Spurious correlation #1,958 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Biomass power generated in Romania and the second variable is US Shoe Store Sales. The chart goes from 1992 to 2021, 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 Biomass power generated in Romania and the second variable is US Shoe Store Sales. The chart goes from 1992 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Romania's biomass power output rose, so did the local wildlife population. This led to an unexpected surge in the demand for stylish and durable footwear in the US, as people wanted to step out in the latest 'wildlife chic' fashion trend. The connection between Romanian biomass and American shoe sales seems to be a classic case of 'energy in, shoe-trend out'!

^{Show image generation prompt} Model: dalle-3
Prompt: An image that looks like it is a scene from a Disney movie, showing a bustling city in Romania, with a large biomass power plant providing a futuristic backdrop, surrounded by expansive, vibrant green fields. In the heart of the city, a lively US shoe store attracts bustling foot traffic as delighted customers enthusiastically browse and try on chic, trendy footwear, adding a touch of metropolitan flair to the enchanting scene. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Biomass power generated in Romania and US Shoe Store Sales. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: A photo-realistic image Data cyber art Cute 2D animation Glitch art An image that looks like it is a scene from A Disney Movie
ChatGPT: An image that looks like it is a scene from A Disney 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 Biomass power generated in Romania and US Shoe Store Sales together. Keep the description simple.
ChatGPT: In a bustling city in Romania, a large biomass power plant hums in the background, surrounded by lush green fields. Meanwhile, in the center of the city, a busy US shoe store displays a variety of trendy footwear, with customers happily browsing and trying on shoes.

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 Disney Movie ] and depicting this scene: In a bustling city in Romania, a large biomass power plant hums in the background, surrounded by lush green fields. Meanwhile, in the center of the city, a busy US shoe store displays a variety of trendy footwear, with customers happily browsing and trying on shoes. 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 Disney movie, showing a bustling city in Romania, with a large biomass power plant providing a futuristic backdrop, surrounded by expansive, vibrant green fields. In the heart of the city, a lively US shoe store attracts bustling foot traffic as delighted customers enthusiastically browse and try on chic, trendy footwear, adding a touch of metropolitan flair to the enchanting scene.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{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 Biomass power generated in Romania caused US Shoe Store Sales to increase.

AI academic paper

(Because p < 0.01)

Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales

The Journal of Ecological Economics and Fashion Trends

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 Biomass power generated in Romania and US Shoe Store Sales. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales"

[[ABSTRACT]]
This study delves into the unexpected link between Biomass power generated in Romania and US Shoe Store Sales, exploring a correlation that is as surprising as finding a high-heeled shoe in a hiking store. Drawing on data from the Energy Information Administration and Statista, we uncover a correlation coefficient of 0.9190965 and p < 0.01 from 1992 to 2021, showing a relationship between these seemingly unrelated factors that is tighter than a new pair of sneakers. Through rigorous analysis, we demonstrate that the connection between Biomass power and shoe sales is not just a foot note, but a statistically significant relationship that deviates from the norm in an amusing way.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
What do biomass power generation in Romania and US shoe store sales have in common? At first glance, one might think this is the setup for a bad joke, but the surprising truth is that there may be a tangible connection between these seemingly unrelated variables. Just like a good pair of loafers, this unexpected relationship has the potential to provide a comfortable fit for our understanding of economic and environmental dynamics. Talk about a "sole-ful" revelation!
The goal of this research is to shed light on the peculiar association between biomass energy production in Romania and the sales of footwear in the United States. While some may consider this an odd pairing, we assure you that the correlation we've uncovered is not an "arch" effect but a statistically significant and "heel-y" intriguing phenomenon. We aim to lace up our analysis of this curious connection and see if it holds water or if it's merely a statistical "shoehorn."
Like an eager shoe salesman, we are enthusiastic about presenting our findings, which have been derived from meticulous data analysis spanning nearly three decades. We have harnessed the power of statistical methods to gauge the strength of the relationship between these variables, aiming to bridge the gap between environmental and economic indicators in a way that is not just "tongue-in-cheek," but based on rigorous empirical evidence.
As we step into this unconventional journey of exploration, we aim to "shoe-horn" our way into the realm of unexpected correlations, proving that sometimes the most unlikely pairings can yield fascinating insights. It's time to put our best foot forward and walk through the unexpected link between biomass power in Romania and the alluring world of US shoe store sales.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith and Doe (2005) examined the intricate web of factors influencing biomass power generation in Eastern Europe, elucidating the complex interplay of economic, political, and environmental elements. Their findings laid the groundwork for understanding the nuances of biomass energy production and its potential impact on global markets. Little did they know that their work would inadvertently pave the way for the "sole-ful" connection we are about to uncover.

On the other hand, Jones et al. (2010) focused on consumer behavior and purchasing patterns in the US footwear industry, analyzing trends in sneaker sales and high heels to understand the ever-evolving landscape of shoe preferences. Their comprehensive study delved into the psychology behind shoe buying, leaving no heel unturned in their quest to unravel the mysteries of the retail shoe market. Though they may not have had biomass power in mind, their work unknowingly laid the foundation for our investigation.

Now, let's lace up our academic boots and tread into the world of non-fiction literature that has relevance to our unexpected research topic. In "The Biomass Revolution" by Dr. Emma Green, the author explores the potential of biomass energy as a sustainable alternative to traditional power sources, offering insights into the global implications of biomass power generation. Meanwhile, "Shoes, Glorious Shoes: A History of Footwear Fashion" by Dr. Michael Soleman chronicles the evolution of shoe design and its influence on consumer culture, providing a fascinating backdrop to our exploration.

Turning to fiction, the novel "Biomass and the Businessman" by Claire Footter weaves a fictional tale of intrigue and corporate espionage set against the backdrop of the burgeoning biomass industry, offering a thrilling narrative that may hold more truth than fiction. In a similarly whimsical vein, "The Cobbler's Code" by Amanda Arch traverses the world of magical footwear and mystical shoemakers, serving as a delightful departure from our usual scholarly pursuits.

And now, let's take a comical sidestep into the world of cinema. Who could forget the classic comedy "Sole Proprietor," a film that follows the misadventures of a hapless entrepreneur trying to make it in the shoe business? Or perhaps "Biomass Bonanza," a documentary that takes a tongue-in-cheek approach to exploring the world of renewable energy, combining informative content with a healthy dose of humor.

As we wade through this quirky amalgamation of literature and media, it becomes clear that our research journey is marked by unexpected twists and turns – much like a poorly tied shoelace. While our topic may raise some eyebrows, we are determined to march ahead and untangle the peculiar connection between biomass power in Romania and US shoe store sales, one chuckle at a time.

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 Biomass power generated in Romania and US Shoe Store Sales. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Energy Information Administration and Statista . You used data from 1992 to 2021

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]]
"Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales"

[[ABSTRACT]]
This study delves into the unexpected link between Biomass power generated in Romania and US Shoe Store Sales, exploring a correlation that is as surprising as finding a high-heeled shoe in a hiking store. Drawing on data from the Energy Information Administration and Statista, we uncover a correlation coefficient of 0.9190965 and p < 0.01 from 1992 to 2021, showing a relationship between these seemingly unrelated factors that is tighter than a new pair of sneakers. Through rigorous analysis, we demonstrate that the connection between Biomass power and shoe sales is not just a foot note, but a statistically significant relationship that deviates from the norm in an amusing way.

[[INTRODUCTION]]
What do biomass power generation in Romania and US shoe store sales have in common? At first glance, one might think this is the setup for a bad joke, but the surprising truth is that there may be a tangible connection between these seemingly unrelated variables. Just like a good pair of loafers, this unexpected relationship has the potential to provide a comfortable fit for our understanding of economic and environmental dynamics. Talk about a "sole-ful" revelation!
The goal of this research is to shed light on the peculiar association between biomass energy production in Romania and the sales of footwear in the United States. While some may consider this an odd pairing, we assure you that the correlation we've uncovered is not an "arch" effect but a statistically significant and "heel-y" intriguing phenomenon. We aim to lace up our analysis of this curious connection and see if it holds water or if it's merely a statistical "shoehorn."
Like an eager shoe salesman, we are enthusiastic about presenting our findings, which have been derived from meticulous data analysis spanning nearly three decades. We have harnessed the power of statistical methods to gauge the strength of the relationship between these variables, aiming to bridge the gap between environmental and economic indicators in a way that is not just "tongue-in-cheek," but based on rigorous empirical evidence.
As we step into this unconventional journey of exploration, we aim to "shoe-horn" our way into the realm of unexpected correlations, proving that sometimes the most unlikely pairings can yield fascinating insights. It's time to put our best foot forward and walk through the unexpected link between biomass power in Romania and the alluring world of US shoe store sales.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To tackle the challenging task of unraveling the enigmatic connection between Biomass power generated in Romania and US Shoe Store Sales, our research team employed a methodological approach that was as meticulous as checking for pebbles in your shoe after a long walk. We gathered data from the Energy Information Administration and Statista, employing a mix of quantitative analysis and a pinch of statistical magic to uncover the hidden relationship between these disparate variables.

First, we scoured the digital landscape like intrepid adventurers, navigating through the vast terrain of the internet in search of relevant data. It was like a quest for the Holy Grail, except instead of a chalice, we were hunting for data points spanning from 1992 to 2021. We channeled our inner data detectives, sifting through the massive haystack of online information to find the proverbial statistical needles.

Once we had amassed a treasure trove of data, we donned our metaphorical lab coats and crunched the numbers with all the enthusiasm of a mad scientist in a B-movie. Our statistical analysis employed robust methods such as correlation analysis, regression models, and time series analysis, adding as much rigor to our study as a sturdy pair of steel-toed boots.

After applying these analytical tools, we unearthed a correlation coefficient of 0.9190965 and p < 0.01, revealing a relationship between Biomass power generation in Romania and US Shoe Store Sales that was as striking as discovering a gold coin in your couch cushions. This statistical significance was not just a fluke; it was as dependable as a trusty pair of sneakers.

To ensure the reliability and validity of our findings, we subjected our data to rigorous scrutiny, employing cross-validation techniques and sensitivity analyses. We wanted to make sure our results were as sturdy as a well-crafted pair of clogs and not as shaky as a pair of high heels on uneven ground.

Finally, we applied time series forecasting models to peer into the future, attempting to predict how changes in Biomass power generation in Romania might impact US Shoe Store Sales. It was like gazing into a crystal ball, except instead of predicting your love life, we were trying to forecast market trends with the same level of accuracy as a well-worn shoe cobbler.

In summary, our methodology combined data wrangling prowess, statistical acumen, and a touch of whimsy to unravel the peculiar connection between Biomass power in Romania and the captivating world of US shoe sales. Our approach was as rigorous as a marathon runner's training regimen, and we are confident that our findings will stand the test of time like a classic pair of leather loafers.

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 Biomass power generated in Romania and US Shoe Store Sales. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales"

[[ABSTRACT]]
This study delves into the unexpected link between Biomass power generated in Romania and US Shoe Store Sales, exploring a correlation that is as surprising as finding a high-heeled shoe in a hiking store. Drawing on data from the Energy Information Administration and Statista, we uncover a correlation coefficient of 0.9190965 and p < 0.01 from 1992 to 2021, showing a relationship between these seemingly unrelated factors that is tighter than a new pair of sneakers. Through rigorous analysis, we demonstrate that the connection between Biomass power and shoe sales is not just a foot note, but a statistically significant relationship that deviates from the norm in an amusing way.

[[LITERATURE REVIEW]]
In their seminal work, Smith and Doe (2005) examined the intricate web of factors influencing biomass power generation in Eastern Europe, elucidating the complex interplay of economic, political, and environmental elements. Their findings laid the groundwork for understanding the nuances of biomass energy production and its potential impact on global markets. Little did they know that their work would inadvertently pave the way for the "sole-ful" connection we are about to uncover.
On the other hand, Jones et al. (2010) focused on consumer behavior and purchasing patterns in the US footwear industry, analyzing trends in sneaker sales and high heels to understand the ever-evolving landscape of shoe preferences. Their comprehensive study delved into the psychology behind shoe buying, leaving no heel unturned in their quest to unravel the mysteries of the retail shoe market. Though they may not have had biomass power in mind, their work unknowingly laid the foundation for our investigation.
Now, let's lace up our academic boots and tread into the world of non-fiction literature that has relevance to our unexpected research topic. In "The Biomass Revolution" by Dr. Emma Green, the author explores the potential of biomass energy as a sustainable alternative to traditional power sources, offering insights into the global implications of biomass power generation. Meanwhile, "Shoes, Glorious Shoes: A History of Footwear Fashion" by Dr. Michael Soleman chronicles the evolution of shoe design and its influence on consumer culture, providing a fascinating backdrop to our exploration.
Turning to fiction, the novel "Biomass and the Businessman" by Claire Footter weaves a fictional tale of intrigue and corporate espionage set against the backdrop of the burgeoning biomass industry, offering a thrilling narrative that may hold more truth than fiction. In a similarly whimsical vein, "The Cobbler's Code" by Amanda Arch traverses the world of magical footwear and mystical shoemakers, serving as a delightful departure from our usual scholarly pursuits.
And now, let's take a comical sidestep into the world of cinema. Who could forget the classic comedy "Sole Proprietor," a film that follows the misadventures of a hapless entrepreneur trying to make it in the shoe business? Or perhaps "Biomass Bonanza," a documentary that takes a tongue-in-cheek approach to exploring the world of renewable energy, combining informative content with a healthy dose of humor.
As we wade through this quirky amalgamation of literature and media, it becomes clear that our research journey is marked by unexpected twists and turns – much like a poorly tied shoelace. While our topic may raise some eyebrows, we are determined to march ahead and untangle the peculiar connection between biomass power in Romania and US shoe store sales, one chuckle at a time.

[[RESULTS]]
Our analysis of the relationship between Biomass power generated in Romania and US Shoe Store Sales has uncovered a remarkably strong correlation of 0.9190965, a r-squared value of 0.8447383, and a p-value of less than 0.01. This correlation is no "shoe-in" - it's a statistically significant finding that is as striking as a neon sneaker in a sea of black dress shoes.
The scatterplot in Fig. 1 depicts this robust correlation, revealing a trend tighter than a shoelace tied by a professional scout. This correlation reminds us that sometimes in research, we have to be prepared for the unexpected, just like finding an extra pair of socks in a new shoebox – it may seem odd, but it works surprisingly well.
The strength of this connection between Biomass power and shoe sales is more solid than a well-made work boot – it's a relationship that stands up to rigorous statistical scrutiny. It seems that when it comes to these variables, there's no need for a "loafer" statistical analysis – this correlation means business.
In conclusion, our findings suggest that the connection between Biomass power generated in Romania and US Shoe Store Sales is not a "mis-step" in our analysis, but a statistically significant and compelling relationship. It's clear that in the realm of economic and environmental indicators, sometimes the most unexpected pairings yield the most intriguing results. So, let's "heel" to that!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our investigation support and extend prior research exploring the intricate relationship between Biomass power generation in Romania and US Shoe Store Sales. As surprising as it may seem, our findings align closely with the work of Smith and Doe (2005), who laid the groundwork for understanding the complexities of biomass energy production. Just as an unexpected sale at a shoe store can brighten anyone's day, our results shed light on the unexpected but robust association between these seemingly unconnected variables.

Additionally, our research resonates with the work of Jones et al. (2010) as we unveil the statistically significant link between biomass power generation and consumer behavior in the US footwear industry. Like a well-crafted pair of insoles, our findings provide a comfortable fit with prior studies, acknowledging the role of consumer preferences and purchasing patterns in shaping market dynamics. Who would have thought that biomass power and shoe sales could walk so perfectly hand in hand – it's almost as iconic as a dad in sneakers and high socks.

Our study expands on the existing literature by quantitatively demonstrating the strength of the association, with a correlation coefficient tighter than a shoelace in a double knot. This result is no "flip-flop" – it's a firm validation of the unexpected connection we've unearthed. The statistical significance of our findings serves as a sturdy foundation for further exploration, much like a dependable pair of steel-toed boots in an industrial setting.

As we navigate the whimsical landscape of our research, we cannot help but marvel at the unlikely convergence of biomass power and shoe sales. It's as if Cinderella's glass slipper found a new, environmentally conscious home in the world of renewable energy economics. This unexpected pairing serves as a reminder that in the realm of statistical analysis, surprises often abound – much like finding a forgotten coin in the pocket of an old pair of jeans.

In this spirit, our study not only contributes to the empirical understanding of seemingly disparate phenomena but also adds a touch of levity to the traditionally serious domain of scientific inquiry. After all, laughter is the best medicine, just as a well-designed pair of sneakers can bring comfort and joy. So, let's continue to tread the path of research with open minds and a good sense of humor – because sometimes, the most unexpected connections lead us to the most enlightening discoveries.

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 Biomass power generated in Romania and US Shoe Store Sales. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales"

[[ABSTRACT]]
This study delves into the unexpected link between Biomass power generated in Romania and US Shoe Store Sales, exploring a correlation that is as surprising as finding a high-heeled shoe in a hiking store. Drawing on data from the Energy Information Administration and Statista, we uncover a correlation coefficient of 0.9190965 and p < 0.01 from 1992 to 2021, showing a relationship between these seemingly unrelated factors that is tighter than a new pair of sneakers. Through rigorous analysis, we demonstrate that the connection between Biomass power and shoe sales is not just a foot note, but a statistically significant relationship that deviates from the norm in an amusing way.

[[INTRDUCTION]]
What do biomass power generation in Romania and US shoe store sales have in common? At first glance, one might think this is the setup for a bad joke, but the surprising truth is that there may be a tangible connection between these seemingly unrelated variables. Just like a good pair of loafers, this unexpected relationship has the potential to provide a comfortable fit for our understanding of economic and environmental dynamics. Talk about a "sole-ful" revelation!
The goal of this research is to shed light on the peculiar association between biomass energy production in Romania and the sales of footwear in the United States. While some may consider this an odd pairing, we assure you that the correlation we've uncovered is not an "arch" effect but a statistically significant and "heel-y" intriguing phenomenon. We aim to lace up our analysis of this curious connection and see if it holds water or if it's merely a statistical "shoehorn."
Like an eager shoe salesman, we are enthusiastic about presenting our findings, which have been derived from meticulous data analysis spanning nearly three decades. We have harnessed the power of statistical methods to gauge the strength of the relationship between these variables, aiming to bridge the gap between environmental and economic indicators in a way that is not just "tongue-in-cheek," but based on rigorous empirical evidence.
As we step into this unconventional journey of exploration, we aim to "shoe-horn" our way into the realm of unexpected correlations, proving that sometimes the most unlikely pairings can yield fascinating insights. It's time to put our best foot forward and walk through the unexpected link between biomass power in Romania and the alluring world of US shoe store sales.

[[RESULTS]]
Our analysis of the relationship between Biomass power generated in Romania and US Shoe Store Sales has uncovered a remarkably strong correlation of 0.9190965, a r-squared value of 0.8447383, and a p-value of less than 0.01. This correlation is no "shoe-in" - it's a statistically significant finding that is as striking as a neon sneaker in a sea of black dress shoes.
The scatterplot in Fig. 1 depicts this robust correlation, revealing a trend tighter than a shoelace tied by a professional scout. This correlation reminds us that sometimes in research, we have to be prepared for the unexpected, just like finding an extra pair of socks in a new shoebox – it may seem odd, but it works surprisingly well.
The strength of this connection between Biomass power and shoe sales is more solid than a well-made work boot – it's a relationship that stands up to rigorous statistical scrutiny. It seems that when it comes to these variables, there's no need for a "loafer" statistical analysis – this correlation means business.
In conclusion, our findings suggest that the connection between Biomass power generated in Romania and US Shoe Store Sales is not a "mis-step" in our analysis, but a statistically significant and compelling relationship. It's clear that in the realm of economic and environmental indicators, sometimes the most unexpected pairings yield the most intriguing results. So, let's "heel" to that!

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our findings reveal a surprisingly strong and statistically significant relationship between Biomass power generated in Romania and US Shoe Store Sales. It seems these two variables are more connected than the laces on a pair of running shoes – simply inseparable!

Our research has not only illuminated this unexpected connection but has also demonstrated that the correlation coefficient of 0.9190965 and p < 0.01 between Biomass power and shoe sales is as solid as a pair of steel-toed boots. Who would have thought that the humble act of generating power from organic materials in Romania could have an impact on the buying patterns of footwear across the pond in the US? It's a tantalizing mystery, like finding a missing sock in the laundry – improbable, yet undeniably linked!

The robustness of this relationship, with an r-squared value of 0.8447383, is like a well-crafted pair of sandals – it holds up under scrutiny and supports further investigation into this unanticipated coupling. It's a veritable Cinderella story in the world of statistical analysis – finding a perfect fit where none was expected.

Therefore, on the basis of these compelling findings, we assert that further research into the connection between Biomass power generated in Romania and US Shoe Store Sales is superfluous. We've tied this correlation up like a pair of double knots – there's no need to reinvent the wheel, or in this case, the heel! It's time to put this quirky juxtaposition to rest and step into new, equally surprising research endeavors. As they say in the world of statistical analysis – "shoe" must go on!

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 Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Ecological Economics and Fashion Trends

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 Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Sustainable Energy and International Commerce

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 Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales with an abstract of This study delves into the unexpected link between Biomass power generated in Romania and US Shoe Store Sales, exploring a correlation that is as surprising as finding a high-heeled shoe in a hiking store. Drawing on data from the Energy Information Administration and Statista, we uncover a correlation coefficient of 0.9190965 and p < 0.01 from 1992 to 2021, showing a relationship between these seemingly unrelated factors that is tighter than a new pair of sneakers. Through rigorous analysis, we demonstrate that the connection between Biomass power and shoe sales is not just a foot note, but a statistically significant relationship that deviates from the norm in an amusing way.

ChatGPT:

Biomass energy, Romania, US shoe store sales, correlation, surprising correlation, Biomass power, Energy Information Administration, Statista, correlation coefficient, statistical analysis, relationship, unexpected link, Romania biomass energy, shoe sales statistics

*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

Biomass power generated in Romania
Detailed data title: Total biomass power generated in Romania in billion kWh
Source: Energy Information Administration
See what else correlates with Biomass power generated in Romania

US Shoe Store Sales
Source: Statista
See what else correlates with US Shoe Store Sales

Correlation r = 0.9190965 (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 = 0.8447383 (Coefficient of determination)
This means 84.5% of the change in the one variable (i.e., US Shoe Store Sales) is predictable based on the change in the other (i.e., Biomass power generated in Romania) over the 30 years from 1992 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.6E-13.^Show 0.0000000000007645395338580557
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 0.92 in 7.6E-11% of random cases. Said differently, if you correlated 1,307,976,835,356 random variables^Note You don't actually need 1 trillion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 29 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 29 because we have two variables measured over a period of 30 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.

[ 0.84, 0.96 ] 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.

	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Biomass power generated in Romania (Billion kWh)	0.057	0.069	0	0.003	0	0.011	0.011	0	0	0	0	0	0	0	0	0.035	0.024	0.01	0.111	0.198	0.212	0.252	0.505	0.524	0.531	0.525	0.437	0.504	0.444	0.607627
US Shoe Store Sales (Dollars)	18620000000000	19030000000000	19910000000000	20340000000000	21240000000000	21450000000000	22240000000000	22690000000000	22880000000000	22880000000000	23200000000000	23170000000000	23690000000000	25260000000000	26680000000000	26810000000000	26690000000000	25070000000000	26370000000000	28070000000000	29510000000000	29880000000000	33960000000000	35310000000000	36920000000000	36330000000000	37200000000000	37630000000000	29640000000000	39150000000000

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([0.057,0.069,0,0.003,0,0.011,0.011,0,0,0,0,0,0,0,0,0.035,0.024,0.01,0.111,0.198,0.212,0.252,0.505,0.524,0.531,0.525,0.437,0.504,0.444,0.607627,])
array_2 = np.array([18620000000000,19030000000000,19910000000000,20340000000000,21240000000000,21450000000000,22240000000000,22690000000000,22880000000000,22880000000000,23200000000000,23170000000000,23690000000000,25260000000000,26680000000000,26810000000000,26690000000000,25070000000000,26370000000000,28070000000000,29510000000000,29880000000000,33960000000000,35310000000000,36920000000000,36330000000000,37200000000000,37630000000000,29640000000000,39150000000000,])
array_1_name = "Biomass power generated in Romania"
array_2_name = "US Shoe Store Sales"

# 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 Biomass power generated in Romania
Line chart for only US Shoe Store Sales
AI-generated correlation image
The spurious research paper: Putting Their Best Foot Forward: The Sole-ful Connection Between Biomass Energy in Romania and US Shoe Store Sales

View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!

Correlation ID: 1958 · Black Variable ID: 23917 · Red Variable ID: 145


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