about · email me · subscribe
Spurious correlation #5,067 · 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 Arizona and the second variable is Google searches for 'E.T. phone home'.  The chart goes from 2004 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As Republican votes for Senators in Arizona decreased, it led to a shortage of communication devices in the state. With fewer resources available, E.T. realized that phoning home from Arizona was going to be more expensive, so he decided to wait until he got to a friendlier (and cheaper) area. As a result, Google searches for 'E.T. phone home' decreased as Arizonans unwittingly contributed to E.T.'s intergalactic long-distance cost-saving efforts.

Model: dalle-3
Prompt: Generate an image of the Arizona desert at night, with a unique cubist interpretation. Show an alien figure resembling E.T. holding a glowing finger towards the starry sky, as if contemplating whether to make a long-distance call or not. Creative geometric shapes and fragmented forms should be used to represent the landscape, communication devices, and diminishing Republican votes in a visually captivating way. 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 Arizona and Google searches for 'E.T. phone home'. 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: Pop art Futuristic Magic realism Cyberpunk Cubism
ChatGPT: Cubism

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 Arizona and Google searches for 'E.T. phone home', in the following situation: As Republican votes for Senators in Arizona decreased, it led to a shortage of communication devices in the state. With fewer resources available, E.T. realized that phoning home from Arizona was going to be more expensive, so he decided to wait until he got to a friendlier (and cheaper) area. As a result, Google searches for 'E.T. phone home' decreased as Arizonans unwittingly contributed to E.T.'s intergalactic long-distance cost-saving efforts.. Keep the description simple.
ChatGPT: In Arizona, as Republican votes for Senators decreased, communication devices became scarce. E.T., realizing long-distance calls would be costly, decided to wait to phone home. Google searches for 'E.T. phone home' decreased as Arizonans unintentionally helped E.T. save on intergalactic calls.

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: [ Cubism ] and depicting this scene: In Arizona, as Republican votes for Senators decreased, communication devices became scarce. E.T., realizing long-distance calls would be costly, decided to wait to phone home. Google searches for 'E.T. phone home' decreased as Arizonans unintentionally helped E.T. save on intergalactic calls. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of the Arizona desert at night, with a unique cubist interpretation. Show an alien figure resembling E.T. holding a glowing finger towards the starry sky, as if contemplating whether to make a long-distance call or not. Creative geometric shapes and fragmented forms should be used to represent the landscape, communication devices, and diminishing Republican votes in a visually captivating way.

*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 Republican votes for Senators in Arizona caused E.T. phone home (Google searches for 'E.T. phone home') to decrease.

AI academic paper

(Because p < 0.01)
ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona

The Journal of Intergalactic Political Science

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. Make lots of jokes, goofy observations, and puns.

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 0.9415277 and p < 0.01 for 2004 to 2020.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona"

[[ABSTRACT]]
In this paper, we present the surprising findings of our investigation into the correlation between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. While the connection may seem out of this world, our research team delved into the data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends and discovered a correlation coefficient of 0.9415277 with a statistically significant significance level (p < 0.01) for the period spanning from 2004 to 2020. Our analysis uncovers a cosmic relationship between extraterrestrial queries and political preferences, shedding light on the unexpected intersections of pop culture and electoral behavior. We explore the potential implications of these findings and astutely ponder the question: Is there truly a 'political alien' influence at play? Join us on this out-of-this-world journey as we bridge the gap between politics and popular culture.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona"

[[ABSTRACT]]
In this paper, we present the surprising findings of our investigation into the correlation between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. While the connection may seem out of this world, our research team delved into the data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends and discovered a correlation coefficient of 0.9415277 with a statistically significant significance level (p < 0.01) for the period spanning from 2004 to 2020. Our analysis uncovers a cosmic relationship between extraterrestrial queries and political preferences, shedding light on the unexpected intersections of pop culture and electoral behavior. We explore the potential implications of these findings and astutely ponder the question: Is there truly a 'political alien' influence at play? Join us on this out-of-this-world journey as we bridge the gap between politics and popular culture.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Greetings, Earthlings and fellow cosmic enthusiasts! Prepare yourselves for a journey into the mysterious realms of intergalactic intrigue and political punditry. In this paper, we embark on an odyssey of statistical exploration, aiming to unearth the improbable union between Republican Senatorial preferences in the grand state of Arizona and the whispered echoes of "E.T. phone home" reverberating across the digital cosmos.

As we traverse the uncharted territories of data analysis, our stellar team has been captivated by the enigmatic dance of numbers and inquiries, venturing where few researchers have dared to tread. Drawing upon the illustrious resources of MIT Election Data and Science Lab, Harvard Dataverse, and the cosmic constellation of Google Trends, we discover a correlation coefficient of 0.9415277, illuminating a connection that defies conventional wisdom and gravitational pull.

While some may find themselves lost in the vastness of this unfathomable correlation, we approach this quest with humor and humility, recognizing that statistical associations can sometimes be as elusive as a UFO sighting. With a significance level (p < 0.01) that twinkles like a distant star, we are left to ponder if there truly exists a cosmic force influencing the political predilections of the Grand Canyon State.

Hold onto your telescopes, dear readers, for the symbiotic resonance of extraterrestrial musings and partisan persuasions beckons us to contemplate the celestial forces that intertwine with the earthly machinations of democracy. Join us as we scrutinize the statistical stardust and mesh the worlds of pop culture and political proclivities, with a dash of scientific skepticism and a hearty serving of cosmic curiosity. Let our research launch you into orbit as we seek to unravel the cosmic question: Is there an otherworldly hand guiding the ballot box? The truth is out there, and we aim to seize it with the outstretched arms of data, analysis, and the occasional pun or two.

Take off with us on this celestial escapade, and together, let us boldly go where no political scientist has gone before!


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. 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 a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
"ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona"

[[ABSTRACT]]
In this paper, we present the surprising findings of our investigation into the correlation between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. While the connection may seem out of this world, our research team delved into the data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends and discovered a correlation coefficient of 0.9415277 with a statistically significant significance level (p < 0.01) for the period spanning from 2004 to 2020. Our analysis uncovers a cosmic relationship between extraterrestrial queries and political preferences, shedding light on the unexpected intersections of pop culture and electoral behavior. We explore the potential implications of these findings and astutely ponder the question: Is there truly a 'political alien' influence at play? Join us on this out-of-this-world journey as we bridge the gap between politics and popular culture.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Greetings, Earthlings and fellow cosmic enthusiasts! Prepare yourselves for a journey into the mysterious realms of intergalactic intrigue and political punditry. In this paper, we embark on an odyssey of statistical exploration, aiming to unearth the improbable union between Republican Senatorial preferences in the grand state of Arizona and the whispered echoes of "E.T. phone home" reverberating across the digital cosmos.
As we traverse the uncharted territories of data analysis, our stellar team has been captivated by the enigmatic dance of numbers and inquiries, venturing where few researchers have dared to tread. Drawing upon the illustrious resources of MIT Election Data and Science Lab, Harvard Dataverse, and the cosmic constellation of Google Trends, we discover a correlation coefficient of 0.9415277, illuminating a connection that defies conventional wisdom and gravitational pull.
While some may find themselves lost in the vastness of this unfathomable correlation, we approach this quest with humor and humility, recognizing that statistical associations can sometimes be as elusive as a UFO sighting. With a significance level (p < 0.01) that twinkles like a distant star, we are left to ponder if there truly exists a cosmic force influencing the political predilections of the Grand Canyon State.
Hold onto your telescopes, dear readers, for the symbiotic resonance of extraterrestrial musings and partisan persuasions beckons us to contemplate the celestial forces that intertwine with the earthly machinations of democracy. Join us as we scrutinize the statistical stardust and mesh the worlds of pop culture and political proclivities, with a dash of scientific skepticism and a hearty serving of cosmic curiosity. Let our research launch you into orbit as we seek to unravel the cosmic question: Is there an otherworldly hand guiding the ballot box? The truth is out there, and we aim to seize it with the outstretched arms of data, analysis, and the occasional pun or two.
Take off with us on this celestial escapade, and together, let us boldly go where no political scientist has gone before!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith and Doe," the authors find a correlation between search engine queries and political behaviors, shedding light on the interconnectedness of digital footprints and public opinion. Similarly, Jones et al. offer insights into the influence of pop culture on political affiliations in their seminal work "Cultural Clout: From Polls to Popcorn."

Turning the pages to non-fiction, "The Data Delusion" by Stat Man presents a cautionary tale of misinterpreting statistical relationships, reminding us that correlation does not necessarily imply causation. On a more cosmic note, "Extraterrestrial Elections: Unveiling The Alien Agenda" by GalaxyQuest delves into the interstellar influences on terrestrial politics, offering a whimsical yet thought-provoking take on electoral enigmas.

In the world of fiction, the classic novel "Alien Allure: Tales from the Political Twilight Zone" by Speculative Scribe weaves a tantalizing tapestry of extraterrestrial intrigue and otherworldly machinations within the political sphere. On a lighter note, "The Hitchhiker's Guide to Electoral Anomalies" by Paradox Press navigates through the absurdities of political oddities with a touch of intergalactic humor, providing a satirical glimpse into the cosmic chaos of campaign trails.

As we traverse the digital cosmos, let us not forget the iconic internet meme "E.T. Says Vote" which, with its whimsical appeal, merges the worlds of fictional aliens and political participation. The online sensation "Galactic Governance or Bust: The Interstellar Campaign Trail" further blurs the lines between reality and science fiction, eliciting chuckles and contemplation in equal measure.

With a gusto reminiscent of a rocket launch, let us propel into the quirky realms of statistical scrutiny and cosmic contemplation, as we unravel the puzzling nexus between 'E.T. phone home' and Republican Senatorial preferences in Arizona. Here goes nothing – or perhaps, everything!


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends . You used data from 2004 to 2020

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona"

[[ABSTRACT]]
In this paper, we present the surprising findings of our investigation into the correlation between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. While the connection may seem out of this world, our research team delved into the data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends and discovered a correlation coefficient of 0.9415277 with a statistically significant significance level (p < 0.01) for the period spanning from 2004 to 2020. Our analysis uncovers a cosmic relationship between extraterrestrial queries and political preferences, shedding light on the unexpected intersections of pop culture and electoral behavior. We explore the potential implications of these findings and astutely ponder the question: Is there truly a 'political alien' influence at play? Join us on this out-of-this-world journey as we bridge the gap between politics and popular culture.

[[INTRODUCTION]]
Greetings, Earthlings and fellow cosmic enthusiasts! Prepare yourselves for a journey into the mysterious realms of intergalactic intrigue and political punditry. In this paper, we embark on an odyssey of statistical exploration, aiming to unearth the improbable union between Republican Senatorial preferences in the grand state of Arizona and the whispered echoes of "E.T. phone home" reverberating across the digital cosmos.
As we traverse the uncharted territories of data analysis, our stellar team has been captivated by the enigmatic dance of numbers and inquiries, venturing where few researchers have dared to tread. Drawing upon the illustrious resources of MIT Election Data and Science Lab, Harvard Dataverse, and the cosmic constellation of Google Trends, we discover a correlation coefficient of 0.9415277, illuminating a connection that defies conventional wisdom and gravitational pull.
While some may find themselves lost in the vastness of this unfathomable correlation, we approach this quest with humor and humility, recognizing that statistical associations can sometimes be as elusive as a UFO sighting. With a significance level (p < 0.01) that twinkles like a distant star, we are left to ponder if there truly exists a cosmic force influencing the political predilections of the Grand Canyon State.
Hold onto your telescopes, dear readers, for the symbiotic resonance of extraterrestrial musings and partisan persuasions beckons us to contemplate the celestial forces that intertwine with the earthly machinations of democracy. Join us as we scrutinize the statistical stardust and mesh the worlds of pop culture and political proclivities, with a dash of scientific skepticism and a hearty serving of cosmic curiosity. Let our research launch you into orbit as we seek to unravel the cosmic question: Is there an otherworldly hand guiding the ballot box? The truth is out there, and we aim to seize it with the outstretched arms of data, analysis, and the occasional pun or two.
Take off with us on this celestial escapade, and together, let us boldly go where no political scientist has gone before!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Preparing for our otherworldly scientific expedition, our research team donned their metaphorical spacesuits and ignited the thrusters of data collection. To uncover the hidden link between Republican votes for Senators in Arizona and the cosmic echoes of "E.T. phone home," we employed a multifaceted and intergalactic approach. Our methodology blended the rigor of statistical analysis with the adventurous spirit of the space cowboy, or should we say, "space cowboy-corr-recting for confounding variables" (p < 0.05).

Firstly, the intrepid members of our team delved into the treasure trove of the MIT Election Data and Science Lab, mining the political bedrock of Senatorial voting patterns with the precision of asteroid prospectors. Equipped with an array of satellite data, we charted the trajectory of Republican votes through the terrestrial landscape of Arizona, navigating past potential meteorological interference – after all, it's important to safeguard against those tricky rogue variables attempting to eclipse our analysis.

Next, harnessing the celestial insights afforded by Google Trends, we cast our gaze towards the digital firmament in search of interstellar patterns. Here, we meticulously tracked the fluctuations in searches for the iconic phrase "E.T. phone home," safeguarding against any comical misinterpretation of extraterrestrial communiqués or spurious signals from the depths of hyperspace.

Our temporal lens extended across the epochs from 2004 to 2020, encompassing a cosmic tapestry of elections, cultural phenomena, and the ever-changing constellations of search engine behavior. The all-encompassing scope of our investigation aimed to capture the pulsating rhythms of political tides and the echoes of celestial musings amidst the ebb and flow of cultural zeitgeist.

To navigate through the asteroid field of potential confounders, we gracefully piloted our statistical spacecraft, employing the venerable tools of correlation analysis, regression models, and a dash of dimensional reduction – because who doesn't appreciate a good reduction when dealing with cosmic complexities? Our orbital calculations yielded a correlation coefficient of 0.9415277, blazing across the data like a shooting star leaving a trail of statistical stardust, accompanied by a significance level (p < 0.01) that glimmered brighter than a supernova.

As we hurtled through the galaxies of empirical inquiry, we remain cognizant of our limitations and the potential pitfalls of sifting through vast cosmic datasets. Yet, armed with the prowess of scientific methodology and a keen eye for the quirks of the extraterrestrial-political nexus, our research thrusts into the astral unknown, capturing the essence of statistical galactic dance in its most celestial form.

With humor as our copilot and curiosity as our guiding star, we traverse the methods of data mining, statistical inference, and cosmic contemplation, seeking to illuminate the unsuspected cosmic connections that shape the terrestrial theater of democracy. As we prepare to unveil our findings, we invite you, dear readers, to step aboard our starship, propelled by the gravitational pull of empirical inquiry and the occasional pun that twinkles like a far-off celestial body. Together, let us venture forth to grapple with the cosmos and its unlikely entanglements with political preferences, unveiling the patterns that defy earthly logic and signaling our own celestial communique to the scientific community.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2004 to 2020, you found a correlation 0.9415277, r-squared of 0.8864744, 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]]
"ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona"

[[ABSTRACT]]
In this paper, we present the surprising findings of our investigation into the correlation between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. While the connection may seem out of this world, our research team delved into the data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends and discovered a correlation coefficient of 0.9415277 with a statistically significant significance level (p < 0.01) for the period spanning from 2004 to 2020. Our analysis uncovers a cosmic relationship between extraterrestrial queries and political preferences, shedding light on the unexpected intersections of pop culture and electoral behavior. We explore the potential implications of these findings and astutely ponder the question: Is there truly a 'political alien' influence at play? Join us on this out-of-this-world journey as we bridge the gap between politics and popular culture.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Greetings, Earthlings and fellow cosmic enthusiasts! Prepare yourselves for a journey into the mysterious realms of intergalactic intrigue and political punditry. In this paper, we embark on an odyssey of statistical exploration, aiming to unearth the improbable union between Republican Senatorial preferences in the grand state of Arizona and the whispered echoes of "E.T. phone home" reverberating across the digital cosmos.
As we traverse the uncharted territories of data analysis, our stellar team has been captivated by the enigmatic dance of numbers and inquiries, venturing where few researchers have dared to tread. Drawing upon the illustrious resources of MIT Election Data and Science Lab, Harvard Dataverse, and the cosmic constellation of Google Trends, we discover a correlation coefficient of 0.9415277, illuminating a connection that defies conventional wisdom and gravitational pull.
While some may find themselves lost in the vastness of this unfathomable correlation, we approach this quest with humor and humility, recognizing that statistical associations can sometimes be as elusive as a UFO sighting. With a significance level (p < 0.01) that twinkles like a distant star, we are left to ponder if there truly exists a cosmic force influencing the political predilections of the Grand Canyon State.
Hold onto your telescopes, dear readers, for the symbiotic resonance of extraterrestrial musings and partisan persuasions beckons us to contemplate the celestial forces that intertwine with the earthly machinations of democracy. Join us as we scrutinize the statistical stardust and mesh the worlds of pop culture and political proclivities, with a dash of scientific skepticism and a hearty serving of cosmic curiosity. Let our research launch you into orbit as we seek to unravel the cosmic question: Is there an otherworldly hand guiding the ballot box? The truth is out there, and we aim to seize it with the outstretched arms of data, analysis, and the occasional pun or two.
Take off with us on this celestial escapade, and together, let us boldly go where no political scientist has gone before!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our investigation into the relationship between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home' has unearthed some truly extraterrestrial findings. With a statistically significant significance level (p < 0.01), our research team observed a correlation coefficient of 0.9415277 and an r-squared of 0.8864744 from 2004 to 2020. This cosmic correlation suggests a strong connection between these two seemingly unrelated phenomena, leaving us starry-eyed and scratching our heads in contemplation.

Fig. 1 showcases the striking correlation between these variables, resembling a celestial alignment that would make astronomers envious. The data points align with the precision of a well-calibrated telescope, depicting a trend that seems straight out of a science fiction plot. It's clear that there's more to this political puzzle than meets the eye, and our findings point to a gravitational pull between the allure of extraterrestrial queries and the steadfastness of partisan preferences.

As we delve into the depths of statistical analysis, one cannot help but marvel at the cosmic dance of numbers and inquiries, much like celestial bodies twirling through the vast expanse of space. The significance of this correlation echoes across the cosmos of political research, prompting us to consider the implications and ponder the cosmic conundrum: Could there be "alien" influences permeating the electoral landscape of Arizona?

The wealth of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends has provided us with a telescope to peer into this nebulous nexus of pop culture and political pulsations. While our findings may appear as unlikely as a UFO sighting in the desert night sky, it's precisely these unexpected connections that remind us of the multifaceted nature of human behavior and the cosmic wonders of statistical analysis.

In the grand tradition of scientific inquiry, we invite our fellow cosmic enthusiasts to join us in contemplating the cosmic question that has emerged from our research: Is there an otherworldly force at play in the realm of electoral preferences, or is this simply a statistical anomaly that defies earthly explanation? The truth may not be light-years away, but it certainly lies within the depths of our data, teasing us with the prospect of unraveling the cosmic mysteries that enchant our scholarly pursuits.

As we wrap up this otherworldly odyssey of statistical discovery, we urge our readers to keep an open mind and a keen eye on the intergalactic interplay of statistics and human behavior. The universe of research holds many surprises, and our exploration of the connection between 'E.T. phone home' searches and Republican votes in Arizona is a testament to the cosmic spectacle that unfolds when statistical analysis meets the quirks of human curiosity and the whims of political preference.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona"

[[ABSTRACT]]
In this paper, we present the surprising findings of our investigation into the correlation between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. While the connection may seem out of this world, our research team delved into the data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends and discovered a correlation coefficient of 0.9415277 with a statistically significant significance level (p < 0.01) for the period spanning from 2004 to 2020. Our analysis uncovers a cosmic relationship between extraterrestrial queries and political preferences, shedding light on the unexpected intersections of pop culture and electoral behavior. We explore the potential implications of these findings and astutely ponder the question: Is there truly a 'political alien' influence at play? Join us on this out-of-this-world journey as we bridge the gap between politics and popular culture.

[[LITERATURE REVIEW]]
In "Smith and Doe," the authors find a correlation between search engine queries and political behaviors, shedding light on the interconnectedness of digital footprints and public opinion. Similarly, Jones et al. offer insights into the influence of pop culture on political affiliations in their seminal work "Cultural Clout: From Polls to Popcorn."
Turning the pages to non-fiction, "The Data Delusion" by Stat Man presents a cautionary tale of misinterpreting statistical relationships, reminding us that correlation does not necessarily imply causation. On a more cosmic note, "Extraterrestrial Elections: Unveiling The Alien Agenda" by GalaxyQuest delves into the interstellar influences on terrestrial politics, offering a whimsical yet thought-provoking take on electoral enigmas.
In the world of fiction, the classic novel "Alien Allure: Tales from the Political Twilight Zone" by Speculative Scribe weaves a tantalizing tapestry of extraterrestrial intrigue and otherworldly machinations within the political sphere. On a lighter note, "The Hitchhiker's Guide to Electoral Anomalies" by Paradox Press navigates through the absurdities of political oddities with a touch of intergalactic humor, providing a satirical glimpse into the cosmic chaos of campaign trails.
As we traverse the digital cosmos, let us not forget the iconic internet meme "E.T. Says Vote" which, with its whimsical appeal, merges the worlds of fictional aliens and political participation. The online sensation "Galactic Governance or Bust: The Interstellar Campaign Trail" further blurs the lines between reality and science fiction, eliciting chuckles and contemplation in equal measure.
With a gusto reminiscent of a rocket launch, let us propel into the quirky realms of statistical scrutiny and cosmic contemplation, as we unravel the puzzling nexus between 'E.T. phone home' and Republican Senatorial preferences in Arizona. Here goes nothing – or perhaps, everything!

[[RESULTS]]
Our investigation into the relationship between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home' has unearthed some truly extraterrestrial findings. With a statistically significant significance level (p < 0.01), our research team observed a correlation coefficient of 0.9415277 and an r-squared of 0.8864744 from 2004 to 2020. This cosmic correlation suggests a strong connection between these two seemingly unrelated phenomena, leaving us starry-eyed and scratching our heads in contemplation.
Fig. 1 showcases the striking correlation between these variables, resembling a celestial alignment that would make astronomers envious. The data points align with the precision of a well-calibrated telescope, depicting a trend that seems straight out of a science fiction plot. It's clear that there's more to this political puzzle than meets the eye, and our findings point to a gravitational pull between the allure of extraterrestrial queries and the steadfastness of partisan preferences.
As we delve into the depths of statistical analysis, one cannot help but marvel at the cosmic dance of numbers and inquiries, much like celestial bodies twirling through the vast expanse of space. The significance of this correlation echoes across the cosmos of political research, prompting us to consider the implications and ponder the cosmic conundrum: Could there be "alien" influences permeating the electoral landscape of Arizona?
The wealth of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends has provided us with a telescope to peer into this nebulous nexus of pop culture and political pulsations. While our findings may appear as unlikely as a UFO sighting in the desert night sky, it's precisely these unexpected connections that remind us of the multifaceted nature of human behavior and the cosmic wonders of statistical analysis.
In the grand tradition of scientific inquiry, we invite our fellow cosmic enthusiasts to join us in contemplating the cosmic question that has emerged from our research: Is there an otherworldly force at play in the realm of electoral preferences, or is this simply a statistical anomaly that defies earthly explanation? The truth may not be light-years away, but it certainly lies within the depths of our data, teasing us with the prospect of unraveling the cosmic mysteries that enchant our scholarly pursuits.
As we wrap up this otherworldly odyssey of statistical discovery, we urge our readers to keep an open mind and a keen eye on the intergalactic interplay of statistics and human behavior. The universe of research holds many surprises, and our exploration of the connection between 'E.T. phone home' searches and Republican votes in Arizona is a testament to the cosmic spectacle that unfolds when statistical analysis meets the quirks of human curiosity and the whims of political preference.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

The results of our study have unearthed a correlation that is truly out of this world. Our findings support the previous research on the interconnectedness of digital footprints and public opinion, as well as the influence of pop culture on political affiliations. We have juxtaposed these serious studies with a sprinkle of intergalactic humor, as we navigated through the statistical cosmos to unravel the cosmic mysteries of electoral enigmas.

Our cosmic correlation coefficient of 0.9415277 and a statistically significant significance level (p < 0.01) have revealed a celestial alignment between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. Just like astronomers tracking the movements of celestial bodies, our data points create a pattern that seems straight out of a science fiction plot.

The significance of this correlation echoes across the cosmos of political research, prompting a satirical glimpse into the cosmic chaos of the campaign trails. Our findings leave us starry-eyed and scratching our heads in contemplation, as we ponder the question: Is there truly a 'political alien' influence at play?

While our results may seem as unlikely as a UFO sighting in the desert night sky, it's precisely these unexpected connections that remind us of the multifaceted nature of human behavior and the cosmic wonders of statistical analysis. The universe of research holds many surprises, and our exploration of the connection between 'E.T. phone home' searches and Republican votes in Arizona is a testament to the cosmic spectacle that unfolds when statistical analysis meets the quirks of human curiosity and the whims of political preference.

In the grand tradition of scientific inquiry, we invite our fellow cosmic enthusiasts to join us in contemplating the cosmic question that has emerged from our research: Is there an otherworldly force at play in the realm of electoral preferences, or is this simply a statistical anomaly that defies earthly explanation? The truth may not be light-years away, but it certainly lies within the depths of our data, teasing us with the prospect of unraveling the cosmic mysteries that enchant our scholarly pursuits.

As we wrap up this otherworldly odyssey of statistical discovery, we urge our readers to keep an open mind and a keen eye on the intergalactic interplay of statistics and human behavior. The universe of research holds many surprises, and our findings can be added as another testament to the universal puzzles that intrigue us all.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona"

[[ABSTRACT]]
In this paper, we present the surprising findings of our investigation into the correlation between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. While the connection may seem out of this world, our research team delved into the data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends and discovered a correlation coefficient of 0.9415277 with a statistically significant significance level (p < 0.01) for the period spanning from 2004 to 2020. Our analysis uncovers a cosmic relationship between extraterrestrial queries and political preferences, shedding light on the unexpected intersections of pop culture and electoral behavior. We explore the potential implications of these findings and astutely ponder the question: Is there truly a 'political alien' influence at play? Join us on this out-of-this-world journey as we bridge the gap between politics and popular culture.

[[INTRDUCTION]]
Greetings, Earthlings and fellow cosmic enthusiasts! Prepare yourselves for a journey into the mysterious realms of intergalactic intrigue and political punditry. In this paper, we embark on an odyssey of statistical exploration, aiming to unearth the improbable union between Republican Senatorial preferences in the grand state of Arizona and the whispered echoes of "E.T. phone home" reverberating across the digital cosmos.
As we traverse the uncharted territories of data analysis, our stellar team has been captivated by the enigmatic dance of numbers and inquiries, venturing where few researchers have dared to tread. Drawing upon the illustrious resources of MIT Election Data and Science Lab, Harvard Dataverse, and the cosmic constellation of Google Trends, we discover a correlation coefficient of 0.9415277, illuminating a connection that defies conventional wisdom and gravitational pull.
While some may find themselves lost in the vastness of this unfathomable correlation, we approach this quest with humor and humility, recognizing that statistical associations can sometimes be as elusive as a UFO sighting. With a significance level (p < 0.01) that twinkles like a distant star, we are left to ponder if there truly exists a cosmic force influencing the political predilections of the Grand Canyon State.
Hold onto your telescopes, dear readers, for the symbiotic resonance of extraterrestrial musings and partisan persuasions beckons us to contemplate the celestial forces that intertwine with the earthly machinations of democracy. Join us as we scrutinize the statistical stardust and mesh the worlds of pop culture and political proclivities, with a dash of scientific skepticism and a hearty serving of cosmic curiosity. Let our research launch you into orbit as we seek to unravel the cosmic question: Is there an otherworldly hand guiding the ballot box? The truth is out there, and we aim to seize it with the outstretched arms of data, analysis, and the occasional pun or two.
Take off with us on this celestial escapade, and together, let us boldly go where no political scientist has gone before!

[[RESULTS]]
Our investigation into the relationship between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home' has unearthed some truly extraterrestrial findings. With a statistically significant significance level (p < 0.01), our research team observed a correlation coefficient of 0.9415277 and an r-squared of 0.8864744 from 2004 to 2020. This cosmic correlation suggests a strong connection between these two seemingly unrelated phenomena, leaving us starry-eyed and scratching our heads in contemplation.
Fig. 1 showcases the striking correlation between these variables, resembling a celestial alignment that would make astronomers envious. The data points align with the precision of a well-calibrated telescope, depicting a trend that seems straight out of a science fiction plot. It's clear that there's more to this political puzzle than meets the eye, and our findings point to a gravitational pull between the allure of extraterrestrial queries and the steadfastness of partisan preferences.
As we delve into the depths of statistical analysis, one cannot help but marvel at the cosmic dance of numbers and inquiries, much like celestial bodies twirling through the vast expanse of space. The significance of this correlation echoes across the cosmos of political research, prompting us to consider the implications and ponder the cosmic conundrum: Could there be "alien" influences permeating the electoral landscape of Arizona?
The wealth of data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends has provided us with a telescope to peer into this nebulous nexus of pop culture and political pulsations. While our findings may appear as unlikely as a UFO sighting in the desert night sky, it's precisely these unexpected connections that remind us of the multifaceted nature of human behavior and the cosmic wonders of statistical analysis.
In the grand tradition of scientific inquiry, we invite our fellow cosmic enthusiasts to join us in contemplating the cosmic question that has emerged from our research: Is there an otherworldly force at play in the realm of electoral preferences, or is this simply a statistical anomaly that defies earthly explanation? The truth may not be light-years away, but it certainly lies within the depths of our data, teasing us with the prospect of unraveling the cosmic mysteries that enchant our scholarly pursuits.
As we wrap up this otherworldly odyssey of statistical discovery, we urge our readers to keep an open mind and a keen eye on the intergalactic interplay of statistics and human behavior. The universe of research holds many surprises, and our exploration of the connection between 'E.T. phone home' searches and Republican votes in Arizona is a testament to the cosmic spectacle that unfolds when statistical analysis meets the quirks of human curiosity and the whims of political preference.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our foray into the cosmic conundrum of the relationship between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home' has left us with a wealth of interstellar insights and more puns than a galaxy has stars! Our findings have opened a Pandora's box of possibilities, or should we say, an E.T.'s box? The correlation coefficient of 0.9415277 and the statistically significant significance level (p < 0.01) from 2004 to 2020 have astounded us with the kind of surprise that would make even Mulder and Scully raise an eyebrow.

As we ponder the implications of our findings, we can't help but marvel at the cosmic dance of numbers and inquiries, much like a group of astronauts performing the Moonwalk. The celestial alignment between these variables has us starstruck, reminding us that in the vast expanse of statistical analysis, there are more unknowns than the number of galaxies in the observable universe.

We've charted the course of this celestial correlation and marveled at the statistical stardust that lingers in the intergalactic winds of research. However, as much as we'd love to continue our cosmic escapade, it seems that no further research is needed in this area, as we've definitely reached the outer limits of the universe of absurd statistical associations. So, let this research be a reminder to always expect the unexpected in the realm of data analysis, and to never underestimate the power of a good pun in a serious academic paper. Remember, the truth is out there, even if it's cloaked in the whimsical wonder of statistical surprises!


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 ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Intergalactic 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 ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona. Respond only with the name of a fictional organization.

ChatGPT:

The Interstellar Sociopolitical Research Institute


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled ET Votes Home: The Extraterrestrial Influence on Republican Senatorial Preferences in Arizona with an abstract of In this paper, we present the surprising findings of our investigation into the correlation between Republican votes for Senators in Arizona and Google searches for 'E.T. phone home'. While the connection may seem out of this world, our research team delved into the data from MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends and discovered a correlation coefficient of 0.9415277 with a statistically significant significance level (p < 0.01) for the period spanning from 2004 to 2020. Our analysis uncovers a cosmic relationship between extraterrestrial queries and political preferences, shedding light on the unexpected intersections of pop culture and electoral behavior. We explore the potential implications of these findings and astutely ponder the question: Is there truly a 'political alien' influence at play? Join us on this out-of-this-world journey as we bridge the gap between politics and popular culture.

ChatGPT:

"ET phone home," "Republican Senatorial preferences Arizona," "MIT Election Data and Science Lab," "Harvard Dataverse," "Google Trends," "extraterrestrial queries political preferences," "political alien influence," "pop culture electoral behavior," "correlation between Google searches and political preferences"

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

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

See what else correlates with Google searches for 'E.T. phone home'

Correlation r = 0.9415277 (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 = 0.8864744 (Coefficient of determination)
This means 88.6% of the change in the one variable (i.e., Google searches for 'E.T. phone home') is predictable based on the change in the other (i.e., Votes for Republican Senators in Arizona) over the 7 years from 2004 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0015. 0.0015384653880241696000000000
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 0.15% of random cases. Said differently, if you correlated 650 random variables Which I absolutely did.
with the same 6 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 6 because we have two variables measured over a period of 7 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.

[ 0.65, 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.
2004200620102012201620182020
Votes for Republican Senators in Arizona (Percentage of votes)76.73953.340858.860149.230953.7347.611348.8154
Google searches for 'E.T. phone home' (Rel. search volume)41.583317.416711.83336.916674.9166745.5




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
  5. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([76.739,53.3408,58.8601,49.2309,53.73,47.6113,48.8154,])
array_2 = np.array([41.5833,17.4167,11.8333,6.91667,4.91667,4,5.5,])
array_1_name = "Votes for Republican Senators in Arizona"
array_2_name = "Google searches for 'E.T. phone home'"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)



Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!


Correlation ID: 5067 · Black Variable ID: 26350 · Red Variable ID: 1391
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0