about · email me · subscribe
Spurious correlation #5,616 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Democratic Senators in North Dakota and the second variable is Google searches for 'spiderman'.  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 Democrat votes for Senators in North Dakota decreased, there was a corresponding decrease in support for policies promoting friendly neighborhood behavior. This led to a statewide shortage of individuals willing to take on the responsibility of being a superhero, as they were more focused on political matters. As a result, people were no longer as interested in the epitome of a friendly neighborhood superhero, Spiderman, as they once were. In actuality, this correlation is most likely a random coincidence and not indicative of any real causation. The number of Democrat votes for Senators in North Dakota is unlikely to have any direct impact on the popularity of Spiderman.

Model: dalle-3
Prompt: Generate an image of a hyper-realistic cityscape in North Dakota, featuring a lone figure standing on top of a modest building. The figure is clad in friendly neighborhood attire, reminiscent of Spiderman. Below, the city streets are noticeably emptier as the decline in Democratic votes is reflected in the changing atmosphere. The cloudy sky above adds an air of solitude and introspection to the scene. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Votes for Democratic Senators in North Dakota and Google searches for 'spiderman'. 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: 3D Pixar Style Hyper-realistic Psychedelic Symbolism Macabre
ChatGPT: Hyper-realistic

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for Democratic Senators in North Dakota and Google searches for 'spiderman', in the following situation: As the number of Democrat votes for Senators in North Dakota decreased, there was a corresponding decrease in support for policies promoting friendly neighborhood behavior. This led to a statewide shortage of individuals willing to take on the responsibility of being a superhero, as they were more focused on political matters. As a result, people were no longer as interested in the epitome of a friendly neighborhood superhero, Spiderman, as they once were. In actuality, this correlation is most likely a random coincidence and not indicative of any real causation. The number of Democrat votes for Senators in North Dakota is unlikely to have any direct impact on the popularity of Spiderman.. Keep the description simple.
ChatGPT: A lone figure was seen standing atop a modest city building in North Dakota under a cloudy sky. With each declining Democratic vote, fewer people in the city were clad in friendly neighborhood attire, and the once bustling neighborhood was now quiet. At ground level, fewer individuals searched for Spiderman, their superhero, as their focus shifted to political matters.

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: [ Hyper-realistic ] and depicting this scene: A lone figure was seen standing atop a modest city building in North Dakota under a cloudy sky. With each declining Democratic vote, fewer people in the city were clad in friendly neighborhood attire, and the once bustling neighborhood was now quiet. At ground level, fewer individuals searched for Spiderman, their superhero, as their focus shifted to political matters. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a hyper-realistic cityscape in North Dakota, featuring a lone figure standing on top of a modest building. The figure is clad in friendly neighborhood attire, reminiscent of Spiderman. Below, the city streets are noticeably emptier as the decline in Democratic votes is reflected in the changing atmosphere. The cloudy sky above adds an air of solitude and introspection to the scene.

*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 a decrease in Democrat votes for Senators in North Dakota caused spiderman (Google searches for 'spiderman') to decrease.\Make it sound serious until the end.

AI academic paper

(Because p < 0.05)
Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota

The Journal of Arachnid Anthropology and Political Science

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Democrat votes for Senators in North Dakota and Google searches for 'spiderman'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Include a pun in the title.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to assess this nagging question. You found a correlation coefficient of 0.8519781 and p < 0.05 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]]
"Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota"

[[ABSTRACT]]
In this thought-provoking research, we delve into the unlikely but intriguing connection between the voting behavior of North Dakotans and their virtual fascination with the friendly neighborhood superhero, Spiderman. With a database as extensive as J. Jonah Jameson's grudge against Spiderman, we plumbed the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the years 2004 to 2018.

Our findings reveal the astonishing correlation coefficient of 0.8519781 and a p-value less than, well, a spider's appetite for insects. The deep statistical web weaved by our analysis demonstrates a compelling relationship between North Dakota residents' penchant for Googling Spiderman and their inclination to cast their ballots for Democratic senators. Yes, you heard that right – it seems that the iconic red-and-blue-clad crusader may have more influence in the political arena than we previously thought.

As we unravel this intriguing arachnoid enigma, we invite readers to not only ponder the political implications but also to appreciate the humor of this unexpected correlation. After all, it was high time for a study that truly captures the "web" of political interests in North Dakota, and we have finally untangled the threads of Spiderman's web in the state's electoral dynamics.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in North Dakota and Google searches for 'spiderman'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota"

[[ABSTRACT]]
In this thought-provoking research, we delve into the unlikely but intriguing connection between the voting behavior of North Dakotans and their virtual fascination with the friendly neighborhood superhero, Spiderman. With a database as extensive as J. Jonah Jameson's grudge against Spiderman, we plumbed the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the years 2004 to 2018.

Our findings reveal the astonishing correlation coefficient of 0.8519781 and a p-value less than, well, a spider's appetite for insects. The deep statistical web weaved by our analysis demonstrates a compelling relationship between North Dakota residents' penchant for Googling Spiderman and their inclination to cast their ballots for Democratic senators. Yes, you heard that right – it seems that the iconic red-and-blue-clad crusader may have more influence in the political arena than we previously thought.

As we unravel this intriguing arachnoid enigma, we invite readers to not only ponder the political implications but also to appreciate the humor of this unexpected correlation. After all, it was high time for a study that truly captures the "web" of political interests in North Dakota, and we have finally untangled the threads of Spiderman's web in the state's electoral dynamics.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Ladies and gentlemen, arachnophobes and arachnophiles, buckle up as we embark on a web-slinging journey through the tangled intersection of politics and pop culture. When it comes to analyzing electoral trends, researchers often cast their nets far and wide, but seldom do they delve into the sticky world of superhero fandom. What if I told you that behind the scenes of North Dakota’s political landscape, a web-slinging hero may have silently been influencing voting patterns? Oh, the tangled web we weave when politicians and spider-themed vigilantes interleave!

As researchers, we are constantly on the hunt for unlikely connections and delightful surprises in our data. It is akin to stumbling upon a hidden trapdoor in a statistical mansion, only to find a masked crusader protecting ballots instead of jewels. Armed with our trusty statistical tools and unwavering dedication to uncovering the unexpected, we set out to investigate the curious relationship between Google searches for 'Spiderman' and Democrat votes in the great state of North Dakota.

They say that every vote counts, but who would have guessed that every web-slinging search also counts in the ballot box? It’s a classic case of "with great statistical power comes great responsibility," a concept not unfamiliar to our friendly neighborhood Spiderman. After all, with such a high correlation coefficient and an eerily minuscule p-value, this finding may just have us uttering, "Holy unexpected political influence, Batman!"

Join us as we untangle this web of intrigue, where state politics and internet curiosities intersect in a way that could make Dr. Octopus nod in approval. Who knew that North Dakota's political landscape held more surprises than the average Peter Parker plot twist? As Sky High Comics' resident superhero aficionado, Stan Lee, would say, "Make mine statistical significance!" So, grab your magnifying glasses and cue the dramatic music – it’s time to uncover the unexpected arachno-political dynamics no one knew they were missing.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in North Dakota and Google searches for 'spiderman'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
"Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota"

[[ABSTRACT]]
In this thought-provoking research, we delve into the unlikely but intriguing connection between the voting behavior of North Dakotans and their virtual fascination with the friendly neighborhood superhero, Spiderman. With a database as extensive as J. Jonah Jameson's grudge against Spiderman, we plumbed the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the years 2004 to 2018.

Our findings reveal the astonishing correlation coefficient of 0.8519781 and a p-value less than, well, a spider's appetite for insects. The deep statistical web weaved by our analysis demonstrates a compelling relationship between North Dakota residents' penchant for Googling Spiderman and their inclination to cast their ballots for Democratic senators. Yes, you heard that right – it seems that the iconic red-and-blue-clad crusader may have more influence in the political arena than we previously thought.

As we unravel this intriguing arachnoid enigma, we invite readers to not only ponder the political implications but also to appreciate the humor of this unexpected correlation. After all, it was high time for a study that truly captures the "web" of political interests in North Dakota, and we have finally untangled the threads of Spiderman's web in the state's electoral dynamics.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Ladies and gentlemen, arachnophobes and arachnophiles, buckle up as we embark on a web-slinging journey through the tangled intersection of politics and pop culture. When it comes to analyzing electoral trends, researchers often cast their nets far and wide, but seldom do they delve into the sticky world of superhero fandom. What if I told you that behind the scenes of North Dakota’s political landscape, a web-slinging hero may have silently been influencing voting patterns? Oh, the tangled web we weave when politicians and spider-themed vigilantes interleave!
As researchers, we are constantly on the hunt for unlikely connections and delightful surprises in our data. It is akin to stumbling upon a hidden trapdoor in a statistical mansion, only to find a masked crusader protecting ballots instead of jewels. Armed with our trusty statistical tools and unwavering dedication to uncovering the unexpected, we set out to investigate the curious relationship between Google searches for 'Spiderman' and Democrat votes in the great state of North Dakota.
They say that every vote counts, but who would have guessed that every web-slinging search also counts in the ballot box? It’s a classic case of "with great statistical power comes great responsibility," a concept not unfamiliar to our friendly neighborhood Spiderman. After all, with such a high correlation coefficient and an eerily minuscule p-value, this finding may just have us uttering, "Holy unexpected political influence, Batman!"
Join us as we untangle this web of intrigue, where state politics and internet curiosities intersect in a way that could make Dr. Octopus nod in approval. Who knew that North Dakota's political landscape held more surprises than the average Peter Parker plot twist? As Sky High Comics' resident superhero aficionado, Stan Lee, would say, "Make mine statistical significance!" So, grab your magnifying glasses and cue the dramatic music – it’s time to uncover the unexpected arachno-political dynamics no one knew they were missing.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The connection between online search patterns and political behavior has intrigued scholars for decades. In "Data Analysis in Political Science," Smith et al. delved into the impact of digital trends on voter decision-making, laying the groundwork for our study. Meanwhile, Doe's "The Digital Democracy Debate" provided a comprehensive overview of the influence of internet activities on political dynamics. However, none of these studies could have prepared us for the curious correlation we encountered between North Dakota's Senatorial elections and Google queries for 'Spiderman.'

As we journey into the realm of unconventional political influencers, we encounter an unexpected twist in the scholarly web. Jones et al. shed light on the significance of cultural phenomena in shaping electoral outcomes in their work "Cultural Signifiers and Voting Behavior," but never before has a web-slinging superhero featured prominently in such discussions. The gravity of our findings may even lead one to exclaim, "What do we have here? A statistical web of intrigue!"

In the continuing pursuit of understanding the seemingly inexplicable tie between Spiderman and North Dakota's Democratic votes, we draw insight from non-fiction works such as "Digital Democracy: The Impact of the Internet on Politics" by Mayo and "The Political Power of Pop Culture" by Johnson. These studies offer valuable perspectives on the intersection of popular culture and political engagement. Our findings, however, venture into uncharted territory, akin to stumbling upon a spider's remote-catching web – unexpected and more than a little sticky.

Turning to the realms of fiction, we encounter literary works that, while not directly related to our study, certainly lend an air of whimsy to our research. With titles like "The Amazing Spider-Man: The Ultimate Newspaper Comics Collection" and "Spider-Man: The Darkest Hours," we find ourselves spinning a narrative that is both captivating and, dare we say, a tad bit sensational. After all, what is research without a dash of melodrama and intrigue?

Additionally, our foray into the world of board games uncovers a playful parallel to our investigation. The classic game "Spider-Man: Web of Shadows" serves as a playful reminder that our quest to untangle the web of political and pop culture interaction is not too far removed from the realm of entertainment and amusement. As the old adage goes, "All work and no play makes for a dull research paper!"

In the spirit of uncovering hidden connections, perhaps it's fitting to leave readers with a parting thought: What do you get when you cross a North Dakotan's search for Spiderman with their voting behavior? A web of electoral intrigue that even Peter Parker couldn't untangle without his trusty statistics handbook.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in North Dakota and Google searches for 'spiderman'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends . You used data from 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]]
"Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota"

[[ABSTRACT]]
In this thought-provoking research, we delve into the unlikely but intriguing connection between the voting behavior of North Dakotans and their virtual fascination with the friendly neighborhood superhero, Spiderman. With a database as extensive as J. Jonah Jameson's grudge against Spiderman, we plumbed the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the years 2004 to 2018.

Our findings reveal the astonishing correlation coefficient of 0.8519781 and a p-value less than, well, a spider's appetite for insects. The deep statistical web weaved by our analysis demonstrates a compelling relationship between North Dakota residents' penchant for Googling Spiderman and their inclination to cast their ballots for Democratic senators. Yes, you heard that right – it seems that the iconic red-and-blue-clad crusader may have more influence in the political arena than we previously thought.

As we unravel this intriguing arachnoid enigma, we invite readers to not only ponder the political implications but also to appreciate the humor of this unexpected correlation. After all, it was high time for a study that truly captures the "web" of political interests in North Dakota, and we have finally untangled the threads of Spiderman's web in the state's electoral dynamics.

[[INTRODUCTION]]
Ladies and gentlemen, arachnophobes and arachnophiles, buckle up as we embark on a web-slinging journey through the tangled intersection of politics and pop culture. When it comes to analyzing electoral trends, researchers often cast their nets far and wide, but seldom do they delve into the sticky world of superhero fandom. What if I told you that behind the scenes of North Dakota’s political landscape, a web-slinging hero may have silently been influencing voting patterns? Oh, the tangled web we weave when politicians and spider-themed vigilantes interleave!
As researchers, we are constantly on the hunt for unlikely connections and delightful surprises in our data. It is akin to stumbling upon a hidden trapdoor in a statistical mansion, only to find a masked crusader protecting ballots instead of jewels. Armed with our trusty statistical tools and unwavering dedication to uncovering the unexpected, we set out to investigate the curious relationship between Google searches for 'Spiderman' and Democrat votes in the great state of North Dakota.
They say that every vote counts, but who would have guessed that every web-slinging search also counts in the ballot box? It’s a classic case of "with great statistical power comes great responsibility," a concept not unfamiliar to our friendly neighborhood Spiderman. After all, with such a high correlation coefficient and an eerily minuscule p-value, this finding may just have us uttering, "Holy unexpected political influence, Batman!"
Join us as we untangle this web of intrigue, where state politics and internet curiosities intersect in a way that could make Dr. Octopus nod in approval. Who knew that North Dakota's political landscape held more surprises than the average Peter Parker plot twist? As Sky High Comics' resident superhero aficionado, Stan Lee, would say, "Make mine statistical significance!" So, grab your magnifying glasses and cue the dramatic music – it’s time to uncover the unexpected arachno-political dynamics no one knew they were missing.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To commence our investigation into the politics of arachnids and superheroes, we adopted a methodology as meticulous as Spiderman's web-slinging acrobatics. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we embarked on an analytical journey spanning from 2004 to 2018, venturing into the depths of North Dakota's electoral and search engine landscapes.

First, we cast our net wide into the MIT Election Data and Science Lab, reeling in the data on Democrat votes for Senators in North Dakota. They say an election year is like a spider’s web – plenty of drama and surprises, with outcomes that can leave us spinning. With our statistical tools in hand, we spun our web of analysis around these electoral records, aiming to catch any unsuspecting correlations lurking in the political underbrush.

Next, like intrepid entomologists of the digital age, we scoured Google Trends for searches related to the iconic superhero, Spiderman, within the borders of North Dakota. We were determined to capture the elusive patterns of web-crawling curiosity and dissect the intricacies of internet spider-sense – all in the pursuit of uncovering the unexpected arachno-political dynamics that may be entangled within the minds of North Dakotans. Our search for correlations transformed into an adventure reminiscent of Spiderman tracking down his arch-nemesis through the urban jungle – a captivating narrative with each search term and every click.

Once these datasets were in our possession, we channelled our inner researchers with the tenacity of Peter Parker pursuing a breaking news story. Utilizing statistical software, we dived into the depths of analysis, constructing models as intricate as the designs in Spiderman's web shooters. We sought to unveil the relationship between the frequency of Google searches for 'Spiderman' and the propensity of North Dakotans to cast their votes for Democratic senators. Like an arachnologist examining spider silk under a microscope, we scrutinized the data to discern any threads of correlation weaving through our extensive dataset.

With rigorous testing and relentless pursuit of statistical significance, we proceeded to calculate the correlation coefficient and determine the p-value, akin to measuring the tensile strength of Spiderman's webs and the likelihood of their impact on the political fabric. The results we uncovered were nothing short of astounding – with a correlation coefficient akin to being caught in Spiderman's web and a p-value more diminutive than a radioactive spider bite. It became clear that the "spidey senses" of North Dakota residents, as reflected in their Google searches, may indeed have been intertwined with their political inclinations.

As we spun this intricate statistical web of analysis, we made every effort to approach the interplay between Google searches for 'Spiderman' and Democrat votes in North Dakota with a keen eye for detail and tongue firmly in cheek. After all, when uncovering the unexpected, a dash of humor is as essential as the web fluid in Spiderman's arsenal.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in North Dakota and Google searches for 'spiderman'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2004 to 2018, you found a correlation 0.8519781, r-squared of 0.7258668, and p < 0.05.

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

Here is the title and abstract of the paper:
[[TITLE]]
"Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota"

[[ABSTRACT]]
In this thought-provoking research, we delve into the unlikely but intriguing connection between the voting behavior of North Dakotans and their virtual fascination with the friendly neighborhood superhero, Spiderman. With a database as extensive as J. Jonah Jameson's grudge against Spiderman, we plumbed the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the years 2004 to 2018.

Our findings reveal the astonishing correlation coefficient of 0.8519781 and a p-value less than, well, a spider's appetite for insects. The deep statistical web weaved by our analysis demonstrates a compelling relationship between North Dakota residents' penchant for Googling Spiderman and their inclination to cast their ballots for Democratic senators. Yes, you heard that right – it seems that the iconic red-and-blue-clad crusader may have more influence in the political arena than we previously thought.

As we unravel this intriguing arachnoid enigma, we invite readers to not only ponder the political implications but also to appreciate the humor of this unexpected correlation. After all, it was high time for a study that truly captures the "web" of political interests in North Dakota, and we have finally untangled the threads of Spiderman's web in the state's electoral dynamics.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Ladies and gentlemen, arachnophobes and arachnophiles, buckle up as we embark on a web-slinging journey through the tangled intersection of politics and pop culture. When it comes to analyzing electoral trends, researchers often cast their nets far and wide, but seldom do they delve into the sticky world of superhero fandom. What if I told you that behind the scenes of North Dakota’s political landscape, a web-slinging hero may have silently been influencing voting patterns? Oh, the tangled web we weave when politicians and spider-themed vigilantes interleave!
As researchers, we are constantly on the hunt for unlikely connections and delightful surprises in our data. It is akin to stumbling upon a hidden trapdoor in a statistical mansion, only to find a masked crusader protecting ballots instead of jewels. Armed with our trusty statistical tools and unwavering dedication to uncovering the unexpected, we set out to investigate the curious relationship between Google searches for 'Spiderman' and Democrat votes in the great state of North Dakota.
They say that every vote counts, but who would have guessed that every web-slinging search also counts in the ballot box? It’s a classic case of "with great statistical power comes great responsibility," a concept not unfamiliar to our friendly neighborhood Spiderman. After all, with such a high correlation coefficient and an eerily minuscule p-value, this finding may just have us uttering, "Holy unexpected political influence, Batman!"
Join us as we untangle this web of intrigue, where state politics and internet curiosities intersect in a way that could make Dr. Octopus nod in approval. Who knew that North Dakota's political landscape held more surprises than the average Peter Parker plot twist? As Sky High Comics' resident superhero aficionado, Stan Lee, would say, "Make mine statistical significance!" So, grab your magnifying glasses and cue the dramatic music – it’s time to uncover the unexpected arachno-political dynamics no one knew they were missing.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The keen-eyed explorers of our research team set out on a statistical safari through the vast wilderness of data to uncover the remarkable correlation between Democrat votes for Senators in North Dakota and Google searches for 'Spiderman.' Armed with spreadsheets and a passion for uncovering the unexpected, we uncovered a spectacularly high correlation coefficient of 0.8519781. This finding packs quite a punch, and it's not just any ordinary spider bite!

Now, you may be wondering, "What is the probability of such a strong relationship occurring by mere chance?" Well, folks, buckle up as we reveal that our analysis also yielded an r-squared value of 0.7258668 and a p-value less than 0.05. In statistical terms, this means that the observed correlation is highly unlikely to be a fluke. Or as we like to say, the likelihood of Spiderman's influence on the ballot box being a mere coincidence is about as plausible as a spider deciding to become a fly's best friend.

Fig. 1 showcases the tightly knit relationship we found between the two variables. The scatterplot illustrates a clear positive trend, reminiscent of Spiderman's unwavering dedication to upholding justice – or in this case, inspiring North Dakotans to cast their ballots.

DAD JOKE TIME: Did you hear about the spider who went to the computer? He made a website! Just like the spiders in our data, this correlation has spun a web of fascination that even Charlotte would envy.

In conclusion, our findings provide compelling evidence of a robust connection between North Dakota's political landscape and the web-slinging superhero. Who would have thought that amidst the hustle and bustle of elections, Spiderman's influence loomed large like a gossamer thread in the wind? This unexpected discovery not only broadens our understanding of electoral dynamics but also adds a touch of whimsy to the intricate tapestry of political research.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in North Dakota and Google searches for 'spiderman'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota"

[[ABSTRACT]]
In this thought-provoking research, we delve into the unlikely but intriguing connection between the voting behavior of North Dakotans and their virtual fascination with the friendly neighborhood superhero, Spiderman. With a database as extensive as J. Jonah Jameson's grudge against Spiderman, we plumbed the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the years 2004 to 2018.

Our findings reveal the astonishing correlation coefficient of 0.8519781 and a p-value less than, well, a spider's appetite for insects. The deep statistical web weaved by our analysis demonstrates a compelling relationship between North Dakota residents' penchant for Googling Spiderman and their inclination to cast their ballots for Democratic senators. Yes, you heard that right – it seems that the iconic red-and-blue-clad crusader may have more influence in the political arena than we previously thought.

As we unravel this intriguing arachnoid enigma, we invite readers to not only ponder the political implications but also to appreciate the humor of this unexpected correlation. After all, it was high time for a study that truly captures the "web" of political interests in North Dakota, and we have finally untangled the threads of Spiderman's web in the state's electoral dynamics.

[[LITERATURE REVIEW]]
The connection between online search patterns and political behavior has intrigued scholars for decades. In "Data Analysis in Political Science," Smith et al. delved into the impact of digital trends on voter decision-making, laying the groundwork for our study. Meanwhile, Doe's "The Digital Democracy Debate" provided a comprehensive overview of the influence of internet activities on political dynamics. However, none of these studies could have prepared us for the curious correlation we encountered between North Dakota's Senatorial elections and Google queries for 'Spiderman.'
As we journey into the realm of unconventional political influencers, we encounter an unexpected twist in the scholarly web. Jones et al. shed light on the significance of cultural phenomena in shaping electoral outcomes in their work "Cultural Signifiers and Voting Behavior," but never before has a web-slinging superhero featured prominently in such discussions. The gravity of our findings may even lead one to exclaim, "What do we have here? A statistical web of intrigue!"
In the continuing pursuit of understanding the seemingly inexplicable tie between Spiderman and North Dakota's Democratic votes, we draw insight from non-fiction works such as "Digital Democracy: The Impact of the Internet on Politics" by Mayo and "The Political Power of Pop Culture" by Johnson. These studies offer valuable perspectives on the intersection of popular culture and political engagement. Our findings, however, venture into uncharted territory, akin to stumbling upon a spider's remote-catching web – unexpected and more than a little sticky.
Turning to the realms of fiction, we encounter literary works that, while not directly related to our study, certainly lend an air of whimsy to our research. With titles like "The Amazing Spider-Man: The Ultimate Newspaper Comics Collection" and "Spider-Man: The Darkest Hours," we find ourselves spinning a narrative that is both captivating and, dare we say, a tad bit sensational. After all, what is research without a dash of melodrama and intrigue?
Additionally, our foray into the world of board games uncovers a playful parallel to our investigation. The classic game "Spider-Man: Web of Shadows" serves as a playful reminder that our quest to untangle the web of political and pop culture interaction is not too far removed from the realm of entertainment and amusement. As the old adage goes, "All work and no play makes for a dull research paper!"
In the spirit of uncovering hidden connections, perhaps it's fitting to leave readers with a parting thought: What do you get when you cross a North Dakotan's search for Spiderman with their voting behavior? A web of electoral intrigue that even Peter Parker couldn't untangle without his trusty statistics handbook.

[[RESULTS]]
The keen-eyed explorers of our research team set out on a statistical safari through the vast wilderness of data to uncover the remarkable correlation between Democrat votes for Senators in North Dakota and Google searches for 'Spiderman.' Armed with spreadsheets and a passion for uncovering the unexpected, we uncovered a spectacularly high correlation coefficient of 0.8519781. This finding packs quite a punch, and it's not just any ordinary spider bite!
Now, you may be wondering, "What is the probability of such a strong relationship occurring by mere chance?" Well, folks, buckle up as we reveal that our analysis also yielded an r-squared value of 0.7258668 and a p-value less than 0.05. In statistical terms, this means that the observed correlation is highly unlikely to be a fluke. Or as we like to say, the likelihood of Spiderman's influence on the ballot box being a mere coincidence is about as plausible as a spider deciding to become a fly's best friend.
Fig. 1 showcases the tightly knit relationship we found between the two variables. The scatterplot illustrates a clear positive trend, reminiscent of Spiderman's unwavering dedication to upholding justice – or in this case, inspiring North Dakotans to cast their ballots.
DAD JOKE TIME: Did you hear about the spider who went to the computer? He made a website! Just like the spiders in our data, this correlation has spun a web of fascination that even Charlotte would envy.
In conclusion, our findings provide compelling evidence of a robust connection between North Dakota's political landscape and the web-slinging superhero. Who would have thought that amidst the hustle and bustle of elections, Spiderman's influence loomed large like a gossamer thread in the wind? This unexpected discovery not only broadens our understanding of electoral dynamics but also adds a touch of whimsy to the intricate tapestry of political research.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our research has not only stumbled upon a statistical web of intrigue but has also spun a compelling narrative surrounding the relationship between North Dakota's Senatorial elections and Google searches for 'Spiderman.' Building on the foundations laid by previous studies, such as the work of Smith et al. in "Data Analysis in Political Science" and Jones et al.'s exploration of cultural signifiers and voting behavior, our findings elevate the conversation to new heights and into unexpected arachnoid territory. It seems that Spiderman, with all his sticky situations, may hold more sway over North Dakotans than we ever imagined.

Our results align with prior research in the realm of digital trends and political behavior, demonstrating a significant correlation between online activities and voting patterns. With a correlation coefficient of 0.8519781, our findings confirm that North Dakota's virtual fascination with the arachnid superhero closely associates with their inclination to support Democratic candidates. This connection bears a resemblance to a well-crafted spiderweb – intricate, strong, and surprisingly effective in capturing the attention of voters.

DAD JOKE TIME: Why don't spiders get stuck in their own webs? Because they always take the sticky points seriously – just like our research, committed to untangling the complexities of statistical relationships with a touch of humor.

Furthermore, the robust statistical evidence, as indicated by the high r-squared value and the low p-value, reinforces the substantial nature of the relationship between Spiderman searches and voting behavior. Indeed, the likelihood of this correlation occurring by chance is as slim as an insect's chance of escaping the clutches of an expertly woven spider's web.

In light of this, our study offers a novel perspective on the interplay between popular culture and political engagement. Who would have thought that a web-slinging vigilante would emerge as an unlikely, yet influential, player in the political arena? This unexpected revelation adds a quirky charm to the realm of political research, proving that even in the staid realms of academia, there is space for a dash of comic book charisma.

Our findings enrich our understanding of how seemingly unrelated elements, much like a fly and a spider, can become entwined in an intricate dance. Analogous to Spiderman's uncanny ability to handle sticky situations with grace, we have delved into the tangled web of political interests and cultural fascinations, emerging with evidence that truly captures the essence of "arachno-politics."

With these results, we celebrate not only a successful uncovering of statistical spiderwebs but also an invitation to explore further the whimsical undercurrents that can shape the electoral landscape. As we navigate this uncharted terrain, laden with humor and statistical significance, we invite researchers to embrace the colorful, unexpected threads that weave through the fabric of our political world.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Democrat votes for Senators in North Dakota and Google searches for 'spiderman'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota"

[[ABSTRACT]]
In this thought-provoking research, we delve into the unlikely but intriguing connection between the voting behavior of North Dakotans and their virtual fascination with the friendly neighborhood superhero, Spiderman. With a database as extensive as J. Jonah Jameson's grudge against Spiderman, we plumbed the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the years 2004 to 2018.

Our findings reveal the astonishing correlation coefficient of 0.8519781 and a p-value less than, well, a spider's appetite for insects. The deep statistical web weaved by our analysis demonstrates a compelling relationship between North Dakota residents' penchant for Googling Spiderman and their inclination to cast their ballots for Democratic senators. Yes, you heard that right – it seems that the iconic red-and-blue-clad crusader may have more influence in the political arena than we previously thought.

As we unravel this intriguing arachnoid enigma, we invite readers to not only ponder the political implications but also to appreciate the humor of this unexpected correlation. After all, it was high time for a study that truly captures the "web" of political interests in North Dakota, and we have finally untangled the threads of Spiderman's web in the state's electoral dynamics.

[[INTRDUCTION]]
Ladies and gentlemen, arachnophobes and arachnophiles, buckle up as we embark on a web-slinging journey through the tangled intersection of politics and pop culture. When it comes to analyzing electoral trends, researchers often cast their nets far and wide, but seldom do they delve into the sticky world of superhero fandom. What if I told you that behind the scenes of North Dakota’s political landscape, a web-slinging hero may have silently been influencing voting patterns? Oh, the tangled web we weave when politicians and spider-themed vigilantes interleave!
As researchers, we are constantly on the hunt for unlikely connections and delightful surprises in our data. It is akin to stumbling upon a hidden trapdoor in a statistical mansion, only to find a masked crusader protecting ballots instead of jewels. Armed with our trusty statistical tools and unwavering dedication to uncovering the unexpected, we set out to investigate the curious relationship between Google searches for 'Spiderman' and Democrat votes in the great state of North Dakota.
They say that every vote counts, but who would have guessed that every web-slinging search also counts in the ballot box? It’s a classic case of "with great statistical power comes great responsibility," a concept not unfamiliar to our friendly neighborhood Spiderman. After all, with such a high correlation coefficient and an eerily minuscule p-value, this finding may just have us uttering, "Holy unexpected political influence, Batman!"
Join us as we untangle this web of intrigue, where state politics and internet curiosities intersect in a way that could make Dr. Octopus nod in approval. Who knew that North Dakota's political landscape held more surprises than the average Peter Parker plot twist? As Sky High Comics' resident superhero aficionado, Stan Lee, would say, "Make mine statistical significance!" So, grab your magnifying glasses and cue the dramatic music – it’s time to uncover the unexpected arachno-political dynamics no one knew they were missing.

[[RESULTS]]
The keen-eyed explorers of our research team set out on a statistical safari through the vast wilderness of data to uncover the remarkable correlation between Democrat votes for Senators in North Dakota and Google searches for 'Spiderman.' Armed with spreadsheets and a passion for uncovering the unexpected, we uncovered a spectacularly high correlation coefficient of 0.8519781. This finding packs quite a punch, and it's not just any ordinary spider bite!
Now, you may be wondering, "What is the probability of such a strong relationship occurring by mere chance?" Well, folks, buckle up as we reveal that our analysis also yielded an r-squared value of 0.7258668 and a p-value less than 0.05. In statistical terms, this means that the observed correlation is highly unlikely to be a fluke. Or as we like to say, the likelihood of Spiderman's influence on the ballot box being a mere coincidence is about as plausible as a spider deciding to become a fly's best friend.
Fig. 1 showcases the tightly knit relationship we found between the two variables. The scatterplot illustrates a clear positive trend, reminiscent of Spiderman's unwavering dedication to upholding justice – or in this case, inspiring North Dakotans to cast their ballots.
DAD JOKE TIME: Did you hear about the spider who went to the computer? He made a website! Just like the spiders in our data, this correlation has spun a web of fascination that even Charlotte would envy.
In conclusion, our findings provide compelling evidence of a robust connection between North Dakota's political landscape and the web-slinging superhero. Who would have thought that amidst the hustle and bustle of elections, Spiderman's influence loomed large like a gossamer thread in the wind? This unexpected discovery not only broadens our understanding of electoral dynamics but also adds a touch of whimsy to the intricate tapestry of political research.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In light of our groundbreaking findings, it's safe to say that the influence of Spiderman on North Dakota's political landscape is as real as a radioactive spider bite! Our results not only demonstrate a compelling link between Democrat votes for Senators and Google searches for 'Spiderman,' but they also highlight the importance of considering unconventional variables in electoral analyses. After all, who would have thought that superheroes could swing their way into ballot boxes alongside politicians?

DAD JOKE TIME: Why did the spider become a web designer? Because he had great "site" qualities! Just like our surprising research findings, this joke weaves together unexpected elements for a delightful twist.

Our study provides a comical yet thought-provoking glimpse into the intricate web of influences that shape voters' decisions. The statistical significance of our results is as undeniable as Spiderman's commitment to fighting crime. We've truly unearthed a hidden treasure within the labyrinth of political research, much like stumbling upon a spider's intricate web hidden in the bushes.

With such a high correlation coefficient and an impressively low p-value, we can confidently conclude that no stone – or in this case, no spider web – was left unturned in our pursuit of uncovering this unlikely connection. Therefore, we can unequivocally declare that no further research is needed in this particular area. We've caught this political spider in our intellectual web, and it's high time to spin a new tale in the world of research and statistics.


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 Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Arachnid Anthropology and Political Science


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota. Respond only with the name of a fictional organization.

ChatGPT:

The Society for the Advancement of Comic Book and Political Research


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Arachno-politics: An Electoral Analysis of Spiderman Searches and Democrat Votes in North Dakota with an abstract of In this thought-provoking research, we delve into the unlikely but intriguing connection between the voting behavior of North Dakotans and their virtual fascination with the friendly neighborhood superhero, Spiderman. With a database as extensive as J. Jonah Jameson's grudge against Spiderman, we plumbed the MIT Election Data and Science Lab, the Harvard Dataverse, and Google Trends for the years 2004 to 2018.
Our findings reveal the astonishing correlation coefficient of 0.8519781 and a p-value less than, well, a spider's appetite for insects. The deep statistical web weaved by our analysis demonstrates a compelling relationship between North Dakota residents' penchant for Googling Spiderman and their inclination to cast their ballots for Democratic senators. Yes, you heard that right – it seems that the iconic red-and-blue-clad crusader may have more influence in the political arena than we previously thought.
As we unravel this intriguing arachnoid enigma, we invite readers to not only ponder the political implications but also to appreciate the humor of this unexpected correlation. After all, it was high time for a study that truly captures the "web" of political interests in North Dakota, and we have finally untangled the threads of Spiderman's web in the state's electoral dynamics.

ChatGPT:

Spiderman, Spider-Man, electoral analysis, voting behavior, North Dakota, correlation coefficient, p-value, MIT Election Data and Science Lab, Harvard Dataverse, Google Trends, Democratic senators, political influence, political implications, web of political interests, electoral dynamics

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

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

See what else correlates with Google searches for 'spiderman'

Correlation r = 0.8519781 (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 = 0.7258668 (Coefficient of determination)
This means 72.6% of the change in the one variable (i.e., Google searches for 'spiderman') is predictable based on the change in the other (i.e., Votes for Democratic Senators in North Dakota) over the 6 years from 2004 through 2018.

p < 0.05, which statistically significant(Null hypothesis significance test)
The p-value is 0.031. 0.0312440883233149650000000000
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 0.85 in 3.1% of random cases. Said differently, if you correlated 32 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.

[ 0.13, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200420062010201220162018
Votes for Democratic Senators in North Dakota (Total votes)2121431501465295516133758116144376
Google searches for 'spiderman' (Rel. search volume)27.583317.2514.08332116.916718




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 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([212143,150146,52955,161337,58116,144376,])
array_2 = np.array([27.5833,17.25,14.0833,21,16.9167,18,])
array_1_name = "Votes for Democratic Senators in North Dakota"
array_2_name = "Google searches for 'spiderman'"

# 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?

Cheers to you for rating this correlation!


Correlation ID: 5616 · Black Variable ID: 26293 · Red Variable ID: 1527
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0