Spurious correlation #5,862 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of movies Tom Cruise appeared in and the second variable is Votes for the Democratic Presidential candidate in Montana. The chart goes from 1981 to 2020, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of movies Tom Cruise appeared in and the second variable is Votes for the Democratic Presidential candidate in Montana. The chart goes from 1981 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of action-packed Tom Cruise movies soared, so did the adrenaline levels of Montanans. This adrenaline, in turn, led to a surge in spontaneous line-dancing, a beloved local pastime. Unbeknownst to many, these dance moves coincidentally spelled out "Vote Democrat" in an ancient, long-forgotten dialect. It's a true case of Maverick influence - both on and off the screen!

^{Show image generation prompt} Model: dalle-3
Prompt: Certainly! Here's an enhanced image generation prompt for DALL-E 3: Create an image in the style of a TIME magazine cover featuring an idyllic Montana town with a bustling movie theater marquee showcasing the latest Tom Cruise movies. The town's main square is filled with a lively crowd of movie-goers, and in a surprising turn of events, they spontaneously form a synchronized line-dance that subtly spells out "Vote Democrat" in an ancient, lively pattern. The scene captures the unexpected influence of Maverick on both the big screen and local politics. The image should capture the energy and excitement of the moment, with a focus on the intricate formation of the line-dance and the vibrant atmosphere of the town square. 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: The number of movies Tom Cruise appeared in and Votes for the Democrat Presidential candidate in Montana. 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: Cubism Surrealism Whimsical illustration Minimalism A TIME magazine cover image
ChatGPT: A TIME magazine cover image

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 The number of movies Tom Cruise appeared in and Votes for the Democrat Presidential candidate in Montana, in the following situation: As the number of action-packed Tom Cruise movies soared, so did the adrenaline levels of Montanans. This adrenaline, in turn, led to a surge in spontaneous line-dancing, a beloved local pastime. Unbeknownst to many, these dance moves coincidentally spelled out "Vote Democrat" in an ancient, long-forgotten dialect. It's a true case of Maverick influence - both on and off the screen!. Keep the description simple.
ChatGPT: In the heart of Montana, a bustling movie theater marquee proudly displays the increasing number of action-packed Tom Cruise movies. As the crowd spills out onto the streets, their adrenaline levels surge, leading to spontaneous line-dancing in the town square. Unbeknownst to the dancers, their synchronized moves form the words "Vote Democrat" in a lively and ancient pattern. This scene captures the unexpected influence of Maverick on both the big screen and local politics.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A TIME magazine cover image ] and depicting this scene: In the heart of Montana, a bustling movie theater marquee proudly displays the increasing number of action-packed Tom Cruise movies. As the crowd spills out onto the streets, their adrenaline levels surge, leading to spontaneous line-dancing in the town square. Unbeknownst to the dancers, their synchronized moves form the words "Vote Democrat" in a lively and ancient pattern. This scene captures the unexpected influence of Maverick on both the big screen and local politics. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Certainly! Here's an enhanced image generation prompt for DALL-E 3: Create an image in the style of a TIME magazine cover featuring an idyllic Montana town with a bustling movie theater marquee showcasing the latest Tom Cruise movies. The town's main square is filled with a lively crowd of movie-goers, and in a surprising turn of events, they spontaneously form a synchronized line-dance that subtly spells out "Vote Democrat" in an ancient, lively pattern. The scene captures the unexpected influence of Maverick on both the big screen and local politics. The image should capture the energy and excitement of the moment, with a focus on the intricate formation of the line-dance and the vibrant atmosphere of the town square.

*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.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in The number of movies Tom Cruise appeared in caused Votes for the Democrat Presidential candidate in Montana to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Cruise Control: Analyzing the Influence of Tom Cruise's Filmography on Montana's Democratic Votes

The Journal of Celebrity Politics

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You 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 The number of movies Tom Cruise appeared in and Votes for the Democrat Presidential candidate in Montana. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Cruise Control: Analyzing the Influence of Tom Cruise's Filmography on Montana's Democratic Votes"

[[ABSTRACT]]
Lights, camera, action! In this study, we embark on an unconventional journey to unravel the mysterious link between the silver screen charisma of Tom Cruise and the political preferences of the good folks in Montana. Drawing data from The Movie DB and the MIT Election Data and Science Lab, we engaged in a lively dance of statistical analysis to determine whether Tom Cruise's prolific appearances on the big screen could sway the penchant for the Democratic presidential candidate in the picturesque landscapes of Montana. Our findings unveiled a striking correlation coefficient of 0.8966439 and a minuscule p-value of less than 0.01, spanning the years 1981 to 2020. As we navigate through the cinematic and political terrain, we uncover surprising connections, raising eyebrows and eliciting chuckles in equal measure. Strap in, as we decode the electoral ripples of Tom Cruise's Hollywood odyssey, and brace yourself for more plot twists than a Mission: Impossible sequel.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Lights, camera, statistical analysis! As we dive headfirst into the realm of Hollywood and politics, our research aims to uncover the unexpected correlation between the number of movies featuring the ever-charismatic Tom Cruise and the votes for the Democratic presidential candidate in the rugged terrain of Montana. Now, you might be wondering what Tom Cruise's filmography has to do with political leanings in Montana, and you're not alone - we had our fair share of raised eyebrows and quizzical looks when we embarked on this peculiar investigation.
But fear not, dear readers, for the world of statistical analysis knows no bounds, and sometimes the most unlikely variables come together in a statistical tango that leaves us all in awe. With our trusty data from The Movie DB and the MIT Election Data and Science Lab, we set out on a quest to untangle this web of cinematic and political intrigue, armed with nothing but regression models, confidence intervals, and a healthy dose of curiosity.
While some might say our endeavor is as improbable as a Mission: Impossible plot, we are not deterred, for it is the unexpected connections that often yield the most delightful surprises in the world of research. With each click of the projector and each tick of the voting machine, we aim to shed light on the tantalizing interplay between art and politics, peppered with just the right amount of statistical spice.
So, buckle up and grab your popcorn, because this ride promises more twists and turns than a Hollywood blockbuster, as we set out to uncover the mesmerizing influence of Tom Cruise's silver screen escapades on the political landscape of Montana. Let the show begin!

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In Jones' seminal work, "The Intersection of Celebrity and Politics," the author delves into the captivating world of how celebrity status can intersect with the realm of politics, prompting us to consider how the mesmerizing aura of a celebrity figure such as Tom Cruise could potentially extend its reach into the political preferences of a specific demographic. However, while Jones' work lays a solid foundation for understanding the dynamics at play, it fails to consider the sheer gravitational pull of those pearly-white Tom Cruise smiles on the silver screen. And let's be honest, that's a grave oversight in any analysis involving the man who brought us "Risky Business" and "Top Gun."

In a similar vein, Smith's thought-provoking paper, "Filmography and Social Influence," treads cautiously on the edges of the influence that an actor's filmography can have on societal behaviors and preferences. While Smith astutely highlights the potential for cinematic narratives to mold our collective consciousness, there is a distinct absence of Tom Cruise fever in the analysis, an omission that feels more glaring than an oversized pair of aviator sunglasses.

Doe's meticulous study, "Political Leanings in the Wild West," ventures into the political landscape of the American West, shedding light on the idiosyncratic voting patterns that define this rugged region. While the work offers valuable insights into the complex interplay of demographics and political affinities, it fails to account for the mesmerizing allure of a certain action hero and his impact on the voting fervor of the Montanans. An oversight bigger than the stunts in "Mission: Impossible."

Transitioning into a more eclectic exploration of related literature, we turn to real-world accounts of Montana's political pulse. Books such as "Montana: The Last Best Place" and "This House of Sky" provide a historical and cultural backdrop for understanding the unique characteristics of the state's electorate. However, they unfortunately lack any discourse on how Tom Cruise's filmography might interplay with the political ethos, a glaring omission that screams louder than the engine roar of a fighter jet in "Top Gun."

Amidst this ocean of serious literature, we encounter fictional works that tantalize the imagination and hint at the possible intersections between cinema and political inclinations. "The Pelican Brief" by John Grisham and "Primary Colors" by Anonymous beckon us with their political intrigue and cinematic flair, teasing a tantalizing link between political machinations and the silver screen. And though these works are fictional, they still beckon us forth on a journey more thrilling than any of Tom Cruise's on-screen escapades.

Now, as we venture further down the rabbit hole, we cannot discount the subtle influences of our childhood viewing experiences. Cartoons such as "The Magic School Bus" and "Scooby-Doo" emboldened our youthful spirits with a sense of adventure and mystery, much like the plot twists we anticipate in our investigation. Even the colorful world of "Sesame Street" taught us valuable lessons that carry resonance into our adult lives - such as the importance of sharing and, of course, the undeniable charm of a certain cookie enthusiast named Cookie Monster. So, hold onto your hats and take a trip down memory lane with us, as we unravel the enigmatic ties between movie magic and Montana's Democratic voting tendencies.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of movies Tom Cruise appeared in and Votes for the Democrat Presidential candidate in Montana. 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]]
"Cruise Control: Analyzing the Influence of Tom Cruise's Filmography on Montana's Democratic Votes"

[[ABSTRACT]]
Lights, camera, action! In this study, we embark on an unconventional journey to unravel the mysterious link between the silver screen charisma of Tom Cruise and the political preferences of the good folks in Montana. Drawing data from The Movie DB and the MIT Election Data and Science Lab, we engaged in a lively dance of statistical analysis to determine whether Tom Cruise's prolific appearances on the big screen could sway the penchant for the Democratic presidential candidate in the picturesque landscapes of Montana. Our findings unveiled a striking correlation coefficient of 0.8966439 and a minuscule p-value of less than 0.01, spanning the years 1981 to 2020. As we navigate through the cinematic and political terrain, we uncover surprising connections, raising eyebrows and eliciting chuckles in equal measure. Strap in, as we decode the electoral ripples of Tom Cruise's Hollywood odyssey, and brace yourself for more plot twists than a Mission: Impossible sequel.

[[LITERATURE REVIEW]]
In Jones' seminal work, "The Intersection of Celebrity and Politics," the author delves into the captivating world of how celebrity status can intersect with the realm of politics, prompting us to consider how the mesmerizing aura of a celebrity figure such as Tom Cruise could potentially extend its reach into the political preferences of a specific demographic. However, while Jones' work lays a solid foundation for understanding the dynamics at play, it fails to consider the sheer gravitational pull of those pearly-white Tom Cruise smiles on the silver screen. And let's be honest, that's a grave oversight in any analysis involving the man who brought us "Risky Business" and "Top Gun."
In a similar vein, Smith's thought-provoking paper, "Filmography and Social Influence," treads cautiously on the edges of the influence that an actor's filmography can have on societal behaviors and preferences. While Smith astutely highlights the potential for cinematic narratives to mold our collective consciousness, there is a distinct absence of Tom Cruise fever in the analysis, an omission that feels more glaring than an oversized pair of aviator sunglasses.
Doe's meticulous study, "Political Leanings in the Wild West," ventures into the political landscape of the American West, shedding light on the idiosyncratic voting patterns that define this rugged region. While the work offers valuable insights into the complex interplay of demographics and political affinities, it fails to account for the mesmerizing allure of a certain action hero and his impact on the voting fervor of the Montanans. An oversight bigger than the stunts in "Mission: Impossible."
Transitioning into a more eclectic exploration of related literature, we turn to real-world accounts of Montana's political pulse. Books such as "Montana: The Last Best Place" and "This House of Sky" provide a historical and cultural backdrop for understanding the unique characteristics of the state's electorate. However, they unfortunately lack any discourse on how Tom Cruise's filmography might interplay with the political ethos, a glaring omission that screams louder than the engine roar of a fighter jet in "Top Gun."
Amidst this ocean of serious literature, we encounter fictional works that tantalize the imagination and hint at the possible intersections between cinema and political inclinations. "The Pelican Brief" by John Grisham and "Primary Colors" by Anonymous beckon us with their political intrigue and cinematic flair, teasing a tantalizing link between political machinations and the silver screen. And though these works are fictional, they still beckon us forth on a journey more thrilling than any of Tom Cruise's on-screen escapades.
Now, as we venture further down the rabbit hole, we cannot discount the subtle influences of our childhood viewing experiences. Cartoons such as "The Magic School Bus" and "Scooby-Doo" emboldened our youthful spirits with a sense of adventure and mystery, much like the plot twists we anticipate in our investigation. Even the colorful world of "Sesame Street" taught us valuable lessons that carry resonance into our adult lives - such as the importance of sharing and, of course, the undeniable charm of a certain cookie enthusiast named Cookie Monster. So, hold onto your hats and take a trip down memory lane with us, as we unravel the enigmatic ties between movie magic and Montana's Democratic voting tendencies.

[[RESULTS]]
In the electrifying display of statistical prowess, our analysis revealed a striking correlation coefficient of 0.8966439 between the number of movies featuring Tom Cruise and the votes for the Democratic presidential candidate in the breathtaking state of Montana. This correlation, with an r-squared of 0.8039703, left us wide-eyed and grinning like Cheshire cats, as it exceeded our wildest expectations.
The scatterplot (Fig. 1) graphically illustrates the robust relationship between these seemingly disparate variables – cue the dramatic music, for this is a tale that even Hollywood itself would find hard to script! The figure showcases the unmistakable trend, akin to the plot development in a blockbuster hit, where more Tom Cruise movies coincided with a surge in Democratic votes.
With a p-value of less than 0.01, our results carried more weight than a Hollywood blockbuster, reassuring us that this connection was not merely a statistical fluke – it was the real deal, folks. While some may consider our findings as improbable as a plot twist from a Mission: Impossible sequel, we stand firm in our discovery of this intriguing association.
It appears that Tom Cruise's magnetic presence on the silver screen may have cast a spell on the political inclinations of the good folks in Montana. Could it be that the glitz and glamour of Hollywood seeped into the realm of politics, nudging voters towards the Democratic candidate? Or perhaps there's a deeper, yet-to-be-revealed storyline at play here, one with more suspense and intrigue than any espionage thriller.
Our results open the door to a whole new dimension of electoral analysis, where the celluloid adventures of a Hollywood icon intersect with the complex tapestry of political preferences. As we peel back the layers of this enigmatic correlation, we invite researchers and enthusiasts alike to join us in this exhilarating exploration of the unexpected interplay between Tinseltown and the ballot box. Lights, camera, statistical action – this is where the magic happens!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our findings bring to light a connection that is more unexpected than an M. Night Shyamalan plot twist. The remarkable correlation we uncovered between the number of movies featuring the one and only Tom "Maverick" Cruise and the votes for the Democratic presidential candidate in the picturesque landscapes of Montana not only supports, but elevates and amplifies the prior research in this field of inquiry.

Drawing from the pioneering work of Jones, we see the extension of celebrity influence from the realm of entertainment to the political sphere. While Jones's focus may not have been on Tom Cruise specifically, our results suggest that perhaps when it comes to Montana, it's not just "Risky Business" - it's serious political sway.

Smith's exploration of filmography and social influence takes on a new layer of significance in light of our findings. It's as if the potential societal impact of an actor's body of work has burst forth from the silver screen and taken residence in the polling booths of Montana. It turns out that the real mission not impossible was to unveil the potent impact of Cruise's filmography on the political fabric of the Big Sky Country.

Doe's extensive study on political leanings in the Wild West, while not directly addressing the specific allure of a Hollywood icon, now demands a revisitation. The oversight of the magnetic charisma of a certain action hero on the political pulse of Montanans is as large as the Montana sky itself. Our results encourage a reexamination of political leanings in this rugged terrain under the formidable shadow of the silver screen.

As we dive deeper into the implications of our findings, we are reminded that sometimes, reality can be stranger than fiction – yes, even stranger than a "Top Gun" sequel released several decades after the original. Our results stand as a testament to the unforeseen connections that can emerge when we unravel the threads of statistical significance. It's as if we've stumbled upon the ultimate plot twist in the grand narrative of research.

Eager, fascinated minds are invited to join us as we traverse uncharted territory at the intersection of Hollywood mystique and political inclination. The unexpected fusion of our previous eccentric musings on the possible intersections between cinema and political leanings with the delightful absurdity of a serious academic correlation has created a concoction more potent than any "cocktail" – one that will leave the scientific community buzzing with excitement and curiosity. So, grab your popcorn and join us in unpacking this wild, unexpected ride through the far-reaching influences of Tom Cruise's cinematic odyssey on the unlikely stage of Montana's political theater.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of movies Tom Cruise appeared in and Votes for the Democrat Presidential candidate in Montana. 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]]
"Cruise Control: Analyzing the Influence of Tom Cruise's Filmography on Montana's Democratic Votes"

[[ABSTRACT]]
Lights, camera, action! In this study, we embark on an unconventional journey to unravel the mysterious link between the silver screen charisma of Tom Cruise and the political preferences of the good folks in Montana. Drawing data from The Movie DB and the MIT Election Data and Science Lab, we engaged in a lively dance of statistical analysis to determine whether Tom Cruise's prolific appearances on the big screen could sway the penchant for the Democratic presidential candidate in the picturesque landscapes of Montana. Our findings unveiled a striking correlation coefficient of 0.8966439 and a minuscule p-value of less than 0.01, spanning the years 1981 to 2020. As we navigate through the cinematic and political terrain, we uncover surprising connections, raising eyebrows and eliciting chuckles in equal measure. Strap in, as we decode the electoral ripples of Tom Cruise's Hollywood odyssey, and brace yourself for more plot twists than a Mission: Impossible sequel.

[[INTRDUCTION]]
Lights, camera, statistical analysis! As we dive headfirst into the realm of Hollywood and politics, our research aims to uncover the unexpected correlation between the number of movies featuring the ever-charismatic Tom Cruise and the votes for the Democratic presidential candidate in the rugged terrain of Montana. Now, you might be wondering what Tom Cruise's filmography has to do with political leanings in Montana, and you're not alone - we had our fair share of raised eyebrows and quizzical looks when we embarked on this peculiar investigation.
But fear not, dear readers, for the world of statistical analysis knows no bounds, and sometimes the most unlikely variables come together in a statistical tango that leaves us all in awe. With our trusty data from The Movie DB and the MIT Election Data and Science Lab, we set out on a quest to untangle this web of cinematic and political intrigue, armed with nothing but regression models, confidence intervals, and a healthy dose of curiosity.
While some might say our endeavor is as improbable as a Mission: Impossible plot, we are not deterred, for it is the unexpected connections that often yield the most delightful surprises in the world of research. With each click of the projector and each tick of the voting machine, we aim to shed light on the tantalizing interplay between art and politics, peppered with just the right amount of statistical spice.
So, buckle up and grab your popcorn, because this ride promises more twists and turns than a Hollywood blockbuster, as we set out to uncover the mesmerizing influence of Tom Cruise's silver screen escapades on the political landscape of Montana. Let the show begin!

[[RESULTS]]
In the electrifying display of statistical prowess, our analysis revealed a striking correlation coefficient of 0.8966439 between the number of movies featuring Tom Cruise and the votes for the Democratic presidential candidate in the breathtaking state of Montana. This correlation, with an r-squared of 0.8039703, left us wide-eyed and grinning like Cheshire cats, as it exceeded our wildest expectations.
The scatterplot (Fig. 1) graphically illustrates the robust relationship between these seemingly disparate variables – cue the dramatic music, for this is a tale that even Hollywood itself would find hard to script! The figure showcases the unmistakable trend, akin to the plot development in a blockbuster hit, where more Tom Cruise movies coincided with a surge in Democratic votes.
With a p-value of less than 0.01, our results carried more weight than a Hollywood blockbuster, reassuring us that this connection was not merely a statistical fluke – it was the real deal, folks. While some may consider our findings as improbable as a plot twist from a Mission: Impossible sequel, we stand firm in our discovery of this intriguing association.
It appears that Tom Cruise's magnetic presence on the silver screen may have cast a spell on the political inclinations of the good folks in Montana. Could it be that the glitz and glamour of Hollywood seeped into the realm of politics, nudging voters towards the Democratic candidate? Or perhaps there's a deeper, yet-to-be-revealed storyline at play here, one with more suspense and intrigue than any espionage thriller.
Our results open the door to a whole new dimension of electoral analysis, where the celluloid adventures of a Hollywood icon intersect with the complex tapestry of political preferences. As we peel back the layers of this enigmatic correlation, we invite researchers and enthusiasts alike to join us in this exhilarating exploration of the unexpected interplay between Tinseltown and the ballot box. Lights, camera, statistical action – this is where the magic happens!

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our foray into the parallel universes of Hollywood and Montana's political landscape has left us breathless, not unlike the dramatic pause before a climactic scene. The robust correlation we uncovered between the number of Tom Cruise movies and Democratic votes in Montana is a plot twist worthy of an Oscar nomination, highlighting the unexpected synergy between the silver screen and the ballot box.

While some may believe our findings to be as unlikely as a scientific study on the correlation between ice cream consumption and shark attacks, the statistical evidence speaks for itself – Tom Cruise's magnetic performances have evidently captured the hearts and perhaps also the votes of the good folks in Montana.

As we bid adieu to this captivating odyssey of data analysis, we can't help but marvel at the peculiar dance of variables and coefficients that brought us to this juncture. It's as if our regression models were performing a breathtaking Tango, with Tom Cruise's filmography and Democratic votes leading the dance with seamless precision.

Now, as for the practical implications of our findings, we cannot deny the allure of incorporating Hollywood glamour into political campaigns. Picture this: 'Top Gun' themed political rallies, 'Jerry Maguire' inspired policy proposals, and 'Mission: Impossible' campaign promises – a tantalizing prospect, indeed.

However, we must exercise caution, lest our political landscape becomes an all-too-literal circus, complete with Hollywood stunt doubles and over-the-top explosions. Our research serves as a poignant reminder of the unexpected connections that lurk beneath the surface, waiting to be uncovered through the magical lens of statistical analysis.

In closing, we assert with utmost confidence that no further research is needed in this domain. It's time to roll the credits on this enthralling chapter and savor the delightful surprise that statistical inquiry so often bestows upon us.

Lights out, statistical action – that's a wrap!

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 Cruise Control: Analyzing the Influence of Tom Cruise's Filmography on Montana's Democratic Votes. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Celebrity Politics

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 Cruise Control: Analyzing the Influence of Tom Cruise's Filmography on Montana's Democratic Votes. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Celebrity Influence Studies

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 Cruise Control: Analyzing the Influence of Tom Cruise's Filmography on Montana's Democratic Votes with an abstract of Lights, camera, action! In this study, we embark on an unconventional journey to unravel the mysterious link between the silver screen charisma of Tom Cruise and the political preferences of the good folks in Montana. Drawing data from The Movie DB and the MIT Election Data and Science Lab, we engaged in a lively dance of statistical analysis to determine whether Tom Cruise's prolific appearances on the big screen could sway the penchant for the Democratic presidential candidate in the picturesque landscapes of Montana. Our findings unveiled a striking correlation coefficient of 0.8966439 and a minuscule p-value of less than 0.01, spanning the years 1981 to 2020. As we navigate through the cinematic and political terrain, we uncover surprising connections, raising eyebrows and eliciting chuckles in equal measure. Strap in, as we decode the electoral ripples of Tom Cruise's Hollywood odyssey, and brace yourself for more plot twists than a Mission: Impossible sequel.

ChatGPT:

Tom Cruise filmography, Montana Democratic votes, political preferences, statistical analysis, correlation coefficient, p-value, The Movie DB, MIT Election Data and Science Lab, political landscape, cinematic connections, electoral influence, Mission: Impossible sequel

*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

The number of movies Tom Cruise appeared in
Source: The Movie DB
Additional Info: ^{See full details} War of the Worlds (2005); Minority Report (2002); Eyes Wide Shut (1999); The Last Samurai (2003); Interview with the Vampire (1994); Top Gun (1986); A Few Good Men (1992); Mission: Impossible II (2000); Mission: Impossible (1996); Mission: Impossible III (2006); Collateral (2004); Vanilla Sky (2001); Days of Thunder (1990); Valkyrie (2008); Born on the Fourth of July (1989); Stanley Kubrick: A Life in Pictures (2001); Far and Away (1992); Cocktail (1988); Legend (1985); Risky Business (1983); Jerry Maguire (1996); Losin' It (1982); The Firm (1993); Knight and Day (2010); All the Right Moves (1983); Space Station 3D (2002); Industrial Light & Magic: Creating the Impossible (2010); Mission: Impossible - Ghost Protocol (2011); Oblivion (2013); Jack Reacher (2012); The Mummy (2017); Mission: Impossible - Rogue Nation (2015); Edge of Tomorrow (2014); American Made (2017); Jack Reacher: Never Go Back (2016); Mission: Impossible - Fallout (2018); Together: The Hendrick Motorsports Story (2009); Mission: Impossible - Dead Reckoning Part One (2023); Special Delivery: Michael Mann on Making 'Collateral' (2004); Cruise on Kubrick (1999); The Dream is Always the Same: The Story of Risky Business (2008); James Corden's Top Gun Training with Tom Cruise (2022); Top Gun: Maverick (2022); Danger Zone: The Making of Top Gun (2004); On Your Six: Thirty Years of Top Gun (2020); Remembering Stanley Kubrick (1999); Tom Cruise: The Last Movie Star (2023); Tom Cruise: Impossible Missions (2023); Tom Cruise: Lights, Camera, Action (2022); Rain Man (1988); Lions for Lambs (2007); The Color of Money (1986); Winning: The Racing Life of Paul Newman (2015); The Last Movie: Stanley Kubrick and 'Eyes Wide Shut' (1999); City of Night: The Making of 'Collateral' (2004); Hitting It Hard (2002); Tom Cruise: An Eternal Youth (2020); Mission: Improbable (2001); Jack Reacher: When the Man Comes Around (2013); The Last Last Late Late Show (2023); Nicole Kidman, eyes wide open (2023); Rock of Ages (2012); Time Out: The Truth About HIV, AIDS and You (1992); In the Shadow of the Vampire: The Making of Interview with the Vampire (2000); The Valkyrie Legacy (2008); Taps (1981); Kubrick by Kubrick (2020); The Golden Hour: Making of Days of Thunder (2020); Junket Whore (1998); Paparazzi: Full Throttle LA (2016); Going Clear: Scientology and the Prison of Belief (2015); The Art of Action: Martial Arts in the Movies (2002); Donald Trump Is President and You're Not: A Portrait of Donald J. Trump (2020); The Outsiders (1983); Tropic Thunder (2008); My Scientology Movie (2016); Scientologists at War (2013); Close Up (2012); America: A Tribute to Heroes (2001); Val (2021); MTV's 10th Anniversary Special (1991); Magnolia (1999); Final Cut: Ladies and Gentlemen (2012); Parkinson at 50 (2021); Endless Love (1981); Religulous (2008); Austin Powers in Goldmember (2002); 2002://complicated (2023); Paul McCartney: Back in the U.S. (2002); Ségo et Sarko sont dans un bateau... (2007); Young Guns (1988); The Coronation Concert (2023); Spielberg (2017); And the Oscar Goes to... (2014); Never Sleep Again: The Elm Street Legacy (2010); Waking Sleeping Beauty (2009)

See what else correlates with The number of movies Tom Cruise appeared in

Votes for the Democratic Presidential candidate in Montana
Detailed data title: Total votes cast for the Democrat Presidential candidate in Montana
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Democratic Presidential candidate in Montana

Correlation r = 0.8966439 (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 = 0.8039703 (Coefficient of determination)
This means 80.4% of the change in the one variable (i.e., Votes for the Democratic Presidential candidate in Montana) is predictable based on the change in the other (i.e., The number of movies Tom Cruise appeared in) over the 9 years from 1981 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00105.^Show 0.0010549843801502753000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.9 in 0.105% of random cases. Said differently, if you correlated 948 random variables^Note Which I absolutely did.
with the same 8 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 8 because we have two variables measured over a period of 9 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.

[ 0.57, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	1988	1992	1996	2000	2004	2008	2012	2016	2020
The number of movies Tom Cruise appeared in (Movie appearances)	3	3	2	2	4	5	4	3	5
Votes for the Democratic Presidential candidate in Montana (Total votes)	168936	154507	167922	137126	173710	231667	201839	177709	244786

Why this works

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.
Lack of causal connection: There is probably^Note 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.
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^Note 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.
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. ^{Show the steps to do this.} 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([3,3,2,2,4,5,4,3,5,])
array_2 = np.array([168936,154507,167922,137126,173710,231667,201839,177709,244786,])
array_1_name = "The number of movies Tom Cruise appeared in"
array_2_name = "Votes for the Democratic Presidential candidate in Montana"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only The number of movies Tom Cruise appeared in
Line chart for only Votes for the Democratic Presidential candidate in Montana
AI-generated correlation image
The spurious research paper: Cruise Control: Analyzing the Influence of Tom Cruise's Filmography on Montana's Democratic Votes

View another random correlation

How fun was this correlation?

Kudos for rating!

Correlation ID: 5862 · Black Variable ID: 26627 · Red Variable ID: 26000


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: