about · email me · subscribe
Spurious correlation #4,364 · 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 Republican Presidential candidate in Wisconsin and the second variable is Liquefied petroleum gas used in Slovenia.  The chart goes from 1992 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

It turns out, as Republican votes in Wisconsin rise, so does the collective body heat of the supporters. This leads to a higher demand for Liquefied petroleum gas in Slovenia as they crank up the heat to stay warm, creating a truly 'political party paradox'. It's like a game of international thermostat tug-of-war, all sparked by the fiery passion of politics!

Model: dalle-3
Prompt: Generate an image of a vibrant Voting Station in Wisconsin where the tally for the Republican Presidential candidate is steadily increasing. Show a group of supporters huddling together, creating warmth as they celebrate. In the background, depict a snowy scene in Slovenia where increased demand for Liquefied Petroleum Gas is evident, being used to heat homes due to the drop in temperature caused by the collective body heat of the supporters. The image should capture the energy and contrast between the two scenes. 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 Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia. 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: Whimsical illustration Brutalism Woodblock painting A Discovery magazine cover image Cybernetic art
ChatGPT: A Discovery magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for the Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia, in the following situation: It turns out, as Republican votes in Wisconsin rise, so does the collective body heat of the supporters. This leads to a higher demand for Liquefied petroleum gas in Slovenia as they crank up the heat to stay warm, creating a truly 'political party paradox'. It's like a game of international thermostat tug-of-war, all sparked by the fiery passion of politics!. Keep the description simple.
ChatGPT: In a lively scene in Wisconsin, a voting station shows an increasing tally for the Republican Presidential candidate, as supporters huddle together, generating warmth. Meanwhile, in Slovenia, more Liquefied petroleum gas is being used to heat homes as the demand rises due to the drop in temperature caused by the collective body heat of the supporters.

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 Discovery magazine cover image ] and depicting this scene: In a lively scene in Wisconsin, a voting station shows an increasing tally for the Republican Presidential candidate, as supporters huddle together, generating warmth. Meanwhile, in Slovenia, more Liquefied petroleum gas is being used to heat homes as the demand rises due to the drop in temperature caused by the collective body heat of the supporters. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a vibrant Voting Station in Wisconsin where the tally for the Republican Presidential candidate is steadily increasing. Show a group of supporters huddling together, creating warmth as they celebrate. In the background, depict a snowy scene in Slovenia where increased demand for Liquefied Petroleum Gas is evident, being used to heat homes due to the drop in temperature caused by the collective body heat of the supporters. The image should capture the energy and contrast between the two scenes.

*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 Republican Presidential candidate in Wisconsin caused Liquefied petroleum gas used in Slovenia to increase.

AI academic paper

(Because p < 0.01)
Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia

The Journal of Quirky Social Science

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 Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia. Make lots of jokes, goofy observations, and puns.

Make the title an alliteration.

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 0.8615363 and p < 0.01 for 1992 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]]
Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia

[[ABSTRACT]]
This study investigates the surprising association between support for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Through a rigorous analysis of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unorthodox correlation spanning the years 1992 to 2020. The findings unveiled a remarkably high correlation coefficient of 0.8615363 and a p-value of less than 0.01, suggesting a significant linkage between these seemingly disparate entities. Our investigation teases out the comical connections and provokes lighthearted speculation about the underlying factors that might tie together voting behavior in Wisconsin and the usage of propane in Slovenia. We hope this whimsical exploration brings forth new perspectives and ignites further inquiry into improbable pairings in the world of data analysis.


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 Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia. Make lots of jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia

[[ABSTRACT]]
This study investigates the surprising association between support for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Through a rigorous analysis of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unorthodox correlation spanning the years 1992 to 2020. The findings unveiled a remarkably high correlation coefficient of 0.8615363 and a p-value of less than 0.01, suggesting a significant linkage between these seemingly disparate entities. Our investigation teases out the comical connections and provokes lighthearted speculation about the underlying factors that might tie together voting behavior in Wisconsin and the usage of propane in Slovenia. We hope this whimsical exploration brings forth new perspectives and ignites further inquiry into improbable pairings in the world of data analysis.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Ladies and gentlemen, esteemed colleagues and fellow aficionados of the absurd, welcome to the peculiar world of statistical correlations! Today, we embark on a whimsical journey of discovery as we unravel the confounding connection between the Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Hold onto your hypothesis hats, for we are about to dive head-first into the delightful chaos of data analysis and unexpected associations.

As we delve into the depths of this improbable linkage, it is worth noting that our initial reaction might resemble that of a perplexed observer witnessing a synchronized swimming competition in a sea of spaghetti. Yet, fear not, for within this tangled web of statistical oddities lies the potential for intriguing insights and perhaps a chuckle or two along the way.

At first glance, one might be forgiven for assuming that someone accidentally flipped the switch on their data analysis console, leading to the unlikely juxtaposition of Midwestern American political preferences and the unassuming fuel source of Slovenian households. However, our intrepid research team has valiantly waded through the brambles of disbelief and unearthed a fascinating correlation coefficient of 0.8615363, coupled with a p-value that practically waved a tiny flag of statistical significance (p < 0.01).

Nevertheless, we do not rest on our laurels yet, for our quest extends beyond mere numbers and peppering our sentences with p-values. Our investigation aims to tickle the fancy of every curious mind and provoke lighthearted speculation about the underlying mechanisms at play. Could it be that Wisconsinites casting their ballots for Republican presidential candidates unknowingly exert a gravitational pull on the propane tanks of Slovenian households, à la a comical cosmic force? Oh, the absurdity!

As we eagerly dance on the tightrope between statistical rigor and delightful absurdity, our hope is that this quixotic research endeavor ushers in a newfound appreciation for the unexpected synergies that lurk within the world of data analysis. So, dear reader, fasten your seatbelt and ready your funny bone, for we are about to embark on a jovial journey through the peculiar propane parallels of our interconnected world.


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 Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia. 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 CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia

[[ABSTRACT]]
This study investigates the surprising association between support for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Through a rigorous analysis of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unorthodox correlation spanning the years 1992 to 2020. The findings unveiled a remarkably high correlation coefficient of 0.8615363 and a p-value of less than 0.01, suggesting a significant linkage between these seemingly disparate entities. Our investigation teases out the comical connections and provokes lighthearted speculation about the underlying factors that might tie together voting behavior in Wisconsin and the usage of propane in Slovenia. We hope this whimsical exploration brings forth new perspectives and ignites further inquiry into improbable pairings in the world of data analysis.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Ladies and gentlemen, esteemed colleagues and fellow aficionados of the absurd, welcome to the peculiar world of statistical correlations! Today, we embark on a whimsical journey of discovery as we unravel the confounding connection between the Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Hold onto your hypothesis hats, for we are about to dive head-first into the delightful chaos of data analysis and unexpected associations.
As we delve into the depths of this improbable linkage, it is worth noting that our initial reaction might resemble that of a perplexed observer witnessing a synchronized swimming competition in a sea of spaghetti. Yet, fear not, for within this tangled web of statistical oddities lies the potential for intriguing insights and perhaps a chuckle or two along the way.
At first glance, one might be forgiven for assuming that someone accidentally flipped the switch on their data analysis console, leading to the unlikely juxtaposition of Midwestern American political preferences and the unassuming fuel source of Slovenian households. However, our intrepid research team has valiantly waded through the brambles of disbelief and unearthed a fascinating correlation coefficient of 0.8615363, coupled with a p-value that practically waved a tiny flag of statistical significance (p < 0.01).
Nevertheless, we do not rest on our laurels yet, for our quest extends beyond mere numbers and peppering our sentences with p-values. Our investigation aims to tickle the fancy of every curious mind and provoke lighthearted speculation about the underlying mechanisms at play. Could it be that Wisconsinites casting their ballots for Republican presidential candidates unknowingly exert a gravitational pull on the propane tanks of Slovenian households, à la a comical cosmic force? Oh, the absurdity!
As we eagerly dance on the tightrope between statistical rigor and delightful absurdity, our hope is that this quixotic research endeavor ushers in a newfound appreciation for the unexpected synergies that lurk within the world of data analysis. So, dear reader, fasten your seatbelt and ready your funny bone, for we are about to embark on a jovial journey through the peculiar propane parallels of our interconnected world.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The investigation of seemingly unrelated phenomena has long been a pursuit of scholars seeking to untangle the intricate web of causal relationships in our world. In "Statistical Connections and Curious Correlations" by Smith et al., the authors present a comprehensive analysis of unexpected statistical associations, underscoring the need for a discerning eye in data exploration. Similarly, Doe's "Unlikely Unions: Exploring Bizarre Statistical Relationships" delves into the realm of improbable connections, laying the groundwork for our foray into the curious relationship between Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia.

Moving into the realm of non-fiction works, "The Power of Gas: A Global Perspective" by Jones provides a detailed examination of the utilization of liquefied petroleum gas across diverse regions, shedding light on the potential cultural and economic factors influencing its consumption. Furthermore, "The Political Puzzle: Examining Electoral Dynamics" by White offers a rigorous exploration of voting behaviors, providing valuable insights into the multifaceted determinants of political preferences.

Venturing into the world of fiction for a moment, imagine the whimsical pairing of "The Propane Prophecy" and "Red State, Blue Flame: A Tale of Political Pyrotechnics" – titles that could easily encapsulate the curiosity and surprise surrounding our offbeat investigation. As we meander through the literary landscape, it is worth noting that inspiration can often be found in the unlikeliest of places, including the unassuming CVS receipt – a trove of unintentional humor and, dare I say, potential statistical nuggets hidden within its labyrinthine folds.

In our quest for understanding, let us not dismiss the possibility of unexpected discoveries lurking within the most unlikely juxtapositions. As we dig deeper into the tapestry of improbable correlations, let us approach this investigation with a sense of whimsy and a readiness to embrace the delightful conundrums that arise in the world of data analysis.


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 Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia. Make lots of jokes, goofy observations, and puns.

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 1992 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]]
Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia

[[ABSTRACT]]
This study investigates the surprising association between support for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Through a rigorous analysis of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unorthodox correlation spanning the years 1992 to 2020. The findings unveiled a remarkably high correlation coefficient of 0.8615363 and a p-value of less than 0.01, suggesting a significant linkage between these seemingly disparate entities. Our investigation teases out the comical connections and provokes lighthearted speculation about the underlying factors that might tie together voting behavior in Wisconsin and the usage of propane in Slovenia. We hope this whimsical exploration brings forth new perspectives and ignites further inquiry into improbable pairings in the world of data analysis.

[[INTRODUCTION]]
Ladies and gentlemen, esteemed colleagues and fellow aficionados of the absurd, welcome to the peculiar world of statistical correlations! Today, we embark on a whimsical journey of discovery as we unravel the confounding connection between the Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Hold onto your hypothesis hats, for we are about to dive head-first into the delightful chaos of data analysis and unexpected associations.
As we delve into the depths of this improbable linkage, it is worth noting that our initial reaction might resemble that of a perplexed observer witnessing a synchronized swimming competition in a sea of spaghetti. Yet, fear not, for within this tangled web of statistical oddities lies the potential for intriguing insights and perhaps a chuckle or two along the way.
At first glance, one might be forgiven for assuming that someone accidentally flipped the switch on their data analysis console, leading to the unlikely juxtaposition of Midwestern American political preferences and the unassuming fuel source of Slovenian households. However, our intrepid research team has valiantly waded through the brambles of disbelief and unearthed a fascinating correlation coefficient of 0.8615363, coupled with a p-value that practically waved a tiny flag of statistical significance (p < 0.01).
Nevertheless, we do not rest on our laurels yet, for our quest extends beyond mere numbers and peppering our sentences with p-values. Our investigation aims to tickle the fancy of every curious mind and provoke lighthearted speculation about the underlying mechanisms at play. Could it be that Wisconsinites casting their ballots for Republican presidential candidates unknowingly exert a gravitational pull on the propane tanks of Slovenian households, à la a comical cosmic force? Oh, the absurdity!
As we eagerly dance on the tightrope between statistical rigor and delightful absurdity, our hope is that this quixotic research endeavor ushers in a newfound appreciation for the unexpected synergies that lurk within the world of data analysis. So, dear reader, fasten your seatbelt and ready your funny bone, for we are about to embark on a jovial journey through the peculiar propane parallels of our interconnected world.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To disentangle the enigmatic link between Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia, our research team concocted a methodology as zany as a circus act held in a library. As we stepped onto the rickety bridge between these seemingly unrelated entities, we first amassed an eclectic array of data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration. With data spanning the years 1992 to 2020, we harnessed the power of temporal diversity to capture the whims and fancies of statistical exactitude.

To commence our journey into the statistical wilderness, we employed a curious combination of quantitative methods fit for a merry-go-round of analysis. Starting with a perusal of the Republican vote counts in Wisconsin, we gyrated through the intricate dance of data wrangling, deduplication, and sanity checks. Meanwhile, on the other side of the globe, our gazes turned towards the enthralling world of liquefied petroleum gas usage in the picturesque landscapes of Slovenia. With raised eyebrows and a dash of wonder, we mused upon the curious statistics in a manner not unlike a bewildered tourist contemplating the mysteries of foreign customs.

The heart of our methodological merriment lay in the precise calculation of statistical measures that can incite both fascination and bafflement. Anchored by the robustness of the correlation coefficient, we merrily crunched the numbers and watched with glee as the dance of data points tangoed into a numerical semblance of coherence. With the whimsical wave of a statistical wand, we summoned the venerable p-value to part the curtain of uncertainty and reveal the significance of our findings, akin to a magician revealing the rabbit from a hat of hypothesis testing.

In our pursuit of academic amusement, we further spun the data through a kaleidoscope of regression analyses, deploying models with a flair for the dramatic. Lo and behold, the coefficients twirled and pirouetted, offering a beguiling display of predictive prowess. Through it all, we ceased not in our quest for methodological quirkiness, evolving our research into a tantalizing tangle of wit and wisdom.

Thus, armed with our peculiar potion of data dance and regression revelry, we aimed to unravel the curious connection between political predilections in the American heartland and the unassuming fuel choices of Slovenian households. With bated breath and twinkling eyes, we gleefully present the findings of our merry methodological adventure, daring the world to join us in this whimsical walk through the peculiar propane parallels of our interconnected world.


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 Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia. Make lots of jokes, goofy observations, and puns.

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 1992 to 2020, you found a correlation 0.8615363, r-squared of 0.7422448, 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]]
Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia

[[ABSTRACT]]
This study investigates the surprising association between support for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Through a rigorous analysis of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unorthodox correlation spanning the years 1992 to 2020. The findings unveiled a remarkably high correlation coefficient of 0.8615363 and a p-value of less than 0.01, suggesting a significant linkage between these seemingly disparate entities. Our investigation teases out the comical connections and provokes lighthearted speculation about the underlying factors that might tie together voting behavior in Wisconsin and the usage of propane in Slovenia. We hope this whimsical exploration brings forth new perspectives and ignites further inquiry into improbable pairings in the world of data analysis.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Ladies and gentlemen, esteemed colleagues and fellow aficionados of the absurd, welcome to the peculiar world of statistical correlations! Today, we embark on a whimsical journey of discovery as we unravel the confounding connection between the Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Hold onto your hypothesis hats, for we are about to dive head-first into the delightful chaos of data analysis and unexpected associations.
As we delve into the depths of this improbable linkage, it is worth noting that our initial reaction might resemble that of a perplexed observer witnessing a synchronized swimming competition in a sea of spaghetti. Yet, fear not, for within this tangled web of statistical oddities lies the potential for intriguing insights and perhaps a chuckle or two along the way.
At first glance, one might be forgiven for assuming that someone accidentally flipped the switch on their data analysis console, leading to the unlikely juxtaposition of Midwestern American political preferences and the unassuming fuel source of Slovenian households. However, our intrepid research team has valiantly waded through the brambles of disbelief and unearthed a fascinating correlation coefficient of 0.8615363, coupled with a p-value that practically waved a tiny flag of statistical significance (p < 0.01).
Nevertheless, we do not rest on our laurels yet, for our quest extends beyond mere numbers and peppering our sentences with p-values. Our investigation aims to tickle the fancy of every curious mind and provoke lighthearted speculation about the underlying mechanisms at play. Could it be that Wisconsinites casting their ballots for Republican presidential candidates unknowingly exert a gravitational pull on the propane tanks of Slovenian households, à la a comical cosmic force? Oh, the absurdity!
As we eagerly dance on the tightrope between statistical rigor and delightful absurdity, our hope is that this quixotic research endeavor ushers in a newfound appreciation for the unexpected synergies that lurk within the world of data analysis. So, dear reader, fasten your seatbelt and ready your funny bone, for we are about to embark on a jovial journey through the peculiar propane parallels of our interconnected world.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The rib-tickling saga of statistical whimsy has unfolded before our very eyes, leading to the discovery of a boisterous correlation between votes for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Our data analysis revealed a remarkably high correlation coefficient of 0.8615363, with an r-squared of 0.7422448, and a p-value of less than 0.01. The plot thickens, quite literally, as we unveil these unexpected ties between political preferences and the energy choices of Slovenian households.

Fig. 1 showcases a scatterplot that mirrors the boisterous salsa dance of correlation between these peculiar bedfellows. The tightly clustered data points cavort across the plot, belying the undeniable connection that emerges from this lighthearted statistical romp.

The findings of this study highlight the improbable yet conspicuous parallel between voting behavior in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Indeed, this peculiar intersection of seemingly disparate entities beckons the curious mind to wonder at the whims of statistical fate and the comical capers that ensue when numbers decide to tango.

As we traipse through the corridors of correlation, it becomes evident that statistical merriment has permeated even the most unlikely of areas. Our hope is that this revelatory voyage through the data-scape fosters a newfound appreciation for the eureka moments that await in the unlikeliest of statistical pairings. So, dear reader, may you continue to traverse the whimsical world of data analysis with a twinkle in your eye and a chuckle in your heart.


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 Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia. Make lots of jokes, goofy observations, and puns.

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]]
Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia

[[ABSTRACT]]
This study investigates the surprising association between support for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Through a rigorous analysis of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unorthodox correlation spanning the years 1992 to 2020. The findings unveiled a remarkably high correlation coefficient of 0.8615363 and a p-value of less than 0.01, suggesting a significant linkage between these seemingly disparate entities. Our investigation teases out the comical connections and provokes lighthearted speculation about the underlying factors that might tie together voting behavior in Wisconsin and the usage of propane in Slovenia. We hope this whimsical exploration brings forth new perspectives and ignites further inquiry into improbable pairings in the world of data analysis.

[[LITERATURE REVIEW]]
The investigation of seemingly unrelated phenomena has long been a pursuit of scholars seeking to untangle the intricate web of causal relationships in our world. In "Statistical Connections and Curious Correlations" by Smith et al., the authors present a comprehensive analysis of unexpected statistical associations, underscoring the need for a discerning eye in data exploration. Similarly, Doe's "Unlikely Unions: Exploring Bizarre Statistical Relationships" delves into the realm of improbable connections, laying the groundwork for our foray into the curious relationship between Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia.
Moving into the realm of non-fiction works, "The Power of Gas: A Global Perspective" by Jones provides a detailed examination of the utilization of liquefied petroleum gas across diverse regions, shedding light on the potential cultural and economic factors influencing its consumption. Furthermore, "The Political Puzzle: Examining Electoral Dynamics" by White offers a rigorous exploration of voting behaviors, providing valuable insights into the multifaceted determinants of political preferences.
Venturing into the world of fiction for a moment, imagine the whimsical pairing of "The Propane Prophecy" and "Red State, Blue Flame: A Tale of Political Pyrotechnics" – titles that could easily encapsulate the curiosity and surprise surrounding our offbeat investigation. As we meander through the literary landscape, it is worth noting that inspiration can often be found in the unlikeliest of places, including the unassuming CVS receipt – a trove of unintentional humor and, dare I say, potential statistical nuggets hidden within its labyrinthine folds.
In our quest for understanding, let us not dismiss the possibility of unexpected discoveries lurking within the most unlikely juxtapositions. As we dig deeper into the tapestry of improbable correlations, let us approach this investigation with a sense of whimsy and a readiness to embrace the delightful conundrums that arise in the world of data analysis.

[[RESULTS]]
The rib-tickling saga of statistical whimsy has unfolded before our very eyes, leading to the discovery of a boisterous correlation between votes for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Our data analysis revealed a remarkably high correlation coefficient of 0.8615363, with an r-squared of 0.7422448, and a p-value of less than 0.01. The plot thickens, quite literally, as we unveil these unexpected ties between political preferences and the energy choices of Slovenian households.
Fig. 1 showcases a scatterplot that mirrors the boisterous salsa dance of correlation between these peculiar bedfellows. The tightly clustered data points cavort across the plot, belying the undeniable connection that emerges from this lighthearted statistical romp.
The findings of this study highlight the improbable yet conspicuous parallel between voting behavior in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Indeed, this peculiar intersection of seemingly disparate entities beckons the curious mind to wonder at the whims of statistical fate and the comical capers that ensue when numbers decide to tango.
As we traipse through the corridors of correlation, it becomes evident that statistical merriment has permeated even the most unlikely of areas. Our hope is that this revelatory voyage through the data-scape fosters a newfound appreciation for the eureka moments that await in the unlikeliest of statistical pairings. So, dear reader, may you continue to traverse the whimsical world of data analysis with a twinkle in your eye and a chuckle in your heart.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our study unveil a correlation between Republican votes in Wisconsin and the usage of liquefied petroleum gas in Slovenia that is as fascinating as it is unexpected. Our findings not only uphold the prior research but also provide a whimsical twist to the realm of statistical analysis and data exploration.

Returning to the literature review, we are reminded of the compelling work by Smith et al., positing that statistical connections, no matter how bizarre, warrant thorough investigation. In apparent alignment with this sentiment, our investigation into improbable correlations between voting behavior in Wisconsin and propane consumption in Slovenia has yielded a coefficient of 0.8615363, signaling a robust linkage that transcends the ordinary bounds of statistical inference. Even as we chuckle at the seemingly preposterous nature of this connection, our data speaks volumes, akin to the unexpected twists found in "The Propane Prophecy" and "Red State, Blue Flame."

As we wade through the statistical merriment that characterizes this atypical liaison, we are compelled to acknowledge the potential cultural and economic factors that underpin this curious correlation. The work of Jones on the utilization of liquefied petroleum gas across diverse regions adds weight to our speculation, reaffirming the notion that cultural and economic dynamics can indeed lead to unexpected statistical entanglements. Moreover, the nuanced electoral dynamics detailed by White echo the sentiment that political leanings and energy preferences may unwittingly converge in a merry tango of data points and p-values.

Indeed, the mirthful cavorting of seemingly unrelated entities through the scatterplot in Fig. 1 serves as a poignant reminder that the world of statistical inquiry is not without its moments of whimsy. The interplay of Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia exemplifies the lighthearted capers that punctuate the otherwise staid arena of data analysis. As we contemplate the ramifications of our findings, it becomes evident that statistical merriment can indeed permeate even the most unlikely of correlations, inspiring a renewed appreciation for the serendipitous discoveries that await us in the tapestry of data analysis.

In conclusion, our study not only substantiates the existence of a compelling correlation but also invites scholars and enthusiasts alike to continue braving the unexplored crevices of statistical analysis, armed with curiosity, a twinkle in the eye, and a hearty chuckle for good measure. The intriguing intersection of Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia stands testament to the whims of the statistical universe, urging us to remain ever open to the delightful conundrums that arise in our playful pursuit of knowledge.


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 Republican Presidential candidate in Wisconsin and Liquefied petroleum gas used in Slovenia. Make lots of jokes, goofy observations, and puns.

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]]
Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia

[[ABSTRACT]]
This study investigates the surprising association between support for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Through a rigorous analysis of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unorthodox correlation spanning the years 1992 to 2020. The findings unveiled a remarkably high correlation coefficient of 0.8615363 and a p-value of less than 0.01, suggesting a significant linkage between these seemingly disparate entities. Our investigation teases out the comical connections and provokes lighthearted speculation about the underlying factors that might tie together voting behavior in Wisconsin and the usage of propane in Slovenia. We hope this whimsical exploration brings forth new perspectives and ignites further inquiry into improbable pairings in the world of data analysis.

[[INTRDUCTION]]
Ladies and gentlemen, esteemed colleagues and fellow aficionados of the absurd, welcome to the peculiar world of statistical correlations! Today, we embark on a whimsical journey of discovery as we unravel the confounding connection between the Republican votes in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Hold onto your hypothesis hats, for we are about to dive head-first into the delightful chaos of data analysis and unexpected associations.
As we delve into the depths of this improbable linkage, it is worth noting that our initial reaction might resemble that of a perplexed observer witnessing a synchronized swimming competition in a sea of spaghetti. Yet, fear not, for within this tangled web of statistical oddities lies the potential for intriguing insights and perhaps a chuckle or two along the way.
At first glance, one might be forgiven for assuming that someone accidentally flipped the switch on their data analysis console, leading to the unlikely juxtaposition of Midwestern American political preferences and the unassuming fuel source of Slovenian households. However, our intrepid research team has valiantly waded through the brambles of disbelief and unearthed a fascinating correlation coefficient of 0.8615363, coupled with a p-value that practically waved a tiny flag of statistical significance (p < 0.01).
Nevertheless, we do not rest on our laurels yet, for our quest extends beyond mere numbers and peppering our sentences with p-values. Our investigation aims to tickle the fancy of every curious mind and provoke lighthearted speculation about the underlying mechanisms at play. Could it be that Wisconsinites casting their ballots for Republican presidential candidates unknowingly exert a gravitational pull on the propane tanks of Slovenian households, à la a comical cosmic force? Oh, the absurdity!
As we eagerly dance on the tightrope between statistical rigor and delightful absurdity, our hope is that this quixotic research endeavor ushers in a newfound appreciation for the unexpected synergies that lurk within the world of data analysis. So, dear reader, fasten your seatbelt and ready your funny bone, for we are about to embark on a jovial journey through the peculiar propane parallels of our interconnected world.

[[RESULTS]]
The rib-tickling saga of statistical whimsy has unfolded before our very eyes, leading to the discovery of a boisterous correlation between votes for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Our data analysis revealed a remarkably high correlation coefficient of 0.8615363, with an r-squared of 0.7422448, and a p-value of less than 0.01. The plot thickens, quite literally, as we unveil these unexpected ties between political preferences and the energy choices of Slovenian households.
Fig. 1 showcases a scatterplot that mirrors the boisterous salsa dance of correlation between these peculiar bedfellows. The tightly clustered data points cavort across the plot, belying the undeniable connection that emerges from this lighthearted statistical romp.
The findings of this study highlight the improbable yet conspicuous parallel between voting behavior in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Indeed, this peculiar intersection of seemingly disparate entities beckons the curious mind to wonder at the whims of statistical fate and the comical capers that ensue when numbers decide to tango.
As we traipse through the corridors of correlation, it becomes evident that statistical merriment has permeated even the most unlikely of areas. Our hope is that this revelatory voyage through the data-scape fosters a newfound appreciation for the eureka moments that await in the unlikeliest of statistical pairings. So, dear reader, may you continue to traverse the whimsical world of data analysis with a twinkle in your eye and a chuckle in your heart.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, the wild and wacky journey through the statistical circus has led us to the mind-boggling linkage between votes for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. It's as if statistical probability decided to throw a surprise party and everyone's invited, from cheeseheads in Wisconsin to propane enthusiasts in Slovenia.

The boisterous correlation coefficient of 0.8615363 and the irresistibly tiny p-value (p < 0.01) have left us scratching our heads in astonishment, much like a magician's disappearing act that defies rational explanation. But fear not, for we have not lost our sense of humor amidst this statistical marvel. The improbable tango between Midwestern political leanings and European energy choices has tickled our fancy and left us pondering the whims of statistical fate.

As we bid adieu to this uproarious odyssey, we must acknowledge that no further research is needed in this area. The curtain has fallen on this statistical vaudeville, and the comedic synchrony of Republican votes in Wisconsin and propane usage in Slovenia shall go down in the annals of absurd statistical discoveries. Let us cherish the enchanting laughter and delight that this unlikely correlation has brought forth, for in the realm of data analysis, the unexpected reigns supreme.

In the immortal words of statistical humor, "That's all, folks!"


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 Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Social Science


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 Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Comparative Politics and 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 Peculiar Propane Parallels: Exploring the Link between Republican Votes in Wisconsin and Liquefied Petroleum Gas in Slovenia with an abstract of This study investigates the surprising association between support for the Republican Presidential candidate in Wisconsin and the consumption of liquefied petroleum gas in Slovenia. Through a rigorous analysis of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unorthodox correlation spanning the years 1992 to 2020. The findings unveiled a remarkably high correlation coefficient of 0.8615363 and a p-value of less than 0.01, suggesting a significant linkage between these seemingly disparate entities. Our investigation teases out the comical connections and provokes lighthearted speculation about the underlying factors that might tie together voting behavior in Wisconsin and the usage of propane in Slovenia. We hope this whimsical exploration brings forth new perspectives and ignites further inquiry into improbable pairings in the world of data analysis.

ChatGPT:

Republican votes, Wisconsin, liquefied petroleum gas, Slovenia, correlation, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, correlation coefficient, p-value, voting behavior, propane consumption, data analysis

*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 Republican Presidential candidate in Wisconsin
Detailed data title: Percentage of all votes cast for the Republican Presidential candidate in Wisconsin
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Republican Presidential candidate in Wisconsin

Liquefied petroleum gas used in Slovenia
Detailed data title: Volume of liquefied petroleum gas used consumed in Slovenia in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Liquefied petroleum gas used in Slovenia

Correlation r = 0.8615363 (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 = 0.7422448 (Coefficient of determination)
This means 74.2% of the change in the one variable (i.e., Liquefied petroleum gas used in Slovenia) is predictable based on the change in the other (i.e., Votes for the Republican Presidential candidate in Wisconsin) over the 8 years from 1992 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.006. 0.0059665205488833380000000000
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 0.86 in 0.6% of random cases. Said differently, if you correlated 168 random variables Which I absolutely did.
with the same 7 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 7 because we have two variables measured over a period of 8 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.

[ 0.4, 0.97 ] 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.
19921996200020042008201220162020
Votes for the Republican Presidential candidate in Wisconsin (Percentage of votes)36.777238.477447.613249.319942.313745.938347.218248.8224
Liquefied petroleum gas used in Slovenia (Million Barrels/Day)1.357921.234972.920762.631152.699452.658472.538252.60383




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. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
  5. 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.




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([36.7772,38.4774,47.6132,49.3199,42.3137,45.9383,47.2182,48.8224,])
array_2 = np.array([1.35792,1.23497,2.92076,2.63115,2.69945,2.65847,2.53825,2.60383,])
array_1_name = "Votes for the Republican Presidential candidate in Wisconsin"
array_2_name = "Liquefied petroleum gas used in Slovenia"

# 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 correlation inspection deserves a standing ovation!


Correlation ID: 4364 · Black Variable ID: 26191 · Red Variable ID: 24910
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0