about · email me · subscribe
Spurious correlation #4,776 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The wind speed in Minneapolis and the second variable is Gasoline pumped in Cuba.  The chart goes from 1984 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The decrease in wind speed in Minneapolis led to a shortage of a key ingredient for creating wind power. This shortage caused a decrease in the production of electricity, which in turn affected the energy supply needed to refine gasoline. As a result, there was a decrease in the amount of gasoline pumped in Cuba. It seems like even the gentlest breeze in Minneapolis can have far-reaching effects on the other side of the world!

Model: dalle-3
Prompt: Generate an image of two stark landscapes, one featuring the Minneapolis wind turbines against a Brutalist urban backdrop, and the other showcasing the quiet gas station in Cuba. The Minneapolis scene should convey a sense of industrial grandeur with imposing structures and the motionless wind turbines, while the Cuban scene should emphasize the eerie emptiness of the gas station with a Brutalist architectural style. Both scenes should capture the contrasting stillness and convey the unifying theme of decreased activity. 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 wind speed in Minneapolis and Gasoline pumped in Cuba. 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: Brutalism Oragami Minimalism Art nouveau Pop art
ChatGPT: Brutalism

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 wind speed in Minneapolis and Gasoline pumped in Cuba, in the following situation: The decrease in wind speed in Minneapolis led to a shortage of a key ingredient for creating wind power. This shortage caused a decrease in the production of electricity, which in turn affected the energy supply needed to refine gasoline. As a result, there was a decrease in the amount of gasoline pumped in Cuba. It seems like even the gentlest breeze in Minneapolis can have far-reaching effects on the other side of the world!. Keep the description simple.
ChatGPT: In Minneapolis, the wind turbines stand still as the gentle breeze slows down, causing a decrease in wind speed. Meanwhile, in Cuba, a gas station sits quiet as fewer cars line up to pump gasoline, reflecting a decrease in the amount of fuel being pumped. The stillness in both scenes highlights the impactful connection between the two variables, despite being in different parts of the world.

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: [ Brutalism ] and depicting this scene: In Minneapolis, the wind turbines stand still as the gentle breeze slows down, causing a decrease in wind speed. Meanwhile, in Cuba, a gas station sits quiet as fewer cars line up to pump gasoline, reflecting a decrease in the amount of fuel being pumped. The stillness in both scenes highlights the impactful connection between the two variables, despite being in different parts of the world. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of two stark landscapes, one featuring the Minneapolis wind turbines against a Brutalist urban backdrop, and the other showcasing the quiet gas station in Cuba. The Minneapolis scene should convey a sense of industrial grandeur with imposing structures and the motionless wind turbines, while the Cuban scene should emphasize the eerie emptiness of the gas station with a Brutalist architectural style. Both scenes should capture the contrasting stillness and convey the unifying theme of decreased activity.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in The wind speed in Minneapolis caused Gasoline pumped in Cuba to decrease.

AI academic paper

(Because p < 0.01)
A Cubic Link: Winds in Twin Cities and Gasoline in Cuba

Journal of Comparative Aerodynamics

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between The wind speed in Minneapolis and Gasoline pumped in Cuba. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from NOAA National Climate Data Center and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9040148 and p < 0.01 for 1984 to 2021.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
A Cubic Link: Winds in Twin Cities and Gasoline in Cuba

[[ABSTRACT]]
This research delves into the whimsical connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba. We embarked on this comical journey using data from the NOAA National Climate Data Center and the Energy Information Administration to unravel the peculiar correlation. Our team uncovered a surprising correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021, leaving us scratching our heads about the whimsical ways in which seemingly unrelated elements could be interconnected. Our findings add a gust of humor to the seemingly mundane realm of data analysis, as we uncover the breezy link between far-flung regions and seemingly unconnected variables.


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 introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between The wind speed in Minneapolis and Gasoline pumped in Cuba. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
A Cubic Link: Winds in Twin Cities and Gasoline in Cuba

[[ABSTRACT]]
This research delves into the whimsical connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba. We embarked on this comical journey using data from the NOAA National Climate Data Center and the Energy Information Administration to unravel the peculiar correlation. Our team uncovered a surprising correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021, leaving us scratching our heads about the whimsical ways in which seemingly unrelated elements could be interconnected. Our findings add a gust of humor to the seemingly mundane realm of data analysis, as we uncover the breezy link between far-flung regions and seemingly unconnected variables.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As scholars and researchers, we are often drawn to uncovering the hidden connections and intricate relationships that underpin the fabric of our world. While some may scoff at the notion of tying wind speed in Minneapolis to the amount of gasoline pumped in Cuba, we embraced this seemingly whimsical endeavor with open arms and a healthy dose of skepticism. After all, who wouldn't want to unravel a breezy mystery that dances across the statistical landscape like a playful zephyr?

With a gust of curiosity and a dash of statistical know-how, we set out to explore this enigmatic relationship. The idea may seem as far-fetched as trying to correlate the price of tea in China with lunar phases, but we were undeterred in our pursuit of uncovering the unexpected and delightfully absurd.

Our journey began by harnessing the power of data from the NOAA National Climate Data Center and the Energy Information Administration. Armed with spreadsheets and a dash of humor, we navigated through the sea of numbers and variables, all the while keeping our wits about us like intrepid explorers on a whimsical quest.

Little did we know that our pursuit would lead us to a correlation coefficient of 0.9040148 and a p-value that left us gobsmacked. It was as if the statistical winds had conspired to blow our expectations away, leaving us in a state of bewildered amusement. Who would have thought that the winds of Minneapolis could whisper their influence all the way to the gas pumps of Cuba with such undeniable statistical force?

In the realm of academia, where serious faces and solemn nods often prevail, our findings serve as a breath of fresh air, injecting a breezy levity into the sometimes staid world of data analysis. It's a reminder that even in the most unlikely places, from the icy gusts of the Twin Cities to the balmy shores of the Caribbean, there exists a whisper of connection that defies conventional wisdom.

As we take you through our research journey, we invite you to join us in a lighthearted exploration of statistical zephyrs, geographic chuckles, and the joyful dance of seemingly unrelated variables. Prepare to be swept away by the zany connections that await, and brace yourself for a whirlwind of statistical revelation and playful punnery.


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 wind speed in Minneapolis and Gasoline pumped in Cuba. 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
A Cubic Link: Winds in Twin Cities and Gasoline in Cuba

[[ABSTRACT]]
This research delves into the whimsical connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba. We embarked on this comical journey using data from the NOAA National Climate Data Center and the Energy Information Administration to unravel the peculiar correlation. Our team uncovered a surprising correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021, leaving us scratching our heads about the whimsical ways in which seemingly unrelated elements could be interconnected. Our findings add a gust of humor to the seemingly mundane realm of data analysis, as we uncover the breezy link between far-flung regions and seemingly unconnected variables.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As scholars and researchers, we are often drawn to uncovering the hidden connections and intricate relationships that underpin the fabric of our world. While some may scoff at the notion of tying wind speed in Minneapolis to the amount of gasoline pumped in Cuba, we embraced this seemingly whimsical endeavor with open arms and a healthy dose of skepticism. After all, who wouldn't want to unravel a breezy mystery that dances across the statistical landscape like a playful zephyr?
With a gust of curiosity and a dash of statistical know-how, we set out to explore this enigmatic relationship. The idea may seem as far-fetched as trying to correlate the price of tea in China with lunar phases, but we were undeterred in our pursuit of uncovering the unexpected and delightfully absurd.
Our journey began by harnessing the power of data from the NOAA National Climate Data Center and the Energy Information Administration. Armed with spreadsheets and a dash of humor, we navigated through the sea of numbers and variables, all the while keeping our wits about us like intrepid explorers on a whimsical quest.
Little did we know that our pursuit would lead us to a correlation coefficient of 0.9040148 and a p-value that left us gobsmacked. It was as if the statistical winds had conspired to blow our expectations away, leaving us in a state of bewildered amusement. Who would have thought that the winds of Minneapolis could whisper their influence all the way to the gas pumps of Cuba with such undeniable statistical force?
In the realm of academia, where serious faces and solemn nods often prevail, our findings serve as a breath of fresh air, injecting a breezy levity into the sometimes staid world of data analysis. It's a reminder that even in the most unlikely places, from the icy gusts of the Twin Cities to the balmy shores of the Caribbean, there exists a whisper of connection that defies conventional wisdom.
As we take you through our research journey, we invite you to join us in a lighthearted exploration of statistical zephyrs, geographic chuckles, and the joyful dance of seemingly unrelated variables. Prepare to be swept away by the zany connections that await, and brace yourself for a whirlwind of statistical revelation and playful punnery.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.," the authors found a strong positive correlation between wind speed in urban areas and the consumption of fossil fuels in distant tropical regions. Further empirical evidence by Doe and Jones supported these findings, indicating a statistically significant relationship between atmospheric movements and the global flow of petroleum-based products.

But now, let's pivot from solemn studies to some literary sources that could blow some fresh air into this seemingly improbable connection. "The Age of Wind and Gasoline" by Lorem Ipsum explores the historical winds that propelled ships carrying valuable fuel across the seas. Meanwhile, "From Gusts to Gas Pumps: A Tale of Two Hemispheres" by Ipsum Lorem delves into the whimsical journey of a zephyr from the icy winds of the north to the balmy breezes of the Caribbean, all while carrying the faint aroma of gasoline.

In a surprising turn of events, the fictional works "Whims of Windward: A Zephyr's Tale" by Jane Zephyr and "The Gasoline Conundrum" by John Pumpman seem to capture the essence of this whimsical correlation in an unexpectedly accurate manner, despite their fictional nature. As unlikely as it may seem, these imaginative writings offer a delightfully entertaining, if not entirely scientific, perspective on the interconnectedness of winds and petroleum products.

In addition to these literary endeavors, social media posts have also weighed in on this eccentric correlation. A tweet by @GassyGusts pondered, "Are the breezes of Minneapolis secretly fueling the cars in Cuba? #WindAndGasMystery #ZephyrConspiracy." Although not a scientific inquiry by any stretch, the tweet embodies the playful curiosity that surrounds this unexpected correlation, adding a touch of levity to the otherwise serious discourse on atmospheric physics and global energy consumption.

As we breeze through these diverse sources, it becomes clear that the connection between wind speed in Minneapolis and gasoline pumped in Cuba extends beyond the boundaries of scientific investigation, weaving its whimsical threads through literature and online musings. The lively interplay between fact and fiction, serious research and whimsical ponderings, serves as a reminder that the winds of inquiry can carry us to unexpected and delightfully humorous destinations.


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 wind speed in Minneapolis and Gasoline pumped in Cuba. 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 NOAA National Climate Data Center and Energy Information Administration . You used data from 1984 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]]
A Cubic Link: Winds in Twin Cities and Gasoline in Cuba

[[ABSTRACT]]
This research delves into the whimsical connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba. We embarked on this comical journey using data from the NOAA National Climate Data Center and the Energy Information Administration to unravel the peculiar correlation. Our team uncovered a surprising correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021, leaving us scratching our heads about the whimsical ways in which seemingly unrelated elements could be interconnected. Our findings add a gust of humor to the seemingly mundane realm of data analysis, as we uncover the breezy link between far-flung regions and seemingly unconnected variables.

[[INTRODUCTION]]
As scholars and researchers, we are often drawn to uncovering the hidden connections and intricate relationships that underpin the fabric of our world. While some may scoff at the notion of tying wind speed in Minneapolis to the amount of gasoline pumped in Cuba, we embraced this seemingly whimsical endeavor with open arms and a healthy dose of skepticism. After all, who wouldn't want to unravel a breezy mystery that dances across the statistical landscape like a playful zephyr?
With a gust of curiosity and a dash of statistical know-how, we set out to explore this enigmatic relationship. The idea may seem as far-fetched as trying to correlate the price of tea in China with lunar phases, but we were undeterred in our pursuit of uncovering the unexpected and delightfully absurd.
Our journey began by harnessing the power of data from the NOAA National Climate Data Center and the Energy Information Administration. Armed with spreadsheets and a dash of humor, we navigated through the sea of numbers and variables, all the while keeping our wits about us like intrepid explorers on a whimsical quest.
Little did we know that our pursuit would lead us to a correlation coefficient of 0.9040148 and a p-value that left us gobsmacked. It was as if the statistical winds had conspired to blow our expectations away, leaving us in a state of bewildered amusement. Who would have thought that the winds of Minneapolis could whisper their influence all the way to the gas pumps of Cuba with such undeniable statistical force?
In the realm of academia, where serious faces and solemn nods often prevail, our findings serve as a breath of fresh air, injecting a breezy levity into the sometimes staid world of data analysis. It's a reminder that even in the most unlikely places, from the icy gusts of the Twin Cities to the balmy shores of the Caribbean, there exists a whisper of connection that defies conventional wisdom.
As we take you through our research journey, we invite you to join us in a lighthearted exploration of statistical zephyrs, geographic chuckles, and the joyful dance of seemingly unrelated variables. Prepare to be swept away by the zany connections that await, and brace yourself for a whirlwind of statistical revelation and playful punnery.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To embark on our whimsical quest to uncover the peculiar connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba, we employed a blend of data collection and statistical tomfoolery that would make even the most serious researcher crack a smile.

Data Collection:
We gathered historical wind speed data from the NOAA National Climate Data Center, embracing the gusty spirit of adventure as we sifted through decades of wind-related statistics. The data felt like a breath of fresh air, albeit one that occasionally ruffled our scholarly feathers. As for gasoline consumption in Cuba, we turned to the Energy Information Administration, where we filled our digital gas cans with information spanning from 1984 to 2021. The juxtaposition of these two seemingly unrelated datasets imbued our research with an element of delightful absurdity, leading us down a playful path of statistical inquiry.

Statistical Analysis:
With our treasure trove of data in hand, we unleashed a tempest of statistical analysis to unravel the windy enigma. Channeling the spirits of both serious academia and jovial curiosity, we calculated correlation coefficients and p-values with a fervor that would have made even the most stoic statistician crack a smile. Our trusty statistical software became the wind in our analytical sails, guiding us through the turbulent seas of data, all the while reminding us not to get swept away by the statistical whimsy.

Correlation Coefficients and P-Values:
As we twirled through the dance of correlation coefficients, we uncovered a surprisingly robust value of 0.9040148, lending a gust of statistical credibility to our zephyrous hypothesis. The p-value, with its unmistakable indication of statistical significance (less than 0.01), left us feeling as if we had stumbled upon a humorous punchline in the midst of our data-driven comedy show. These numerical revelations served as the wind beneath our research wings, propelling us toward the undeniable conclusion that there existed a breezy link between Minneapolis and Cuba that defied conventional logic.

Wind Direction and Gasoline Consumption:
In addition to the statistical rigamarole, we also delved into the directional components of wind in Minneapolis, hoping to discern any quirky patterns that might playfully nudge the gasoline pumps in Cuba. Our analysis of wind direction, while not without its technical challenges, added a dash of whimsy to our findings, reminding us that even numerical headings can harbor a humorous tale of interconnectedness.

Limitations and Windbreaks:
Though our research journey was filled with breezy absurdity and statistical mirth, we must acknowledge the limitations of our study. The unpredictable nature of both wind patterns and global gasoline markets lends a whimsical uncertainty to our findings. Furthermore, the potential influence of variables such as political winds, economic gusts, and cultural breezes remains an enigmatic force that dances at the edge of our research horizon. As the winds of academia continue to blow, we recognize that our findings, while delightfully compelling, are but a gentle zephyr in the grand scheme of scholarly inquiry.

In essence, our methodology embraced the winds of statistical analysis, the data-driven gusts of inquiry, and the playful zephyrs of absurdity, culminating in a journey that breathed life into the seemingly mundane realms of research. As we move forward, we invite fellow researchers to join us in the lighthearted pursuit of uncovering the unexpected, the whimsical, and the breezy connections that defy the staid conventions of scholarly inquiry. Together, let us set sail on the winds of statistical revelation and revel in the joyful dance of seemingly unrelated variables, for there is whimsy to be found in the most unexpected of places.


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

Please make up the results section of an academic research paper presenting the findings of the connection between The wind speed in Minneapolis and Gasoline pumped in Cuba. 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 NOAA National Climate Data Center and Energy Information Administration .

For the time period 1984 to 2021, you found a correlation 0.9040148, r-squared of 0.8172428, and p < 0.01.

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

Here is the title and abstract of the paper:
[[TITLE]]
A Cubic Link: Winds in Twin Cities and Gasoline in Cuba

[[ABSTRACT]]
This research delves into the whimsical connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba. We embarked on this comical journey using data from the NOAA National Climate Data Center and the Energy Information Administration to unravel the peculiar correlation. Our team uncovered a surprising correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021, leaving us scratching our heads about the whimsical ways in which seemingly unrelated elements could be interconnected. Our findings add a gust of humor to the seemingly mundane realm of data analysis, as we uncover the breezy link between far-flung regions and seemingly unconnected variables.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As scholars and researchers, we are often drawn to uncovering the hidden connections and intricate relationships that underpin the fabric of our world. While some may scoff at the notion of tying wind speed in Minneapolis to the amount of gasoline pumped in Cuba, we embraced this seemingly whimsical endeavor with open arms and a healthy dose of skepticism. After all, who wouldn't want to unravel a breezy mystery that dances across the statistical landscape like a playful zephyr?
With a gust of curiosity and a dash of statistical know-how, we set out to explore this enigmatic relationship. The idea may seem as far-fetched as trying to correlate the price of tea in China with lunar phases, but we were undeterred in our pursuit of uncovering the unexpected and delightfully absurd.
Our journey began by harnessing the power of data from the NOAA National Climate Data Center and the Energy Information Administration. Armed with spreadsheets and a dash of humor, we navigated through the sea of numbers and variables, all the while keeping our wits about us like intrepid explorers on a whimsical quest.
Little did we know that our pursuit would lead us to a correlation coefficient of 0.9040148 and a p-value that left us gobsmacked. It was as if the statistical winds had conspired to blow our expectations away, leaving us in a state of bewildered amusement. Who would have thought that the winds of Minneapolis could whisper their influence all the way to the gas pumps of Cuba with such undeniable statistical force?
In the realm of academia, where serious faces and solemn nods often prevail, our findings serve as a breath of fresh air, injecting a breezy levity into the sometimes staid world of data analysis. It's a reminder that even in the most unlikely places, from the icy gusts of the Twin Cities to the balmy shores of the Caribbean, there exists a whisper of connection that defies conventional wisdom.
As we take you through our research journey, we invite you to join us in a lighthearted exploration of statistical zephyrs, geographic chuckles, and the joyful dance of seemingly unrelated variables. Prepare to be swept away by the zany connections that await, and brace yourself for a whirlwind of statistical revelation and playful punnery.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Upon delving into the mystical world of data, we unearthed a correlation coefficient of 0.9040148 between the wind speed in Minneapolis and the volume of gasoline pumped in Cuba from 1984 to 2021. This unexpected result left us flabbergasted, much like a sudden gust of wind catching us off guard. With an r-squared value of 0.8172428, we found ourselves blown away by the strength of this connection – figuratively speaking, of course.

Our p-value of less than 0.01 added a touch of statistical drama to the mix, leaving us feeling as though we had stumbled upon a mathematical whirlwind that defied all expectations. Who would have thought that the breezy antics of Minneapolis's wind and the gas-guzzling habits of Cuba could be so closely intertwined?

Remarkably, our findings are visually represented in Figure 1, a scatterplot that vividly illustrates the robust correlation between the wind speed in Minneapolis and the amount of gasoline pumped in Cuba. One might say that this graph blew us away, but that would only add to the pun fun swirling around this unlikely coupling of variables.

It seems that even in the realm of data analysis, there exists a playful breeze of connection between disparate elements. Our results serve as a gentle reminder that beneath the serious exterior of statistics and research, a whimsical dance of data can enliven the spirit and tickle the funny bone. Who knew that a tale as old as time – or at least as old as statistical analysis – could unfold in such an unexpected and lighthearted manner?


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 wind speed in Minneapolis and Gasoline pumped in Cuba. 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]]
A Cubic Link: Winds in Twin Cities and Gasoline in Cuba

[[ABSTRACT]]
This research delves into the whimsical connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba. We embarked on this comical journey using data from the NOAA National Climate Data Center and the Energy Information Administration to unravel the peculiar correlation. Our team uncovered a surprising correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021, leaving us scratching our heads about the whimsical ways in which seemingly unrelated elements could be interconnected. Our findings add a gust of humor to the seemingly mundane realm of data analysis, as we uncover the breezy link between far-flung regions and seemingly unconnected variables.

[[LITERATURE REVIEW]]
In "Smith et al.," the authors found a strong positive correlation between wind speed in urban areas and the consumption of fossil fuels in distant tropical regions. Further empirical evidence by Doe and Jones supported these findings, indicating a statistically significant relationship between atmospheric movements and the global flow of petroleum-based products.
But now, let's pivot from solemn studies to some literary sources that could blow some fresh air into this seemingly improbable connection. "The Age of Wind and Gasoline" by Lorem Ipsum explores the historical winds that propelled ships carrying valuable fuel across the seas. Meanwhile, "From Gusts to Gas Pumps: A Tale of Two Hemispheres" by Ipsum Lorem delves into the whimsical journey of a zephyr from the icy winds of the north to the balmy breezes of the Caribbean, all while carrying the faint aroma of gasoline.
In a surprising turn of events, the fictional works "Whims of Windward: A Zephyr's Tale" by Jane Zephyr and "The Gasoline Conundrum" by John Pumpman seem to capture the essence of this whimsical correlation in an unexpectedly accurate manner, despite their fictional nature. As unlikely as it may seem, these imaginative writings offer a delightfully entertaining, if not entirely scientific, perspective on the interconnectedness of winds and petroleum products.
In addition to these literary endeavors, social media posts have also weighed in on this eccentric correlation. A tweet by @GassyGusts pondered, "Are the breezes of Minneapolis secretly fueling the cars in Cuba? #WindAndGasMystery #ZephyrConspiracy." Although not a scientific inquiry by any stretch, the tweet embodies the playful curiosity that surrounds this unexpected correlation, adding a touch of levity to the otherwise serious discourse on atmospheric physics and global energy consumption.
As we breeze through these diverse sources, it becomes clear that the connection between wind speed in Minneapolis and gasoline pumped in Cuba extends beyond the boundaries of scientific investigation, weaving its whimsical threads through literature and online musings. The lively interplay between fact and fiction, serious research and whimsical ponderings, serves as a reminder that the winds of inquiry can carry us to unexpected and delightfully humorous destinations.

[[RESULTS]]
Upon delving into the mystical world of data, we unearthed a correlation coefficient of 0.9040148 between the wind speed in Minneapolis and the volume of gasoline pumped in Cuba from 1984 to 2021. This unexpected result left us flabbergasted, much like a sudden gust of wind catching us off guard. With an r-squared value of 0.8172428, we found ourselves blown away by the strength of this connection – figuratively speaking, of course.
Our p-value of less than 0.01 added a touch of statistical drama to the mix, leaving us feeling as though we had stumbled upon a mathematical whirlwind that defied all expectations. Who would have thought that the breezy antics of Minneapolis's wind and the gas-guzzling habits of Cuba could be so closely intertwined?
Remarkably, our findings are visually represented in Figure 1, a scatterplot that vividly illustrates the robust correlation between the wind speed in Minneapolis and the amount of gasoline pumped in Cuba. One might say that this graph blew us away, but that would only add to the pun fun swirling around this unlikely coupling of variables.
It seems that even in the realm of data analysis, there exists a playful breeze of connection between disparate elements. Our results serve as a gentle reminder that beneath the serious exterior of statistics and research, a whimsical dance of data can enliven the spirit and tickle the funny bone. Who knew that a tale as old as time – or at least as old as statistical analysis – could unfold in such an unexpected and lighthearted manner?

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings serve as a breath of fresh air in the realm of statistical analysis, affirming the quirky connection between the wind speed in Minneapolis and the gasoline pumped in Cuba. The results not only corroborate the prior research by Smith et al. and Doe and Jones but also add a whimsical twist to the serious discourse on atmospheric physics and global energy consumption. It appears that the winds of inquiry have indeed led us to an unexpected destination, much like a zephyr meandering its way across continents.

The robust correlation coefficient of 0.9040148 and the substantial r-squared value of 0.8172428 paint a vivid picture of the wind-gasoline connection, akin to a gust of wind painting ripples on the surface of a pond. Our findings support the notion that atmospheric movements in one region can exert a whimsical influence on activities in a seemingly disparate part of the globe. Who would have thought that the breezy antics of Minneapolis's wind and the gas-guzzling habits of Cuba could be so closely intertwined, much like characters in a comical play unwittingly affecting each other's actions?

It is worth noting that our data analysis has brought some levity to the otherwise serious world of statistics and research. The p-value of less than 0.01 added a touch of statistical drama to the mix, leaving us feeling as though we had stumbled upon a mathematical whirlwind that defied all expectations. Much like a sudden gust of wind catching us off guard, our results have sparked a delightful sense of astonishment and amusement.

Figure 1, our scatterplot, vividly illustrates the breezy correlation between the wind speed in Minneapolis and the volume of gasoline pumped in Cuba. One might say that this graph blew us away, but that would only add to the pun fun swirling around this unlikely coupling of variables. These visual representations add a touch of whimsy to the otherwise solemn world of data visualization, reminding us that even in the domain of empirical evidence, there lurks a playful breeze of connection between far-flung elements.

Our study offers a lighthearted reminder that the winds of inquiry can carry us to unexpected and delightfully humorous destinations. Our results, while unexpected, have blown in like a playful zephyr, adding a touch of whimsy to the serious discourse on atmospheric physics, global energy consumption, and the interplay of seemingly unrelated variables. As we continue to navigate the winds of research, let us remain open to the whimsical surprises that await us, much like a zephyr carrying the faint aroma of gasoline across distant shores.


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 wind speed in Minneapolis and Gasoline pumped in Cuba. 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]]
A Cubic Link: Winds in Twin Cities and Gasoline in Cuba

[[ABSTRACT]]
This research delves into the whimsical connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba. We embarked on this comical journey using data from the NOAA National Climate Data Center and the Energy Information Administration to unravel the peculiar correlation. Our team uncovered a surprising correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021, leaving us scratching our heads about the whimsical ways in which seemingly unrelated elements could be interconnected. Our findings add a gust of humor to the seemingly mundane realm of data analysis, as we uncover the breezy link between far-flung regions and seemingly unconnected variables.

[[INTRDUCTION]]
As scholars and researchers, we are often drawn to uncovering the hidden connections and intricate relationships that underpin the fabric of our world. While some may scoff at the notion of tying wind speed in Minneapolis to the amount of gasoline pumped in Cuba, we embraced this seemingly whimsical endeavor with open arms and a healthy dose of skepticism. After all, who wouldn't want to unravel a breezy mystery that dances across the statistical landscape like a playful zephyr?
With a gust of curiosity and a dash of statistical know-how, we set out to explore this enigmatic relationship. The idea may seem as far-fetched as trying to correlate the price of tea in China with lunar phases, but we were undeterred in our pursuit of uncovering the unexpected and delightfully absurd.
Our journey began by harnessing the power of data from the NOAA National Climate Data Center and the Energy Information Administration. Armed with spreadsheets and a dash of humor, we navigated through the sea of numbers and variables, all the while keeping our wits about us like intrepid explorers on a whimsical quest.
Little did we know that our pursuit would lead us to a correlation coefficient of 0.9040148 and a p-value that left us gobsmacked. It was as if the statistical winds had conspired to blow our expectations away, leaving us in a state of bewildered amusement. Who would have thought that the winds of Minneapolis could whisper their influence all the way to the gas pumps of Cuba with such undeniable statistical force?
In the realm of academia, where serious faces and solemn nods often prevail, our findings serve as a breath of fresh air, injecting a breezy levity into the sometimes staid world of data analysis. It's a reminder that even in the most unlikely places, from the icy gusts of the Twin Cities to the balmy shores of the Caribbean, there exists a whisper of connection that defies conventional wisdom.
As we take you through our research journey, we invite you to join us in a lighthearted exploration of statistical zephyrs, geographic chuckles, and the joyful dance of seemingly unrelated variables. Prepare to be swept away by the zany connections that await, and brace yourself for a whirlwind of statistical revelation and playful punnery.

[[RESULTS]]
Upon delving into the mystical world of data, we unearthed a correlation coefficient of 0.9040148 between the wind speed in Minneapolis and the volume of gasoline pumped in Cuba from 1984 to 2021. This unexpected result left us flabbergasted, much like a sudden gust of wind catching us off guard. With an r-squared value of 0.8172428, we found ourselves blown away by the strength of this connection – figuratively speaking, of course.
Our p-value of less than 0.01 added a touch of statistical drama to the mix, leaving us feeling as though we had stumbled upon a mathematical whirlwind that defied all expectations. Who would have thought that the breezy antics of Minneapolis's wind and the gas-guzzling habits of Cuba could be so closely intertwined?
Remarkably, our findings are visually represented in Figure 1, a scatterplot that vividly illustrates the robust correlation between the wind speed in Minneapolis and the amount of gasoline pumped in Cuba. One might say that this graph blew us away, but that would only add to the pun fun swirling around this unlikely coupling of variables.
It seems that even in the realm of data analysis, there exists a playful breeze of connection between disparate elements. Our results serve as a gentle reminder that beneath the serious exterior of statistics and research, a whimsical dance of data can enliven the spirit and tickle the funny bone. Who knew that a tale as old as time – or at least as old as statistical analysis – could unfold in such an unexpected and lighthearted manner?

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]
In conclusion, our research has blown the lid off the unlikely yet uproarious connection between the wind speed in Minneapolis and the volume of gasoline pumped in Cuba. The delightful surprise of a correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021 has left us reeling in both astonishment and amusement. It's as if statistical science decided to perform a comedic sketch, and we were mere spectators to its whimsical theatrics.

This study has not just uncovered a significant statistical relationship but has also added a gust of humor to the otherwise dry domain of data analysis. It's as if the winds of Minneapolis and the gasoline consumption in Cuba decided to tango across the stage of statistical significance, leaving us grinning at the unexpected choreography of data.

Our findings not only serve as a fascinating insight into the whimsical interplay of variables but also stand as a testament to the delightful unpredictability of statistical research. As researchers, we have learned that even in the most unlikely of places and with the most unusual pairings of variables, the unexpected can unfold with a flourish of statistical whimsy.

In light of these comically charming results, we assert that further research into this delightfully breezy connection between wind speed in Minneapolis and gasoline pumped in Cuba is unnecessary. The playful winds of statistical correlation have spoken, and we'd be remiss to disturb the jovial dance they've orchestrated. After all, sometimes, in the world of research, it's best to let the statistical zephyrs have the limelight and simply enjoy the show.


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 A Cubic Link: Winds in Twin Cities and Gasoline in Cuba. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Comparative Aerodynamics


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 A Cubic Link: Winds in Twin Cities and Gasoline in Cuba. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Transdimensional Energy Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled A Cubic Link: Winds in Twin Cities and Gasoline in Cuba with an abstract of This research delves into the whimsical connection between wind speed in Minneapolis and the amount of gasoline pumped in Cuba. We embarked on this comical journey using data from the NOAA National Climate Data Center and the Energy Information Administration to unravel the peculiar correlation. Our team uncovered a surprising correlation coefficient of 0.9040148 and a p-value of less than 0.01 from 1984 to 2021, leaving us scratching our heads about the whimsical ways in which seemingly unrelated elements could be interconnected. Our findings add a gust of humor to the seemingly mundane realm of data analysis, as we uncover the breezy link between far-flung regions and seemingly unconnected variables.

ChatGPT:

wind speed, Minneapolis, gasoline consumption, Cuba, correlation coefficient, data analysis, NOAA National Climate Data Center, Energy Information Administration

*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 wind speed in Minneapolis
Detailed data title: Annual Average Wind Speed at MINNEAPOLIS ST. PAUL INTERNATIONAL AIRPORT, MN US
Source: NOAA National Climate Data Center
See what else correlates with The wind speed in Minneapolis

Gasoline pumped in Cuba
Detailed data title: Volume of gasoline pumped consumed in Cuba in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Gasoline pumped in Cuba

Correlation r = 0.9040148 (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 = 0.8172428 (Coefficient of determination)
This means 81.7% of the change in the one variable (i.e., Gasoline pumped in Cuba) is predictable based on the change in the other (i.e., The wind speed in Minneapolis) over the 38 years from 1984 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.5E-15. 0.0000000000000075130813909994
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.9 in 7.5E-13% of random cases. Said differently, if you correlated 133,101,180,189,262 random variables You don't actually need 133 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 37 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 37 because we have two variables measured over a period of 38 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.

[ 0.82, 0.95 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021
The wind speed in Minneapolis (Wind mph)11.611.61110.51110.310.710.510.110.110.510.510.19.28.79.69.69.29.69.49.48.99.29.28.78.58.38.58.58.99.69.69.49.48.79.28.98.7
Gasoline pumped in Cuba (Million Barrels/Day)26.804527.30792826272625232020202125129.39.511.97939.745238.272939.628388.6465310.09588.833816.800637.36476.169645.281596.473455.398445.328332.944613145.772366.894116.473455.538665.53866




Why this works

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

    For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

    (This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
    They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([11.6,11.6,11,10.5,11,10.3,10.7,10.5,10.1,10.1,10.5,10.5,10.1,9.2,8.7,9.6,9.6,9.2,9.6,9.4,9.4,8.9,9.2,9.2,8.7,8.5,8.3,8.5,8.5,8.9,9.6,9.6,9.4,9.4,8.7,9.2,8.9,8.7,])
array_2 = np.array([26.8045,27.3079,28,26,27,26,25,23,20,20,20,21,25,12,9.3,9.5,11.9793,9.74523,8.27293,9.62838,8.64653,10.0958,8.83381,6.80063,7.3647,6.16964,5.28159,6.47345,5.39844,5.32833,2.9446,13,14,5.77236,6.89411,6.47345,5.53866,5.53866,])
array_1_name = "The wind speed in Minneapolis"
array_2_name = "Gasoline pumped in Cuba"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!


Correlation ID: 4776 · Black Variable ID: 25344 · Red Variable ID: 24334
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0