about · email me · subscribe
Spurious correlation #4,342 · 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 Republican Senators in Mississippi and the second variable is Popularity of the 'thats what she said' 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 Republican votes for Senators in Mississippi increased, the frequency of country-style metaphors also rose. This inadvertently led to a surge in the popularity of the "that's what she said" meme, as the good ol' folks found themselves unwittingly setting up the perfect punchlines for innuendos. It seems like politics wasn't the only thing getting a little cheeky in Mississippi!

Create a meme inspired by the thats what she said meme that in some way references Republican votes for Senators in Mississippi. Try to emulate the style of the meme - don’t violate the copyright, just make it look and feel like the original meme.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humerus 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 changes in Republican votes for Senators in Mississippi caused Popularity of the 'thats what she said' meme.

AI academic paper

(Because p < 0.01)
Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes

Journal of Memetic Studies

Jan 2024

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




Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Republican votes for Senators in Mississippi and Popularity of the 'thats what she said' meme. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Rhyme words in the title.

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 0.9232903 and p < 0.01 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]]
Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes

[[ABSTRACT]]
This study investigates the curious correlation between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme. The research team made use of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends to examine this peculiar nexus between political inclinations and internet humor. Our analysis revealed a strikingly high correlation coefficient of 0.9232903 and a p-value less than 0.01 for the time period spanning from 2006 to 2020. The implications of these findings are as intriguing as the unexpected comeback of a well-timed 'that's what she said' joke.


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 Republican votes for Senators in Mississippi and Popularity of the 'thats what she said' 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]]
Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes

[[ABSTRACT]]
This study investigates the curious correlation between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme. The research team made use of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends to examine this peculiar nexus between political inclinations and internet humor. Our analysis revealed a strikingly high correlation coefficient of 0.9232903 and a p-value less than 0.01 for the time period spanning from 2006 to 2020. The implications of these findings are as intriguing as the unexpected comeback of a well-timed 'that's what she said' joke.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of political behavior and internet culture has long been a subject of curiosity and, perhaps, amusement. While the dynamics of political elections have been extensively studied, the influence of internet memes on voter preference has not received as much attention. However, in the digital age, where information and humor propagate at the speed of a well-timed pun, it is vital to analyze and understand the potential connections between online trends and political phenomena.

In this study, we delve into the correlation between Republican votes for Senators in the state of Mississippi and the prevalence of the ubiquitous 'that's what she said' meme. While some may find this topic to be lighthearted and whimsical, we urge our readers to take our analysis with the same seriousness as one would apply to a statistical test. After all, as scientists, we know the importance of always staying on the "p-value" side of life.

As we embark on this statistical journey, we aim to untangle the intertwined web of political ideologies and internet humor, leading to a better understanding of the underlying dynamics at play. Just as one might carefully sift through data points, so too shall we sift through the layers of this intriguing correlation, keeping a keen eye out for any unexpected twists, much like the denouement of a well-crafted 'that's what she said' jest.

By leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we endeavor to shed light on this seemingly preposterous link and present our findings in a manner that is both informative and, dare we say, amusing. As we proceed, let us not forget the wise words of Sir Arthur Conan Doyle, "It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories, instead of theories to suit facts." So, with a spirit of scientific curiosity and a dash of humor, let us set forth on this statistical odyssey, prepared for the unexpected and ready to embrace the delightfully bizarre.


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 Republican votes for Senators in Mississippi and Popularity of the 'thats what she said' 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes

[[ABSTRACT]]
This study investigates the curious correlation between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme. The research team made use of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends to examine this peculiar nexus between political inclinations and internet humor. Our analysis revealed a strikingly high correlation coefficient of 0.9232903 and a p-value less than 0.01 for the time period spanning from 2006 to 2020. The implications of these findings are as intriguing as the unexpected comeback of a well-timed 'that's what she said' joke.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of political behavior and internet culture has long been a subject of curiosity and, perhaps, amusement. While the dynamics of political elections have been extensively studied, the influence of internet memes on voter preference has not received as much attention. However, in the digital age, where information and humor propagate at the speed of a well-timed pun, it is vital to analyze and understand the potential connections between online trends and political phenomena.
In this study, we delve into the correlation between Republican votes for Senators in the state of Mississippi and the prevalence of the ubiquitous 'that's what she said' meme. While some may find this topic to be lighthearted and whimsical, we urge our readers to take our analysis with the same seriousness as one would apply to a statistical test. After all, as scientists, we know the importance of always staying on the "p-value" side of life.
As we embark on this statistical journey, we aim to untangle the intertwined web of political ideologies and internet humor, leading to a better understanding of the underlying dynamics at play. Just as one might carefully sift through data points, so too shall we sift through the layers of this intriguing correlation, keeping a keen eye out for any unexpected twists, much like the denouement of a well-crafted 'that's what she said' jest.
By leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we endeavor to shed light on this seemingly preposterous link and present our findings in a manner that is both informative and, dare we say, amusing. As we proceed, let us not forget the wise words of Sir Arthur Conan Doyle, "It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories, instead of theories to suit facts." So, with a spirit of scientific curiosity and a dash of humor, let us set forth on this statistical odyssey, prepared for the unexpected and ready to embrace the delightfully bizarre.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The relationship between Republican votes for Senators in Mississippi and the popularity of the 'that's what she said' meme has been a relatively unexplored area of inquiry. While most studies in the realm of political science tend to focus on traditional factors such as policy platforms, candidate characteristics, and socio-economic trends, a few daring researchers have ventured into the realm of internet culture and its potential impact on political behavior.

Smith et al. in their seminal work "Internet Memes: A New Frontier in Political Analysis" laid the groundwork for understanding the intersection of memes and politics. Their analysis of meme dissemination patterns and their effects on public opinion hinted at the possibility of memes exerting an influence on political preferences. In a similar vein, Doe's study "The Viral Effect: How Memes Shape Political Discourse" examined the diffusion of memes within the online ecosystem and posited that memes could serve as subtle influencers in shaping voter sentiment.

Jones et al. further expounded on this by exploring the peculiar manifestations of internet humor in politically oriented communities. In "Laughing all the way to the Polls: The Role of Humor in Shaping Political Allegiances," the authors delved into the psychological underpinnings of humor and its potential impact on political decision-making. Their nuanced analysis opened up the possibility of memes, such as the 'that's what she said' variety, playing a role in shaping voter perceptions.

Moving beyond the academic sphere, popular non-fiction literature also offers intriguing perspectives on the subject. "The Internet: A Playground for Political Playfulness" by Johnson provides an insightful examination of the ways in which internet culture intertwines with political discourse. Meanwhile, "Meme Magic: Unraveling the Mysteries of Online Humor" by Thompson dissects the intricate dynamics of meme propagation and its potential implications for societal attitudes and behaviors.

In the realm of fiction, there are curious intersections between literary works and the themes at hand. For instance, the dystopian novel "1984" by George Orwell, though not directly related to internet memes, presents a cautionary tale about the manipulation of language and thought, which could be tangentially linked to the influence of memes on political narratives. Furthermore, the satirical wit found in Terry Pratchett's "Discworld" series offers a whimsical perspective on the power of humor in shaping societal norms and belief systems, perhaps shedding light on the potential impact of memes on political allegiances.

In a playful twist, the researchers even ventured into the realm of children's cartoons and television shows for inspiration. A detailed analysis of the comedic timing and interplay of humor in popular animated series such as "SpongeBob SquarePants" and "The Simpsons" provided insight into the psychological mechanisms of humor and its potential resonance with diverse audiences. After all, as the saying goes, "All work and no play makes statistical analysis a dull endeavor."

As we embark on this whimsical statistical escapade, it is imperative to approach the analysis with a lighthearted yet astute demeanor, much like the punchline of a well-delivered jest. With a wink and a nod to the unexpected quirks of human behavior, we delve into the depths of data, prepared to uncover the hidden, and perhaps humorous, connections between Republican votes in Mississippi and the enduring popularity of the 'that's what she said' meme.


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 Republican votes for Senators in Mississippi and Popularity of the 'thats what she said' 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]]
Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes

[[ABSTRACT]]
This study investigates the curious correlation between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme. The research team made use of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends to examine this peculiar nexus between political inclinations and internet humor. Our analysis revealed a strikingly high correlation coefficient of 0.9232903 and a p-value less than 0.01 for the time period spanning from 2006 to 2020. The implications of these findings are as intriguing as the unexpected comeback of a well-timed 'that's what she said' joke.

[[INTRODUCTION]]
The intersection of political behavior and internet culture has long been a subject of curiosity and, perhaps, amusement. While the dynamics of political elections have been extensively studied, the influence of internet memes on voter preference has not received as much attention. However, in the digital age, where information and humor propagate at the speed of a well-timed pun, it is vital to analyze and understand the potential connections between online trends and political phenomena.
In this study, we delve into the correlation between Republican votes for Senators in the state of Mississippi and the prevalence of the ubiquitous 'that's what she said' meme. While some may find this topic to be lighthearted and whimsical, we urge our readers to take our analysis with the same seriousness as one would apply to a statistical test. After all, as scientists, we know the importance of always staying on the "p-value" side of life.
As we embark on this statistical journey, we aim to untangle the intertwined web of political ideologies and internet humor, leading to a better understanding of the underlying dynamics at play. Just as one might carefully sift through data points, so too shall we sift through the layers of this intriguing correlation, keeping a keen eye out for any unexpected twists, much like the denouement of a well-crafted 'that's what she said' jest.
By leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we endeavor to shed light on this seemingly preposterous link and present our findings in a manner that is both informative and, dare we say, amusing. As we proceed, let us not forget the wise words of Sir Arthur Conan Doyle, "It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories, instead of theories to suit facts." So, with a spirit of scientific curiosity and a dash of humor, let us set forth on this statistical odyssey, prepared for the unexpected and ready to embrace the delightfully bizarre.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Sample Selection:
The research team embarked on a digital hunt across the vast expanse of the internet to capture the elusive data required for this study. Our primary hunting grounds were the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends. We wrangled in every statistic, trend, and bytes of information related to the Republican votes for Senators in Mississippi and the waxing and waning popularity of the 'that's what she said' meme from the year 2006 to 2020. The data was corralled and tamed for analysis, much like rounding up stray variables for a statistical rodeo.

Data Analysis:
Once the data was lassoed and securely stored, we employed a series of statistical methods as robust as an academic's morning coffee. We computed correlation coefficients with the delightfully named Pearson's r statistic, seeking to uncover the hidden connections between political leanings and internet quips. Alongside this, we performed a thorough examination of Google search trends, exploring the ebb and flow of 'that's what she said' meme popularity and its potential echoes in the ballot boxes of Mississippi.

Statistical Rigor and Caveats:
Ensuring statistical rigor, we slapped on our metaphorical Sherlock Holmes hats and Sherlock Holmes magnifying glasses, inspecting each data point with a discerning eye for any lurking confounding variables. We performed numerous diagnostic tests to validate the robustness of the correlation between Republican votes and meme popularity, being ever wary of spurious correlations that might sneak in like a punchline out of the blue.

Incorporating Time Series Analysis:
To capture the temporal dynamics inherent in both political voting patterns and internet memes, we delved into the intricate realm of time series analysis. Here, we employed an assortment of models ranging from the classic autoregressive integrated moving average (ARIMA) to the more modern techniques such as the prophet algorithm, with the fervent hope of unraveling the interplay between political landscapes and the evolution of the 'that's what she said' meme.

Caveats and Limitations:
It is imperative to acknowledge the limitations of our study. While we have meticulously combed through disparate data sources, causality remains a mystery worthy of Sherlock Holmes' prowess. Additionally, our findings are specific to the context of Mississippi and the time period from 2006 to 2020, and heeding the words of Douglas Adams, we recognize that this study only provides a peek through the "keyhole" of a much larger comedic and political universe.

Ethical Approval:
In adherence to the scientific code of conduct, this study obtained ethical approval from the Institutional Review Board, ensuring that our statistical horseplay adhered to the established principles of research integrity.

Intrigued by the whimsy?
Next, we present the results with the same flair and inquisitiveness that one might expect from the denouement of a well-delivered 'that's what she said' jest. By employing a variety of analytical tools and an unquenchable thirst for statistical enlightenment, we illuminate the unexpected nexus between Republican votes in Mississippi and the 'that's what she said' meme, inviting readers to partake in this academic journey peppered with both rigor and mirth.


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 Republican votes for Senators in Mississippi and Popularity of the 'thats what she said' 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 0.9232903, r-squared of 0.8524650, 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]]
Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes

[[ABSTRACT]]
This study investigates the curious correlation between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme. The research team made use of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends to examine this peculiar nexus between political inclinations and internet humor. Our analysis revealed a strikingly high correlation coefficient of 0.9232903 and a p-value less than 0.01 for the time period spanning from 2006 to 2020. The implications of these findings are as intriguing as the unexpected comeback of a well-timed 'that's what she said' joke.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of political behavior and internet culture has long been a subject of curiosity and, perhaps, amusement. While the dynamics of political elections have been extensively studied, the influence of internet memes on voter preference has not received as much attention. However, in the digital age, where information and humor propagate at the speed of a well-timed pun, it is vital to analyze and understand the potential connections between online trends and political phenomena.
In this study, we delve into the correlation between Republican votes for Senators in the state of Mississippi and the prevalence of the ubiquitous 'that's what she said' meme. While some may find this topic to be lighthearted and whimsical, we urge our readers to take our analysis with the same seriousness as one would apply to a statistical test. After all, as scientists, we know the importance of always staying on the "p-value" side of life.
As we embark on this statistical journey, we aim to untangle the intertwined web of political ideologies and internet humor, leading to a better understanding of the underlying dynamics at play. Just as one might carefully sift through data points, so too shall we sift through the layers of this intriguing correlation, keeping a keen eye out for any unexpected twists, much like the denouement of a well-crafted 'that's what she said' jest.
By leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we endeavor to shed light on this seemingly preposterous link and present our findings in a manner that is both informative and, dare we say, amusing. As we proceed, let us not forget the wise words of Sir Arthur Conan Doyle, "It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories, instead of theories to suit facts." So, with a spirit of scientific curiosity and a dash of humor, let us set forth on this statistical odyssey, prepared for the unexpected and ready to embrace the delightfully bizarre.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

In exploring the correlation between Republican votes for Senators in Mississippi and the popularity of the 'that's what she said' meme, our analysis yielded an impressive correlation coefficient of 0.9232903, indicating a strong positive relationship between these seemingly unrelated variables. This result suggests that as Republican votes for Senators in Mississippi increased, so did the prevalence of the 'that's what she said' meme. The coefficient of determination (r-squared) of 0.8524650 further reinforced the robustness of this correlation, implying that approximately 85.25% of the variation in meme popularity can be explained by the variation in Republican votes.

Our findings also revealed a p-value of less than 0.01, indicating that the observed correlation is highly unlikely to have occurred by chance alone. This statistically significant result provides compelling evidence in support of the existence of a tangible link between political voting patterns and the dissemination of a well-timed double entendre. While we were initially astounded by this unexpected relationship, as researchers, we understand the importance of approaching our findings with the same skepticism as one would have towards an implausible punchline.

To visually demonstrate the strength of this connection, we present Figure 1, a scatterplot showcasing the unmistakable positive correlation between Republican votes for Senators in Mississippi and the prominence of the 'that's what she said' meme. The figure succinctly captures the essence of our discovery, albeit without the comedic timing that often accompanies a well-executed 'that's what she said' retort.

In summary, our investigation has uncovered a compelling association between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme, shedding light on an intriguing paradox of political and internet culture. While the implications of this correlation may raise eyebrows, we invite readers to approach our results with an open mind and a wry sense of humor. After all, as researchers, it is our duty to embrace the unexpected twists and turns of empirical inquiry, much like the denouement of a surprising jest.


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 Republican votes for Senators in Mississippi and Popularity of the 'thats what she said' 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]]
Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes

[[ABSTRACT]]
This study investigates the curious correlation between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme. The research team made use of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends to examine this peculiar nexus between political inclinations and internet humor. Our analysis revealed a strikingly high correlation coefficient of 0.9232903 and a p-value less than 0.01 for the time period spanning from 2006 to 2020. The implications of these findings are as intriguing as the unexpected comeback of a well-timed 'that's what she said' joke.

[[LITERATURE REVIEW]]
The relationship between Republican votes for Senators in Mississippi and the popularity of the 'that's what she said' meme has been a relatively unexplored area of inquiry. While most studies in the realm of political science tend to focus on traditional factors such as policy platforms, candidate characteristics, and socio-economic trends, a few daring researchers have ventured into the realm of internet culture and its potential impact on political behavior.
Smith et al. in their seminal work "Internet Memes: A New Frontier in Political Analysis" laid the groundwork for understanding the intersection of memes and politics. Their analysis of meme dissemination patterns and their effects on public opinion hinted at the possibility of memes exerting an influence on political preferences. In a similar vein, Doe's study "The Viral Effect: How Memes Shape Political Discourse" examined the diffusion of memes within the online ecosystem and posited that memes could serve as subtle influencers in shaping voter sentiment.
Jones et al. further expounded on this by exploring the peculiar manifestations of internet humor in politically oriented communities. In "Laughing all the way to the Polls: The Role of Humor in Shaping Political Allegiances," the authors delved into the psychological underpinnings of humor and its potential impact on political decision-making. Their nuanced analysis opened up the possibility of memes, such as the 'that's what she said' variety, playing a role in shaping voter perceptions.
Moving beyond the academic sphere, popular non-fiction literature also offers intriguing perspectives on the subject. "The Internet: A Playground for Political Playfulness" by Johnson provides an insightful examination of the ways in which internet culture intertwines with political discourse. Meanwhile, "Meme Magic: Unraveling the Mysteries of Online Humor" by Thompson dissects the intricate dynamics of meme propagation and its potential implications for societal attitudes and behaviors.
In the realm of fiction, there are curious intersections between literary works and the themes at hand. For instance, the dystopian novel "1984" by George Orwell, though not directly related to internet memes, presents a cautionary tale about the manipulation of language and thought, which could be tangentially linked to the influence of memes on political narratives. Furthermore, the satirical wit found in Terry Pratchett's "Discworld" series offers a whimsical perspective on the power of humor in shaping societal norms and belief systems, perhaps shedding light on the potential impact of memes on political allegiances.
In a playful twist, the researchers even ventured into the realm of children's cartoons and television shows for inspiration. A detailed analysis of the comedic timing and interplay of humor in popular animated series such as "SpongeBob SquarePants" and "The Simpsons" provided insight into the psychological mechanisms of humor and its potential resonance with diverse audiences. After all, as the saying goes, "All work and no play makes statistical analysis a dull endeavor."
As we embark on this whimsical statistical escapade, it is imperative to approach the analysis with a lighthearted yet astute demeanor, much like the punchline of a well-delivered jest. With a wink and a nod to the unexpected quirks of human behavior, we delve into the depths of data, prepared to uncover the hidden, and perhaps humorous, connections between Republican votes in Mississippi and the enduring popularity of the 'that's what she said' meme.

[[RESULTS]]
In exploring the correlation between Republican votes for Senators in Mississippi and the popularity of the 'that's what she said' meme, our analysis yielded an impressive correlation coefficient of 0.9232903, indicating a strong positive relationship between these seemingly unrelated variables. This result suggests that as Republican votes for Senators in Mississippi increased, so did the prevalence of the 'that's what she said' meme. The coefficient of determination (r-squared) of 0.8524650 further reinforced the robustness of this correlation, implying that approximately 85.25% of the variation in meme popularity can be explained by the variation in Republican votes.
Our findings also revealed a p-value of less than 0.01, indicating that the observed correlation is highly unlikely to have occurred by chance alone. This statistically significant result provides compelling evidence in support of the existence of a tangible link between political voting patterns and the dissemination of a well-timed double entendre. While we were initially astounded by this unexpected relationship, as researchers, we understand the importance of approaching our findings with the same skepticism as one would have towards an implausible punchline.
To visually demonstrate the strength of this connection, we present Figure 1, a scatterplot showcasing the unmistakable positive correlation between Republican votes for Senators in Mississippi and the prominence of the 'that's what she said' meme. The figure succinctly captures the essence of our discovery, albeit without the comedic timing that often accompanies a well-executed 'that's what she said' retort.
In summary, our investigation has uncovered a compelling association between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme, shedding light on an intriguing paradox of political and internet culture. While the implications of this correlation may raise eyebrows, we invite readers to approach our results with an open mind and a wry sense of humor. After all, as researchers, it is our duty to embrace the unexpected twists and turns of empirical inquiry, much like the denouement of a surprising jest.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The implications of our findings are as significant as a well-timed 'that's what she said' joke - both surprising and thought-provoking. Our results not only support but also amplify the prior research that delved into the curious nexus between political behavior and meme culture. Smith et al.'s pioneering work on meme dissemination patterns and public opinion hinted at the potential influence of memes on political preferences, and our study provides empirical evidence to bolster this claim. Similarly, Doe's exploration of the viral effect of memes within the online ecosystem aligns seamlessly with our findings, albeit with a touch of unexpected humor. The correlation coefficient of 0.9232903, akin to a punchline that lands just right, offers compelling support for the notion that meme prevalence intertwines with political behavior in unforeseen ways.

Our research also resonates with Jones et al.'s insights into internet humor's impact on political decision-making. The statistical significance we observed, with a p-value less than 0.01, reinforces the persuasive influence of 'that's what she said' meme popularity on Republican votes in Mississippi, adding a layer of levity to the serious realm of political allegiances. Just as 'The Internet: A Playground for Political Playfulness' by Johnson presciently outlined the ways in which internet culture interfaces with politics, our study provides a whimsical yet robust demonstration of this fusion by unearthing the unexpected correlation between an internet meme and political voting patterns.

In a delightful twist, our findings even touch upon the playful concepts explored in Terry Pratchett's "Discworld" series, where satire and humor can shape societal beliefs in unexpected ways. As researchers, it is imperative to approach these unanticipated connections with the same lighthearted yet discerning stance as the humor found in animated series such as "SpongeBob SquarePants" and "The Simpsons." Our study's robust statistical support for the association between Republican votes and the 'that's what she said' meme popularity invites us to embrace the unexpected quirks of human behavior, much like the punchline of a well-delivered jest.

Our discussion aptly reflects the almost paradoxical nature of our research - delving into the serious realm of political analysis while uncovering unexpected connections that evoke a sense of humor. As we delve into the depths of data, a lighthearted yet astute demeanor is essential, much like the punchline of a well-delivered joke. We encourage fellow researchers to approach our findings with an open mind and a penchant for embracing the quirky, much like the denouement of a surprising jest.


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 Republican votes for Senators in Mississippi and Popularity of the 'thats what she said' 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]]
Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes

[[ABSTRACT]]
This study investigates the curious correlation between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme. The research team made use of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends to examine this peculiar nexus between political inclinations and internet humor. Our analysis revealed a strikingly high correlation coefficient of 0.9232903 and a p-value less than 0.01 for the time period spanning from 2006 to 2020. The implications of these findings are as intriguing as the unexpected comeback of a well-timed 'that's what she said' joke.

[[INTRDUCTION]]
The intersection of political behavior and internet culture has long been a subject of curiosity and, perhaps, amusement. While the dynamics of political elections have been extensively studied, the influence of internet memes on voter preference has not received as much attention. However, in the digital age, where information and humor propagate at the speed of a well-timed pun, it is vital to analyze and understand the potential connections between online trends and political phenomena.
In this study, we delve into the correlation between Republican votes for Senators in the state of Mississippi and the prevalence of the ubiquitous 'that's what she said' meme. While some may find this topic to be lighthearted and whimsical, we urge our readers to take our analysis with the same seriousness as one would apply to a statistical test. After all, as scientists, we know the importance of always staying on the "p-value" side of life.
As we embark on this statistical journey, we aim to untangle the intertwined web of political ideologies and internet humor, leading to a better understanding of the underlying dynamics at play. Just as one might carefully sift through data points, so too shall we sift through the layers of this intriguing correlation, keeping a keen eye out for any unexpected twists, much like the denouement of a well-crafted 'that's what she said' jest.
By leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we endeavor to shed light on this seemingly preposterous link and present our findings in a manner that is both informative and, dare we say, amusing. As we proceed, let us not forget the wise words of Sir Arthur Conan Doyle, "It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories, instead of theories to suit facts." So, with a spirit of scientific curiosity and a dash of humor, let us set forth on this statistical odyssey, prepared for the unexpected and ready to embrace the delightfully bizarre.

[[RESULTS]]
In exploring the correlation between Republican votes for Senators in Mississippi and the popularity of the 'that's what she said' meme, our analysis yielded an impressive correlation coefficient of 0.9232903, indicating a strong positive relationship between these seemingly unrelated variables. This result suggests that as Republican votes for Senators in Mississippi increased, so did the prevalence of the 'that's what she said' meme. The coefficient of determination (r-squared) of 0.8524650 further reinforced the robustness of this correlation, implying that approximately 85.25% of the variation in meme popularity can be explained by the variation in Republican votes.
Our findings also revealed a p-value of less than 0.01, indicating that the observed correlation is highly unlikely to have occurred by chance alone. This statistically significant result provides compelling evidence in support of the existence of a tangible link between political voting patterns and the dissemination of a well-timed double entendre. While we were initially astounded by this unexpected relationship, as researchers, we understand the importance of approaching our findings with the same skepticism as one would have towards an implausible punchline.
To visually demonstrate the strength of this connection, we present Figure 1, a scatterplot showcasing the unmistakable positive correlation between Republican votes for Senators in Mississippi and the prominence of the 'that's what she said' meme. The figure succinctly captures the essence of our discovery, albeit without the comedic timing that often accompanies a well-executed 'that's what she said' retort.
In summary, our investigation has uncovered a compelling association between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme, shedding light on an intriguing paradox of political and internet culture. While the implications of this correlation may raise eyebrows, we invite readers to approach our results with an open mind and a wry sense of humor. After all, as researchers, it is our duty to embrace the unexpected twists and turns of empirical inquiry, much like the denouement of a surprising jest.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In the grand tradition of academic inquiry, our study has unearthed a correlation between Republican votes for Senators in Mississippi and the spread of the 'that's what she said' meme that is as improbable as a pun at a statistics convention. The robust correlation coefficient and statistically significant p-value point to a connection that raises eyebrows much like a well-timed punchline does. These findings underscore the seemingly inexplicable relationship between political allegiances and the viral nature of a cleverly crafted innuendo. While we are tempted to conclude with a pun, we must resist the urge and maintain the decorum of scholarly discourse.

In light of these results, it is evident that future research should continue to delve into the unexpected intersections of political behavior and internet culture, much like a determined detective unravels a surprising mystery. However, for this particular correlation, it seems safe to say: that's what she said, and no further research is needed.


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 Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Memetic Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Memetic Studies and Cultural Analysis


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 Ridin' Mississippian Senators: A Statistical Examination of 'That's What She Said' Meme Popularity and Republican Votes with an abstract of This study investigates the curious correlation between Republican votes for Senators in Mississippi and the prevalence of the 'that's what she said' meme. The research team made use of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends to examine this peculiar nexus between political inclinations and internet humor. Our analysis revealed a strikingly high correlation coefficient of 0.9232903 and a p-value less than 0.01 for the time period spanning from 2006 to 2020. The implications of these findings are as intriguing as the unexpected comeback of a well-timed 'that's what she said' joke.

ChatGPT:

Republican votes Mississippi Senators, 'That's What She Said' meme, political inclination internet humor, correlation political inclinations meme, MIT Election Data and Science Lab, Harvard Dataverse, Google Trends, correlation coefficient Republican votes meme, p-value political humor correlation, political inclinations and internet humor analysis

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

Popularity of the 'thats what she said' meme
Detailed data title: Relative volume of Google searches for 'thats what she said' (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 'thats what she said' meme

Correlation r = 0.9232903 (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 = 0.8524650 (Coefficient of determination)
This means 85.2% of the change in the one variable (i.e., Popularity of the 'thats what she said' meme) is predictable based on the change in the other (i.e., Votes for Republican Senators in Mississippi) over the 6 years from 2006 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.008601. 0.0086008687336919420000000000
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 0.92 in 0.8601% of random cases. Said differently, if you correlated 116 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.

[ 0.45, 0.99 ] 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 Republican Senators in Mississippi (Total votes)38839914495207096263784811034390709511
Popularity of the 'thats what she said' meme (Relative popularity)332.513.33339.51411




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."


# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([388399,1449520,709626,378481,1034390,709511,])
array_2 = np.array([3,32.5,13.3333,9.5,14,11,])
array_1_name = "Votes for Republican Senators in Mississippi"
array_2_name = "Popularity of the 'thats what she said' 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?

Your rating is pure awesomeness!


Correlation ID: 4342 · Black Variable ID: 26265 · Red Variable ID: 25169
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0