about · email me · subscribe
Spurious correlation #4,416 · 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 Indiana and the second variable is Google searches for 'funny cat videos'.  The chart goes from 2004 to 2018, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the number of Republican votes for Senators in Indiana increased, so did the purr-pensity for people to seek out some light-hearted entertainment. Maybe it's because they were feline good about the election results or perhaps they just needed a break from the political cat-fighting. Whatever the reason, it seems like the voters were not the only ones getting a kick out of the proceedings - it was a meow-ment of revelation for the internet as funny cat videos clawed their way to the top of the search charts. It's like they say, when it rains, it purrs!

Model: dalle-3
Prompt: Generate an image of a cyber folk celebration in Indiana, with people cheering and smiling as they watch Republican votes for Senators increase on TV. In the background, showcase a computer screen with multiple tabs open, one displaying a video of a playful cat chasing a laser pointer, drawing the attention of the onlookers. Capture the growing excitement and the increasing number of "funny cat videos" being searched, with laughter filling the room. Aim for a vibrant and engaging visual that captures the energetic and celebratory atmosphere. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Cyber folk Voxel art Magic realism Low poly Psychedelic
ChatGPT: Cyber folk

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Republican votes for Senators in Indiana and Google searches for 'funny cat videos', in the following situation: As the number of Republican votes for Senators in Indiana increased, so did the purr-pensity for people to seek out some light-hearted entertainment. Maybe it's because they were feline good about the election results or perhaps they just needed a break from the political cat-fighting. Whatever the reason, it seems like the voters were not the only ones getting a kick out of the proceedings - it was a meow-ment of revelation for the internet as funny cat videos clawed their way to the top of the search charts. It's like they say, when it rains, it purrs!. Keep the description simple.
ChatGPT: A group of people in Indiana celebrate as Republican votes for Senators increase, smiling and cheering as they watch the results on TV. In the background, a computer screen shows multiple tabs open, with one displaying a video of a playful cat chasing a laser pointer, drawing the attention of the onlookers. As the excitement grows, so does the number of "funny cat videos" being searched, with laughter filling the room.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ Cyber folk ] and depicting this scene: A group of people in Indiana celebrate as Republican votes for Senators increase, smiling and cheering as they watch the results on TV. In the background, a computer screen shows multiple tabs open, with one displaying a video of a playful cat chasing a laser pointer, drawing the attention of the onlookers. As the excitement grows, so does the number of "funny cat videos" being searched, with laughter filling the room. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a cyber folk celebration in Indiana, with people cheering and smiling as they watch Republican votes for Senators increase on TV. In the background, showcase a computer screen with multiple tabs open, one displaying a video of a playful cat chasing a laser pointer, drawing the attention of the onlookers. Capture the growing excitement and the increasing number of "funny cat videos" being searched, with laughter filling the room. Aim for a vibrant and engaging visual that captures the energetic and celebratory atmosphere.

*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 Republican votes for Senators in Indiana caused funny cat videos (Google searches for 'funny cat videos') to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'

Journal of Feline Political Science

Jan 2024

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




Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. Make lots of jokes, goofy observations, and puns.

Make the title an alliteration.

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 0.9716816 and p < 0.01 for 2004 to 2018.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'

[[ABSTRACT]]
Feline politicians and internet humor have more in common than meets the eye. This research delves deep into the correlation between Republican votes for Senators in Indiana and the prevalence of Google searches for 'funny cat videos' from 2004 to 2018. By analyzing data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our study reveals a surprisingly strong positive correlation coefficient of 0.9716816 and p-value less than 0.01, indicating a significant relationship between voting behavior and the pursuit of purrfection in online entertainment. The implications of these feline political preferences are whisker-thin yet far-reaching, shedding light on the underlying psychology of voters and the not-so-pawsitive impact of internet distractions on election outcomes. So, next time you see a politician purrpouncing their policies, don't be surprised if they have a penchant for paw-sitively hilarious cat videos!


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 Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'

[[ABSTRACT]]
Feline politicians and internet humor have more in common than meets the eye. This research delves deep into the correlation between Republican votes for Senators in Indiana and the prevalence of Google searches for 'funny cat videos' from 2004 to 2018. By analyzing data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our study reveals a surprisingly strong positive correlation coefficient of 0.9716816 and p-value less than 0.01, indicating a significant relationship between voting behavior and the pursuit of purrfection in online entertainment. The implications of these feline political preferences are whisker-thin yet far-reaching, shedding light on the underlying psychology of voters and the not-so-pawsitive impact of internet distractions on election outcomes. So, next time you see a politician purrpouncing their policies, don't be surprised if they have a penchant for paw-sitively hilarious cat videos!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Politics and internet memes may seem like odd bedfellows, but as the saying goes, "There is always a method to an internet cat's madness." In this study, we explore the curious linkage between Republican votes for Senators in Indiana and the insatiable quest for 'funny cat videos' in the vast savannah of the world wide web. Our research aims to dissect this seemingly whimsical connection and uncover the not-so-furry mysteries lurking beneath the surface.

The decision to embark on this quest was not made on a whim. Despite the prevailing notion that politics is as serious as a cat's aloof demeanor, we boldly set out to challenge the status quo and explore the uncharted territories of the interwebs. We were motivated by the age-old conundrum: why do people seek out 'funny cat videos,' and how does this behavior intersect with their political inclinations? While some may dismiss this question as mere fluff, we approached it with the fervor of a cat chasing a laser pointer, determined to unearth the hidden patterns within the digital litter box of internet searches.

Our journey into the realm of political feline fandom began by perusing mounds of data harvested from the MIT Election Data and Science Lab, the Harvard Dataverse, and the depths of Google Trends. We meticulously examined years of Republican votes for Senators in Indiana and the frequency of Google searches for 'funny cat videos' from 2004 to 2018, aiming to sniff out any discernible correlation between these seemingly disparate entities. To our surprise – and, dare we say, amusement – our analysis uncovered a correlation coefficient of 0.9716816, with a p-value of less than 0.01, signifying a remarkably robust association between these two seemingly unrelated phenomena.

Now, before you paws and dismiss our findings as mere folly, we invite you to join us in this academic game of cat and mouse. The implications of our discoveries stretch far beyond the confines of mere statistical purrsonalities. They scratch at the surface of the intricate web of human behavior, shedding light on the nuanced interplay between political allegiance and the pursuit of internet escapism. This study aims to challenge the conventional wisdom that politics and humor are as incompatible as dogs and cats, and to reveal the subtle, yet significant, ways in which trivial internet pursuits can leave pawprints on the gravitas of elections.

As we embark on this feline-inspired journey of curiosity, we invite you to set aside your preconceptions and embrace the unexpected. After all, as we meowve forward in our exploration of this whimsical terrain, one might say that we are not only barking up the wrong tree, but also tampering with the very fabric of our understanding of political behavior. So, grab your catnip and get ready to unravel the mystery of how purrfectly innocent internet searches may have an unsuspected significance in the grand scheme of politics.


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 Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'

[[ABSTRACT]]
Feline politicians and internet humor have more in common than meets the eye. This research delves deep into the correlation between Republican votes for Senators in Indiana and the prevalence of Google searches for 'funny cat videos' from 2004 to 2018. By analyzing data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our study reveals a surprisingly strong positive correlation coefficient of 0.9716816 and p-value less than 0.01, indicating a significant relationship between voting behavior and the pursuit of purrfection in online entertainment. The implications of these feline political preferences are whisker-thin yet far-reaching, shedding light on the underlying psychology of voters and the not-so-pawsitive impact of internet distractions on election outcomes. So, next time you see a politician purrpouncing their policies, don't be surprised if they have a penchant for paw-sitively hilarious cat videos!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Politics and internet memes may seem like odd bedfellows, but as the saying goes, "There is always a method to an internet cat's madness." In this study, we explore the curious linkage between Republican votes for Senators in Indiana and the insatiable quest for 'funny cat videos' in the vast savannah of the world wide web. Our research aims to dissect this seemingly whimsical connection and uncover the not-so-furry mysteries lurking beneath the surface.
The decision to embark on this quest was not made on a whim. Despite the prevailing notion that politics is as serious as a cat's aloof demeanor, we boldly set out to challenge the status quo and explore the uncharted territories of the interwebs. We were motivated by the age-old conundrum: why do people seek out 'funny cat videos,' and how does this behavior intersect with their political inclinations? While some may dismiss this question as mere fluff, we approached it with the fervor of a cat chasing a laser pointer, determined to unearth the hidden patterns within the digital litter box of internet searches.
Our journey into the realm of political feline fandom began by perusing mounds of data harvested from the MIT Election Data and Science Lab, the Harvard Dataverse, and the depths of Google Trends. We meticulously examined years of Republican votes for Senators in Indiana and the frequency of Google searches for 'funny cat videos' from 2004 to 2018, aiming to sniff out any discernible correlation between these seemingly disparate entities. To our surprise – and, dare we say, amusement – our analysis uncovered a correlation coefficient of 0.9716816, with a p-value of less than 0.01, signifying a remarkably robust association between these two seemingly unrelated phenomena.
Now, before you paws and dismiss our findings as mere folly, we invite you to join us in this academic game of cat and mouse. The implications of our discoveries stretch far beyond the confines of mere statistical purrsonalities. They scratch at the surface of the intricate web of human behavior, shedding light on the nuanced interplay between political allegiance and the pursuit of internet escapism. This study aims to challenge the conventional wisdom that politics and humor are as incompatible as dogs and cats, and to reveal the subtle, yet significant, ways in which trivial internet pursuits can leave pawprints on the gravitas of elections.
As we embark on this feline-inspired journey of curiosity, we invite you to set aside your preconceptions and embrace the unexpected. After all, as we meowve forward in our exploration of this whimsical terrain, one might say that we are not only barking up the wrong tree, but also tampering with the very fabric of our understanding of political behavior. So, grab your catnip and get ready to unravel the mystery of how purrfectly innocent internet searches may have an unsuspected significance in the grand scheme of politics.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith et al. (2010) laid the groundwork for understanding the intersection of internet culture and political behavior, albeit without the feline flair. The authors uncovered the complexities of online virality and its potential influence on voter engagement, setting the stage for our paw-sitively intriguing investigation into the connection between Republican votes for Senators in Indiana and Google searches for 'funny cat videos.'

Expanding from the realms of political science and internet phenomenon, Doe (2015) delved into the psychological underpinnings of humor and its impact on decision-making processes. While their study focused primarily on the broader implications of humor in cognitive processes, our research takes a playful leap into the world of feline-inspired mirth and its unexpected resonance in the political landscape.

The findings of Jones (2018) provided a compelling backdrop for our exploration, highlighting the ripple effects of internet distractions on attention spans and cognitive engagement. We extrapolate from this work to illuminate the curious dance between political allegiances and the pursuit of internet whimsy, particularly in the form of humorous cat videos—a phenomenon that has gripped the hearts and minds of online denizens with feline fervor.

Moving from academic literature to more pop-culture-inspired texts, we draw inspiration from "How to Tell If Your Cat Is Plotting to Kill You" by Oatmeal (2012), delving into the quirky and enigmatic world of feline behavior. Though seemingly unrelated to politics at first glance, the intricate dynamics of cat psychology offer a paws-tively intriguing lens through which to explore the inexplicable attraction to funny cat videos and its potential impact on voter behaviors.

In a similar vein, the whimsical tales found in "The Cat Who... series" by Lilian Jackson Braun (1966-2007) provide a fictional yet thought-provoking glimpse into the enigmatic nature of feline companionship. As we navigate the terrain of our research, these novels serve as a reminder that the influence of cats, whether real or virtual, can be far-reaching and perhaps even politically charged.

On a tangentially related note, a motley assortment of movie marathons—ranging from "The Aristocats" to "The Lion King"—has provided our research team with valuable insights into the portrayal of feline characters in popular culture. While these films may seem like a whimsical diversion, they have sharpened our claws for the rigorous analytical quest of unraveling the purrfectly improbable correlation between Republican votes for Senators in Indiana and the seemingly innocent pursuit of 'funny cat videos' in the digital realm.

So, with this diverse tapestry of literature and media as our backdrop, we plunge into the heart of our research, ready to unravel the mystery of how the pursuit of feline-infused internet hilarity may hold unexpected significance in the grand tapestry of political behavior and decision-making.


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 Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends . You used data from 2004 to 2018

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'

[[ABSTRACT]]
Feline politicians and internet humor have more in common than meets the eye. This research delves deep into the correlation between Republican votes for Senators in Indiana and the prevalence of Google searches for 'funny cat videos' from 2004 to 2018. By analyzing data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our study reveals a surprisingly strong positive correlation coefficient of 0.9716816 and p-value less than 0.01, indicating a significant relationship between voting behavior and the pursuit of purrfection in online entertainment. The implications of these feline political preferences are whisker-thin yet far-reaching, shedding light on the underlying psychology of voters and the not-so-pawsitive impact of internet distractions on election outcomes. So, next time you see a politician purrpouncing their policies, don't be surprised if they have a penchant for paw-sitively hilarious cat videos!

[[INTRODUCTION]]
Politics and internet memes may seem like odd bedfellows, but as the saying goes, "There is always a method to an internet cat's madness." In this study, we explore the curious linkage between Republican votes for Senators in Indiana and the insatiable quest for 'funny cat videos' in the vast savannah of the world wide web. Our research aims to dissect this seemingly whimsical connection and uncover the not-so-furry mysteries lurking beneath the surface.
The decision to embark on this quest was not made on a whim. Despite the prevailing notion that politics is as serious as a cat's aloof demeanor, we boldly set out to challenge the status quo and explore the uncharted territories of the interwebs. We were motivated by the age-old conundrum: why do people seek out 'funny cat videos,' and how does this behavior intersect with their political inclinations? While some may dismiss this question as mere fluff, we approached it with the fervor of a cat chasing a laser pointer, determined to unearth the hidden patterns within the digital litter box of internet searches.
Our journey into the realm of political feline fandom began by perusing mounds of data harvested from the MIT Election Data and Science Lab, the Harvard Dataverse, and the depths of Google Trends. We meticulously examined years of Republican votes for Senators in Indiana and the frequency of Google searches for 'funny cat videos' from 2004 to 2018, aiming to sniff out any discernible correlation between these seemingly disparate entities. To our surprise – and, dare we say, amusement – our analysis uncovered a correlation coefficient of 0.9716816, with a p-value of less than 0.01, signifying a remarkably robust association between these two seemingly unrelated phenomena.
Now, before you paws and dismiss our findings as mere folly, we invite you to join us in this academic game of cat and mouse. The implications of our discoveries stretch far beyond the confines of mere statistical purrsonalities. They scratch at the surface of the intricate web of human behavior, shedding light on the nuanced interplay between political allegiance and the pursuit of internet escapism. This study aims to challenge the conventional wisdom that politics and humor are as incompatible as dogs and cats, and to reveal the subtle, yet significant, ways in which trivial internet pursuits can leave pawprints on the gravitas of elections.
As we embark on this feline-inspired journey of curiosity, we invite you to set aside your preconceptions and embrace the unexpected. After all, as we meowve forward in our exploration of this whimsical terrain, one might say that we are not only barking up the wrong tree, but also tampering with the very fabric of our understanding of political behavior. So, grab your catnip and get ready to unravel the mystery of how purrfectly innocent internet searches may have an unsuspected significance in the grand scheme of politics.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Fulfilling our mission to uncover the enigmatic correlation between Republican votes for Senators in Indiana and the pursuit of 'funny cat videos' on the world wide web, we embarked on a methodological journey akin to a cat's curious exploration of a new cardboard box. Our approach was not for the faint of heart, as we traversed the labyrinthine paths of data collection and analysis with the tenacity of a determined house cat stalking a laser dot.

To begin our endeavor, we diligently scoured the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the relevant data from 2004 to 2018, fueled by the fervent drive to unravel the intertwined mysteries of politics and internet humor. Our pursuit of this data was akin to hunting for a purrfectly hidden mouse in a digital haystack, sifting through vast troves of information with the precision of a feline paw meticulously grooming itself.

The first leg of our methodological expedition involved the acquisition of historical voting data for Republican Senators in the state of Indiana. Leveraging datasets from reputable sources, we meticulously gathered information on Republican votes in each senatorial election, meticulously tabulating and organizing them with the fastidiousness of a cat grooming its whiskers.

In tandem with our examination of political voting behavior, we ventured into the untamed wilderness of the internet – namely, Google Trends – to uncover the trends in searches for 'funny cat videos'. This phase of data collection required a keen eye for detail, as we navigated the jungle of search queries with the caution of a cat stealthily stalking its prey.

With these datasets in hand, we proceeded to analyze the correlation between Republican votes for Senators in Indiana and the frequency of Google searches for 'funny cat videos'. Employing sophisticated statistical tools and techniques, we harnessed the power of correlation analysis to extract meaningful insights from the seemingly disparate datasets. Our statistical analysis was as precise as a cat's leap onto a windowsill, revealing a striking correlation coefficient of 0.9716816 and a p-value of less than 0.01.

Finally, to ensure the robustness and validity of our findings, we subjected our data and analysis to rigorous scrutiny, approaching the task with a rigor and thoroughness reminiscent of a cat meticulously grooming its fur. Through model validation and sensitivity analysis, we corroborated our initial findings, further affirming the compelling relationship between Republican senatorial votes in Indiana and the allure of 'funny cat videos' on the internet.

In conclusion, our methodological concoction may seem whimsical, but it was executed with the precision of a feline maintaining its sleek coat. Our journey into the heart of this peculiar correlation between feline-inspired internet humor and political inclinations demonstrates that even the most unexpected intersections can yield valuable insights. Through a blend of data collection, statistical analysis, and unwavering curiosity, we have scratched the surface of a complex relationship that transcends the typical confines of political research. So, as we conclude this methodological adventure, we invite fellow researchers to embrace the unexpected and embark on their own purr-pendicular pursuits in the realm of data-driven discovery.


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 Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 2004 to 2018, you found a correlation 0.9716816, r-squared of 0.9441652, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'

[[ABSTRACT]]
Feline politicians and internet humor have more in common than meets the eye. This research delves deep into the correlation between Republican votes for Senators in Indiana and the prevalence of Google searches for 'funny cat videos' from 2004 to 2018. By analyzing data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our study reveals a surprisingly strong positive correlation coefficient of 0.9716816 and p-value less than 0.01, indicating a significant relationship between voting behavior and the pursuit of purrfection in online entertainment. The implications of these feline political preferences are whisker-thin yet far-reaching, shedding light on the underlying psychology of voters and the not-so-pawsitive impact of internet distractions on election outcomes. So, next time you see a politician purrpouncing their policies, don't be surprised if they have a penchant for paw-sitively hilarious cat videos!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Politics and internet memes may seem like odd bedfellows, but as the saying goes, "There is always a method to an internet cat's madness." In this study, we explore the curious linkage between Republican votes for Senators in Indiana and the insatiable quest for 'funny cat videos' in the vast savannah of the world wide web. Our research aims to dissect this seemingly whimsical connection and uncover the not-so-furry mysteries lurking beneath the surface.
The decision to embark on this quest was not made on a whim. Despite the prevailing notion that politics is as serious as a cat's aloof demeanor, we boldly set out to challenge the status quo and explore the uncharted territories of the interwebs. We were motivated by the age-old conundrum: why do people seek out 'funny cat videos,' and how does this behavior intersect with their political inclinations? While some may dismiss this question as mere fluff, we approached it with the fervor of a cat chasing a laser pointer, determined to unearth the hidden patterns within the digital litter box of internet searches.
Our journey into the realm of political feline fandom began by perusing mounds of data harvested from the MIT Election Data and Science Lab, the Harvard Dataverse, and the depths of Google Trends. We meticulously examined years of Republican votes for Senators in Indiana and the frequency of Google searches for 'funny cat videos' from 2004 to 2018, aiming to sniff out any discernible correlation between these seemingly disparate entities. To our surprise – and, dare we say, amusement – our analysis uncovered a correlation coefficient of 0.9716816, with a p-value of less than 0.01, signifying a remarkably robust association between these two seemingly unrelated phenomena.
Now, before you paws and dismiss our findings as mere folly, we invite you to join us in this academic game of cat and mouse. The implications of our discoveries stretch far beyond the confines of mere statistical purrsonalities. They scratch at the surface of the intricate web of human behavior, shedding light on the nuanced interplay between political allegiance and the pursuit of internet escapism. This study aims to challenge the conventional wisdom that politics and humor are as incompatible as dogs and cats, and to reveal the subtle, yet significant, ways in which trivial internet pursuits can leave pawprints on the gravitas of elections.
As we embark on this feline-inspired journey of curiosity, we invite you to set aside your preconceptions and embrace the unexpected. After all, as we meowve forward in our exploration of this whimsical terrain, one might say that we are not only barking up the wrong tree, but also tampering with the very fabric of our understanding of political behavior. So, grab your catnip and get ready to unravel the mystery of how purrfectly innocent internet searches may have an unsuspected significance in the grand scheme of politics.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

**RESULTS**

The results of our investigation into the connection between Republican votes for Senators in Indiana and Google searches for 'funny cat videos' from 2004 to 2018 revealed a startlingly robust correlation coefficient of 0.9716816, with an r-squared of 0.9441652, and a p-value of less than 0.01. This strong positive correlation signifies a purrsuasively significant relationship between these seemingly unrelated variables.

To visually depict these findings, we have included a scatterplot (Fig. 1), which highlights the remarkable consistency in the relationship between Republican votes and 'funny cat video' searches. The scatterplot elegantly captures the unmistakable trend, with Republican votes increasing in sync with the frequency of 'funny cat video' searches, demonstrating a level of synchronization that would make any well-coordinated feline duo proud.

The near-perfect correlation coefficient serves as a powerful reminder that statistics can sometimes elicit an unexpected chuckle, akin to discovering a cat attempting to mimic a dog's bark. This finding not only raises eyebrows but also beckons us to ponder the curious ways in which digital distractions intertwine with electoral behavior. Just as a cat stealthily stalks its prey, this correlation sneaked up on us, leaving us both puzzled and amused.

The implications of this connection extend beyond the world of politics and internet antics; they reverberate through the very fabric of human behavior, leaving us pondering the surprising depths of the interplay between political allegiance and online purrsuits. This research not only adds a whimsical note to the symphony of political science but also underscores the importance of considering seemingly trivial pursuits in the broader context of sociopolitical phenomena.

In conclusion, our findings meowserve as a testament to the unanticipated connections that permeate the sociopolitical landscape, inviting us to approach our understanding of voter behavior with an open mind and a willingness to embrace the unexpected. This study encourages us to recognize the peculiar ways in which seemingly unconnected phenomena can converge, reminding us that, at times, the most unlikely pairings can yield the most striking insights.

Stay tuned for further research that aims to uncover more curious connections in the world of politics and internet culture. After all, as we continue to delve into the enigmatic nexus between political proclivities and online obsessions, one cannot help but wonder: are there more unforeseen correlations that may yet cross our path, like a cat stealthily chasing a laser pointer?


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 Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'

[[ABSTRACT]]
Feline politicians and internet humor have more in common than meets the eye. This research delves deep into the correlation between Republican votes for Senators in Indiana and the prevalence of Google searches for 'funny cat videos' from 2004 to 2018. By analyzing data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our study reveals a surprisingly strong positive correlation coefficient of 0.9716816 and p-value less than 0.01, indicating a significant relationship between voting behavior and the pursuit of purrfection in online entertainment. The implications of these feline political preferences are whisker-thin yet far-reaching, shedding light on the underlying psychology of voters and the not-so-pawsitive impact of internet distractions on election outcomes. So, next time you see a politician purrpouncing their policies, don't be surprised if they have a penchant for paw-sitively hilarious cat videos!

[[LITERATURE REVIEW]]
In their seminal work, Smith et al. (2010) laid the groundwork for understanding the intersection of internet culture and political behavior, albeit without the feline flair. The authors uncovered the complexities of online virality and its potential influence on voter engagement, setting the stage for our paw-sitively intriguing investigation into the connection between Republican votes for Senators in Indiana and Google searches for 'funny cat videos.'
Expanding from the realms of political science and internet phenomenon, Doe (2015) delved into the psychological underpinnings of humor and its impact on decision-making processes. While their study focused primarily on the broader implications of humor in cognitive processes, our research takes a playful leap into the world of feline-inspired mirth and its unexpected resonance in the political landscape.
The findings of Jones (2018) provided a compelling backdrop for our exploration, highlighting the ripple effects of internet distractions on attention spans and cognitive engagement. We extrapolate from this work to illuminate the curious dance between political allegiances and the pursuit of internet whimsy, particularly in the form of humorous cat videos—a phenomenon that has gripped the hearts and minds of online denizens with feline fervor.
Moving from academic literature to more pop-culture-inspired texts, we draw inspiration from "How to Tell If Your Cat Is Plotting to Kill You" by Oatmeal (2012), delving into the quirky and enigmatic world of feline behavior. Though seemingly unrelated to politics at first glance, the intricate dynamics of cat psychology offer a paws-tively intriguing lens through which to explore the inexplicable attraction to funny cat videos and its potential impact on voter behaviors.
In a similar vein, the whimsical tales found in "The Cat Who... series" by Lilian Jackson Braun (1966-2007) provide a fictional yet thought-provoking glimpse into the enigmatic nature of feline companionship. As we navigate the terrain of our research, these novels serve as a reminder that the influence of cats, whether real or virtual, can be far-reaching and perhaps even politically charged.
On a tangentially related note, a motley assortment of movie marathons—ranging from "The Aristocats" to "The Lion King"—has provided our research team with valuable insights into the portrayal of feline characters in popular culture. While these films may seem like a whimsical diversion, they have sharpened our claws for the rigorous analytical quest of unraveling the purrfectly improbable correlation between Republican votes for Senators in Indiana and the seemingly innocent pursuit of 'funny cat videos' in the digital realm.
So, with this diverse tapestry of literature and media as our backdrop, we plunge into the heart of our research, ready to unravel the mystery of how the pursuit of feline-infused internet hilarity may hold unexpected significance in the grand tapestry of political behavior and decision-making.

[[RESULTS]]
The results of our investigation into the connection between Republican votes for Senators in Indiana and Google searches for 'funny cat videos' from 2004 to 2018 revealed a startlingly robust correlation coefficient of 0.9716816, with an r-squared of 0.9441652, and a p-value of less than 0.01. This strong positive correlation signifies a purrsuasively significant relationship between these seemingly unrelated variables.
To visually depict these findings, we have included a scatterplot (Fig. 1), which highlights the remarkable consistency in the relationship between Republican votes and 'funny cat video' searches. The scatterplot elegantly captures the unmistakable trend, with Republican votes increasing in sync with the frequency of 'funny cat video' searches, demonstrating a level of synchronization that would make any well-coordinated feline duo proud.
The near-perfect correlation coefficient serves as a powerful reminder that statistics can sometimes elicit an unexpected chuckle, akin to discovering a cat attempting to mimic a dog's bark. This finding not only raises eyebrows but also beckons us to ponder the curious ways in which digital distractions intertwine with electoral behavior. Just as a cat stealthily stalks its prey, this correlation sneaked up on us, leaving us both puzzled and amused.
The implications of this connection extend beyond the world of politics and internet antics; they reverberate through the very fabric of human behavior, leaving us pondering the surprising depths of the interplay between political allegiance and online purrsuits. This research not only adds a whimsical note to the symphony of political science but also underscores the importance of considering seemingly trivial pursuits in the broader context of sociopolitical phenomena.
In conclusion, our findings meowserve as a testament to the unanticipated connections that permeate the sociopolitical landscape, inviting us to approach our understanding of voter behavior with an open mind and a willingness to embrace the unexpected. This study encourages us to recognize the peculiar ways in which seemingly unconnected phenomena can converge, reminding us that, at times, the most unlikely pairings can yield the most striking insights.
Stay tuned for further research that aims to uncover more curious connections in the world of politics and internet culture. After all, as we continue to delve into the enigmatic nexus between political proclivities and online obsessions, one cannot help but wonder: are there more unforeseen correlations that may yet cross our path, like a cat stealthily chasing a laser pointer?

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

In this purr-ticularly riveting study, we uncovered a remarkable correlation between Republican votes for Senators in Indiana and Google searches for 'funny cat videos' that left even the most serious of political pundits feline intrigued. Our tail of statistical meowgic revealed an awe-inspiring correlation coefficient of 0.9716816, a finding so astonishing that it could make even the most stoic of researchers purr in delight.

Building upon the paw-sitively engaging findings of our feline-inspired literature review, our results pawfermed remarkably well. Much like a well-preened cat, our findings align with prior research on the unexpected intersections of internet whimsy and political predilections. The correlation we uncovered is no mere catnap; it's a tantalizing thread that weaves together the enigmatic world of online cat videos and the ever-surprising realm of political behavior.

The amusing antics of our statistical meowneuvres, including the purrfectly astute scatterplot, mirror the flexible and whimsical nature of our furry feline friends. They remind us that research can sometimes reveal unexpected connections, much like discovering a cat who enjoys a dip in the goldfish bowl.

By embracing the unexpected correlations that permeate the sociopolitical landscape, we encourage our fellow researchers to approach their work with a playful twinkle in their eyes and a willingness to embrace the purrplexing, even the purrplexing intersections of internet humor and political proclivities.

As we embark on further research endeavors, we remain ever-curious about the unexpected connections that may await us, just like a cat stealthily chasing a laser pointer. After all, who knows what other surprising correlations may yet cross our path: perhaps an affinity for slapstick comedy and voting patterns or even a penchant for memes and legislative preferences. There's a wealth of quirky connections to explore, and we're determined to pawsitively revel in the ensuing discoveries.


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 Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'

[[ABSTRACT]]
Feline politicians and internet humor have more in common than meets the eye. This research delves deep into the correlation between Republican votes for Senators in Indiana and the prevalence of Google searches for 'funny cat videos' from 2004 to 2018. By analyzing data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our study reveals a surprisingly strong positive correlation coefficient of 0.9716816 and p-value less than 0.01, indicating a significant relationship between voting behavior and the pursuit of purrfection in online entertainment. The implications of these feline political preferences are whisker-thin yet far-reaching, shedding light on the underlying psychology of voters and the not-so-pawsitive impact of internet distractions on election outcomes. So, next time you see a politician purrpouncing their policies, don't be surprised if they have a penchant for paw-sitively hilarious cat videos!

[[INTRDUCTION]]
Politics and internet memes may seem like odd bedfellows, but as the saying goes, "There is always a method to an internet cat's madness." In this study, we explore the curious linkage between Republican votes for Senators in Indiana and the insatiable quest for 'funny cat videos' in the vast savannah of the world wide web. Our research aims to dissect this seemingly whimsical connection and uncover the not-so-furry mysteries lurking beneath the surface.
The decision to embark on this quest was not made on a whim. Despite the prevailing notion that politics is as serious as a cat's aloof demeanor, we boldly set out to challenge the status quo and explore the uncharted territories of the interwebs. We were motivated by the age-old conundrum: why do people seek out 'funny cat videos,' and how does this behavior intersect with their political inclinations? While some may dismiss this question as mere fluff, we approached it with the fervor of a cat chasing a laser pointer, determined to unearth the hidden patterns within the digital litter box of internet searches.
Our journey into the realm of political feline fandom began by perusing mounds of data harvested from the MIT Election Data and Science Lab, the Harvard Dataverse, and the depths of Google Trends. We meticulously examined years of Republican votes for Senators in Indiana and the frequency of Google searches for 'funny cat videos' from 2004 to 2018, aiming to sniff out any discernible correlation between these seemingly disparate entities. To our surprise – and, dare we say, amusement – our analysis uncovered a correlation coefficient of 0.9716816, with a p-value of less than 0.01, signifying a remarkably robust association between these two seemingly unrelated phenomena.
Now, before you paws and dismiss our findings as mere folly, we invite you to join us in this academic game of cat and mouse. The implications of our discoveries stretch far beyond the confines of mere statistical purrsonalities. They scratch at the surface of the intricate web of human behavior, shedding light on the nuanced interplay between political allegiance and the pursuit of internet escapism. This study aims to challenge the conventional wisdom that politics and humor are as incompatible as dogs and cats, and to reveal the subtle, yet significant, ways in which trivial internet pursuits can leave pawprints on the gravitas of elections.
As we embark on this feline-inspired journey of curiosity, we invite you to set aside your preconceptions and embrace the unexpected. After all, as we meowve forward in our exploration of this whimsical terrain, one might say that we are not only barking up the wrong tree, but also tampering with the very fabric of our understanding of political behavior. So, grab your catnip and get ready to unravel the mystery of how purrfectly innocent internet searches may have an unsuspected significance in the grand scheme of politics.

[[RESULTS]]
The results of our investigation into the connection between Republican votes for Senators in Indiana and Google searches for 'funny cat videos' from 2004 to 2018 revealed a startlingly robust correlation coefficient of 0.9716816, with an r-squared of 0.9441652, and a p-value of less than 0.01. This strong positive correlation signifies a purrsuasively significant relationship between these seemingly unrelated variables.
To visually depict these findings, we have included a scatterplot (Fig. 1), which highlights the remarkable consistency in the relationship between Republican votes and 'funny cat video' searches. The scatterplot elegantly captures the unmistakable trend, with Republican votes increasing in sync with the frequency of 'funny cat video' searches, demonstrating a level of synchronization that would make any well-coordinated feline duo proud.
The near-perfect correlation coefficient serves as a powerful reminder that statistics can sometimes elicit an unexpected chuckle, akin to discovering a cat attempting to mimic a dog's bark. This finding not only raises eyebrows but also beckons us to ponder the curious ways in which digital distractions intertwine with electoral behavior. Just as a cat stealthily stalks its prey, this correlation sneaked up on us, leaving us both puzzled and amused.
The implications of this connection extend beyond the world of politics and internet antics; they reverberate through the very fabric of human behavior, leaving us pondering the surprising depths of the interplay between political allegiance and online purrsuits. This research not only adds a whimsical note to the symphony of political science but also underscores the importance of considering seemingly trivial pursuits in the broader context of sociopolitical phenomena.
In conclusion, our findings meowserve as a testament to the unanticipated connections that permeate the sociopolitical landscape, inviting us to approach our understanding of voter behavior with an open mind and a willingness to embrace the unexpected. This study encourages us to recognize the peculiar ways in which seemingly unconnected phenomena can converge, reminding us that, at times, the most unlikely pairings can yield the most striking insights.
Stay tuned for further research that aims to uncover more curious connections in the world of politics and internet culture. After all, as we continue to delve into the enigmatic nexus between political proclivities and online obsessions, one cannot help but wonder: are there more unforeseen correlations that may yet cross our path, like a cat stealthily chasing a laser pointer?

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

Our research has whiskered us away on a captivating journey into the unexpected nexus between Republican votes for Senators in Indiana and Google searches for 'funny cat videos'. With a correlation coefficient as strong as an alley cat's craving for tuna, the link between these seemingly disparate phenomena has left us feline intrigued. The visual representation of our findings in the scatterplot (Fig. 1) is a meowsterpiece in itself, capturing the harmonious dance between political leanings and online feline frivolity.

As we wrap up this study, it's essential to acknowledge the quirks and quips that have emerged. We've been reminded that even the most serious of subjects can have a purrfectly whimsical side. Our findings not only provoke a chuckle but also purrplex us with their unexpected relevance to human behavior and decision-making.

In light of these results, we are convinced that no further research is needed in this area—at least for now. As much as we're tempted to continue tumbling down the rabbit hole of peculiar connections, we'll resist the urge for now and leave you with the following thought: just as a cat always lands on its feet, so too may our understanding of political behavior always find unexpected footing in the most unlikely of places. Thank you for joining us on this whisker-laden adventure.


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Feline Political Science


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos'. Respond only with the name of a fictional organization.

ChatGPT:

The Feline Studies Institute


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Purrfect Politics: Republican Votes for Senators in Indiana and the Purrplexing Connection to Google Searches for 'Funny Cat Videos' with an abstract of Feline politicians and internet humor have more in common than meets the eye. This research delves deep into the correlation between Republican votes for Senators in Indiana and the prevalence of Google searches for 'funny cat videos' from 2004 to 2018. By analyzing data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our study reveals a surprisingly strong positive correlation coefficient of 0.9716816 and p-value less than 0.01, indicating a significant relationship between voting behavior and the pursuit of purrfection in online entertainment. The implications of these feline political preferences are whisker-thin yet far-reaching, shedding light on the underlying psychology of voters and the not-so-pawsitive impact of internet distractions on election outcomes. So, next time you see a politician purrpouncing their policies, don't be surprised if they have a penchant for paw-sitively hilarious cat videos!

ChatGPT:

Republican votes, Senators, Indiana, Google searches, funny cat videos, correlation, MIT Election Data and Science Lab, Harvard Dataverse, data analysis, correlation coefficient, p-value, voting behavior, online entertainment, feline political preferences, voter psychology, internet distractions, election outcomes.

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

Google searches for 'funny cat videos'
Detailed data title: Relative volume of Google searches for 'funny cat videos' (United States, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'funny cat videos'

Correlation r = 0.9716816 (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 = 0.9441652 (Coefficient of determination)
This means 94.4% of the change in the one variable (i.e., Google searches for 'funny cat videos') is predictable based on the change in the other (i.e., Votes for Republican Senators in Indiana) over the 6 years from 2004 through 2018.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0012. 0.0011915409401246422000000000
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 0.97 in 0.12% of random cases. Said differently, if you correlated 839 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.

[ 0.76, 1 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!


All values for the years included above: If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200420062010201220162018
Votes for Republican Senators in Indiana (Total votes)9039131171550952116113362014239901158000
Google searches for 'funny cat videos' (Rel. search volume)7.0833317.583311.513.166725.583316.6667




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([903913,1171550,952116,1133620,1423990,1158000,])
array_2 = np.array([7.08333,17.5833,11.5,13.1667,25.5833,16.6667,])
array_1_name = "Votes for Republican Senators in Indiana"
array_2_name = "Google searches for 'funny cat videos'"

# 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?

I'm grateful for your review!


Correlation ID: 4416 · Black Variable ID: 26236 · Red Variable ID: 1414
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0