about · email me · subscribe
Spurious correlation #5,223 · 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 Democratic Senators in New Jersey and the second variable is Popularity of the 'never gonna give you up' meme.  The chart goes from 2006 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As Democrat votes for Senators in New Jersey increased, it led to a rise in overall political enthusiasm. This surge in political energy somehow triggered a chain reaction of internet memes, and the 'never gonna give you up' meme experienced a resurgence as a form of light-hearted, bipartisan rickrolling. Who knew that political shifts in the Garden State could have such a groovy impact on internet culture?

Create a meme inspired by the never gonna give you up meme that in some way references Democrat votes for Senators in New Jersey. Try to emulate the style of the meme - don’t violate the copyright, just make it look and feel like the original meme.
This image generation prompt was also generated by AI, using the following sequence:

*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 Democrat votes for Senators in New Jersey caused Popularity of the 'never gonna give you up' meme to increase. Make it feel plausible.

AI academic paper

(Because p < 0.05)
Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme

The Journal of Political Memetics

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Democrat votes for Senators in New Jersey and Popularity of the 'never gonna give you up' meme. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to assess this nagging question. You found a correlation coefficient of 0.8303568 and p < 0.05 for 2006 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]]
"Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme"

[[ABSTRACT]]
This paper examines the unexpected relationship between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. Using a mix of political and internet data, we set out to determine whether there is a statistically significant correlation between these seemingly unrelated phenomena. Our team collected and analyzed data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, focusing on the period from 2006 to 2020. Employing robust statistical methods, we discovered a surprising correlation coefficient of 0.8303568 and p < 0.05, suggesting a strong association between the two variables. Our findings provide a unique insight into the intersection of political sentiment and internet culture, and may lead to further inquiries into the influence of unconventional factors on voting behavior. While our results may seem far-fetched, they highlight the importance of considering unconventional variables in political analysis – because, as the meme says, we're never gonna give up finding unexpected connections in the data.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in New Jersey and Popularity of the 'never gonna give you up' meme. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme"

[[ABSTRACT]]
This paper examines the unexpected relationship between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. Using a mix of political and internet data, we set out to determine whether there is a statistically significant correlation between these seemingly unrelated phenomena. Our team collected and analyzed data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, focusing on the period from 2006 to 2020. Employing robust statistical methods, we discovered a surprising correlation coefficient of 0.8303568 and p < 0.05, suggesting a strong association between the two variables. Our findings provide a unique insight into the intersection of political sentiment and internet culture, and may lead to further inquiries into the influence of unconventional factors on voting behavior. While our results may seem far-fetched, they highlight the importance of considering unconventional variables in political analysis – because, as the meme says, we're never gonna give up finding unexpected connections in the data.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

As the age-old adage goes, "Never gonna give you up, never gonna let you down." In the vast landscape of political analysis and memeology, one might not expect a correlation between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. It seems as unlikely as dividing by zero or finding a statistically significant p-value on the first try. Yet, as researchers, we know that truth can be stranger than fiction, and that the depths of data conceal unexpected treasures akin to a series of Russian dolls – you never quite know what surprising revelation lies beneath the surface.

In the annals of scientific exploration, it is the pursuit of these curious connections that drives us, much like a determined scientist in a lab, desperate to unravel the tangled web of correlations. As with any good mystery, our investigation commences with a question that requires a Sherlock Holmes-like intuition: "Could there be a link between the political landscape in New Jersey and the lyrical enchantment of Rick Astley's 1987 hit single?" To answer this query, we embarked on a data-driven journey, navigating through political statistics and internet trends, armed with the trusty tools of robust statistical analysis and a healthy dose of skepticism.

Armed with these tools, we endeavored to explore the hitherto overlooked relationship between voting tendencies and internet phenomena, a pursuit as thrilling and suspenseful as an episode of "Phineas and Ferb." Through our investigation, we seek to shed light on the unexpected interplay between political ideology and digital culture, unearthing hidden connections in the labyrinthine corridors of data. While some may view our pursuit as quixotic, we hold true to the belief that the pursuit of knowledge is akin to a treasure hunt – one may stumble upon the most extraordinary discoveries in the most unlikely places.

Our paper stands as a testament to the notion that, in the world of research, one should expect the unexpected and embrace the peculiar. We followed the data's breadcrumb trail, through the maze of information, to arrive at a finding that, while seemingly absurd, showcases the whimsical and enchanting nature of scientific inquiry. Our results may be as mind-boggling as a riddle wrapped in an enigma, but they serve as a testament to the unyielding spirit of curiosity that propels us toward novel and unconventional empirical connections. After all, in the grand masquerade ball of research, one never knows which masked correlation will waltz into the limelight next.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in New Jersey and Popularity of the 'never gonna give you up' meme. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name some cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme"

[[ABSTRACT]]
This paper examines the unexpected relationship between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. Using a mix of political and internet data, we set out to determine whether there is a statistically significant correlation between these seemingly unrelated phenomena. Our team collected and analyzed data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, focusing on the period from 2006 to 2020. Employing robust statistical methods, we discovered a surprising correlation coefficient of 0.8303568 and p < 0.05, suggesting a strong association between the two variables. Our findings provide a unique insight into the intersection of political sentiment and internet culture, and may lead to further inquiries into the influence of unconventional factors on voting behavior. While our results may seem far-fetched, they highlight the importance of considering unconventional variables in political analysis – because, as the meme says, we're never gonna give up finding unexpected connections in the data.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
As the age-old adage goes, "Never gonna give you up, never gonna let you down." In the vast landscape of political analysis and memeology, one might not expect a correlation between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. It seems as unlikely as dividing by zero or finding a statistically significant p-value on the first try. Yet, as researchers, we know that truth can be stranger than fiction, and that the depths of data conceal unexpected treasures akin to a series of Russian dolls – you never quite know what surprising revelation lies beneath the surface.
In the annals of scientific exploration, it is the pursuit of these curious connections that drives us, much like a determined scientist in a lab, desperate to unravel the tangled web of correlations. As with any good mystery, our investigation commences with a question that requires a Sherlock Holmes-like intuition: "Could there be a link between the political landscape in New Jersey and the lyrical enchantment of Rick Astley's 1987 hit single?" To answer this query, we embarked on a data-driven journey, navigating through political statistics and internet trends, armed with the trusty tools of robust statistical analysis and a healthy dose of skepticism.
Armed with these tools, we endeavored to explore the hitherto overlooked relationship between voting tendencies and internet phenomena, a pursuit as thrilling and suspenseful as an episode of "Phineas and Ferb." Through our investigation, we seek to shed light on the unexpected interplay between political ideology and digital culture, unearthing hidden connections in the labyrinthine corridors of data. While some may view our pursuit as quixotic, we hold true to the belief that the pursuit of knowledge is akin to a treasure hunt – one may stumble upon the most extraordinary discoveries in the most unlikely places.
Our paper stands as a testament to the notion that, in the world of research, one should expect the unexpected and embrace the peculiar. We followed the data's breadcrumb trail, through the maze of information, to arrive at a finding that, while seemingly absurd, showcases the whimsical and enchanting nature of scientific inquiry. Our results may be as mind-boggling as a riddle wrapped in an enigma, but they serve as a testament to the unyielding spirit of curiosity that propels us toward novel and unconventional empirical connections. After all, in the grand masquerade ball of research, one never knows which masked correlation will waltz into the limelight next.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In the realm of political analysis and cultural phenomena, researchers have long been fascinated by the curious correlations and unexpected connections that lie beneath the surface of seemingly unrelated variables. While traditional studies have focused on demographic trends, policy preferences, and campaign strategies, a pertinent question arises: do internet memes have any bearing on political behavior? Is there a connection between the voting patterns of Democrat senators in New Jersey and the popular 'never gonna give you up' meme? This literature review delves into the existing research while maintaining a lighthearted, albeit academically rigorous, approach to uncovering potential insights.

Smith et al. (2017) conducted a comprehensive analysis of political behavior in the digital age, examining the influence of internet culture on voter sentiment. Their study highlighted the impact of viral content on shaping political attitudes, shedding light on the potential for memes to permeate the electoral landscape. Likewise, Doe and Jones (2015) explored the psychological underpinnings of internet memes and their resonance with different demographic groups, serving as a foundational framework for understanding the broader societal impact of online content, albeit without a direct focus on specific political outcomes.

Turning to non-fiction literature, "The Age of Memeology" by Lorem (2019) offers intriguing insights into the evolution of internet memes and their role in contemporary society. Lorem's work delves into the cultural significance of memes, prompting readers to consider the profound implications of these seemingly lighthearted phenomena. Moreover, Ipsum's "Viral Politics: The Digital Influence of Memes" (2018) presents a meticulous exploration of the interplay between online content and political dynamics, laying the groundwork for our investigation into the correlation between political voting patterns and internet virality.

Transitioning to works of fiction, the imaginative realm of literature offers unexpected parallels to our research inquiry. With references to themes of unexpected connections and whimsical discoveries, "The Curious Incident of the Meme in the Night-Time" by Mark Haddon (2003) provides a playful nod to the mysterious ties between seemingly unrelated phenomena. In a similar vein, "The Da Vinci Meme" by Dan Brown (2003) may not directly address internet culture, but the novel's enigmatic narrative invites readers to ponder the hidden layers of meaning lurking beneath the surface – much like the peculiar connections we seek to elucidate in our study.

Meanwhile, cartoons and children's shows, with their charming quirkiness and unsuspected depth, offer an unconventional source of inspiration for our investigation. "Phineas and Ferb," a beloved animated series known for its whimsical adventures and ingenious schemes, captures the spirit of exploration and creativity, mirroring our own pursuit of uncovering unexpected correlations. Furthermore, the iconic "SpongeBob SquarePants" presents a lighthearted yet insightful allegory for unlikely connections and surreal happenings, mirroring the unexpected revelations we hope to unravel in our analysis of Democrat votes and viral memes.

As we venture into the uncharted territory of correlating political behavior with internet culture, we draw from a diverse array of literature that parallels the playful, quirky nature of our research pursuit. These references, both academic and imaginative, serve as a testament to the multifaceted and zany nature of knowledge-seeking endeavors, emphasizing the importance of holistic exploration in uncovering unexpected correlations – much like stumbling upon a hidden trinket in the most unlikely of places.



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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in New Jersey and Popularity of the 'never gonna give you up' meme. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends . You used data from 2006 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]]
"Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme"

[[ABSTRACT]]
This paper examines the unexpected relationship between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. Using a mix of political and internet data, we set out to determine whether there is a statistically significant correlation between these seemingly unrelated phenomena. Our team collected and analyzed data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, focusing on the period from 2006 to 2020. Employing robust statistical methods, we discovered a surprising correlation coefficient of 0.8303568 and p < 0.05, suggesting a strong association between the two variables. Our findings provide a unique insight into the intersection of political sentiment and internet culture, and may lead to further inquiries into the influence of unconventional factors on voting behavior. While our results may seem far-fetched, they highlight the importance of considering unconventional variables in political analysis – because, as the meme says, we're never gonna give up finding unexpected connections in the data.

[[INTRODUCTION]]
INTRODUCTION
As the age-old adage goes, "Never gonna give you up, never gonna let you down." In the vast landscape of political analysis and memeology, one might not expect a correlation between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. It seems as unlikely as dividing by zero or finding a statistically significant p-value on the first try. Yet, as researchers, we know that truth can be stranger than fiction, and that the depths of data conceal unexpected treasures akin to a series of Russian dolls – you never quite know what surprising revelation lies beneath the surface.
In the annals of scientific exploration, it is the pursuit of these curious connections that drives us, much like a determined scientist in a lab, desperate to unravel the tangled web of correlations. As with any good mystery, our investigation commences with a question that requires a Sherlock Holmes-like intuition: "Could there be a link between the political landscape in New Jersey and the lyrical enchantment of Rick Astley's 1987 hit single?" To answer this query, we embarked on a data-driven journey, navigating through political statistics and internet trends, armed with the trusty tools of robust statistical analysis and a healthy dose of skepticism.
Armed with these tools, we endeavored to explore the hitherto overlooked relationship between voting tendencies and internet phenomena, a pursuit as thrilling and suspenseful as an episode of "Phineas and Ferb." Through our investigation, we seek to shed light on the unexpected interplay between political ideology and digital culture, unearthing hidden connections in the labyrinthine corridors of data. While some may view our pursuit as quixotic, we hold true to the belief that the pursuit of knowledge is akin to a treasure hunt – one may stumble upon the most extraordinary discoveries in the most unlikely places.
Our paper stands as a testament to the notion that, in the world of research, one should expect the unexpected and embrace the peculiar. We followed the data's breadcrumb trail, through the maze of information, to arrive at a finding that, while seemingly absurd, showcases the whimsical and enchanting nature of scientific inquiry. Our results may be as mind-boggling as a riddle wrapped in an enigma, but they serve as a testament to the unyielding spirit of curiosity that propels us toward novel and unconventional empirical connections. After all, in the grand masquerade ball of research, one never knows which masked correlation will waltz into the limelight next.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
Our team embarked on a quest for data akin to a group of intrepid adventurers seeking the fabled treasure of El Dorado. We scoured the digital landscape, making camps at the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends. Our primary focus was on gathering information related to Democrat votes for Senators in New Jersey and the resounding presence of the 'never gonna give you up' meme from the years 2006 to 2020. With the dedication of a relentless explorer, we navigated through the virtual jungles of online platforms, uncovering the buried troves of statistical data with the vigour of Indiana Jones in a digital kingdom.

Variable Selection:
In the spirit of alchemists seeking the philosopher's stone, we carefully selected our variables with an eye for the unexpected and the unconventional. The primary independent variable was the Democrat votes for Senators in New Jersey, capturing the tempestuous tides of political sentiment through the years. As for the dependent variable, we turned our gaze to the ebbs and flows of the 'never gonna give you up' meme's popularity, with the awareness of a connoisseur selecting the finest vintage. These variables, seemingly as disparate as apples and oranges, were chosen with the understanding that, much like a fine wine and a sumptuous cheese, they might reveal an unsuspected compatibility when brought together.

Statistical Analysis:
With all the data in hand, we set out to perform a series of rigorous statistical analyses, reminiscent of a daring tightrope act in the circus of scientific inquiry. We employed advanced regression models, correlation analyses, and other sophisticated techniques to unveil the hidden connections between our chosen variables. Our toolkit of statistical prowess was as sharp as a well-honed sword, ensuring that our inferences were robust and our findings as sturdy as the traditional tale of the three little pigs.

Control Measures:
To ensure the integrity of our findings, we implemented control measures akin to fortifications guarding a medieval castle. We accounted for potential confounding variables – such as the influence of other memes, political events, and online trends – with the meticulousness of a chess grandmaster calculating their next move. This allowed us to isolate the unique relationship between Democrat votes for Senators in New Jersey and the 'never gonna give you up' meme, navigating past the treacherous waters of spurious correlations.

Ethical Considerations:
In our pursuit of empirical enlightenment, we maintained a steadfast commitment to academic and ethical principles, much like the chivalrous knights of yore. The data collected and analyzed were handled with the utmost care, ensuring the confidentiality and privacy of individual observations. Our research upheld the noble ideals of scholarly rigor and integrity, dispelling any shadows of doubt regarding the ethical propriety of our methods.

Innovation and Resilience:
Like intrepid explorers braving the perils of uncharted territories, we approached our methodology with a spirit of innovation and resilience. We embraced the whimsical and the unorthodox, recognizing that the most extraordinary discoveries often emerge from the most unexpected paths. Through our methodology, we endeavored to exemplify the audacious and daring spirit that propels scientific inquiry into uncharted realms, ever vigilant for the next surprising twist in the tale of empirical discovery.

-------
I hope these offhand remarks and goofy observations are exactly what you had in mind!


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

Please make up the results section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in New Jersey and Popularity of the 'never gonna give you up' meme. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2006 to 2020, you found a correlation 0.8303568, r-squared of 0.6894925, and p < 0.05.

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]]
"Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme"

[[ABSTRACT]]
This paper examines the unexpected relationship between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. Using a mix of political and internet data, we set out to determine whether there is a statistically significant correlation between these seemingly unrelated phenomena. Our team collected and analyzed data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, focusing on the period from 2006 to 2020. Employing robust statistical methods, we discovered a surprising correlation coefficient of 0.8303568 and p < 0.05, suggesting a strong association between the two variables. Our findings provide a unique insight into the intersection of political sentiment and internet culture, and may lead to further inquiries into the influence of unconventional factors on voting behavior. While our results may seem far-fetched, they highlight the importance of considering unconventional variables in political analysis – because, as the meme says, we're never gonna give up finding unexpected connections in the data.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
As the age-old adage goes, "Never gonna give you up, never gonna let you down." In the vast landscape of political analysis and memeology, one might not expect a correlation between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. It seems as unlikely as dividing by zero or finding a statistically significant p-value on the first try. Yet, as researchers, we know that truth can be stranger than fiction, and that the depths of data conceal unexpected treasures akin to a series of Russian dolls – you never quite know what surprising revelation lies beneath the surface.
In the annals of scientific exploration, it is the pursuit of these curious connections that drives us, much like a determined scientist in a lab, desperate to unravel the tangled web of correlations. As with any good mystery, our investigation commences with a question that requires a Sherlock Holmes-like intuition: "Could there be a link between the political landscape in New Jersey and the lyrical enchantment of Rick Astley's 1987 hit single?" To answer this query, we embarked on a data-driven journey, navigating through political statistics and internet trends, armed with the trusty tools of robust statistical analysis and a healthy dose of skepticism.
Armed with these tools, we endeavored to explore the hitherto overlooked relationship between voting tendencies and internet phenomena, a pursuit as thrilling and suspenseful as an episode of "Phineas and Ferb." Through our investigation, we seek to shed light on the unexpected interplay between political ideology and digital culture, unearthing hidden connections in the labyrinthine corridors of data. While some may view our pursuit as quixotic, we hold true to the belief that the pursuit of knowledge is akin to a treasure hunt – one may stumble upon the most extraordinary discoveries in the most unlikely places.
Our paper stands as a testament to the notion that, in the world of research, one should expect the unexpected and embrace the peculiar. We followed the data's breadcrumb trail, through the maze of information, to arrive at a finding that, while seemingly absurd, showcases the whimsical and enchanting nature of scientific inquiry. Our results may be as mind-boggling as a riddle wrapped in an enigma, but they serve as a testament to the unyielding spirit of curiosity that propels us toward novel and unconventional empirical connections. After all, in the grand masquerade ball of research, one never knows which masked correlation will waltz into the limelight next.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis revealed a surprisingly robust correlation between Democrat votes for Senators in New Jersey and the popularity of the 'never gonna give you up' meme. The correlation coefficient of 0.8303568 indicates a strong positive relationship between these two seemingly unrelated variables. In other words, the more Democrat votes a Senator received in New Jersey, the higher the popularity of the 'never gonna give you up' meme.

Furthermore, the r-squared value of 0.6894925 suggests that approximately 69% of the variation in the popularity of the meme can be explained by the variation in Democrat votes for Senators in New Jersey. This level of explained variation is as striking as a magician perfectly pulling off a disappearing act.

The statistical test produced a p-value of less than 0.05, indicating that the observed correlation is statistically significant. This means that we can be reasonably confident that the relationship we observed is unlikely to have occurred by chance. It's as unlikely as stumbling upon a unicorn in a field of statistics – a rare and unexpected find.

Fig. 1 displays a scatterplot illustrating this noteworthy correlation, further reinforcing the strength of this peculiar relationship. As we delve deeper into the data, we uncover a nexus between political allegiance and internet culture that is as intriguing as a plot twist in a suspenseful thriller.

Our findings not only add a touch of whimsy to the often austere world of statistical analysis but also serve as a reminder that in the grand tapestry of data, unexpected threads of correlation can weave together in the most surprising ways. As we conclude this section, we cannot help but reflect on the words of the meme itself: "I'm never gonna give you up, I'm never gonna let you down." Similarly, our research reaffirms the spirit of perseverance and determination in uncovering the unlikeliest of connections within the vast expanse of data.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in New Jersey and Popularity of the 'never gonna give you up' meme. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme"

[[ABSTRACT]]
This paper examines the unexpected relationship between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. Using a mix of political and internet data, we set out to determine whether there is a statistically significant correlation between these seemingly unrelated phenomena. Our team collected and analyzed data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, focusing on the period from 2006 to 2020. Employing robust statistical methods, we discovered a surprising correlation coefficient of 0.8303568 and p < 0.05, suggesting a strong association between the two variables. Our findings provide a unique insight into the intersection of political sentiment and internet culture, and may lead to further inquiries into the influence of unconventional factors on voting behavior. While our results may seem far-fetched, they highlight the importance of considering unconventional variables in political analysis – because, as the meme says, we're never gonna give up finding unexpected connections in the data.

[[LITERATURE REVIEW]]
In the realm of political analysis and cultural phenomena, researchers have long been fascinated by the curious correlations and unexpected connections that lie beneath the surface of seemingly unrelated variables. While traditional studies have focused on demographic trends, policy preferences, and campaign strategies, a pertinent question arises: do internet memes have any bearing on political behavior? Is there a connection between the voting patterns of Democrat senators in New Jersey and the popular 'never gonna give you up' meme? This literature review delves into the existing research while maintaining a lighthearted, albeit academically rigorous, approach to uncovering potential insights.
Smith et al. (2017) conducted a comprehensive analysis of political behavior in the digital age, examining the influence of internet culture on voter sentiment. Their study highlighted the impact of viral content on shaping political attitudes, shedding light on the potential for memes to permeate the electoral landscape. Likewise, Doe and Jones (2015) explored the psychological underpinnings of internet memes and their resonance with different demographic groups, serving as a foundational framework for understanding the broader societal impact of online content, albeit without a direct focus on specific political outcomes.
Turning to non-fiction literature, "The Age of Memeology" by Lorem (2019) offers intriguing insights into the evolution of internet memes and their role in contemporary society. Lorem's work delves into the cultural significance of memes, prompting readers to consider the profound implications of these seemingly lighthearted phenomena. Moreover, Ipsum's "Viral Politics: The Digital Influence of Memes" (2018) presents a meticulous exploration of the interplay between online content and political dynamics, laying the groundwork for our investigation into the correlation between political voting patterns and internet virality.
Transitioning to works of fiction, the imaginative realm of literature offers unexpected parallels to our research inquiry. With references to themes of unexpected connections and whimsical discoveries, "The Curious Incident of the Meme in the Night-Time" by Mark Haddon (2003) provides a playful nod to the mysterious ties between seemingly unrelated phenomena. In a similar vein, "The Da Vinci Meme" by Dan Brown (2003) may not directly address internet culture, but the novel's enigmatic narrative invites readers to ponder the hidden layers of meaning lurking beneath the surface – much like the peculiar connections we seek to elucidate in our study.
Meanwhile, cartoons and children's shows, with their charming quirkiness and unsuspected depth, offer an unconventional source of inspiration for our investigation. "Phineas and Ferb," a beloved animated series known for its whimsical adventures and ingenious schemes, captures the spirit of exploration and creativity, mirroring our own pursuit of uncovering unexpected correlations. Furthermore, the iconic "SpongeBob SquarePants" presents a lighthearted yet insightful allegory for unlikely connections and surreal happenings, mirroring the unexpected revelations we hope to unravel in our analysis of Democrat votes and viral memes.
As we venture into the uncharted territory of correlating political behavior with internet culture, we draw from a diverse array of literature that parallels the playful, quirky nature of our research pursuit. These references, both academic and imaginative, serve as a testament to the multifaceted and zany nature of knowledge-seeking endeavors, emphasizing the importance of holistic exploration in uncovering unexpected correlations – much like stumbling upon a hidden trinket in the most unlikely of places.


[[RESULTS]]
Our analysis revealed a surprisingly robust correlation between Democrat votes for Senators in New Jersey and the popularity of the 'never gonna give you up' meme. The correlation coefficient of 0.8303568 indicates a strong positive relationship between these two seemingly unrelated variables. In other words, the more Democrat votes a Senator received in New Jersey, the higher the popularity of the 'never gonna give you up' meme.
Furthermore, the r-squared value of 0.6894925 suggests that approximately 69% of the variation in the popularity of the meme can be explained by the variation in Democrat votes for Senators in New Jersey. This level of explained variation is as striking as a magician perfectly pulling off a disappearing act.
The statistical test produced a p-value of less than 0.05, indicating that the observed correlation is statistically significant. This means that we can be reasonably confident that the relationship we observed is unlikely to have occurred by chance. It's as unlikely as stumbling upon a unicorn in a field of statistics – a rare and unexpected find.
Fig. 1 displays a scatterplot illustrating this noteworthy correlation, further reinforcing the strength of this peculiar relationship. As we delve deeper into the data, we uncover a nexus between political allegiance and internet culture that is as intriguing as a plot twist in a suspenseful thriller.
Our findings not only add a touch of whimsy to the often austere world of statistical analysis but also serve as a reminder that in the grand tapestry of data, unexpected threads of correlation can weave together in the most surprising ways. As we conclude this section, we cannot help but reflect on the words of the meme itself: "I'm never gonna give you up, I'm never gonna let you down." Similarly, our research reaffirms the spirit of perseverance and determination in uncovering the unlikeliest of connections within the vast expanse of data.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our research has revealed a tantalizing association between the voting behavior of Democrat senators in New Jersey and the viral ubiquity of the 'never gonna give you up' meme. While at first glance, the correlation between a political voting pattern and an internet sensation may seem as unlikely as a penguin taking flight, our results have defied expectations and underscored the potential influence of online memes on electoral preferences.

Harkening back to our literature review, the unexpected parallels between our analysis and "The Curious Incident of the Meme in the Night-Time" by Mark Haddon take on a new significance. Just as Haddon's protagonist unravels unanticipated connections, our study has shed light on the intricate web linking political sentiments and digital culture. The comical yet thought-provoking ventures of "Phineas and Ferb" and "SpongeBob SquarePants" also resonate with our findings, serving as cheerful reminders of the delight in uncovering peculiar correlations.

In the scholarly realm, Smith et al. (2017) and Doe and Jones (2015) laid the groundwork for our exploration, demonstrating the potency of online content in shaping voter attitudes. Our results align with their assertions, offering empirical validation to their prescient insights. Similarly, the literary musings of Lorem (2019) and Ipsum (2018) on memetic influence in politics find real-world substantiation in the uncanny relationship we have unearthed.

The correlation coefficient of 0.8303568 and the r-squared value of 0.6894925 reflect a robust association between Democrat votes for Senators in New Jersey and the 'never gonna give you up' meme, eclipsing the norms of traditional political analyses. The p-value's confirmation of statistical significance serves as a resounding validation of our improbable discovery, akin to finding a four-leaf clover in a data haystack.

As we continue to ponder the implications of our research, we are reminded of the aptness of the meme's lyrics – much like the refrain "I'm never gonna give you up," our study reaffirms the perseverance and determination necessary to unravel the enigmatic correlations that permeate our vast dataset.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Democrat votes for Senators in New Jersey and Popularity of the 'never gonna give you up' meme. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme"

[[ABSTRACT]]
This paper examines the unexpected relationship between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. Using a mix of political and internet data, we set out to determine whether there is a statistically significant correlation between these seemingly unrelated phenomena. Our team collected and analyzed data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, focusing on the period from 2006 to 2020. Employing robust statistical methods, we discovered a surprising correlation coefficient of 0.8303568 and p < 0.05, suggesting a strong association between the two variables. Our findings provide a unique insight into the intersection of political sentiment and internet culture, and may lead to further inquiries into the influence of unconventional factors on voting behavior. While our results may seem far-fetched, they highlight the importance of considering unconventional variables in political analysis – because, as the meme says, we're never gonna give up finding unexpected connections in the data.

[[INTRDUCTION]]
INTRODUCTION
As the age-old adage goes, "Never gonna give you up, never gonna let you down." In the vast landscape of political analysis and memeology, one might not expect a correlation between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. It seems as unlikely as dividing by zero or finding a statistically significant p-value on the first try. Yet, as researchers, we know that truth can be stranger than fiction, and that the depths of data conceal unexpected treasures akin to a series of Russian dolls – you never quite know what surprising revelation lies beneath the surface.
In the annals of scientific exploration, it is the pursuit of these curious connections that drives us, much like a determined scientist in a lab, desperate to unravel the tangled web of correlations. As with any good mystery, our investigation commences with a question that requires a Sherlock Holmes-like intuition: "Could there be a link between the political landscape in New Jersey and the lyrical enchantment of Rick Astley's 1987 hit single?" To answer this query, we embarked on a data-driven journey, navigating through political statistics and internet trends, armed with the trusty tools of robust statistical analysis and a healthy dose of skepticism.
Armed with these tools, we endeavored to explore the hitherto overlooked relationship between voting tendencies and internet phenomena, a pursuit as thrilling and suspenseful as an episode of "Phineas and Ferb." Through our investigation, we seek to shed light on the unexpected interplay between political ideology and digital culture, unearthing hidden connections in the labyrinthine corridors of data. While some may view our pursuit as quixotic, we hold true to the belief that the pursuit of knowledge is akin to a treasure hunt – one may stumble upon the most extraordinary discoveries in the most unlikely places.
Our paper stands as a testament to the notion that, in the world of research, one should expect the unexpected and embrace the peculiar. We followed the data's breadcrumb trail, through the maze of information, to arrive at a finding that, while seemingly absurd, showcases the whimsical and enchanting nature of scientific inquiry. Our results may be as mind-boggling as a riddle wrapped in an enigma, but they serve as a testament to the unyielding spirit of curiosity that propels us toward novel and unconventional empirical connections. After all, in the grand masquerade ball of research, one never knows which masked correlation will waltz into the limelight next.

[[RESULTS]]
Our analysis revealed a surprisingly robust correlation between Democrat votes for Senators in New Jersey and the popularity of the 'never gonna give you up' meme. The correlation coefficient of 0.8303568 indicates a strong positive relationship between these two seemingly unrelated variables. In other words, the more Democrat votes a Senator received in New Jersey, the higher the popularity of the 'never gonna give you up' meme.
Furthermore, the r-squared value of 0.6894925 suggests that approximately 69% of the variation in the popularity of the meme can be explained by the variation in Democrat votes for Senators in New Jersey. This level of explained variation is as striking as a magician perfectly pulling off a disappearing act.
The statistical test produced a p-value of less than 0.05, indicating that the observed correlation is statistically significant. This means that we can be reasonably confident that the relationship we observed is unlikely to have occurred by chance. It's as unlikely as stumbling upon a unicorn in a field of statistics – a rare and unexpected find.
Fig. 1 displays a scatterplot illustrating this noteworthy correlation, further reinforcing the strength of this peculiar relationship. As we delve deeper into the data, we uncover a nexus between political allegiance and internet culture that is as intriguing as a plot twist in a suspenseful thriller.
Our findings not only add a touch of whimsy to the often austere world of statistical analysis but also serve as a reminder that in the grand tapestry of data, unexpected threads of correlation can weave together in the most surprising ways. As we conclude this section, we cannot help but reflect on the words of the meme itself: "I'm never gonna give you up, I'm never gonna let you down." Similarly, our research reaffirms the spirit of perseverance and determination in uncovering the unlikeliest of connections within the vast expanse of data.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our foray into the whimsical world of political sentiment and internet culture has revealed a correlation between Democrat votes for Senators in New Jersey and the 'never gonna give you up' meme that is as unexpected as stumbling upon a meme in a political debate. Our findings, akin to discovering a gag reel at a statistical seminar, showcase the importance of considering unconventional variables in political analysis. The robust correlation coefficient and statistically significant p-value underscore the unyielding spirit of statistical inquiry, much like a determined researcher peeling the layers of an onion to reveal a surprising result.

It is remarkable to contemplate the hidden threads of correlation that intertwine in the rich tapestry of data, akin to finding a silver lining in a cloud of statistical noise. While these findings may seem as outlandish as a UFO sighting in a bar graph, they emphasize the need for continued exploration into the influence of seemingly disparate factors on political behavior – though, as the data suggests, perhaps we've already hit the peak of unexpected correlations.

Hence, we assert with confidence, reinforced by the meme's own promise, that in the pursuit of empirical inquiry, there's 'never gonna be a correlation as surprising as this one,' and no further 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 Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Memetics


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 Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Electoral Meme Analysis and Research


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 Never Gonna Vote You Up: Analyzing the Correlation Between Democrat Votes for Senators in New Jersey and the Popularity of the 'Never Gonna Give You Up' Meme with an abstract of This paper examines the unexpected relationship between the voting behavior of Democrat senators in New Jersey and the viral sensation of the 'never gonna give you up' meme. Using a mix of political and internet data, we set out to determine whether there is a statistically significant correlation between these seemingly unrelated phenomena. Our team collected and analyzed data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, focusing on the period from 2006 to 2020. Employing robust statistical methods, we discovered a surprising correlation coefficient of 0.8303568 and p < 0.05, suggesting a strong association between the two variables. Our findings provide a unique insight into the intersection of political sentiment and internet culture, and may lead to further inquiries into the influence of unconventional factors on voting behavior. While our results may seem far-fetched, they highlight the importance of considering unconventional variables in political analysis – because, as the meme says, we're never gonna give up finding unexpected connections in the data.

ChatGPT:

New Jersey Senators, Democrat votes, 'Never Gonna Give You Up' meme, viral sensation, correlation analysis, political behavior, internet culture, statistical methods, MIT Election Data and Science Lab, Harvard Dataverse, Google Trends, unconventional variables, voting behavior, political sentiment.

*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 Democratic Senators in New Jersey
Detailed data title: Total number of votes cast for Federal Democrat Senate candidates in New Jersey
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for Democratic Senators in New Jersey

Popularity of the 'never gonna give you up' meme
Detailed data title: Relative volume of Google searches for 'never gonna give you up' (without quotes, in the United States)
Source: Google Trends
Additional Info: Relative search volume is a unique Google thing; the shape of the chart is accurate but the actual numbers are meaningless.

See what else correlates with Popularity of the 'never gonna give you up' meme

Correlation r = 0.8303568 (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 = 0.6894925 (Coefficient of determination)
This means 68.9% of the change in the one variable (i.e., Popularity of the 'never gonna give you up' meme) is predictable based on the change in the other (i.e., Votes for Democratic Senators in New Jersey) over the 6 years from 2006 through 2020.

p < 0.05, which statistically significant(Null hypothesis significance test)
The p-value is 0.0407. 0.0407271474548363300000000000
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 0.83 in 4.07% of random cases. Said differently, if you correlated 25 random variables Which I absolutely did.
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.

[ 0.06, 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.
200620082012201420182020
Votes for Democratic Senators in New Jersey (Total votes)120084019512201987680104387017116502541180
Popularity of the 'never gonna give you up' meme (Relative popularity)2.1666726.916715.7513.416717.833331.0833




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([1200840,1951220,1987680,1043870,1711650,2541180,])
array_2 = np.array([2.16667,26.9167,15.75,13.4167,17.8333,31.0833,])
array_1_name = "Votes for Democratic Senators in New Jersey"
array_2_name = "Popularity of the 'never gonna give you up' meme"

# 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?

Big thanks for reviewing!


Correlation ID: 5223 · Black Variable ID: 26281 · Red Variable ID: 25160
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0