Detailed data title: Percentage of all votes cast for the Republican Presidential candidate in Kentucky
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Republican Presidential candidate in Kentucky

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 = 0.9143842 (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 = 0.8360984 (Coefficient of determination)
This means 83.6% 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., Votes for the Republican Presidential candidate in Kentucky) over the 8 years from 1989 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0015. 0.0014699071373381987000000000
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 0.91 in 0.15% of random cases. Said differently, if you correlated 680 random variables Which I absolutely did.
with the same 7 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 7 because we have two variables measured over a period of 8 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.

[ 0.59, 0.98 ] 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.
19921996200020042008201220162020
Votes for the Republican Presidential candidate in Kentucky (Percentage of votes)41.340944.882256.506559.549557.39960.493162.519662.0866
Number of Lawyers in the United States (Lawyers)799760953260102246010845001162120124520013128701328740




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.
  4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.




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([41.3409,44.8822,56.5065,59.5495,57.399,60.4931,62.5196,62.0866,])
array_2 = np.array([799760,953260,1022460,1084500,1162120,1245200,1312870,1328740,])
array_1_name = "Votes for the Republican Presidential candidate in Kentucky"
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?

Your dedication to rating warms my heart!


Correlation ID: 4982 · Black Variable ID: 26102 · Red Variable ID: 542
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0