about · email me · subscribe
Spurious correlation #4,463 · 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 Wyoming and the second variable is Frank Lampard's Premier League goal tally.  The chart goes from 1996 to 2016, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The increase in Votes for the Republican Presidential candidate in Wyoming caused Frank Lampard's Premier League goal tally to increase because as the votes went up, so did the 'right' support for Lampard, boosting his morale and shooting accuracy! It's the red, white, and blue power of political goal setting!

Model: dalle-3
Prompt: Generate an image that looks like it is a scene from 'Star Wars', capturing the picturesque town square of Wyoming. In the center of the square, a line of enthusiastic voters, each wearing the Republican Party's signature red caps, stretches out as they cast their votes in the election. Alongside them, a soccer pitch is set up, with Frank Lampard, adorned in Chelsea's blue jersey, skillfully scoring a goal. The red, white, and blue colors of the political fervor and the spirited soccer match merge into a powerful and unified display of goal-setting. The scene should be visually captivating, creating a seamless blend of political enthusiasm and sportsmanship within the serene town square set against a futuristic 'Star Wars' backdrop. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally. 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: Data cyber art Magic realism An image that looks like it is a scene from A Disney Movie Celtic art An image that looks like it is a scene from 'Star Wars'
ChatGPT: An image that looks like it is a scene from 'Star Wars'

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 Wyoming and Frank Lampard's Premier League goal tally, in the following situation: The increase in Votes for the Republican Presidential candidate in Wyoming caused Frank Lampard's Premier League goal tally to increase because as the votes went up, so did the 'right' support for Lampard, boosting his morale and shooting accuracy! It's the red, white, and blue power of political goal setting!. Keep the description simple.
ChatGPT: In a picturesque town square in Wyoming, a line of enthusiastic voters wearing the Republican Party's signature red caps stretches out, casting their votes in the election. In the same square, a soccer pitch is set up, and Frank Lampard, adorned in Chelsea's blue jersey, scores a goal as the ball flies into the back of the net with precision, fueled by the support and encouragement from the votes being cast. The red, white, and blue colors of the political fervor and the spirited soccer match beautifully merge into a powerful display of unified goal-setting.

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: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: In a picturesque town square in Wyoming, a line of enthusiastic voters wearing the Republican Party's signature red caps stretches out, casting their votes in the election. In the same square, a soccer pitch is set up, and Frank Lampard, adorned in Chelsea's blue jersey, scores a goal as the ball flies into the back of the net with precision, fueled by the support and encouragement from the votes being cast. The red, white, and blue colors of the political fervor and the spirited soccer match beautifully merge into a powerful display of unified goal-setting. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that looks like it is a scene from 'Star Wars', capturing the picturesque town square of Wyoming. In the center of the square, a line of enthusiastic voters, each wearing the Republican Party's signature red caps, stretches out as they cast their votes in the election. Alongside them, a soccer pitch is set up, with Frank Lampard, adorned in Chelsea's blue jersey, skillfully scoring a goal. The red, white, and blue colors of the political fervor and the spirited soccer match merge into a powerful and unified display of goal-setting. The scene should be visually captivating, creating a seamless blend of political enthusiasm and sportsmanship within the serene town square set against a futuristic 'Star Wars' backdrop.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

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 Wyoming caused Frank Lampard's Premier League goal tally to increase. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance

The Journal of Sports and Political Science

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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Wyoming and Frank Lampard's Premier League goal tally. Make lots of jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, just make it sound clever.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Wikipedia to assess this nagging question. You found a correlation coefficient of 0.9960384 and p < 0.01 for 1996 to 2016.

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]]
"Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance"

[[ABSTRACT]]
This study delves into the uncharted territory of football and politics to unravel the intertwined dynamics between voting behavior in Wyoming and the Premier League goal tally of the iconic Frank Lampard. Through the use of data from esteemed sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the ever-reliable repository of human knowledge, Wikipedia, we meticulously examined the statistical relationship between these two seemingly disparate domains. The findings astoundingly revealed a virtually jaw-dropping correlation coefficient of 0.9960384 and p < 0.01 for the period spanning 1996 to 2016. This correlation, akin to a perfectly executed backheel, suggests a remarkably strong connection that beckons further investigation. Our research underscores the potential for unexpected linkages between sports and civic engagement, shedding light on the whimsical interconnectedness of human pursuits.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Wyoming and Frank Lampard's Premier League goal tally. Make lots of jokes, goofy observations, and puns. 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]]
"Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance"

[[ABSTRACT]]
This study delves into the uncharted territory of football and politics to unravel the intertwined dynamics between voting behavior in Wyoming and the Premier League goal tally of the iconic Frank Lampard. Through the use of data from esteemed sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the ever-reliable repository of human knowledge, Wikipedia, we meticulously examined the statistical relationship between these two seemingly disparate domains. The findings astoundingly revealed a virtually jaw-dropping correlation coefficient of 0.9960384 and p < 0.01 for the period spanning 1996 to 2016. This correlation, akin to a perfectly executed backheel, suggests a remarkably strong connection that beckons further investigation. Our research underscores the potential for unexpected linkages between sports and civic engagement, shedding light on the whimsical interconnectedness of human pursuits.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the world of statistical analysis, unlikely correlations often lurk in the most unexpected places. In this paper, we embark on a whimsical journey through the realms of football and politics to unravel the peculiar relationship between voting behavior in Wyoming and the Premier League goal tally of the indomitable Frank Lampard. Our intent is to illuminate the entwined tapestry of human pursuits, where the heady rush of netting a goal can, apparently, find common ground with the solemn act of casting a vote.

It is well-established that Wyoming holds a unique place in American politics, often mentioned in hushed tones and cryptic allusions during electoral seasons. Drawing this enigmatic state into our purview, we sought to discern any discernible pattern between the votes cast for the Republican Presidential candidate and the on-field exploits of Frank Lampard in the Premier League. As the fireworks of football and the fire and brimstone of politics jostle for our attention, one cannot help but wonder if these seemingly distinct domains might, in fact, share an underlying harmony.

Our investigation hinged on an extraordinary assemblage of data, meticulously acquired from reputable sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the illustrious bastion of human knowledge, Wikipedia. Through careful curation and statistical rigor, we endeavored to discern whether there existed more than a passing resemblance between the political leanings of Wyomingites and the goings-on in Lampard's goal-scoring exploits.

While our inquiry may seem whimsical at first glance, the bedrock of statistical analysis calls for a steadfast commitment to unraveling every mystery, no matter how unconventional. In delving into this uncharted territory, we sought to tease out any meaningful connections that would, much like a perfectly timed through-ball, thread together these seemingly disparate themes.

In the pages that follow, we lay bare the surprising findings that emerged from our excursion into the symphony of numerical data. Brace yourself for the unexpected, for in the world of statistics, the most improbable connections often yield the most intriguing insights.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
"Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance"

[[ABSTRACT]]
This study delves into the uncharted territory of football and politics to unravel the intertwined dynamics between voting behavior in Wyoming and the Premier League goal tally of the iconic Frank Lampard. Through the use of data from esteemed sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the ever-reliable repository of human knowledge, Wikipedia, we meticulously examined the statistical relationship between these two seemingly disparate domains. The findings astoundingly revealed a virtually jaw-dropping correlation coefficient of 0.9960384 and p < 0.01 for the period spanning 1996 to 2016. This correlation, akin to a perfectly executed backheel, suggests a remarkably strong connection that beckons further investigation. Our research underscores the potential for unexpected linkages between sports and civic engagement, shedding light on the whimsical interconnectedness of human pursuits.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the world of statistical analysis, unlikely correlations often lurk in the most unexpected places. In this paper, we embark on a whimsical journey through the realms of football and politics to unravel the peculiar relationship between voting behavior in Wyoming and the Premier League goal tally of the indomitable Frank Lampard. Our intent is to illuminate the entwined tapestry of human pursuits, where the heady rush of netting a goal can, apparently, find common ground with the solemn act of casting a vote.
It is well-established that Wyoming holds a unique place in American politics, often mentioned in hushed tones and cryptic allusions during electoral seasons. Drawing this enigmatic state into our purview, we sought to discern any discernible pattern between the votes cast for the Republican Presidential candidate and the on-field exploits of Frank Lampard in the Premier League. As the fireworks of football and the fire and brimstone of politics jostle for our attention, one cannot help but wonder if these seemingly distinct domains might, in fact, share an underlying harmony.
Our investigation hinged on an extraordinary assemblage of data, meticulously acquired from reputable sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the illustrious bastion of human knowledge, Wikipedia. Through careful curation and statistical rigor, we endeavored to discern whether there existed more than a passing resemblance between the political leanings of Wyomingites and the goings-on in Lampard's goal-scoring exploits.
While our inquiry may seem whimsical at first glance, the bedrock of statistical analysis calls for a steadfast commitment to unraveling every mystery, no matter how unconventional. In delving into this uncharted territory, we sought to tease out any meaningful connections that would, much like a perfectly timed through-ball, thread together these seemingly disparate themes.
In the pages that follow, we lay bare the surprising findings that emerged from our excursion into the symphony of numerical data. Brace yourself for the unexpected, for in the world of statistics, the most improbable connections often yield the most intriguing insights.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Smith (2010) initially delved into the realm of statistical analysis, seeking to uncover the enigmatic relationship between voting patterns and seemingly unrelated domains. This work laid the foundation for our current investigation, providing a principled framework for unearthing correlations that transcend conventional understanding. Building upon this theoretical groundwork, Doe (2014) further expanded the horizon of statistical inquiry, delving into the complex interplay between regional voting behavior and diverse domains of human activity. While these pioneering studies set the stage for our own investigation, it is with a distinct sense of audacity that we venture forth into uncharted terrain, embracing the whimsical entropy of our chosen pursuits.

In "Data Analysis in Sports" by Jones (2018), the authors find that statistical methodologies can be comfortably applied to unravel the mysteries lurking within the annals of sports. This insight fueled our ambition to explore the statistical relationship between votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally. Stretching the boundaries of traditional statistical inquiry, our quest for correlations in seemingly incongruous arenas led us to amusingly unexpected insights.

Turning our attention to non-fiction literature, the seminal work "Soccer and Politics: A Historical Analysis" provides a sobering account of the interwoven dynamics between sports and political landscapes, echoing the themes central to our own study. Moreover, the opus "Election Analytics: Unveiling the Veiled" offers a spark of inspiration, conferring a fresh outlook on the potential for statistical revelation in the realm of political movements. These texts serve as beacons guiding our inquiry, offering contemplative reflections to inform our own perception of the intertwined domains we seek to explore.

Venturing into the realm of fiction, the hauntingly evocative "Goals and Governance: An Unlikely Tale" tantalizingly hints at the intersection between sporting triumphs and electoral sagas, prompting reflections on the improbable parallels we seek to uncover. Similarly, "The Ballot and the Ball: A Tale of Two Passions" captures the whimsical rapport between sports and civic engagement, infusing our inquiry with a sense of literary curiosity. While these works may be the fabrications of creative minds, their imaginative contemplations have left an indelible imprint on our own investigation, flickering with the zeal of exploration.

As part of the research endeavor, the authors immerse themselves in relevant TV shows, including "SportsNation" and "The West Wing", seeking to glean insights from both the sporting arena and the political theater. Immersed in the tumultuous fervor of these televised landscapes, the researchers assimilate a multifaceted understanding of the nuanced interplay between sports and politics, transcending the traditional confines of statistical inquiry.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally. Make lots of jokes, goofy observations, and puns. 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 Wikipedia . You used data from 1996 to 2016

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]]
"Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance"

[[ABSTRACT]]
This study delves into the uncharted territory of football and politics to unravel the intertwined dynamics between voting behavior in Wyoming and the Premier League goal tally of the iconic Frank Lampard. Through the use of data from esteemed sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the ever-reliable repository of human knowledge, Wikipedia, we meticulously examined the statistical relationship between these two seemingly disparate domains. The findings astoundingly revealed a virtually jaw-dropping correlation coefficient of 0.9960384 and p < 0.01 for the period spanning 1996 to 2016. This correlation, akin to a perfectly executed backheel, suggests a remarkably strong connection that beckons further investigation. Our research underscores the potential for unexpected linkages between sports and civic engagement, shedding light on the whimsical interconnectedness of human pursuits.

[[INTRODUCTION]]
In the world of statistical analysis, unlikely correlations often lurk in the most unexpected places. In this paper, we embark on a whimsical journey through the realms of football and politics to unravel the peculiar relationship between voting behavior in Wyoming and the Premier League goal tally of the indomitable Frank Lampard. Our intent is to illuminate the entwined tapestry of human pursuits, where the heady rush of netting a goal can, apparently, find common ground with the solemn act of casting a vote.
It is well-established that Wyoming holds a unique place in American politics, often mentioned in hushed tones and cryptic allusions during electoral seasons. Drawing this enigmatic state into our purview, we sought to discern any discernible pattern between the votes cast for the Republican Presidential candidate and the on-field exploits of Frank Lampard in the Premier League. As the fireworks of football and the fire and brimstone of politics jostle for our attention, one cannot help but wonder if these seemingly distinct domains might, in fact, share an underlying harmony.
Our investigation hinged on an extraordinary assemblage of data, meticulously acquired from reputable sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the illustrious bastion of human knowledge, Wikipedia. Through careful curation and statistical rigor, we endeavored to discern whether there existed more than a passing resemblance between the political leanings of Wyomingites and the goings-on in Lampard's goal-scoring exploits.
While our inquiry may seem whimsical at first glance, the bedrock of statistical analysis calls for a steadfast commitment to unraveling every mystery, no matter how unconventional. In delving into this uncharted territory, we sought to tease out any meaningful connections that would, much like a perfectly timed through-ball, thread together these seemingly disparate themes.
In the pages that follow, we lay bare the surprising findings that emerged from our excursion into the symphony of numerical data. Brace yourself for the unexpected, for in the world of statistics, the most improbable connections often yield the most intriguing insights.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To adequately capture the exquisitely nuanced interplay between the political inclinations of Wyoming's electorate and the goal-scoring finesse of Frank Lampard, our research team embarked on a methodological odyssey of epic proportions. First and foremost, we meticulously sourced data from a plethora of esteemed repositories, including the MIT Election Data and Science Lab, the Harvard Dataverse, and the venerable font of human knowledge and trivia, Wikipedia. As we delved into this data cornucopia, we scrupulously sought every nugget of information relevant to Republican Presidential candidate votes in Wyoming and Frank Lampard's Premier League goal tally from the years 1996 to 2016.

With data in hand, our research hinged on the employment of advanced statistical techniques to unveil the hidden kinship between these seemingly incongruous domains. We began by employing simple scatterplots to visualize any potential patterns and trends, akin to carefully inspecting the stitches on a football to discern its trajectory. Following this, we ventured into the realm of correlation analysis, utilizing Pearson's correlation coefficient to discern the strength and direction of the relationship. Not content with a mere superficial glance, we delved into constructing confidence intervals and performing hypothesis testing, scrutinizing the viability of our findings with the tenacity of a hawk eyeing its prey.

Beyond the standard statistical procedures, we divulged into constructing a series of graphs and visual aids, presenting our findings with the clarity of a spotless goalpost. Furthermore, in a bid to unravel the temporal nuances of this peculiar association, we explored time series analysis to discern any evolving patterns over the years, much like analyzing the ebbs and flows of a football match.

While some may scoff at the unorthodox nature of our inquiry, we approached our data with a precision and ardor typically reserved for scrutinizing stock market trends or electoral polls. Our quest for a deeper understanding of the nexus between Wyoming's political proclivities and Lampard's goal-scoring prowess propelled us to employ a diverse array of statistical tools, serving as both compass and sextant on our journey through this whimsical topography of data.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally. Make lots of jokes, goofy observations, and puns. 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 Wikipedia .

For the time period 1996 to 2016, you found a correlation 0.9960384, r-squared of 0.9920926, 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]]
"Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance"

[[ABSTRACT]]
This study delves into the uncharted territory of football and politics to unravel the intertwined dynamics between voting behavior in Wyoming and the Premier League goal tally of the iconic Frank Lampard. Through the use of data from esteemed sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the ever-reliable repository of human knowledge, Wikipedia, we meticulously examined the statistical relationship between these two seemingly disparate domains. The findings astoundingly revealed a virtually jaw-dropping correlation coefficient of 0.9960384 and p < 0.01 for the period spanning 1996 to 2016. This correlation, akin to a perfectly executed backheel, suggests a remarkably strong connection that beckons further investigation. Our research underscores the potential for unexpected linkages between sports and civic engagement, shedding light on the whimsical interconnectedness of human pursuits.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the world of statistical analysis, unlikely correlations often lurk in the most unexpected places. In this paper, we embark on a whimsical journey through the realms of football and politics to unravel the peculiar relationship between voting behavior in Wyoming and the Premier League goal tally of the indomitable Frank Lampard. Our intent is to illuminate the entwined tapestry of human pursuits, where the heady rush of netting a goal can, apparently, find common ground with the solemn act of casting a vote.
It is well-established that Wyoming holds a unique place in American politics, often mentioned in hushed tones and cryptic allusions during electoral seasons. Drawing this enigmatic state into our purview, we sought to discern any discernible pattern between the votes cast for the Republican Presidential candidate and the on-field exploits of Frank Lampard in the Premier League. As the fireworks of football and the fire and brimstone of politics jostle for our attention, one cannot help but wonder if these seemingly distinct domains might, in fact, share an underlying harmony.
Our investigation hinged on an extraordinary assemblage of data, meticulously acquired from reputable sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the illustrious bastion of human knowledge, Wikipedia. Through careful curation and statistical rigor, we endeavored to discern whether there existed more than a passing resemblance between the political leanings of Wyomingites and the goings-on in Lampard's goal-scoring exploits.
While our inquiry may seem whimsical at first glance, the bedrock of statistical analysis calls for a steadfast commitment to unraveling every mystery, no matter how unconventional. In delving into this uncharted territory, we sought to tease out any meaningful connections that would, much like a perfectly timed through-ball, thread together these seemingly disparate themes.
In the pages that follow, we lay bare the surprising findings that emerged from our excursion into the symphony of numerical data. Brace yourself for the unexpected, for in the world of statistics, the most improbable connections often yield the most intriguing insights.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our intrepid foray into the esoteric realms of football and politics yields a striking revelation: the statistical analysis of voting behavior in Wyoming and Frank Lampard's Premier League goal tally from 1996 to 2016 unearths a remarkably robust correlation. With a r-squared of 0.9920926 and an eye-popping correlation coefficient of 0.9960384, our findings suggest a connection akin to a perfectly executed set-piece play.

Our research team utilized the hallowed tools of statistical inference to probe the depths of this unlikely pairing, and the results astoundingly affirm a relationship that defies conventional wisdom. The scatterplot unveiled in Fig. 1 succinctly encapsulates this extraordinary correlation, showcasing the unanticipated harmony between two seemingly disparate domains. The plot resembles a well-crafted tactical maneuver, with each data point echoing the rhythmic cadence of an engrossing football match.

The sheer strength of this correlation serves as an admonishment to those who dismiss the whimsical interconnectedness of human pursuits. It underscores the potential for hidden patterns that traverse the realms of civic duty and the exhilaration of sports.

It is important to note that while this correlation may seem unexpected, our robust statistical approach assures us of the reliability and validity of the findings. The p-value of less than 0.01 further buttresses the compelling nature of this link, affirming that this association is not merely a fluke occurrence, but rather a compelling testament to the curious interplay between the ballot box and the goal net.

In summation, our findings reveal a connection between voting behavior in Wyoming and Frank Lampard's Premier League goal tally that warrants further scholarly inquiry. This unlikely nexus beckons us to look beyond traditional boundaries and recognize the delightful quirkiness that pervades statistical analysis.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally. Make lots of jokes, goofy observations, and puns. 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]]
"Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance"

[[ABSTRACT]]
This study delves into the uncharted territory of football and politics to unravel the intertwined dynamics between voting behavior in Wyoming and the Premier League goal tally of the iconic Frank Lampard. Through the use of data from esteemed sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the ever-reliable repository of human knowledge, Wikipedia, we meticulously examined the statistical relationship between these two seemingly disparate domains. The findings astoundingly revealed a virtually jaw-dropping correlation coefficient of 0.9960384 and p < 0.01 for the period spanning 1996 to 2016. This correlation, akin to a perfectly executed backheel, suggests a remarkably strong connection that beckons further investigation. Our research underscores the potential for unexpected linkages between sports and civic engagement, shedding light on the whimsical interconnectedness of human pursuits.

[[LITERATURE REVIEW]]
Smith (2010) initially delved into the realm of statistical analysis, seeking to uncover the enigmatic relationship between voting patterns and seemingly unrelated domains. This work laid the foundation for our current investigation, providing a principled framework for unearthing correlations that transcend conventional understanding. Building upon this theoretical groundwork, Doe (2014) further expanded the horizon of statistical inquiry, delving into the complex interplay between regional voting behavior and diverse domains of human activity. While these pioneering studies set the stage for our own investigation, it is with a distinct sense of audacity that we venture forth into uncharted terrain, embracing the whimsical entropy of our chosen pursuits.
In "Data Analysis in Sports" by Jones (2018), the authors find that statistical methodologies can be comfortably applied to unravel the mysteries lurking within the annals of sports. This insight fueled our ambition to explore the statistical relationship between votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally. Stretching the boundaries of traditional statistical inquiry, our quest for correlations in seemingly incongruous arenas led us to amusingly unexpected insights.
Turning our attention to non-fiction literature, the seminal work "Soccer and Politics: A Historical Analysis" provides a sobering account of the interwoven dynamics between sports and political landscapes, echoing the themes central to our own study. Moreover, the opus "Election Analytics: Unveiling the Veiled" offers a spark of inspiration, conferring a fresh outlook on the potential for statistical revelation in the realm of political movements. These texts serve as beacons guiding our inquiry, offering contemplative reflections to inform our own perception of the intertwined domains we seek to explore.
Venturing into the realm of fiction, the hauntingly evocative "Goals and Governance: An Unlikely Tale" tantalizingly hints at the intersection between sporting triumphs and electoral sagas, prompting reflections on the improbable parallels we seek to uncover. Similarly, "The Ballot and the Ball: A Tale of Two Passions" captures the whimsical rapport between sports and civic engagement, infusing our inquiry with a sense of literary curiosity. While these works may be the fabrications of creative minds, their imaginative contemplations have left an indelible imprint on our own investigation, flickering with the zeal of exploration.
As part of the research endeavor, the authors immerse themselves in relevant TV shows, including "SportsNation" and "The West Wing", seeking to glean insights from both the sporting arena and the political theater. Immersed in the tumultuous fervor of these televised landscapes, the researchers assimilate a multifaceted understanding of the nuanced interplay between sports and politics, transcending the traditional confines of statistical inquiry.

[[RESULTS]]
Our intrepid foray into the esoteric realms of football and politics yields a striking revelation: the statistical analysis of voting behavior in Wyoming and Frank Lampard's Premier League goal tally from 1996 to 2016 unearths a remarkably robust correlation. With a r-squared of 0.9920926 and an eye-popping correlation coefficient of 0.9960384, our findings suggest a connection akin to a perfectly executed set-piece play.
Our research team utilized the hallowed tools of statistical inference to probe the depths of this unlikely pairing, and the results astoundingly affirm a relationship that defies conventional wisdom. The scatterplot unveiled in Fig. 1 succinctly encapsulates this extraordinary correlation, showcasing the unanticipated harmony between two seemingly disparate domains. The plot resembles a well-crafted tactical maneuver, with each data point echoing the rhythmic cadence of an engrossing football match.
The sheer strength of this correlation serves as an admonishment to those who dismiss the whimsical interconnectedness of human pursuits. It underscores the potential for hidden patterns that traverse the realms of civic duty and the exhilaration of sports.
It is important to note that while this correlation may seem unexpected, our robust statistical approach assures us of the reliability and validity of the findings. The p-value of less than 0.01 further buttresses the compelling nature of this link, affirming that this association is not merely a fluke occurrence, but rather a compelling testament to the curious interplay between the ballot box and the goal net.
In summation, our findings reveal a connection between voting behavior in Wyoming and Frank Lampard's Premier League goal tally that warrants further scholarly inquiry. This unlikely nexus beckons us to look beyond traditional boundaries and recognize the delightful quirkiness that pervades statistical analysis.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of this study fortuitously align with the prior research that explored the unexpected correlations between voting patterns and seemingly disparate domains. Smith's foundational work on statistical analysis set the stage for our investigation, and the robust correlation we unearthed echoes the audacious spirit of statistical inquiry into uncharted terrain. The correlation coefficient of 0.9960384 and r-squared of 0.9920926 discovered in this study not only support but elevate the earlier pioneering efforts, unveiling a connection akin to a perfectly timed through pass.

Doe's exploration of regional voting behavior and various domains of human activity finds resonance in our findings, underscoring the valuable insight that lies within the whimsical interplay of diverse human pursuits. Our results also tangentially converse with Jones' work on applying statistical methodologies to unravel mysteries in sports, exemplifying the unforeseen potential within the intersecting realms of sports and civic engagement. The unexpected correlation we unveil is a testament to the serendipitous insights that lay veiled within unexplored territories.

Leaving the academic realm, the fictional works "Goals and Governance: An Unlikely Tale" and "The Ballot and the Ball: A Tale of Two Passions" kindle a sense of literary curiosity that aligns with the improbable parallels we uncover. This alignment is not merely a quirky twist but underscores the delightful quirkiness that pervades statistical inquiry.

The robustness of our statistical findings, complemented by the p-value of less than 0.01, buttresses the compelling nature of this unlikely correlation. This association is not a fluke occurrence but rather a compelling testament to the curious interplay between voter behavior and Premier League goal tally. It beckons further scholarly inquiry into the whimsical interconnectedness of human pursuits, inviting analysts to revel in the statistical symphony that permeates diverse domains.

In summary, our findings bolster the existing literature's theme of uncovering surprising correlations between ostensibly unconnected domains. The striking connection we reveal advocates for a broader appreciation of the whimsical interplay within statistical analysis, urging researchers to embrace the unanticipated harmonies that transcend conventional understanding. The unexpected nexus between votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally not only challenges traditional boundaries but also underscores the delightful quirkiness that pervades statistical inquiry. The sheer strength of this correlation serves as a resounding reminder of the serendipitous insights that lay hidden within the mundaneness of civic duty and the exhilaration of sports.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Wyoming and Frank Lampard's Premier League goal tally. Make lots of jokes, goofy observations, and puns. 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]]
"Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance"

[[ABSTRACT]]
This study delves into the uncharted territory of football and politics to unravel the intertwined dynamics between voting behavior in Wyoming and the Premier League goal tally of the iconic Frank Lampard. Through the use of data from esteemed sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the ever-reliable repository of human knowledge, Wikipedia, we meticulously examined the statistical relationship between these two seemingly disparate domains. The findings astoundingly revealed a virtually jaw-dropping correlation coefficient of 0.9960384 and p < 0.01 for the period spanning 1996 to 2016. This correlation, akin to a perfectly executed backheel, suggests a remarkably strong connection that beckons further investigation. Our research underscores the potential for unexpected linkages between sports and civic engagement, shedding light on the whimsical interconnectedness of human pursuits.

[[INTRDUCTION]]
In the world of statistical analysis, unlikely correlations often lurk in the most unexpected places. In this paper, we embark on a whimsical journey through the realms of football and politics to unravel the peculiar relationship between voting behavior in Wyoming and the Premier League goal tally of the indomitable Frank Lampard. Our intent is to illuminate the entwined tapestry of human pursuits, where the heady rush of netting a goal can, apparently, find common ground with the solemn act of casting a vote.
It is well-established that Wyoming holds a unique place in American politics, often mentioned in hushed tones and cryptic allusions during electoral seasons. Drawing this enigmatic state into our purview, we sought to discern any discernible pattern between the votes cast for the Republican Presidential candidate and the on-field exploits of Frank Lampard in the Premier League. As the fireworks of football and the fire and brimstone of politics jostle for our attention, one cannot help but wonder if these seemingly distinct domains might, in fact, share an underlying harmony.
Our investigation hinged on an extraordinary assemblage of data, meticulously acquired from reputable sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the illustrious bastion of human knowledge, Wikipedia. Through careful curation and statistical rigor, we endeavored to discern whether there existed more than a passing resemblance between the political leanings of Wyomingites and the goings-on in Lampard's goal-scoring exploits.
While our inquiry may seem whimsical at first glance, the bedrock of statistical analysis calls for a steadfast commitment to unraveling every mystery, no matter how unconventional. In delving into this uncharted territory, we sought to tease out any meaningful connections that would, much like a perfectly timed through-ball, thread together these seemingly disparate themes.
In the pages that follow, we lay bare the surprising findings that emerged from our excursion into the symphony of numerical data. Brace yourself for the unexpected, for in the world of statistics, the most improbable connections often yield the most intriguing insights.

[[RESULTS]]
Our intrepid foray into the esoteric realms of football and politics yields a striking revelation: the statistical analysis of voting behavior in Wyoming and Frank Lampard's Premier League goal tally from 1996 to 2016 unearths a remarkably robust correlation. With a r-squared of 0.9920926 and an eye-popping correlation coefficient of 0.9960384, our findings suggest a connection akin to a perfectly executed set-piece play.
Our research team utilized the hallowed tools of statistical inference to probe the depths of this unlikely pairing, and the results astoundingly affirm a relationship that defies conventional wisdom. The scatterplot unveiled in Fig. 1 succinctly encapsulates this extraordinary correlation, showcasing the unanticipated harmony between two seemingly disparate domains. The plot resembles a well-crafted tactical maneuver, with each data point echoing the rhythmic cadence of an engrossing football match.
The sheer strength of this correlation serves as an admonishment to those who dismiss the whimsical interconnectedness of human pursuits. It underscores the potential for hidden patterns that traverse the realms of civic duty and the exhilaration of sports.
It is important to note that while this correlation may seem unexpected, our robust statistical approach assures us of the reliability and validity of the findings. The p-value of less than 0.01 further buttresses the compelling nature of this link, affirming that this association is not merely a fluke occurrence, but rather a compelling testament to the curious interplay between the ballot box and the goal net.
In summation, our findings reveal a connection between voting behavior in Wyoming and Frank Lampard's Premier League goal tally that warrants further scholarly inquiry. This unlikely nexus beckons us to look beyond traditional boundaries and recognize the delightful quirkiness that pervades statistical analysis.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In the grand tapestry of statistical analysis, our expedition through the winding corridors of Wyoming's voting behavior and Frank Lampard's Premier League goal tally has unveiled a connection that defies expectation. The robust correlation coefficient of 0.9960384, akin to a perfectly arced free-kick, stands as a testament to the whimsical interconnectedness of human pursuits. While our foray may seem like an unlikely match, much like finding a pair of cleats at a board meeting, it encapsulates the inherent unpredictability that underpins statistical inquiry.

The unforeseen harmony between the ballot box and the goal net, akin to a deceptively quick one-two play, urges us to acknowledge the delightful idiosyncrasies that abound in our numerical excursions. Our findings, supported by a p-value of less than 0.01, assert the compelling nature of this linkage, leaving little doubt about the validity of this unorthodox correlation.

Yet, as we bid adieu to this peculiar intersection of football and politics, we must acknowledge that no further research is needed in this area. The unparalleled sparkle of our findings, much like a well-polished trophy, remains a luminary beacon in the quirky realm of statistical analysis. So, with a nod to statistical serendipity, we trust that this revelation will stand as a testament to the captivating caprice of statistical inquiry.


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 Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Sports and Political Science


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 Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Political and Sports Analyses


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 Goal-tally Politics: A Correlational Analysis of Votes for the Republican Presidential Candidate in Wyoming and Frank Lampard's Premier League Performance with an abstract of This study delves into the uncharted territory of football and politics to unravel the intertwined dynamics between voting behavior in Wyoming and the Premier League goal tally of the iconic Frank Lampard. Through the use of data from esteemed sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the ever-reliable repository of human knowledge, Wikipedia, we meticulously examined the statistical relationship between these two seemingly disparate domains. The findings astoundingly revealed a virtually jaw-dropping correlation coefficient of 0.9960384 and p < 0.01 for the period spanning 1996 to 2016. This correlation, akin to a perfectly executed backheel, suggests a remarkably strong connection that beckons further investigation. Our research underscores the potential for unexpected linkages between sports and civic engagement, shedding light on the whimsical interconnectedness of human pursuits.

ChatGPT:

Wyoming voting behavior, Republican presidential candidate, Frank Lampard, Premier League performance, correlation analysis, football and politics, voting patterns, statistical relationship, data analysis, sports and civic engagement, soccer player performance, American politics, sports and society, political voting trends, correlation coefficient, data sources, MIT Election Data and Science Lab, Harvard Dataverse, Wikipedia, interconnectedness of human pursuits

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

Frank Lampard's Premier League goal tally
Source: Wikipedia
See what else correlates with Frank Lampard's Premier League goal tally

Correlation r = 0.9960384 (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 = 0.9920926 (Coefficient of determination)
This means 99.2% of the change in the one variable (i.e., Frank Lampard's Premier League goal tally) is predictable based on the change in the other (i.e., Votes for the Republican Presidential candidate in Wyoming) over the 6 years from 1996 through 2016.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.4E-5. 0.0000235098528031427550000000
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 1 in 0.0024% of random cases. Said differently, if you correlated 42,535 random variables You don't actually need 42 thousand variables to find a correlation like this one. 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.

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 5 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 5 because we have two variables measured over a period of 6 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.

[ 0.96, 1 ] 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.
199620002004200820122016
Votes for the Republican Presidential candidate in Wyoming (Total votes)105388147947167629164958170962174419
Frank Lampard's Premier League goal tally (Goals scored)1710101112




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




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. 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([105388,147947,167629,164958,170962,174419,])
array_2 = np.array([1,7,10,10,11,12,])
array_1_name = "Votes for the Republican Presidential candidate in Wyoming"
array_2_name = "Frank Lampard's Premier League goal tally"

# 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 rating skills are top-notch!


Correlation ID: 4463 · Black Variable ID: 26049 · Red Variable ID: 98
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0