about · email me · subscribe
Spurious correlation #4,934 · 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 North Dakota and the second variable is Google searches for 'scooby doo where are you'.  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 North Dakotans found themselves enraptured by political rhetoric, they couldn't help but relate to the mystery-solving antics of Scooby and the gang. The thought of unmasking elusive villains resonated deeply with their recent electoral pursuits, leading to a surge in nostalgic searches for the animated sleuth. It seems like in the land of hotly contested races, everyone was just trying to uncover who was really behind all the political shenanigans, and they turned to Scooby Doo for some much-needed lighthearted escapades. It was a time of 'zoinks' and 'jinkies' mixed with a dash of 'red or blue, we've got a mystery to solve, Scooby-Doo!'

Model: dalle-3
Prompt: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s that depicts a scene in North Dakota during the Senator voting count. Show multiple individuals engaging in political activities, such as counting ballots, while others are seen using their smartphones to search for "Scooby-Doo, Where Are You" on Google. Capture the sense of mystery and curiosity in the atmosphere, aiming to create an intriguing blend of political fervor and lighthearted nostalgia, similar to the adventures of Scooby and the gang. The scene should feel bustling with activity, with hints of the distinctive 1960s comic-book aesthetic and color scheme. 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 North Dakota and Google searches for 'scooby doo where are you'. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: a funny image macro Pop art a funny image macro A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Cute 2D animation
ChatGPT: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s

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 North Dakota and Google searches for 'scooby doo where are you', in the following situation: As North Dakotans found themselves enraptured by political rhetoric, they couldn't help but relate to the mystery-solving antics of Scooby and the gang. The thought of unmasking elusive villains resonated deeply with their recent electoral pursuits, leading to a surge in nostalgic searches for the animated sleuth. It seems like in the land of hotly contested races, everyone was just trying to uncover who was really behind all the political shenanigans, and they turned to Scooby Doo for some much-needed lighthearted escapades. It was a time of 'zoinks' and 'jinkies' mixed with a dash of 'red or blue, we've got a mystery to solve, Scooby-Doo!'. Keep the description simple.
ChatGPT: In North Dakota, as Republican votes for Senators were being counted, many people were also busy searching for "Scooby-Doo, Where Are You" on Google. Amidst the political excitement, the state was filled with a sense of mystery and curiosity, just like the adventures of Scooby and the gang. It was a strange but fascinating blend of political fervor and lighthearted nostalgia.

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: [ A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s ] and depicting this scene: In North Dakota, as Republican votes for Senators were being counted, many people were also busy searching for "Scooby-Doo, Where Are You" on Google. Amidst the political excitement, the state was filled with a sense of mystery and curiosity, just like the adventures of Scooby and the gang. It was a strange but fascinating blend of political fervor and lighthearted nostalgia. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s that depicts a scene in North Dakota during the Senator voting count. Show multiple individuals engaging in political activities, such as counting ballots, while others are seen using their smartphones to search for "Scooby-Doo, Where Are You" on Google. Capture the sense of mystery and curiosity in the atmosphere, aiming to create an intriguing blend of political fervor and lighthearted nostalgia, similar to the adventures of Scooby and the gang. The scene should feel bustling with activity, with hints of the distinctive 1960s comic-book aesthetic and color scheme.

*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 North Dakota caused scooby doo where are you (Google searches for 'scooby doo where are you') to increase.

AI academic paper

(Because p < 0.01)
The Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?

The Journal of Political Puzzles and Paradoxes

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 North Dakota and Google searches for 'scooby doo where are you'. Make lots of jokes, goofy observations, and puns.

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

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to assess this nagging question. You found a correlation coefficient of 0.9378509 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 Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?"

[[ABSTRACT]]
In this paper, we delve into the puzzling relationship between Republican voting patterns for Senators in North Dakota and the frequency of Google searches for the iconic phrase "Scooby Doo, Where Are You". Combining data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our research uncovers a surprising correlation that goes beyond your typical "jinkies" moment. With a correlation coefficient of 0.9378509 and p < 0.01 for the years 2004 to 2018, our findings raise the question: what's driving North Dakotans to dust off their magnifying glasses and search for clues in the virtual realm? Could the Republican vote and the search for "Scooby snacks" share a deeper connection than meets the eye? Join us as we unravel this enigmatic correlation while keeping an eye out for any meddling villains along the way!


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 North Dakota and Google searches for 'scooby doo where are you'. Make lots of jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
"The Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?"

[[ABSTRACT]]
In this paper, we delve into the puzzling relationship between Republican voting patterns for Senators in North Dakota and the frequency of Google searches for the iconic phrase "Scooby Doo, Where Are You". Combining data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our research uncovers a surprising correlation that goes beyond your typical "jinkies" moment. With a correlation coefficient of 0.9378509 and p < 0.01 for the years 2004 to 2018, our findings raise the question: what's driving North Dakotans to dust off their magnifying glasses and search for clues in the virtual realm? Could the Republican vote and the search for "Scooby snacks" share a deeper connection than meets the eye? Join us as we unravel this enigmatic correlation while keeping an eye out for any meddling villains along the way!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

The intersection of politics and pop culture has long been a subject of interest for researchers seeking to understand the motivations and behaviors of voters. In this vein, our study embarks on an unconventional journey into the realm of North Dakota Republican voting behavior and its unexpected relationship with the timeless catchphrase, "Scooby Doo, Where Are You?" As we wade through the marshes of political data and the mysterious mists of internet search trends, we find ourselves grappling with an enigma worthy of the Mystery Inc. gang.

The question at the heart of our investigation is a simple yet perplexing one: why is there a correlation between Republican votes for Senators in North Dakota and Google searches for "Scooby Doo, Where Are You"? To shed light on this peculiar association, we have thrown caution to the wind and ventured into uncharted territory, armed with statistical analyses, a healthy dose of curiosity, and perhaps a "zoinks" or two. While the realm of political science may not be known for its cast of colorful characters and talking Great Danes, our journey promises to be no less exciting as we tease apart the threads of this unexpected relationship.

Our study draws from a treasure trove of data, delicately culled from sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends. Through a rigorous analysis spanning the years 2004 to 2018, we have unraveled a tantalizing correlation coefficient of 0.9378509, with a p-value so small it would make even the most skeptical of statisticians raise an eyebrow. This discovery has left us pondering whether there may be more to the North Dakota Republican vote than meets the eye – or in this case, the search bar.

As we embark on this scholarly escapade, we urge our readers to don their metaphorical deerstalker hats and join us in unraveling this peculiar puzzle. With cautionary reminders to watch out for red herrings and the occasional cackling antagonist, we invite you to accompany us on this quirky quest as we strive to decode the mystery of why North Dakotans seem to be turning to the internet in search of their very own political and pop culture conundrum. Let the sleuthing begin!


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 North Dakota and Google searches for 'scooby doo where are you'. 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 cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"The Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?"

[[ABSTRACT]]
In this paper, we delve into the puzzling relationship between Republican voting patterns for Senators in North Dakota and the frequency of Google searches for the iconic phrase "Scooby Doo, Where Are You". Combining data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our research uncovers a surprising correlation that goes beyond your typical "jinkies" moment. With a correlation coefficient of 0.9378509 and p < 0.01 for the years 2004 to 2018, our findings raise the question: what's driving North Dakotans to dust off their magnifying glasses and search for clues in the virtual realm? Could the Republican vote and the search for "Scooby snacks" share a deeper connection than meets the eye? Join us as we unravel this enigmatic correlation while keeping an eye out for any meddling villains along the way!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The intersection of politics and pop culture has long been a subject of interest for researchers seeking to understand the motivations and behaviors of voters. In this vein, our study embarks on an unconventional journey into the realm of North Dakota Republican voting behavior and its unexpected relationship with the timeless catchphrase, "Scooby Doo, Where Are You?" As we wade through the marshes of political data and the mysterious mists of internet search trends, we find ourselves grappling with an enigma worthy of the Mystery Inc. gang.
The question at the heart of our investigation is a simple yet perplexing one: why is there a correlation between Republican votes for Senators in North Dakota and Google searches for "Scooby Doo, Where Are You"? To shed light on this peculiar association, we have thrown caution to the wind and ventured into uncharted territory, armed with statistical analyses, a healthy dose of curiosity, and perhaps a "zoinks" or two. While the realm of political science may not be known for its cast of colorful characters and talking Great Danes, our journey promises to be no less exciting as we tease apart the threads of this unexpected relationship.
Our study draws from a treasure trove of data, delicately culled from sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends. Through a rigorous analysis spanning the years 2004 to 2018, we have unraveled a tantalizing correlation coefficient of 0.9378509, with a p-value so small it would make even the most skeptical of statisticians raise an eyebrow. This discovery has left us pondering whether there may be more to the North Dakota Republican vote than meets the eye – or in this case, the search bar.
As we embark on this scholarly escapade, we urge our readers to don their metaphorical deerstalker hats and join us in unraveling this peculiar puzzle. With cautionary reminders to watch out for red herrings and the occasional cackling antagonist, we invite you to accompany us on this quirky quest as we strive to decode the mystery of why North Dakotans seem to be turning to the internet in search of their very own political and pop culture conundrum. Let the sleuthing begin!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The nexus of political behavior and popular culture has been a topic of interest for researchers, as it provides a unique window into the complex motivations that drive voter actions. While studies by Smith et al. (2016) and Doe et al. (2018) have delved into the influence of media and entertainment on political preferences, our investigation takes a whimsical turn as we explore the curious link between Republican voting patterns in North Dakota and the fervent Google searches for "Scooby Doo, Where Are You." As we venture deeper into this unconventional research terrain, we bid farewell to the solemn halls of traditional political analysis and brace ourselves for a wild ride filled with unexpected twists, hokey disguises, and the occasional groovy musical interlude.

In "The Politics of Pop Culture" by Jones (2017), the author provides a framework for understanding the interplay between popular culture phenomena and political landscapes, laying the groundwork for our exploration of the North Dakota enigma. Furthermore, "Understanding Political Behavior" by Smith (2015) offers insights into the myriad factors that shape voter decisions, prompting us to ponder if the allure of Scooby snacks may hold untold significance in the realm of political allegiance.

Turning to works of non-fiction that offer tangentially related insights, "Media Effects on Political Attitudes" by Thompson (2019) sheds light on the impact of media exposure on individual political beliefs and behaviors – a theme that may illuminate the unexpected correlation we seek to unravel. Similarly, "The Power of Pop Culture" by Anderson (2018) provides a thoughtful analysis of how cultural phenomena can permeate and influence various aspects of society, leaving us to wonder if Shaggy's insatiable appetite for snacks could inspire a similar fervor in the political realm.

Venturing into the realm of fiction, the works of Agatha Christie, the queen of mystery novels, remind us to approach this investigation with a keen eye for hidden clues and red herrings. Could the answer to our enigma take the form of an unexpected twist worthy of Christie's pen? Perhaps there is more than meets the eye beneath the seemingly innocent facade of children's animations, where the likes of "Scooby Doo" and "Where in the World Is Carmen Sandiego?" beckon us into a world of sleuthing and adventure. As we prepare to untangle this curious correlation, we draw inspiration from the cartoon detectives and mystery-solvers of our childhoods, tapping into the spirit of creativity and wonder that propels their escapades.

With a nod to the inexplicable and the improbable, we set off on this scholarly odyssey, armed with analytical tools, a healthy dose of humor, and a dogged determination to uncover the truth behind the unexpected bond between North Dakota Republicans and the perennial query, "Scooby Doo, Where Are You?" In the spirit of our intrepid canine detective and his merry band of companions, we embark on this quest with equal parts skepticism and unbridled curiosity, eager to decode the mystery and perhaps find a few chuckles along the way. Join us as we plunge headlong into the fantastical world of political and pop culture intersections, where the unexpected lurks around every corner and the truth may just be a Scooby snack away. Let the adventure begin!


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 North Dakota and Google searches for 'scooby doo where are you'. Make lots of jokes, goofy observations, and puns.

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 Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?"

[[ABSTRACT]]
In this paper, we delve into the puzzling relationship between Republican voting patterns for Senators in North Dakota and the frequency of Google searches for the iconic phrase "Scooby Doo, Where Are You". Combining data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our research uncovers a surprising correlation that goes beyond your typical "jinkies" moment. With a correlation coefficient of 0.9378509 and p < 0.01 for the years 2004 to 2018, our findings raise the question: what's driving North Dakotans to dust off their magnifying glasses and search for clues in the virtual realm? Could the Republican vote and the search for "Scooby snacks" share a deeper connection than meets the eye? Join us as we unravel this enigmatic correlation while keeping an eye out for any meddling villains along the way!

[[INTRODUCTION]]
INTRODUCTION
The intersection of politics and pop culture has long been a subject of interest for researchers seeking to understand the motivations and behaviors of voters. In this vein, our study embarks on an unconventional journey into the realm of North Dakota Republican voting behavior and its unexpected relationship with the timeless catchphrase, "Scooby Doo, Where Are You?" As we wade through the marshes of political data and the mysterious mists of internet search trends, we find ourselves grappling with an enigma worthy of the Mystery Inc. gang.
The question at the heart of our investigation is a simple yet perplexing one: why is there a correlation between Republican votes for Senators in North Dakota and Google searches for "Scooby Doo, Where Are You"? To shed light on this peculiar association, we have thrown caution to the wind and ventured into uncharted territory, armed with statistical analyses, a healthy dose of curiosity, and perhaps a "zoinks" or two. While the realm of political science may not be known for its cast of colorful characters and talking Great Danes, our journey promises to be no less exciting as we tease apart the threads of this unexpected relationship.
Our study draws from a treasure trove of data, delicately culled from sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends. Through a rigorous analysis spanning the years 2004 to 2018, we have unraveled a tantalizing correlation coefficient of 0.9378509, with a p-value so small it would make even the most skeptical of statisticians raise an eyebrow. This discovery has left us pondering whether there may be more to the North Dakota Republican vote than meets the eye – or in this case, the search bar.
As we embark on this scholarly escapade, we urge our readers to don their metaphorical deerstalker hats and join us in unraveling this peculiar puzzle. With cautionary reminders to watch out for red herrings and the occasional cackling antagonist, we invite you to accompany us on this quirky quest as we strive to decode the mystery of why North Dakotans seem to be turning to the internet in search of their very own political and pop culture conundrum. Let the sleuthing begin!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

METHODOLOGY

To uncover the perplexing correlation between Republican votes for Senators in North Dakota and Google searches for “Scooby Doo, Where Are You," our research team concocted a methodology that combined the precision of a Sherlock Holmes investigation with the whimsy of a Scooby Snack-fueled adventure.

Data Collection:
We embarked on our data collection by harnessing the power of modern technology and delving into the treasure trove of the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends. The MIT Election Data and Science Lab provided us with the critical political voting data, allowing us to scrutinize the electoral inclinations of Republican voters in North Dakota with the same scrutiny as the Mystery Inc. gang scrutinizes a seemingly haunted amusement park.

For the digital footprint of our canine-themed curiosity, we turned to Google Trends, where we searched for the frequency of the iconic phrase "Scooby Doo, Where Are You." Our journey through Google Trends felt akin to navigating a labyrinthine haunted house, as we sought to unveil the patterns behind the cultural call to action that is the timeless search for Scooby and the gang.

Unorthodox Correlation Analysis:
With the dataset in hand, we employed a correlation analysis that would make even the most skeptical of statisticians arch an eyebrow in surprise. Utilizing statistical software with the same precision as Velma's trusty magnifying glass, we calculated the correlation coefficient and p-value for the years 2004 to 2018. Our analysis yielded a correlation coefficient of 0.9378509, with a p-value so minuscule it would make even the most dubious of cryptic villains concede defeat.

Time Series Analysis:
In addition to traditional correlation methods, we harnessed the power of time series analysis to examine the temporal dynamics of the relationship between Republican votes and the frequency of "Scooby Doo, Where Are You" searches. This method allowed us to capture the evolving patterns of curiosity and political expression, akin to tracking the trail of clues left behind by a mischievous specter.

Lighthearted Interpretation:
While our methods were rigorous and scientifically sound, we must acknowledge the lighthearted nature of our interpretation. Just as Scooby and the gang approach each mystery with a blend of seriousness and whimsy, we aimed to infuse our analysis with a touch of playful curiosity. After all, decoding the enigma of political behavior and pop culture fascination should be an adventure, not a mundane chore.

In summary, our methodology combined the rigor of statistical analysis with the lighthearted spirit of a Saturday morning cartoon, allowing us to embark on a scholarly escapade that unpacks the inexplicable connection between North Dakota Republican votes and the enduring search for the ever-elusive canine detective. As we journey through the methodology, we urge our readers to approach the findings with a sense of adventure and a dash of lightheartedness, for the nexus of politics and pop culture can be a captivating rollercoaster ride of unexpected correlations and delightful discoveries. Let the sleuthing continue!


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 North Dakota and Google searches for 'scooby doo where are you'. Make lots of jokes, goofy observations, and puns.

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 0.9378509, r-squared of 0.8795642, 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 Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?"

[[ABSTRACT]]
In this paper, we delve into the puzzling relationship between Republican voting patterns for Senators in North Dakota and the frequency of Google searches for the iconic phrase "Scooby Doo, Where Are You". Combining data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our research uncovers a surprising correlation that goes beyond your typical "jinkies" moment. With a correlation coefficient of 0.9378509 and p < 0.01 for the years 2004 to 2018, our findings raise the question: what's driving North Dakotans to dust off their magnifying glasses and search for clues in the virtual realm? Could the Republican vote and the search for "Scooby snacks" share a deeper connection than meets the eye? Join us as we unravel this enigmatic correlation while keeping an eye out for any meddling villains along the way!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The intersection of politics and pop culture has long been a subject of interest for researchers seeking to understand the motivations and behaviors of voters. In this vein, our study embarks on an unconventional journey into the realm of North Dakota Republican voting behavior and its unexpected relationship with the timeless catchphrase, "Scooby Doo, Where Are You?" As we wade through the marshes of political data and the mysterious mists of internet search trends, we find ourselves grappling with an enigma worthy of the Mystery Inc. gang.
The question at the heart of our investigation is a simple yet perplexing one: why is there a correlation between Republican votes for Senators in North Dakota and Google searches for "Scooby Doo, Where Are You"? To shed light on this peculiar association, we have thrown caution to the wind and ventured into uncharted territory, armed with statistical analyses, a healthy dose of curiosity, and perhaps a "zoinks" or two. While the realm of political science may not be known for its cast of colorful characters and talking Great Danes, our journey promises to be no less exciting as we tease apart the threads of this unexpected relationship.
Our study draws from a treasure trove of data, delicately culled from sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends. Through a rigorous analysis spanning the years 2004 to 2018, we have unraveled a tantalizing correlation coefficient of 0.9378509, with a p-value so small it would make even the most skeptical of statisticians raise an eyebrow. This discovery has left us pondering whether there may be more to the North Dakota Republican vote than meets the eye – or in this case, the search bar.
As we embark on this scholarly escapade, we urge our readers to don their metaphorical deerstalker hats and join us in unraveling this peculiar puzzle. With cautionary reminders to watch out for red herrings and the occasional cackling antagonist, we invite you to accompany us on this quirky quest as we strive to decode the mystery of why North Dakotans seem to be turning to the internet in search of their very own political and pop culture conundrum. Let the sleuthing begin!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis uncovered a surprisingly strong correlation between Republican votes for Senators in North Dakota and Google searches for the iconic phrase "Scooby Doo, Where Are You" for the years 2004 to 2018. The correlation coefficient of 0.9378509 suggests a tight relationship, with an r-squared of 0.8795642, meaning that nearly 88% of the variation in North Dakota Republican votes can be explained by the frequency of "Scooby Doo" searches. To put it simply, it seems that North Dakotans have been hitting the internet in a manner that's eerily synchronized with their voting behavior.

To graphically illustrate this unexpected connection, our team has prepared a visual aid in the form of Figure 1. This scatterplot lays bare the striking correlation between Republican votes and "Scooby Doo" searches, leaving little room for doubt about the curious relationship we've stumbled upon. It's not often that a research paper prompts one to exclaim, "Zoinks!" but we assure you, the temptation is certainly there.

Now, of course, correlation does not imply causation, and we must exercise caution in our interpretation of these findings. We'd hate to point fingers and scream "it was old man Jenkins all along!" without solid evidence to back it up. However, the statistical significance of our findings (p < 0.01) suggests that there may indeed be something brewing in the realm of North Dakota politics and cartoon canine capers.

One plausible explanation could be the presence of a latent variable influencing both Republican voting behavior and the urge to google everyone's favorite mystery-solving dog. Could it be a nostalgic sentiment influencing both political choices and late-night searches for Scooby snacks recipes? Or perhaps there's a deeper connection between the escapades of Scooby and the politicking in the Peace Garden State that we have yet to uncover. As researchers, it is our duty to dig deeper, just like a certain group of meddling kids and their canine companion.

In conclusion, our research sheds light on an unexpectedly strong correlation between North Dakota Republican votes for Senators and Google searches for "Scooby Doo, Where Are You". While the "why" remains shrouded in mystery, we hope that our findings will inspire further scrutiny and bring us one step closer to unraveling the peculiar enigma of this unanticipated relationship. And maybe, just maybe, we'll even find a clue or two about the inner workings of North Dakota politics.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 North Dakota and Google searches for 'scooby doo where are you'. Make lots of jokes, goofy observations, and puns.

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 Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?"

[[ABSTRACT]]
In this paper, we delve into the puzzling relationship between Republican voting patterns for Senators in North Dakota and the frequency of Google searches for the iconic phrase "Scooby Doo, Where Are You". Combining data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our research uncovers a surprising correlation that goes beyond your typical "jinkies" moment. With a correlation coefficient of 0.9378509 and p < 0.01 for the years 2004 to 2018, our findings raise the question: what's driving North Dakotans to dust off their magnifying glasses and search for clues in the virtual realm? Could the Republican vote and the search for "Scooby snacks" share a deeper connection than meets the eye? Join us as we unravel this enigmatic correlation while keeping an eye out for any meddling villains along the way!

[[LITERATURE REVIEW]]
The nexus of political behavior and popular culture has been a topic of interest for researchers, as it provides a unique window into the complex motivations that drive voter actions. While studies by Smith et al. (2016) and Doe et al. (2018) have delved into the influence of media and entertainment on political preferences, our investigation takes a whimsical turn as we explore the curious link between Republican voting patterns in North Dakota and the fervent Google searches for "Scooby Doo, Where Are You." As we venture deeper into this unconventional research terrain, we bid farewell to the solemn halls of traditional political analysis and brace ourselves for a wild ride filled with unexpected twists, hokey disguises, and the occasional groovy musical interlude.
In "The Politics of Pop Culture" by Jones (2017), the author provides a framework for understanding the interplay between popular culture phenomena and political landscapes, laying the groundwork for our exploration of the North Dakota enigma. Furthermore, "Understanding Political Behavior" by Smith (2015) offers insights into the myriad factors that shape voter decisions, prompting us to ponder if the allure of Scooby snacks may hold untold significance in the realm of political allegiance.
Turning to works of non-fiction that offer tangentially related insights, "Media Effects on Political Attitudes" by Thompson (2019) sheds light on the impact of media exposure on individual political beliefs and behaviors – a theme that may illuminate the unexpected correlation we seek to unravel. Similarly, "The Power of Pop Culture" by Anderson (2018) provides a thoughtful analysis of how cultural phenomena can permeate and influence various aspects of society, leaving us to wonder if Shaggy's insatiable appetite for snacks could inspire a similar fervor in the political realm.
Venturing into the realm of fiction, the works of Agatha Christie, the queen of mystery novels, remind us to approach this investigation with a keen eye for hidden clues and red herrings. Could the answer to our enigma take the form of an unexpected twist worthy of Christie's pen? Perhaps there is more than meets the eye beneath the seemingly innocent facade of children's animations, where the likes of "Scooby Doo" and "Where in the World Is Carmen Sandiego?" beckon us into a world of sleuthing and adventure. As we prepare to untangle this curious correlation, we draw inspiration from the cartoon detectives and mystery-solvers of our childhoods, tapping into the spirit of creativity and wonder that propels their escapades.
With a nod to the inexplicable and the improbable, we set off on this scholarly odyssey, armed with analytical tools, a healthy dose of humor, and a dogged determination to uncover the truth behind the unexpected bond between North Dakota Republicans and the perennial query, "Scooby Doo, Where Are You?" In the spirit of our intrepid canine detective and his merry band of companions, we embark on this quest with equal parts skepticism and unbridled curiosity, eager to decode the mystery and perhaps find a few chuckles along the way. Join us as we plunge headlong into the fantastical world of political and pop culture intersections, where the unexpected lurks around every corner and the truth may just be a Scooby snack away. Let the adventure begin!

[[RESULTS]]
Our analysis uncovered a surprisingly strong correlation between Republican votes for Senators in North Dakota and Google searches for the iconic phrase "Scooby Doo, Where Are You" for the years 2004 to 2018. The correlation coefficient of 0.9378509 suggests a tight relationship, with an r-squared of 0.8795642, meaning that nearly 88% of the variation in North Dakota Republican votes can be explained by the frequency of "Scooby Doo" searches. To put it simply, it seems that North Dakotans have been hitting the internet in a manner that's eerily synchronized with their voting behavior.
To graphically illustrate this unexpected connection, our team has prepared a visual aid in the form of Figure 1. This scatterplot lays bare the striking correlation between Republican votes and "Scooby Doo" searches, leaving little room for doubt about the curious relationship we've stumbled upon. It's not often that a research paper prompts one to exclaim, "Zoinks!" but we assure you, the temptation is certainly there.
Now, of course, correlation does not imply causation, and we must exercise caution in our interpretation of these findings. We'd hate to point fingers and scream "it was old man Jenkins all along!" without solid evidence to back it up. However, the statistical significance of our findings (p < 0.01) suggests that there may indeed be something brewing in the realm of North Dakota politics and cartoon canine capers.
One plausible explanation could be the presence of a latent variable influencing both Republican voting behavior and the urge to google everyone's favorite mystery-solving dog. Could it be a nostalgic sentiment influencing both political choices and late-night searches for Scooby snacks recipes? Or perhaps there's a deeper connection between the escapades of Scooby and the politicking in the Peace Garden State that we have yet to uncover. As researchers, it is our duty to dig deeper, just like a certain group of meddling kids and their canine companion.
In conclusion, our research sheds light on an unexpectedly strong correlation between North Dakota Republican votes for Senators and Google searches for "Scooby Doo, Where Are You". While the "why" remains shrouded in mystery, we hope that our findings will inspire further scrutiny and bring us one step closer to unraveling the peculiar enigma of this unanticipated relationship. And maybe, just maybe, we'll even find a clue or two about the inner workings of North Dakota politics.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The correlation we uncovered between Republican votes for Senators in North Dakota and Google searches for "Scooby Doo, Where Are You" is nothing short of mind-boggling. At first glance, it might seem more far-fetched than a Scooby-Doo plot twist, but our results support prior research that has long hinted at the interplay between popular culture and political behavior.

As previously discussed, our investigation takes a whimsical turn into the realm of unconventional correlation. It’s not every day that researchers find themselves pondering whether the GOP in North Dakota is taking cues from the Mystery Inc. gang. Remember how we delved into the influence of media and entertainment on political preferences? Well, it seems that even Shaggy’s propensity for exclaiming "zoinks" may hold hidden significance in the realm of political allegiance.

We can't help but marvel at the unexpected connection we've uncovered. With a correlation coefficient of 0.9378509 and a tight relationship illustrated by an r-squared of 0.8795642, our findings confirm the existence of a compelling link between North Dakota's Republican voters and their virtual quest to find the ever-elusive "Scooby Doo". As bewildering as it may seem, the statistics don't lie – much like how Scooby doesn't lie when presented with the prospect of a Scooby snack.

While correlation does not imply causation, our results lead us to speculate on potential explanations for this uncanny connection. Could there be a latent variable at play, guiding both political behavior and the yearning to revisit the antics of Mystery Inc.? We can't help but entertain the notion that there might be a shared nostalgic sentiment at work, influencing not only political choices but also igniting late-night searches for Velma's latest brain teasers.

As researchers, we are duty-bound to dig deeper into this curious correlation, not unlike a certain group of meddling kids and their canine companion. After all, any explanation that fails to account for this significant correlation would be as unsatisfying as an unmasking that reveals the villain to be "old man Jenkins" yet again.

In conclusion, our research has illuminated an unexpectedly strong bond between North Dakota Republican votes and the irresistible urge to scour the virtual realm for the whereabouts of the Mystery Machine. Our findings not only reaffirm the impact of pop culture on political behavior but also fuel a sense of wonder akin to embarking on a new "Scooby-Doo" mystery. It's our hope that this research inspires further investigation and brings us one step closer to unraveling the enigma of this peculiar relationship. And who knows, maybe we’ll stumble upon a clue or two that sheds light on the inner workings of North Dakota politics.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 North Dakota and Google searches for 'scooby doo where are you'. Make lots of jokes, goofy observations, and puns.

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 Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?"

[[ABSTRACT]]
In this paper, we delve into the puzzling relationship between Republican voting patterns for Senators in North Dakota and the frequency of Google searches for the iconic phrase "Scooby Doo, Where Are You". Combining data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our research uncovers a surprising correlation that goes beyond your typical "jinkies" moment. With a correlation coefficient of 0.9378509 and p < 0.01 for the years 2004 to 2018, our findings raise the question: what's driving North Dakotans to dust off their magnifying glasses and search for clues in the virtual realm? Could the Republican vote and the search for "Scooby snacks" share a deeper connection than meets the eye? Join us as we unravel this enigmatic correlation while keeping an eye out for any meddling villains along the way!

[[INTRDUCTION]]
INTRODUCTION
The intersection of politics and pop culture has long been a subject of interest for researchers seeking to understand the motivations and behaviors of voters. In this vein, our study embarks on an unconventional journey into the realm of North Dakota Republican voting behavior and its unexpected relationship with the timeless catchphrase, "Scooby Doo, Where Are You?" As we wade through the marshes of political data and the mysterious mists of internet search trends, we find ourselves grappling with an enigma worthy of the Mystery Inc. gang.
The question at the heart of our investigation is a simple yet perplexing one: why is there a correlation between Republican votes for Senators in North Dakota and Google searches for "Scooby Doo, Where Are You"? To shed light on this peculiar association, we have thrown caution to the wind and ventured into uncharted territory, armed with statistical analyses, a healthy dose of curiosity, and perhaps a "zoinks" or two. While the realm of political science may not be known for its cast of colorful characters and talking Great Danes, our journey promises to be no less exciting as we tease apart the threads of this unexpected relationship.
Our study draws from a treasure trove of data, delicately culled from sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends. Through a rigorous analysis spanning the years 2004 to 2018, we have unraveled a tantalizing correlation coefficient of 0.9378509, with a p-value so small it would make even the most skeptical of statisticians raise an eyebrow. This discovery has left us pondering whether there may be more to the North Dakota Republican vote than meets the eye – or in this case, the search bar.
As we embark on this scholarly escapade, we urge our readers to don their metaphorical deerstalker hats and join us in unraveling this peculiar puzzle. With cautionary reminders to watch out for red herrings and the occasional cackling antagonist, we invite you to accompany us on this quirky quest as we strive to decode the mystery of why North Dakotans seem to be turning to the internet in search of their very own political and pop culture conundrum. Let the sleuthing begin!

[[RESULTS]]
Our analysis uncovered a surprisingly strong correlation between Republican votes for Senators in North Dakota and Google searches for the iconic phrase "Scooby Doo, Where Are You" for the years 2004 to 2018. The correlation coefficient of 0.9378509 suggests a tight relationship, with an r-squared of 0.8795642, meaning that nearly 88% of the variation in North Dakota Republican votes can be explained by the frequency of "Scooby Doo" searches. To put it simply, it seems that North Dakotans have been hitting the internet in a manner that's eerily synchronized with their voting behavior.
To graphically illustrate this unexpected connection, our team has prepared a visual aid in the form of Figure 1. This scatterplot lays bare the striking correlation between Republican votes and "Scooby Doo" searches, leaving little room for doubt about the curious relationship we've stumbled upon. It's not often that a research paper prompts one to exclaim, "Zoinks!" but we assure you, the temptation is certainly there.
Now, of course, correlation does not imply causation, and we must exercise caution in our interpretation of these findings. We'd hate to point fingers and scream "it was old man Jenkins all along!" without solid evidence to back it up. However, the statistical significance of our findings (p < 0.01) suggests that there may indeed be something brewing in the realm of North Dakota politics and cartoon canine capers.
One plausible explanation could be the presence of a latent variable influencing both Republican voting behavior and the urge to google everyone's favorite mystery-solving dog. Could it be a nostalgic sentiment influencing both political choices and late-night searches for Scooby snacks recipes? Or perhaps there's a deeper connection between the escapades of Scooby and the politicking in the Peace Garden State that we have yet to uncover. As researchers, it is our duty to dig deeper, just like a certain group of meddling kids and their canine companion.
In conclusion, our research sheds light on an unexpectedly strong correlation between North Dakota Republican votes for Senators and Google searches for "Scooby Doo, Where Are You". While the "why" remains shrouded in mystery, we hope that our findings will inspire further scrutiny and bring us one step closer to unraveling the peculiar enigma of this unanticipated relationship. And maybe, just maybe, we'll even find a clue or two about the inner workings of North Dakota politics.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

As we wrap up our study, it's clear that the connection between Republican votes in North Dakota and Google searches for "Scooby Doo, Where Are You" is a head-scratcher worthy of the gang's best efforts. Our results reveal a correlation coefficient as powerful as an unmasking scene, leaving us to ponder the mystery of this unlikely pairing.

While we've uncovered this eyebrow-raising correlation, let's remember that correlation does not imply causation. Nonetheless, it's tempting to imagine North Dakotans casting their votes while humming the Scooby-Doo theme song, or perhaps even shouting "Jinkies!" as they fill out their ballots.

But fear not, dear reader, for we won't leave you hanging like an unanswered cliffhanger. Our findings call for more probing into the whimsical world of North Dakota politics and the enduring appeal of a certain snack-loving, mystery-solving pooch. And who knows, maybe we'll stumble upon a treasure trove of Velma-esque revelations that unravel the mystery behind this unexpected link.

In the immortal words of Scooby himself, "Ruh-roh!" It seems we've gotten ourselves tangled in a web of political and pop culture intrigue. However, with such a strong correlation, it's safe to say that this is no mere "red herring." As for causation, well, that's a mystery as elusive as the elusive Scooby Snacks.

In the grand tradition of detective work, it's now time to put this case to rest. Our conclusion? North Dakota Republicans and their digital pursuit of all things Scooby-Doo are inextricably linked in a manner that defies easy explanation.

With that said, we confidently declare that no more research is needed in this area. The case of the Republican votes and "Scooby Doo, Where Are You" searches is closed – at least until the next episode of "Unsolved Political Mysteries."


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 Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Puzzles and Paradoxes


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 Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'?. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Political Paradoxes and Puzzles


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 Mystery of Voting Behavior: Are North Dakota Republicans Searching for 'Scooby Doo, Where Are You'? with an abstract of In this paper, we delve into the puzzling relationship between Republican voting patterns for Senators in North Dakota and the frequency of Google searches for the iconic phrase "Scooby Doo, Where Are You". Combining data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, our research uncovers a surprising correlation that goes beyond your typical "jinkies" moment. With a correlation coefficient of 0.9378509 and p < 0.01 for the years 2004 to 2018, our findings raise the question: what's driving North Dakotans to dust off their magnifying glasses and search for clues in the virtual realm? Could the Republican vote and the search for "Scooby snacks" share a deeper connection than meets the eye? Join us as we unravel this enigmatic correlation while keeping an eye out for any meddling villains along the way!

ChatGPT:

North Dakota, Republican voting patterns, Senators, Google searches, "Scooby Doo, Where Are You", correlation coefficient, MIT Election Data and Science Lab, Harvard Dataverse, Google Trends, North Dakotans, Republican vote, "Scooby snacks", correlation analysis, voting behavior, political trends, search behavior, mystery, enigmatic correlation

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

Google searches for 'scooby doo where are you'
Detailed data title: Relative volume of Google searches for 'scooby doo where are you' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'scooby doo where are you'

Correlation r = 0.9378509 (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 = 0.8795642 (Coefficient of determination)
This means 88% of the change in the one variable (i.e., Google searches for 'scooby doo where are you') is predictable based on the change in the other (i.e., Votes for Republican Senators in North Dakota) over the 6 years from 2004 through 2018.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0057. 0.0056737465518894945000000000
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 0.94 in 0.57% of random cases. Said differently, if you correlated 176 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.

[ 0.53, 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.
200420062010201220162018
Votes for Republican Senators in North Dakota (Total votes)9855364417181689158401268788179720
Google searches for 'scooby doo where are you' (Rel. search volume)19.833316.58334442.833353.2547.4167




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([98553,64417,181689,158401,268788,179720,])
array_2 = np.array([19.8333,16.5833,44,42.8333,53.25,47.4167,])
array_1_name = "Votes for Republican Senators in North Dakota"
array_2_name = "Google searches for 'scooby doo where are you'"

# 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 much appreciated!


Correlation ID: 4934 · Black Variable ID: 26295 · Red Variable ID: 1382
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0