about · email me · subscribe
Spurious correlation #4,355 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Democratic Presidential candidate in North Carolina and the second variable is Fossil fuel use in Bahrain.  The chart goes from 1980 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Every time a Democrat Presidential candidate in North Carolina gets more votes, a secret underground network of fossil fuel-loving moles in Bahrain receive a signal to ramp up their energy consumption in support. It's a classic case of political fervor igniting distant actions, fueled by a combination of patriotic passion and a penchant for prehistoric power sources!

Model: dalle-3
Prompt: [ A scene from A Disney Movie ] In this scene, imagine a picturesque, vibrant hillside in North Carolina, covered in lush green grass and dotted with colorful flowers. At the center of the hillside stands a digital counter, its numbers incrementing with each vote cast for the Democrat Presidential candidate, symbolizing the democratic process in action. Meanwhile, deep underground in Bahrain, a network of industrious moles scurry through intricately designed tunnels, diligently sensing the signal from the hillside and rushing towards giant fossil fuel-powered turbines. As they reach the turbines, they energetically begin to crank them up to maximum capacity, their fervent energy fueling the machinery. The contrasting scenes of the bustling election activity and the industrious moles intertwine, symbolizing the complex interplay between political passion and the underbelly of energy consumption, creating a visually captivating and thought-provoking image. 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: Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain. 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: Hyper-realistic Macabre An image that looks like it is a scene from a Pixar movie A scene from Skyrim An image that looks like it is a scene from A Disney Movie
ChatGPT: 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 Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain, in the following situation: Every time a Democrat Presidential candidate in North Carolina gets more votes, a secret underground network of fossil fuel-loving moles in Bahrain receive a signal to ramp up their energy consumption in support. It's a classic case of political fervor igniting distant actions, fueled by a combination of patriotic passion and a penchant for prehistoric power sources!. Keep the description simple.
ChatGPT: In North Carolina, as more votes are cast for the Democrat Presidential candidate, a digital counter mounted on a lush green hillside clicks upwards, while in Bahrain, a network of industrious moles deep underground sense the signal and scurry to giant fossil fuel-powered turbines, eagerly cranking them up to maximum capacity with fervent energy. The contrasting scenes of the bustling election activity and the industrious moles symbolize the complex interplay between political passion and the underbelly of energy consumption.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A scene from A Disney Movie ] and depicting this scene: In North Carolina, as more votes are cast for the Democrat Presidential candidate, a digital counter mounted on a lush green hillside clicks upwards, while in Bahrain, a network of industrious moles deep underground sense the signal and scurry to giant fossil fuel-powered turbines, eagerly cranking them up to maximum capacity with fervent energy. The contrasting scenes of the bustling election activity and the industrious moles symbolize the complex interplay between political passion and the underbelly of energy consumption. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ A scene from A Disney Movie ] In this scene, imagine a picturesque, vibrant hillside in North Carolina, covered in lush green grass and dotted with colorful flowers. At the center of the hillside stands a digital counter, its numbers incrementing with each vote cast for the Democrat Presidential candidate, symbolizing the democratic process in action. Meanwhile, deep underground in Bahrain, a network of industrious moles scurry through intricately designed tunnels, diligently sensing the signal from the hillside and rushing towards giant fossil fuel-powered turbines. As they reach the turbines, they energetically begin to crank them up to maximum capacity, their fervent energy fueling the machinery. The contrasting scenes of the bustling election activity and the industrious moles intertwine, symbolizing the complex interplay between political passion and the underbelly of energy consumption, creating a visually captivating and thought-provoking image.

*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 an increase in Votes for the Democrat Presidential candidate in North Carolina caused Fossil fuel use in Bahrain to increase.

AI academic paper

(Because p < 0.01)
Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?

The Journal of Political Quirkiness

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9782189 and p < 0.01 for 1980 to 2020.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?

[[ABSTRACT]]
This study scrutinizes the seemingly baffling link between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain. By using data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we aimed to shed some light on this oddball connection. Our statistical analysis revealed a striking correlation coefficient of 0.9782189 with a p-value less than 0.01 for the period spanning from 1980 to 2020. As we delve into this curious correlation, we unravel layers of complex statistical intricacies and unearth unexpected patterns, prompting us to wonder: is this a serendipitous finding or merely a whimsical statistical fluke? Join us in this unexpected journey through the fumes of fossil fuel use and the crossing paths of political preferences, as we navigate through the realm of correlation with a lighthearted twist.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain. 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]]
Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?

[[ABSTRACT]]
This study scrutinizes the seemingly baffling link between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain. By using data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we aimed to shed some light on this oddball connection. Our statistical analysis revealed a striking correlation coefficient of 0.9782189 with a p-value less than 0.01 for the period spanning from 1980 to 2020. As we delve into this curious correlation, we unravel layers of complex statistical intricacies and unearth unexpected patterns, prompting us to wonder: is this a serendipitous finding or merely a whimsical statistical fluke? Join us in this unexpected journey through the fumes of fossil fuel use and the crossing paths of political preferences, as we navigate through the realm of correlation with a lighthearted twist.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
Ah, the mysteries of statistical correlation. It's like trying to find a polar bear in a snowstorm - you can't help but get lost in the numbers. In this study, we embark on a perplexing journey into the realms of democracy and fossil fuels, where palm votes meet oil floats. It's a tale of two seemingly unconnected variables - the number of votes for the Democrat Presidential candidate in North Carolina and the fossil fuel use in Bahrain. A match made in statistical wonderland or an unlikely pairing akin to mixing oil and water? Let's dig in and uncover the peculiar twists and turns of this enigmatic correlation.

As researchers, we often find ourselves tangled in the web of causality, chasing correlations that beguile and perplex us. Picture this – a Democrat scoring high in North Carolina, while Bahrain's love affair with fossil fuels dances on. What could possibly connect the two? It's like trying to fit a square peg into a round hole; you can't help but wonder if this correlation is a statistical marvel or a whimsical fluke. Nevertheless, armed with our trusted statistical tools and an unabashed sense of curiosity, we set out to unravel this statistical enigma.

Our journey through data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration has led us down a path of unexpected discovery. The correlation coefficient of 0.9782189 beckons us to delve deeper into the statistical rabbit hole, and with a p-value less than 0.01, the plot thickens. But fear not, fellow researchers, for in the midst of complex statistical intricacies, we promise to sprinkle some lightheartedness and humor along the way. After all, who said statistical analysis can't come with a side of puns and quirky observations?

So, let's grab our magnifying glasses and embark on this improbable quest - a journey through the intersecting paths of political preferences and fossil fuel fumes. Will we stumble upon a statistical marvel, or will the data lead us into the wilderness of chance? Join us as we navigate through this unexpected convergence with a twinkle in our eye and an appetite for statistical serendipity.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain. 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?

[[ABSTRACT]]
This study scrutinizes the seemingly baffling link between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain. By using data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we aimed to shed some light on this oddball connection. Our statistical analysis revealed a striking correlation coefficient of 0.9782189 with a p-value less than 0.01 for the period spanning from 1980 to 2020. As we delve into this curious correlation, we unravel layers of complex statistical intricacies and unearth unexpected patterns, prompting us to wonder: is this a serendipitous finding or merely a whimsical statistical fluke? Join us in this unexpected journey through the fumes of fossil fuel use and the crossing paths of political preferences, as we navigate through the realm of correlation with a lighthearted twist.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Ah, the mysteries of statistical correlation. It's like trying to find a polar bear in a snowstorm - you can't help but get lost in the numbers. In this study, we embark on a perplexing journey into the realms of democracy and fossil fuels, where palm votes meet oil floats. It's a tale of two seemingly unconnected variables - the number of votes for the Democrat Presidential candidate in North Carolina and the fossil fuel use in Bahrain. A match made in statistical wonderland or an unlikely pairing akin to mixing oil and water? Let's dig in and uncover the peculiar twists and turns of this enigmatic correlation.
As researchers, we often find ourselves tangled in the web of causality, chasing correlations that beguile and perplex us. Picture this – a Democrat scoring high in North Carolina, while Bahrain's love affair with fossil fuels dances on. What could possibly connect the two? It's like trying to fit a square peg into a round hole; you can't help but wonder if this correlation is a statistical marvel or a whimsical fluke. Nevertheless, armed with our trusted statistical tools and an unabashed sense of curiosity, we set out to unravel this statistical enigma.
Our journey through data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration has led us down a path of unexpected discovery. The correlation coefficient of 0.9782189 beckons us to delve deeper into the statistical rabbit hole, and with a p-value less than 0.01, the plot thickens. But fear not, fellow researchers, for in the midst of complex statistical intricacies, we promise to sprinkle some lightheartedness and humor along the way. After all, who said statistical analysis can't come with a side of puns and quirky observations?
So, let's grab our magnifying glasses and embark on this improbable quest - a journey through the intersecting paths of political preferences and fossil fuel fumes. Will we stumble upon a statistical marvel, or will the data lead us into the wilderness of chance? Join us as we navigate through this unexpected convergence with a twinkle in our eye and an appetite for statistical serendipity.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

As we embark on our expedition through the peculiar world of statistical correlations, we must first delve into existing literature that may shed light on the unexpected connection between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain.

Smith (2015) delved into the intricacies of voter behavior, focusing on the influence of regional demographics on electoral outcomes. Doe and Jones (2017) explored the global energy landscape, unraveling the complex dynamics of fossil fuel consumption among nations. Their rigorous analyses undoubtedly provide valuable insights into the individual components of our unconventional correlation.

Turning to non-fiction works on energy and politics, "The Quest: Energy, Security, and the Remaking of the Modern World" by Daniel Yergin provides a comprehensive analysis of the interplay between energy resources and geopolitical forces. Similarly, "The Signal and the Noise: Why So Many Predictions Fail - But Some Don't" by Nate Silver offers a thought-provoking examination of statistical trends and their implications in the realm of politics and society.

On the fictional side, "The Pelican Brief" by John Grisham, although not directly related to our subject matter, presents a riveting narrative that intertwines legal and political intrigue. Meanwhile, "The Power" by Naomi Alderman offers a dystopian account of power dynamics, serving as a metaphorical exploration of the forces at play in the political landscape.

In our tireless pursuit of knowledge, we cast a wide net in search of insights, leaving no stone unturned in our quest for enlightenment. There is some speculation that the authors may have even conducted their literature review by perusing the backs of shampoo bottles, although this remains unverified. Nonetheless, the eclectic sources at our disposal reflect the diverse avenues through which we seek to unravel the curious correlation at the heart of our study.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration . You used data from 1980 to 2020

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?

[[ABSTRACT]]
This study scrutinizes the seemingly baffling link between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain. By using data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we aimed to shed some light on this oddball connection. Our statistical analysis revealed a striking correlation coefficient of 0.9782189 with a p-value less than 0.01 for the period spanning from 1980 to 2020. As we delve into this curious correlation, we unravel layers of complex statistical intricacies and unearth unexpected patterns, prompting us to wonder: is this a serendipitous finding or merely a whimsical statistical fluke? Join us in this unexpected journey through the fumes of fossil fuel use and the crossing paths of political preferences, as we navigate through the realm of correlation with a lighthearted twist.

[[INTRODUCTION]]
Ah, the mysteries of statistical correlation. It's like trying to find a polar bear in a snowstorm - you can't help but get lost in the numbers. In this study, we embark on a perplexing journey into the realms of democracy and fossil fuels, where palm votes meet oil floats. It's a tale of two seemingly unconnected variables - the number of votes for the Democrat Presidential candidate in North Carolina and the fossil fuel use in Bahrain. A match made in statistical wonderland or an unlikely pairing akin to mixing oil and water? Let's dig in and uncover the peculiar twists and turns of this enigmatic correlation.
As researchers, we often find ourselves tangled in the web of causality, chasing correlations that beguile and perplex us. Picture this – a Democrat scoring high in North Carolina, while Bahrain's love affair with fossil fuels dances on. What could possibly connect the two? It's like trying to fit a square peg into a round hole; you can't help but wonder if this correlation is a statistical marvel or a whimsical fluke. Nevertheless, armed with our trusted statistical tools and an unabashed sense of curiosity, we set out to unravel this statistical enigma.
Our journey through data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration has led us down a path of unexpected discovery. The correlation coefficient of 0.9782189 beckons us to delve deeper into the statistical rabbit hole, and with a p-value less than 0.01, the plot thickens. But fear not, fellow researchers, for in the midst of complex statistical intricacies, we promise to sprinkle some lightheartedness and humor along the way. After all, who said statistical analysis can't come with a side of puns and quirky observations?
So, let's grab our magnifying glasses and embark on this improbable quest - a journey through the intersecting paths of political preferences and fossil fuel fumes. Will we stumble upon a statistical marvel, or will the data lead us into the wilderness of chance? Join us as we navigate through this unexpected convergence with a twinkle in our eye and an appetite for statistical serendipity.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unpack the peculiar marriage of palm votes and oil floats, our research team embarked on a methodological adventure fit for a quirky statistical odyssey. Our approach was akin to wielding a mathematical compass in search of a needle in a haystack, meticulously teasing out correlations while dodging the pitfalls of spuriousness.

First, we collected data on the number of votes for the Democrat Presidential candidate in North Carolina from the MIT Election Data and Science Lab. This involved perusing through countless spreadsheets and databases, a task not for the faint of heart but a thrilling treasure hunt for data enthusiasts. We then ventured to the Harvard Dataverse, where we unearthed a treasure trove of fossil fuel use statistics for Bahrain, delving into the depths of energy consumption data like intrepid explorers navigating uncharted statistical territory.

Our statistical toolkit consisted of a medley of robust techniques, featuring the illustrious Pearson correlation coefficient and its trusty sidekick, the t-test. Together, they formed an eccentric duo, akin to Holmes and Watson, tirelessly investigating the curious connection between political preferences and carbon emissions.

As we rolled up our sleeves and donned our metaphorical lab coats, we meticulously analyzed the data from 1980 to 2020, scrutinizing every data point with the precision of a watchmaker and the perseverance of a marathon runner. We treated each data set like a puzzle piece in a grand statistical jigsaw, piecing together the enigmatic relationship between palm votes and oil floats.

But wait, there's more! In our quest to infuse a sprinkle of merriment into the serious business of statistical analysis, we conducted a sub-analysis using a time series model to observe the evolution of the correlation over the years. This not only allowed us to capture the ebb and flow of this whimsical statistical dance but also provided a dash of drama to our otherwise staid statistical plot.

In essence, our methodology danced on the tightrope of rigorous statistical analysis and whimsical musings, weaving together a research tapestry worthy of a statistical symphony. So, buckle up, fellow voyagers of statistical discovery, as we set sail on a voyage through the turbulent seas of correlation, armed with wit, whimsy, and a hint of statistical serendipity.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 1980 to 2020, you found a correlation 0.9782189, r-squared of 0.9569123, 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]]
Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?

[[ABSTRACT]]
This study scrutinizes the seemingly baffling link between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain. By using data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we aimed to shed some light on this oddball connection. Our statistical analysis revealed a striking correlation coefficient of 0.9782189 with a p-value less than 0.01 for the period spanning from 1980 to 2020. As we delve into this curious correlation, we unravel layers of complex statistical intricacies and unearth unexpected patterns, prompting us to wonder: is this a serendipitous finding or merely a whimsical statistical fluke? Join us in this unexpected journey through the fumes of fossil fuel use and the crossing paths of political preferences, as we navigate through the realm of correlation with a lighthearted twist.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Ah, the mysteries of statistical correlation. It's like trying to find a polar bear in a snowstorm - you can't help but get lost in the numbers. In this study, we embark on a perplexing journey into the realms of democracy and fossil fuels, where palm votes meet oil floats. It's a tale of two seemingly unconnected variables - the number of votes for the Democrat Presidential candidate in North Carolina and the fossil fuel use in Bahrain. A match made in statistical wonderland or an unlikely pairing akin to mixing oil and water? Let's dig in and uncover the peculiar twists and turns of this enigmatic correlation.
As researchers, we often find ourselves tangled in the web of causality, chasing correlations that beguile and perplex us. Picture this – a Democrat scoring high in North Carolina, while Bahrain's love affair with fossil fuels dances on. What could possibly connect the two? It's like trying to fit a square peg into a round hole; you can't help but wonder if this correlation is a statistical marvel or a whimsical fluke. Nevertheless, armed with our trusted statistical tools and an unabashed sense of curiosity, we set out to unravel this statistical enigma.
Our journey through data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration has led us down a path of unexpected discovery. The correlation coefficient of 0.9782189 beckons us to delve deeper into the statistical rabbit hole, and with a p-value less than 0.01, the plot thickens. But fear not, fellow researchers, for in the midst of complex statistical intricacies, we promise to sprinkle some lightheartedness and humor along the way. After all, who said statistical analysis can't come with a side of puns and quirky observations?
So, let's grab our magnifying glasses and embark on this improbable quest - a journey through the intersecting paths of political preferences and fossil fuel fumes. Will we stumble upon a statistical marvel, or will the data lead us into the wilderness of chance? Join us as we navigate through this unexpected convergence with a twinkle in our eye and an appetite for statistical serendipity.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our statistical analysis unveiled a striking correlation coefficient of 0.9782189 between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain for the timeframe of 1980 to 2020. With an r-squared value of 0.9569123 and a p-value less than 0.01, the evidence points to a robust and puzzling relationship between these two seemingly unrelated variables. It's like trying to connect the dots between a donkey and a dragon, but here we are, uncovering a statistical phenomenon that begs for further scrutiny.

Fig. 1 showcases a scatterplot that will make your statistical antennas stand up. It's like finding a needle in a haystack, except in this case, it’s a correlation amidst puffs of fossil fuel fumes and political votes. The plot demonstrates a clear trend, akin to watching a synchronized swimming routine between palm votes and oil floats. It’s a match made in statistical wonderland, leaving us scratching our heads in disbelief - like finding a four-leaf clover in a field of oil rigs.

This unexpected correlation might just be the statistical equivalent of stumbling upon a unicorn in a field of data. It's a head-scratcher that raises eyebrows and prompts us to ponder the serendipity of statistical patterns. As we unravel this peculiar connection, it's clear that statistical analysis can sometimes lead us down paths with unexpected twists and turns. The intertwining threads of political preferences and fossil fuel use have woven a captivating narrative, challenging our assumptions and leaving us with a statistical conundrum worth exploring further.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain. 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]]
Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?

[[ABSTRACT]]
This study scrutinizes the seemingly baffling link between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain. By using data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we aimed to shed some light on this oddball connection. Our statistical analysis revealed a striking correlation coefficient of 0.9782189 with a p-value less than 0.01 for the period spanning from 1980 to 2020. As we delve into this curious correlation, we unravel layers of complex statistical intricacies and unearth unexpected patterns, prompting us to wonder: is this a serendipitous finding or merely a whimsical statistical fluke? Join us in this unexpected journey through the fumes of fossil fuel use and the crossing paths of political preferences, as we navigate through the realm of correlation with a lighthearted twist.

[[LITERATURE REVIEW]]
As we embark on our expedition through the peculiar world of statistical correlations, we must first delve into existing literature that may shed light on the unexpected connection between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain.
Smith (2015) delved into the intricacies of voter behavior, focusing on the influence of regional demographics on electoral outcomes. Doe and Jones (2017) explored the global energy landscape, unraveling the complex dynamics of fossil fuel consumption among nations. Their rigorous analyses undoubtedly provide valuable insights into the individual components of our unconventional correlation.
Turning to non-fiction works on energy and politics, "The Quest: Energy, Security, and the Remaking of the Modern World" by Daniel Yergin provides a comprehensive analysis of the interplay between energy resources and geopolitical forces. Similarly, "The Signal and the Noise: Why So Many Predictions Fail - But Some Don't" by Nate Silver offers a thought-provoking examination of statistical trends and their implications in the realm of politics and society.
On the fictional side, "The Pelican Brief" by John Grisham, although not directly related to our subject matter, presents a riveting narrative that intertwines legal and political intrigue. Meanwhile, "The Power" by Naomi Alderman offers a dystopian account of power dynamics, serving as a metaphorical exploration of the forces at play in the political landscape.
In our tireless pursuit of knowledge, we cast a wide net in search of insights, leaving no stone unturned in our quest for enlightenment. There is some speculation that the authors may have even conducted their literature review by perusing the backs of shampoo bottles, although this remains unverified. Nonetheless, the eclectic sources at our disposal reflect the diverse avenues through which we seek to unravel the curious correlation at the heart of our study.

[[RESULTS]]
Our statistical analysis unveiled a striking correlation coefficient of 0.9782189 between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain for the timeframe of 1980 to 2020. With an r-squared value of 0.9569123 and a p-value less than 0.01, the evidence points to a robust and puzzling relationship between these two seemingly unrelated variables. It's like trying to connect the dots between a donkey and a dragon, but here we are, uncovering a statistical phenomenon that begs for further scrutiny.
Fig. 1 showcases a scatterplot that will make your statistical antennas stand up. It's like finding a needle in a haystack, except in this case, it’s a correlation amidst puffs of fossil fuel fumes and political votes. The plot demonstrates a clear trend, akin to watching a synchronized swimming routine between palm votes and oil floats. It’s a match made in statistical wonderland, leaving us scratching our heads in disbelief - like finding a four-leaf clover in a field of oil rigs.
This unexpected correlation might just be the statistical equivalent of stumbling upon a unicorn in a field of data. It's a head-scratcher that raises eyebrows and prompts us to ponder the serendipity of statistical patterns. As we unravel this peculiar connection, it's clear that statistical analysis can sometimes lead us down paths with unexpected twists and turns. The intertwining threads of political preferences and fossil fuel use have woven a captivating narrative, challenging our assumptions and leaving us with a statistical conundrum worth exploring further.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our results have led us down a fascinating rabbit hole of statistical intrigue, with more twists and turns than a winding road in the Swiss Alps. In light of our findings, it's clear that there is more at play in the realm of political preferences and energy consumption than meets the eye. The nail-biting suspense of unraveling this unusual correlation is akin to watching a thrilling episode of "The Twilight Zone," leaving us with raised eyebrows and perplexed expressions.

Drawing on the literature that took a whimsical stroll through the peculiar world of statistical correlations, we find curious parallels that support and enrich our findings. Smith's exploration of voter behavior and regional demographics aligns with our revelation that palm votes and oil floats may not be as unrelated as they initially seemed. Meanwhile, Doe and Jones' analysis of global energy dynamics provides a compelling backdrop to the unlikely dance between political preferences and fossil fuel use. Who would have thought that these two disparate entities would engage in such an enthralling tango of statistical significance?

As we consider the implications of our findings, we are reminded of the wise words of Nate Silver in "The Signal and the Noise." It is a reminder that statistical trends, no matter how baffling, have the potential to yield valuable insights into the intricate tapestry of political and energy landscapes. Our study serves as a testament to the enduring allure of statistical anomalies and their capacity to surprise and delight, much like stumbling upon a hidden gem in a labyrinth of data.

The tantalizing nature of this correlation between palm votes and oil floats has propelled us into uncharted territory, challenging us to reevaluate our preconceived notions and embrace the unorthodox. Like a rollercoaster ride through the realm of statistical marvels, our study underscores the intrinsic link between seemingly disparate variables, inviting us to embrace the unexpected with open arms.

In the immortal words of John Grisham, "The Pelican Brief" may not have paved the path for our statistical musings, but it certainly resonates with the intrigue and excitement of our unexpected correlation. As we navigate this enthralling terrain of statistical wonder, we are reminded that the journey of exploration is just as fascinating as the destination itself.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Carolina and Fossil fuel use in Bahrain. 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]]
Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?

[[ABSTRACT]]
This study scrutinizes the seemingly baffling link between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain. By using data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we aimed to shed some light on this oddball connection. Our statistical analysis revealed a striking correlation coefficient of 0.9782189 with a p-value less than 0.01 for the period spanning from 1980 to 2020. As we delve into this curious correlation, we unravel layers of complex statistical intricacies and unearth unexpected patterns, prompting us to wonder: is this a serendipitous finding or merely a whimsical statistical fluke? Join us in this unexpected journey through the fumes of fossil fuel use and the crossing paths of political preferences, as we navigate through the realm of correlation with a lighthearted twist.

[[INTRDUCTION]]
Ah, the mysteries of statistical correlation. It's like trying to find a polar bear in a snowstorm - you can't help but get lost in the numbers. In this study, we embark on a perplexing journey into the realms of democracy and fossil fuels, where palm votes meet oil floats. It's a tale of two seemingly unconnected variables - the number of votes for the Democrat Presidential candidate in North Carolina and the fossil fuel use in Bahrain. A match made in statistical wonderland or an unlikely pairing akin to mixing oil and water? Let's dig in and uncover the peculiar twists and turns of this enigmatic correlation.
As researchers, we often find ourselves tangled in the web of causality, chasing correlations that beguile and perplex us. Picture this – a Democrat scoring high in North Carolina, while Bahrain's love affair with fossil fuels dances on. What could possibly connect the two? It's like trying to fit a square peg into a round hole; you can't help but wonder if this correlation is a statistical marvel or a whimsical fluke. Nevertheless, armed with our trusted statistical tools and an unabashed sense of curiosity, we set out to unravel this statistical enigma.
Our journey through data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration has led us down a path of unexpected discovery. The correlation coefficient of 0.9782189 beckons us to delve deeper into the statistical rabbit hole, and with a p-value less than 0.01, the plot thickens. But fear not, fellow researchers, for in the midst of complex statistical intricacies, we promise to sprinkle some lightheartedness and humor along the way. After all, who said statistical analysis can't come with a side of puns and quirky observations?
So, let's grab our magnifying glasses and embark on this improbable quest - a journey through the intersecting paths of political preferences and fossil fuel fumes. Will we stumble upon a statistical marvel, or will the data lead us into the wilderness of chance? Join us as we navigate through this unexpected convergence with a twinkle in our eye and an appetite for statistical serendipity.

[[RESULTS]]
Our statistical analysis unveiled a striking correlation coefficient of 0.9782189 between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain for the timeframe of 1980 to 2020. With an r-squared value of 0.9569123 and a p-value less than 0.01, the evidence points to a robust and puzzling relationship between these two seemingly unrelated variables. It's like trying to connect the dots between a donkey and a dragon, but here we are, uncovering a statistical phenomenon that begs for further scrutiny.
Fig. 1 showcases a scatterplot that will make your statistical antennas stand up. It's like finding a needle in a haystack, except in this case, it’s a correlation amidst puffs of fossil fuel fumes and political votes. The plot demonstrates a clear trend, akin to watching a synchronized swimming routine between palm votes and oil floats. It’s a match made in statistical wonderland, leaving us scratching our heads in disbelief - like finding a four-leaf clover in a field of oil rigs.
This unexpected correlation might just be the statistical equivalent of stumbling upon a unicorn in a field of data. It's a head-scratcher that raises eyebrows and prompts us to ponder the serendipity of statistical patterns. As we unravel this peculiar connection, it's clear that statistical analysis can sometimes lead us down paths with unexpected twists and turns. The intertwining threads of political preferences and fossil fuel use have woven a captivating narrative, challenging our assumptions and leaving us with a statistical conundrum worth exploring further.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our journey through the whimsical wonderland of statistical correlation has left us in awe of the serendipitous connection between palm votes and oil floats. It's as surprising as finding a penguin in the desert of data analysis! The robust correlation coefficient of 0.9782189 and a p-value less than 0.01 showcase a dance between these seemingly unrelated variables that rivals even the most intricate statistical waltz.

As we stand at the crossroads of democracy and fossil fuels, we are reminded that in the world of statistics, correlation does not always imply causation. It's like mixing apples and oranges, or perhaps in this case, ballots and barrels of oil. This eyebrow-raising correlation has raised more questions than it has answered, challenging us to reconsider the whimsical nature of statistical patterns. We might as well have stumbled upon the statistical equivalent of a pot of gold at the end of the correlation rainbow!

Yet, as we bid adieu to this statistical escapade, we firmly assert that no more research is needed in this area. For now, let's leave this quirky correlation as a charming enigma of statistical probability, a reminder that in the realm of data analysis, the unexpected can indeed make an appearance. So, let's raise our statistical glasses to this delightful feat of correlation, and may we always find joy in the whimsical dances of data analysis.


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 Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Quirkiness


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 Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage?. Respond only with the name of a fictional organization.

ChatGPT:

The Association for Quirky Correlation 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 Palm Votes and Oil Floats: A Spurious Correlation or a Political Mirage? with an abstract of This study scrutinizes the seemingly baffling link between the number of votes for the Democrat Presidential candidate in North Carolina and fossil fuel use in Bahrain. By using data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we aimed to shed some light on this oddball connection. Our statistical analysis revealed a striking correlation coefficient of 0.9782189 with a p-value less than 0.01 for the period spanning from 1980 to 2020. As we delve into this curious correlation, we unravel layers of complex statistical intricacies and unearth unexpected patterns, prompting us to wonder: is this a serendipitous finding or merely a whimsical statistical fluke? Join us in this unexpected journey through the fumes of fossil fuel use and the crossing paths of political preferences, as we navigate through the realm of correlation with a lighthearted twist.

ChatGPT:

Palm Votes, Oil Floats, Democrat Presidential candidate, North Carolina, fossil fuel use, Bahrain, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, correlation coefficient, statistical analysis, p-value, 1980-2020, statistical intricacies, unexpected patterns, serendipitous finding, whimsical statistical fluke, fumes of fossil fuel use, political preferences

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

Fossil fuel use in Bahrain
Detailed data title: Total fossil fuel use in Bahrain in billion kWh
Source: Energy Information Administration
See what else correlates with Fossil fuel use in Bahrain

Correlation r = 0.9782189 (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 = 0.9569123 (Coefficient of determination)
This means 95.7% of the change in the one variable (i.e., Fossil fuel use in Bahrain) is predictable based on the change in the other (i.e., Votes for the Democratic Presidential candidate in North Carolina) over the 11 years from 1980 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.9E-7. 0.0000001884394921257831200000
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 0.98 in 1.9E-5% of random cases. Said differently, if you correlated 5,306,743 random variables You don't actually need 5 million 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 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.92, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19801984198819921996200020042008201220162020
Votes for the Democratic Presidential candidate in North Carolina (Total votes)87563582428789016711140401107850125769015258502142650217839021893202684290
Fossil fuel use in Bahrain (Billion kWh)1.5542.2723.2733.6624.71513.02315.17721.4523.288526.799429.8464




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.




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([875635,824287,890167,1114040,1107850,1257690,1525850,2142650,2178390,2189320,2684290,])
array_2 = np.array([1.554,2.272,3.273,3.662,4.715,13.023,15.177,21.45,23.2885,26.7994,29.8464,])
array_1_name = "Votes for the Democratic Presidential candidate in North Carolina"
array_2_name = "Fossil fuel use in Bahrain"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your dedication to rating warms my heart!


Correlation ID: 4355 · Black Variable ID: 26014 · Red Variable ID: 23489
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0