Spurious correlation #3,373 · 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 hotel managers in Vermont and the second variable is Amazon's shipping revenue in millions of dollars. The chart goes from 2006 to 2016, 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 hotel managers in Vermont and the second variable is Amazon's shipping revenue in millions of dollars. The chart goes from 2006 to 2016, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The sudden surge in hotel managers in Vermont led to a spike in demand for decorative moose antler displays, maple syrup-scented pillow mints, and novelty skiing do-not-disturb signs on Amazon, boosting their shipping revenue to unprecedented levels.

^{Show image generation prompt} Model: dalle-3
Prompt: An image that looks like it is a scene from a Pixar movie, portraying a quaint Vermont hotel with a line of colorful Amazon delivery trucks, each with the signature smile logo, unloading a mountain of packages. A group of cheerful hotel managers, with animated expressions, are gathered around a computer, eagerly adding various whimsical and peculiar items to their online shopping carts. The hotel lobby is filled with excitement and bustling activity, reflecting the increase in Amazon's shipping revenue. 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 hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. 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: Art nouveau An image that looks like it is a scene from a Pixar movie Realistic Photorealism Oragami
ChatGPT: An image that looks like it is a scene from a Pixar movie

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 hotel managers in Vermont and Amazon's shipping revenue in millions of dollars, in the following situation: Because the hotel managers in Vermont started a secret competition to see who could order the most obscure items on Amazon for their guest rooms. From novelty toilet paper to personalized bathrobes, they went wild, boosting Amazon's shipping revenue as they tried to one-up each other with the weirdest deliveries.. Keep the description simple.
ChatGPT: In a quaint Vermont hotel, a group of hotel managers eagerly huddles around a computer, each enthusiastically adding peculiar items to their Amazon carts. Meanwhile, a mountain of Amazon boxes is being delivered to the hotel entrance, showcasing the increase in Amazon's shipping revenue.

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: [ An image that looks like it is a scene from a Pixar movie ] and depicting this scene: In a quaint Vermont hotel, a group of hotel managers eagerly huddles around a computer, each enthusiastically adding peculiar items to their Amazon carts. Meanwhile, a mountain of Amazon boxes is being delivered to the hotel entrance, showcasing the increase in Amazon's shipping revenue. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from a Pixar movie, portraying a quaint Vermont hotel with a line of colorful Amazon delivery trucks, each with the signature smile logo, unloading a mountain of packages. A group of cheerful hotel managers, with animated expressions, are gathered around a computer, eagerly adding various whimsical and peculiar items to their online shopping carts. The hotel lobby is filled with excitement and bustling activity, reflecting the increase in Amazon's shipping revenue.

*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 hotel managers in Vermont caused Amazon's shipping revenue in millions of dollars to increase.

AI academic paper

(Because p < 0.01)

Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains

Journal of Quirky Economic Studies

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 hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. 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 few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains

[[ABSTRACT]]
Have you ever pondered the potential link between managing a hotel in Vermont and Amazon's shipping revenues? Well, fret no more, as our research dives into this quirky connection. Utilizing data from the Bureau of Labor Statistics and Statista, we uncovered a surprising correlation between the number of hotel managers in the picturesque state of Vermont and the behemoth that is Amazon's shipping revenue. Despite the skepticism that may arise, our findings reveal a rather robust correlation coefficient of 0.8815298 with p < 0.01 between 2006 and 2016. Join us on this whimsical journey as we unpack the unforeseen relationship between hospitality management and e-commerce shipping empires.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As a wise person once said, "Life is a journey, not a destination." And indeed, our journey of academic inquiry has brought us to the unlikely intersection of hotel management in Vermont and Amazon's shipping magnificence. Who would have thought that the charming world of bed linens and check-ins could possibly intertwine with the colossal domain of cardboard boxes and Prime deliveries?
In the realm of research, one often embarks on a quest to unravel the mysteries of the universe, uncover hidden truths, and of course, to answer questions no one thought to ask. And in the grand tradition of such quirky scientific pursuits, we found ourselves compelled to explore the curious relationship between the number of hotel managers in the Green Mountain State and Amazon's monumental shipping revenue. This endeavor involved diving deep into the data, navigating the treacherous waters of statistics, and occasionally pausing to ponder the whimsical nature of our pursuit.
The rationale behind our investigation was not merely born out of academic curiosity, but also out of a shared fascination with the unexpected, the unorthodox, and the downright peculiar. And what better way to light up the sometimes monotonous world of research than to shine a spotlight on an association that at first glance seems as likely as a penguin in the Sahara?
So, dear reader, fasten your seatbelts (or perhaps in this case, secure your hotel reservations) as we venture forth into the uncharted territory where the hospitality sector meets mammoth e-commerce. Together, we shall navigate through the maze of data, unveil the underlying patterns, and maybe even crack a few unexpected jokes along the way. After all, what's a research paper without a sprinkle of scientific absurdity?

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The investigation into the intriguing relationship between the number of hotel managers in Vermont and Amazon's shipping revenue leads us to peruse the scholarly works of Smith, Doe, and Jones. In "The Journal of Hospitality Management," Smith et al. delve into the intricacies of hotel operations, shedding light on the challenges and triumphs of hospitality management in various geographic contexts. Similarly, Doe's seminal piece in "The Strategic Management Journal" offers insights into the strategies employed by e-commerce giants like Amazon to dominate the shipping industry. Furthermore, Jones's comprehensive analysis in "The Journal of Business Logistics" explores the logistics and supply chain management practices that underpin Amazon's shipping prowess.

Turning our attention to non-fiction books, "The Art of Hospitality" by John Smithson and "Logistics and Supply Chain Management" by Martin Christopher provide valuable perspectives on the hotel management and shipping logistics domains. On the fictional side, "The Grand Hotel" by Scott Fitzgerald and "The Shipping News" by Annie Proulx offer imaginative portrayals of the hospitality industry and maritime activities, albeit in vastly different contexts.

To gain a more comprehensive understanding of the cultural and operational aspects of hotel management, our research delved into TV shows such as "Hotel Hell" and "The Grand Tour." While not directly related to the topic at hand, these programs offered entertainment and perhaps a hint of inspiration for our offbeat exploration.

Now, as we embark on this scholarly voyage, we cannot discount the sheer whimsy of venturing into uncharted waters where the impeccable service of a quaint Vermont inn intermingles with the frenetic world of Amazon's shipping juggernaut. What awaits us in this quirky correlation may be as unexpected as a bellhop moonlighting as an Amazon Prime delivery driver or a concierge offering expedited shipping for weary travelers. So, hold onto your room keys, dear reader, as we navigate through the labyrinth of literature and emerge with a freshly laundered understanding of the bizarre interconnectedness between these seemingly disparate realms.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. 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 Bureau of Larbor Statistics and Statista . You used data from 2006 to 2016

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]]
Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains

[[ABSTRACT]]
Have you ever pondered the potential link between managing a hotel in Vermont and Amazon's shipping revenues? Well, fret no more, as our research dives into this quirky connection. Utilizing data from the Bureau of Labor Statistics and Statista, we uncovered a surprising correlation between the number of hotel managers in the picturesque state of Vermont and the behemoth that is Amazon's shipping revenue. Despite the skepticism that may arise, our findings reveal a rather robust correlation coefficient of 0.8815298 with p < 0.01 between 2006 and 2016. Join us on this whimsical journey as we unpack the unforeseen relationship between hospitality management and e-commerce shipping empires.

[[INTRODUCTION]]
As a wise person once said, "Life is a journey, not a destination." And indeed, our journey of academic inquiry has brought us to the unlikely intersection of hotel management in Vermont and Amazon's shipping magnificence. Who would have thought that the charming world of bed linens and check-ins could possibly intertwine with the colossal domain of cardboard boxes and Prime deliveries?
In the realm of research, one often embarks on a quest to unravel the mysteries of the universe, uncover hidden truths, and of course, to answer questions no one thought to ask. And in the grand tradition of such quirky scientific pursuits, we found ourselves compelled to explore the curious relationship between the number of hotel managers in the Green Mountain State and Amazon's monumental shipping revenue. This endeavor involved diving deep into the data, navigating the treacherous waters of statistics, and occasionally pausing to ponder the whimsical nature of our pursuit.
The rationale behind our investigation was not merely born out of academic curiosity, but also out of a shared fascination with the unexpected, the unorthodox, and the downright peculiar. And what better way to light up the sometimes monotonous world of research than to shine a spotlight on an association that at first glance seems as likely as a penguin in the Sahara?
So, dear reader, fasten your seatbelts (or perhaps in this case, secure your hotel reservations) as we venture forth into the uncharted territory where the hospitality sector meets mammoth e-commerce. Together, we shall navigate through the maze of data, unveil the underlying patterns, and maybe even crack a few unexpected jokes along the way. After all, what's a research paper without a sprinkle of scientific absurdity?

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To uncover the enigmatic link between the number of hotel managers in quaint Vermont and the formidable shipping dominion of Amazon, our research team embarked on a quest that would make even the bravest of statistical adventurers quiver in their lab coats. Our dataset, sourced from the Bureau of Labor Statistics and Statista, served as our treasure map, guiding us through the labyrinthine corridors of data from 2006 to 2016, all in pursuit of the elusive correlation between these seemingly incongruous variables.

First, we indulged in the ancient art of data wrangling, skillfully extracting the number of hotel managers in Vermont from the clutches of spreadsheets and databases. With practiced hands, we combed through the digital underbrush, ensuring that no outlier or imposter sneaked into our calculations.

Next, armed with an arsenal of statistical weaponry, we pitted the count of hotel managers against Amazon's shipping revenue in a battle of coefficients and significance levels. Our trusty Pearson correlation coefficient and its loyal companion, the p-value, stood guard as we scrutinized the relationship between these disparate elements, seeking to unveil the hidden dance of numbers beneath the surface.

As any seasoned researcher knows, no quest is complete without a pilgrimage to the temple of regression analysis. Here, we beseeched the mighty gods of statistical modeling to reveal to us the nature and strength of the association between the number of hotel managers in Vermont and Amazon's shipping revenue, using a variety of regression techniques to decipher their cryptic messages.

To ensure the robustness of our findings, we performed sensitivity analyses, manipulating the variables with the finesse of a magician weaving spells, in order to test the stability and reliability of our results. Additionally, we took great care to address any lurking potential confounders that threatened to cast a shadow of doubt over our conclusions, employing covariates as talismans to ward off spurious correlations.

Finally, after emerging from the dense thicket of data analysis, we presented our findings with the measured confidence of explorers unveiling a long-lost treasure. Our results, bearing the seal of statistical significance and empirical rigor, paint a vivid portrait of the intriguing relationship between the number of hotel managers in Vermont and the staggering ascent of Amazon's shipping revenues. And like any good explorer, we can't help but marvel at the unexpected sights and sounds we encountered along the way.

So, dear reader, hold on to your hats (or your bellhop's cap), as we journey into the heart of this captivating correlation, armed with nothing but the tools of research and a healthy dose of scientific whimsy.

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 hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. 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]]
Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains

[[ABSTRACT]]
Have you ever pondered the potential link between managing a hotel in Vermont and Amazon's shipping revenues? Well, fret no more, as our research dives into this quirky connection. Utilizing data from the Bureau of Labor Statistics and Statista, we uncovered a surprising correlation between the number of hotel managers in the picturesque state of Vermont and the behemoth that is Amazon's shipping revenue. Despite the skepticism that may arise, our findings reveal a rather robust correlation coefficient of 0.8815298 with p < 0.01 between 2006 and 2016. Join us on this whimsical journey as we unpack the unforeseen relationship between hospitality management and e-commerce shipping empires.

[[LITERATURE REVIEW]]
The investigation into the intriguing relationship between the number of hotel managers in Vermont and Amazon's shipping revenue leads us to peruse the scholarly works of Smith, Doe, and Jones. In "The Journal of Hospitality Management," Smith et al. delve into the intricacies of hotel operations, shedding light on the challenges and triumphs of hospitality management in various geographic contexts. Similarly, Doe's seminal piece in "The Strategic Management Journal" offers insights into the strategies employed by e-commerce giants like Amazon to dominate the shipping industry. Furthermore, Jones's comprehensive analysis in "The Journal of Business Logistics" explores the logistics and supply chain management practices that underpin Amazon's shipping prowess.
Turning our attention to non-fiction books, "The Art of Hospitality" by John Smithson and "Logistics and Supply Chain Management" by Martin Christopher provide valuable perspectives on the hotel management and shipping logistics domains. On the fictional side, "The Grand Hotel" by Scott Fitzgerald and "The Shipping News" by Annie Proulx offer imaginative portrayals of the hospitality industry and maritime activities, albeit in vastly different contexts.
To gain a more comprehensive understanding of the cultural and operational aspects of hotel management, our research delved into TV shows such as "Hotel Hell" and "The Grand Tour." While not directly related to the topic at hand, these programs offered entertainment and perhaps a hint of inspiration for our offbeat exploration.
Now, as we embark on this scholarly voyage, we cannot discount the sheer whimsy of venturing into uncharted waters where the impeccable service of a quaint Vermont inn intermingles with the frenetic world of Amazon's shipping juggernaut. What awaits us in this quirky correlation may be as unexpected as a bellhop moonlighting as an Amazon Prime delivery driver or a concierge offering expedited shipping for weary travelers. So, hold onto your room keys, dear reader, as we navigate through the labyrinth of literature and emerge with a freshly laundered understanding of the bizarre interconnectedness between these seemingly disparate realms.

[[RESULTS]]
Upon donning our metaphorical Sherlock Holmes hats and delving into the depths of our data, we uncovered a correlation coefficient of 0.8815298 between the number of hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. As any seasoned researcher can attest, this correlation is about as substantial as a towering stack of Amazon delivery boxes at your front door.
The r-squared value of 0.7770949 further solidifies the robustness of this relationship, suggesting that approximately 77.71% of the variation in Amazon's shipping revenue can be explained by the number of hotel managers in Vermont. It's almost as if the correlation between these two variables is as crystal clear as an Amazon Echo's sound quality.
But wait, there's more! With p < 0.01, our findings are statistically significant, meaning that the likelihood of this correlation occurring by mere chance is about as remote as finding a unicorn in your backyard. It's safe to say that this correlation has passed the scientific sniff test with flying colors.
To further illustrate this unexpected connection, we present Fig. 1, a scatterplot that graphically depicts the strong positive correlation between the count of hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. It's a visual feast for the eyes, much like stumbling upon an unexpectedly whimsical artwork in a prestigious art gallery.
In conclusion, our results suggest that there exists a surprisingly strong and statistically significant association between the number of hotel managers in Vermont and Amazon's shipping revenue. It's as if the world of Swiss cheese and the e-commerce giant decided to have a delightful tango, leaving us all quite bemused and intrigued.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Well, folks, buckle up because we're about to dive into the wacky world of hotel managers and Amazon's shipping revenue. Our results have led us down a rabbit hole filled with surprising correlations and statistical shenanigans. It seems that the innkeepers of Vermont may be more influential on the e-commerce shipping behemoth than we ever imagined.

Our findings align with the previous research that hinted at the intertwining of hospitality management and shipping empires. Smith's work on hotel operations prepares us for the surprising revelation that the number of hotel managers in Vermont can impact the shipping revenue of Amazon. It's like finding a hidden compartment in your suitcase that's filled with statistical significance.

Doe's insights into the strategies of e-commerce giants take on a whole new dimension when we consider the role of Vermont's lodging luminaries in fueling Amazon's shipping gains. It's as if the strategies and tactics of these two seemingly separate industries have engaged in a clandestine collaboration that even Sherlock Holmes would have trouble unraveling.

Furthermore, Jones's analysis of logistics and supply chain management sheds light on the unexpected dance of data points, leading to our discovery of an astonishingly high correlation coefficient. It's like witnessing a ballet performance where the dancers are hotel managers and Amazon's shipping revenue, gracefully pirouetting in statistical harmony.

Now, I know what you're thinking - the connection between hotel managers in Vermont and Amazon's shipping revenue may seem as improbable as a unicorn sighting. But our results, with their robust correlation coefficient and impressive level of significance, defy the odds like a superhero defying the laws of physics.

Our research has opened a pandora's box of peculiar pairings, where the quaint charm of a Vermont inn resonates through the booming halls of Amazon's shipping empire. It's almost as if the data points themselves have conspired to pull off the ultimate statistical magic trick, leaving us in awe of the whimsical interconnectedness of these unassuming variables.

As we continue to unravel the mysteries of this peculiar relationship, it's becoming increasingly clear that the world of statistical analysis is a treasure trove of unexpected connections and improbable pairings. Just when you think you've seen it all, along comes a correlation coefficient that challenges your assumptions and tickles your scientific curiosity.

So, dear reader, join us as we navigate this enchanting labyrinth of correlations and causations, where the charm of hotel management in Vermont meets the unstoppable force of Amazon's shipping revenue. It's a journey that promises to keep us on our toes, much like a delightful dance between two unlikely partners in the grand ballroom of statistical serendipity.

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 hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. 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]]
Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains

[[ABSTRACT]]
Have you ever pondered the potential link between managing a hotel in Vermont and Amazon's shipping revenues? Well, fret no more, as our research dives into this quirky connection. Utilizing data from the Bureau of Labor Statistics and Statista, we uncovered a surprising correlation between the number of hotel managers in the picturesque state of Vermont and the behemoth that is Amazon's shipping revenue. Despite the skepticism that may arise, our findings reveal a rather robust correlation coefficient of 0.8815298 with p < 0.01 between 2006 and 2016. Join us on this whimsical journey as we unpack the unforeseen relationship between hospitality management and e-commerce shipping empires.

[[INTRDUCTION]]
As a wise person once said, "Life is a journey, not a destination." And indeed, our journey of academic inquiry has brought us to the unlikely intersection of hotel management in Vermont and Amazon's shipping magnificence. Who would have thought that the charming world of bed linens and check-ins could possibly intertwine with the colossal domain of cardboard boxes and Prime deliveries?
In the realm of research, one often embarks on a quest to unravel the mysteries of the universe, uncover hidden truths, and of course, to answer questions no one thought to ask. And in the grand tradition of such quirky scientific pursuits, we found ourselves compelled to explore the curious relationship between the number of hotel managers in the Green Mountain State and Amazon's monumental shipping revenue. This endeavor involved diving deep into the data, navigating the treacherous waters of statistics, and occasionally pausing to ponder the whimsical nature of our pursuit.
The rationale behind our investigation was not merely born out of academic curiosity, but also out of a shared fascination with the unexpected, the unorthodox, and the downright peculiar. And what better way to light up the sometimes monotonous world of research than to shine a spotlight on an association that at first glance seems as likely as a penguin in the Sahara?
So, dear reader, fasten your seatbelts (or perhaps in this case, secure your hotel reservations) as we venture forth into the uncharted territory where the hospitality sector meets mammoth e-commerce. Together, we shall navigate through the maze of data, unveil the underlying patterns, and maybe even crack a few unexpected jokes along the way. After all, what's a research paper without a sprinkle of scientific absurdity?

[[RESULTS]]
Upon donning our metaphorical Sherlock Holmes hats and delving into the depths of our data, we uncovered a correlation coefficient of 0.8815298 between the number of hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. As any seasoned researcher can attest, this correlation is about as substantial as a towering stack of Amazon delivery boxes at your front door.
The r-squared value of 0.7770949 further solidifies the robustness of this relationship, suggesting that approximately 77.71% of the variation in Amazon's shipping revenue can be explained by the number of hotel managers in Vermont. It's almost as if the correlation between these two variables is as crystal clear as an Amazon Echo's sound quality.
But wait, there's more! With p < 0.01, our findings are statistically significant, meaning that the likelihood of this correlation occurring by mere chance is about as remote as finding a unicorn in your backyard. It's safe to say that this correlation has passed the scientific sniff test with flying colors.
To further illustrate this unexpected connection, we present Fig. 1, a scatterplot that graphically depicts the strong positive correlation between the count of hotel managers in Vermont and Amazon's shipping revenue in millions of dollars. It's a visual feast for the eyes, much like stumbling upon an unexpectedly whimsical artwork in a prestigious art gallery.
In conclusion, our results suggest that there exists a surprisingly strong and statistically significant association between the number of hotel managers in Vermont and Amazon's shipping revenue. It's as if the world of Swiss cheese and the e-commerce giant decided to have a delightful tango, leaving us all quite bemused and intrigued.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In wrapping up our whimsical escapade through the land of statistical oddities, it is abundantly clear that the relationship between the number of hotel managers in Vermont and Amazon's shipping revenue is as real as the science behind wearing socks with sandals - shocking, yet undeniably present. Our findings have unveiled a correlation coefficient so robust, it could rival the strength of a sumo wrestler. The r-squared value further solidifies this intriguing connection, painting a picture as vivid as a Bob Ross masterpiece.

The statistically significant correlation, with a likelihood of occurring by mere chance as remote as stumbling upon a unicorn at a Renaissance fair, speaks volumes. Our data, much like a magician's reveal, has left us all in awe at the unexpected union of hospitality and e-commerce.

With that said, it seems that our exploration of this peculiar relationship has reached its crescendo. The odds of stumbling upon another correlation quite as fascinating as the one we've unearthed here are about as likely as winning the lottery while being struck by a meteor. It's safe to assert that no further research in this area is needed, for we have unraveled a mystery worthy of a Sherlockian tale. With this, we bid adieu to our quirky investigation, leaving the scientific community with a newfound appreciation for the quirks and surprises that hide within the realm of research.

And remember, fellow researchers, always expect the unexpected - you never know when you might stumble upon a statistical unicorn!

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 Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Economic Studies

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 Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains. Respond only with the name of a fictional organization.

ChatGPT:

The Concord Institute for Socioeconomic Analysis

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 Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains with an abstract of Have you ever pondered the potential link between managing a hotel in Vermont and Amazon's shipping revenues? Well, fret no more, as our research dives into this quirky connection. Utilizing data from the Bureau of Labor Statistics and Statista, we uncovered a surprising correlation between the number of hotel managers in the picturesque state of Vermont and the behemoth that is Amazon's shipping revenue. Despite the skepticism that may arise, our findings reveal a rather robust correlation coefficient of 0.8815298 with p < 0.01 between 2006 and 2016. Join us on this whimsical journey as we unpack the unforeseen relationship between hospitality management and e-commerce shipping empires.

ChatGPT:

hotel managers, Vermont, Amazon, shipping revenue, correlation, Bureau of Labor Statistics, Statista, correlation coefficient, e-commerce, hospitality management

*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 hotel managers in Vermont
Detailed data title: BLS estimate of lodging managers in Vermont
Source: Bureau of Larbor Statistics
See what else correlates with The number of hotel managers in Vermont

Amazon's shipping revenue in millions of dollars
Source: Statista
See what else correlates with Amazon's shipping revenue in millions of dollars

Correlation r = 0.8815298 (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 = 0.7770949 (Coefficient of determination)
This means 77.7% of the change in the one variable (i.e., Amazon's shipping revenue in millions of dollars) is predictable based on the change in the other (i.e., The number of hotel managers in Vermont) over the 11 years from 2006 through 2016.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00033.^Show 0.0003336650623404630600000000
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 0.88 in 0.033% of random cases. Said differently, if you correlated 2,997 random variables^Note Which I absolutely did.
with the same 10 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 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.

[ 0.6, 0.97 ] 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.

	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016
The number of hotel managers in Vermont (Lodging Managers)	160	170	150	150	150	140	160	160	170	240	230
Amazon's shipping revenue in millions of dollars (Dollars)	567000000	740000000	835000000	924000000	1193000000	1552000000	2280000000	3097000000	4486000000	6520000000	8976000000

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.
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. ^Note 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. ^{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([160,170,150,150,150,140,160,160,170,240,230,])
array_2 = np.array([567000000,740000000,835000000,924000000,1193000000,1552000000,2280000000,3097000000,4486000000,6520000000,8976000000,])
array_1_name = "The number of hotel managers in Vermont"
array_2_name = "Amazon's shipping revenue in millions of dollars"

# 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 hotel managers in Vermont
Line chart for only Amazon's shipping revenue in millions of dollars
AI-generated correlation image
The spurious research paper: Checking in at the Inn: The Relationship Between the Count of Hotel Managers in Vermont and Amazon's Shipping Gains

View another random correlation

How fun was this correlation?

Kudos for rating!

Correlation ID: 3373 · Black Variable ID: 15192 · Red Variable ID: 172


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