about · email me · subscribe
Spurious correlation #5,755 · 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 Libertarian Senators in Illinois and the second variable is Kerosene used in Togo.  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

As Libertarian votes for Senators in Illinois increased, it led to a rise in support for smaller government and deregulation. This indirectly boosted the production of kerosene in the US, leading to lower prices for Togo to import. This encouraged Togolese households to use more kerosene for cooking and lighting, sparking a small but significant 'flame' of economic activity in the kerosene industry.

Model: dalle-3
Prompt: [An image that looks like it is a scene from A Disney Movie] Generate an enchanting illustration of a serene countryside in Togo. Picture a charming Togolese household nestled amidst lush greenery, with a warmly glowing kerosene lamp placed in the heart of the scene. The lamp illuminates the rustic surroundings, exuding a sense of magical warmth and comfort. As the moonlight bathes the tranquil landscape, showcase a subtle graph floating in the breeze, representing the increase in votes for Libertarian Senators in Illinois. Let the harmony of these contrasting elements weave a captivating story of indirect influence and interconnectedness through the visual magic of DALLE-3. 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 Libertarian Senators in Illinois and Kerosene used in Togo. 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: Steampunk An image that looks like it is a scene from A Disney Movie Art nouveau Psychedelic Low poly
ChatGPT: An image that looks like it is a scene from A Disney Movie

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for Libertarian Senators in Illinois and Kerosene used in Togo, in the following situation: As Libertarian votes for Senators in Illinois increased, it led to a rise in support for smaller government and deregulation. This indirectly boosted the production of kerosene in the US, leading to lower prices for Togo to import. This encouraged Togolese households to use more kerosene for cooking and lighting, sparking a small but significant 'flame' of economic activity in the kerosene industry.. Keep the description simple.
ChatGPT: In a visual scene, we see a graph showing the increase in votes for Libertarian Senators in Illinois. Alongside it, we see a depiction of a kerosene lamp glowing brightly in a Togolese household, symbolizing the increased use of kerosene for cooking and lighting. This image illustrates the indirect impact of political support for smaller government on the kerosene industry.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from A Disney Movie ] and depicting this scene: In a visual scene, we see a graph showing the increase in votes for Libertarian Senators in Illinois. Alongside it, we see a depiction of a kerosene lamp glowing brightly in a Togolese household, symbolizing the increased use of kerosene for cooking and lighting. This image illustrates the indirect impact of political support for smaller government on the kerosene industry. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [An image that looks like it is a scene from A Disney Movie] Generate an enchanting illustration of a serene countryside in Togo. Picture a charming Togolese household nestled amidst lush greenery, with a warmly glowing kerosene lamp placed in the heart of the scene. The lamp illuminates the rustic surroundings, exuding a sense of magical warmth and comfort. As the moonlight bathes the tranquil landscape, showcase a subtle graph floating in the breeze, representing the increase in votes for Libertarian Senators in Illinois. Let the harmony of these contrasting elements weave a captivating story of indirect influence and interconnectedness through the visual magic of DALLE-3.

*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 increases in Libertarian votes for Senators in Illinois positively influenced Kerosene used in Togo. Include one good pun.

AI academic paper

(Because p < 0.01)
From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo

The Journal of Comparative Political Fire Studies

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Illinois and Kerosene used in Togo. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

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 0.9145332 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]]
From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo

[[ABSTRACT]]
In this research, we delve into the intriguing correlation between the votes cast for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in the West African country of Togo. Our investigation utilizes data from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration to unravel this unlikely but statistically significant association, much like the bond between two atoms - unlikely but still electric.

Our study spans the years 1980 to 2020 and reveals a strong correlation coefficient of 0.9145332 and p < 0.01, leaving us more surprised than a kid who thought he got socks for Christmas but found out there's a video game hidden inside the box. As we sifted through the numbers, just like sifting through a box of assorted chocolates, we discovered a link that may seem as puzzling as a riddle – yet, the data won't let us ignore it, like a persistent knock-knock joke.

This connection is as unexpected as finding a unicorn at a petting zoo, but as researchers, it's our duty to shed light on the most unforeseen of correlations. As much as we're tempted to make a kerosene-related pun here, we need to keep our excitement in check, just like controlling the urge to blurt out a dad joke in serious conversations. Our findings may seem as surreal as a unicorn sighting, but they demand further exploration to uncover the underlying factors contributing to this astonishing correlation.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Illinois and Kerosene used in Togo. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo

[[ABSTRACT]]
In this research, we delve into the intriguing correlation between the votes cast for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in the West African country of Togo. Our investigation utilizes data from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration to unravel this unlikely but statistically significant association, much like the bond between two atoms - unlikely but still electric.

Our study spans the years 1980 to 2020 and reveals a strong correlation coefficient of 0.9145332 and p < 0.01, leaving us more surprised than a kid who thought he got socks for Christmas but found out there's a video game hidden inside the box. As we sifted through the numbers, just like sifting through a box of assorted chocolates, we discovered a link that may seem as puzzling as a riddle – yet, the data won't let us ignore it, like a persistent knock-knock joke.

This connection is as unexpected as finding a unicorn at a petting zoo, but as researchers, it's our duty to shed light on the most unforeseen of correlations. As much as we're tempted to make a kerosene-related pun here, we need to keep our excitement in check, just like controlling the urge to blurt out a dad joke in serious conversations. Our findings may seem as surreal as a unicorn sighting, but they demand further exploration to uncover the underlying factors contributing to this astonishing correlation.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As we embark on this scholarly expedition into the realms of political voting behavior and international energy consumption, we are confronted with a correlation that may raise eyebrows as much as it raises questions. The connection between the votes for Libertarian candidates in the Senate elections in Illinois and the kerosene consumption in Togo is a puzzle as perplexing as the chicken or the egg causality dilemma – except in this case, it's more like deciding between a donkey or an elephant at the zoo.

This eyebrow-raising correlation begs the question: Are the voting trends in the Land of Lincoln somehow influencing the usage of kerosene in the faraway lands of Togo, or is there a clandestine kerosene trade agreement being negotiated over the Lake Shore Drive? It's as puzzling a mystery as trying to figure out why the man who invested in a belt didn't make any money – because he claimed it was a "waist" of money.

The allure of this correlation is as irresistible as a plate of free donuts in the break room, prompting our rigorous investigation into this unexpected and seemingly unrelated pair of variables. The statistical strength of this correlation beckons us to explore its underpinnings with the curiosity of a cat who just discovered a new cardboard box – except, in our case, the box is filled with data and not catnip.

As we delve into this uncharted territory, we must resist the temptation to fuel the fire with kerosene puns, as tempting as it may be. So remember, folks, stay lit-erary, even when discussing illuminating correlations between political preferences and energy consumption.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Illinois and Kerosene used in Togo. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo

[[ABSTRACT]]
In this research, we delve into the intriguing correlation between the votes cast for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in the West African country of Togo. Our investigation utilizes data from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration to unravel this unlikely but statistically significant association, much like the bond between two atoms - unlikely but still electric.

Our study spans the years 1980 to 2020 and reveals a strong correlation coefficient of 0.9145332 and p < 0.01, leaving us more surprised than a kid who thought he got socks for Christmas but found out there's a video game hidden inside the box. As we sifted through the numbers, just like sifting through a box of assorted chocolates, we discovered a link that may seem as puzzling as a riddle – yet, the data won't let us ignore it, like a persistent knock-knock joke.

This connection is as unexpected as finding a unicorn at a petting zoo, but as researchers, it's our duty to shed light on the most unforeseen of correlations. As much as we're tempted to make a kerosene-related pun here, we need to keep our excitement in check, just like controlling the urge to blurt out a dad joke in serious conversations. Our findings may seem as surreal as a unicorn sighting, but they demand further exploration to uncover the underlying factors contributing to this astonishing correlation.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As we embark on this scholarly expedition into the realms of political voting behavior and international energy consumption, we are confronted with a correlation that may raise eyebrows as much as it raises questions. The connection between the votes for Libertarian candidates in the Senate elections in Illinois and the kerosene consumption in Togo is a puzzle as perplexing as the chicken or the egg causality dilemma – except in this case, it's more like deciding between a donkey or an elephant at the zoo.
This eyebrow-raising correlation begs the question: Are the voting trends in the Land of Lincoln somehow influencing the usage of kerosene in the faraway lands of Togo, or is there a clandestine kerosene trade agreement being negotiated over the Lake Shore Drive? It's as puzzling a mystery as trying to figure out why the man who invested in a belt didn't make any money – because he claimed it was a "waist" of money.
The allure of this correlation is as irresistible as a plate of free donuts in the break room, prompting our rigorous investigation into this unexpected and seemingly unrelated pair of variables. The statistical strength of this correlation beckons us to explore its underpinnings with the curiosity of a cat who just discovered a new cardboard box – except, in our case, the box is filled with data and not catnip.
As we delve into this uncharted territory, we must resist the temptation to fuel the fire with kerosene puns, as tempting as it may be. So remember, folks, stay lit-erary, even when discussing illuminating correlations between political preferences and energy consumption.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Numerous academic studies have delved into the intricate relationship between political voting behavior and various global phenomena. Smith et al. explored the impact of political ideology on consumer behavior, while Doe and Jones conducted a comprehensive analysis of the socio-economic factors influencing energy consumption patterns. Additionally, the work of Smith and Johnson sheds light on the interplay between international trade agreements and political dynamics.

Turning our attention to literature beyond the academic realm, books such as "The Libertarian Mind" by David Boaz and "Kerosene" by Chris Wooding offer insightful perspectives on the respective subjects. Furthermore, fictional works like "Atlas Shrugged" by Ayn Rand and "Kerosene" by Gwyneth Jones provide fictionalized accounts that intertwine political ideologies and energy sources in compelling narratives.

In the realm of internet culture, memes such as the "Libertarian Kerosene Conundrum" and "Togo's Kerosene Senate" humorously blend the two seemingly distant concepts, reminding us that even the most unlikely pairings can spark humor and creativity. Just like a good dad joke, these memes find humor in unexpected connections, prompting us to consider the unlikely correlations with a chuckle amidst our scholarly pursuits.

Speaking of dad jokes, did you hear about the guy who invented Lifesavers? They say he made a mint. This unexpected pairing of political votes and kerosene consumption in Togo may seem as amusing as that joke, but our research aims to uncover the underlying mechanisms driving this surprising correlation.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Illinois and Kerosene used in Togo. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo

[[ABSTRACT]]
In this research, we delve into the intriguing correlation between the votes cast for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in the West African country of Togo. Our investigation utilizes data from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration to unravel this unlikely but statistically significant association, much like the bond between two atoms - unlikely but still electric.

Our study spans the years 1980 to 2020 and reveals a strong correlation coefficient of 0.9145332 and p < 0.01, leaving us more surprised than a kid who thought he got socks for Christmas but found out there's a video game hidden inside the box. As we sifted through the numbers, just like sifting through a box of assorted chocolates, we discovered a link that may seem as puzzling as a riddle – yet, the data won't let us ignore it, like a persistent knock-knock joke.

This connection is as unexpected as finding a unicorn at a petting zoo, but as researchers, it's our duty to shed light on the most unforeseen of correlations. As much as we're tempted to make a kerosene-related pun here, we need to keep our excitement in check, just like controlling the urge to blurt out a dad joke in serious conversations. Our findings may seem as surreal as a unicorn sighting, but they demand further exploration to uncover the underlying factors contributing to this astonishing correlation.

[[INTRODUCTION]]
As we embark on this scholarly expedition into the realms of political voting behavior and international energy consumption, we are confronted with a correlation that may raise eyebrows as much as it raises questions. The connection between the votes for Libertarian candidates in the Senate elections in Illinois and the kerosene consumption in Togo is a puzzle as perplexing as the chicken or the egg causality dilemma – except in this case, it's more like deciding between a donkey or an elephant at the zoo.
This eyebrow-raising correlation begs the question: Are the voting trends in the Land of Lincoln somehow influencing the usage of kerosene in the faraway lands of Togo, or is there a clandestine kerosene trade agreement being negotiated over the Lake Shore Drive? It's as puzzling a mystery as trying to figure out why the man who invested in a belt didn't make any money – because he claimed it was a "waist" of money.
The allure of this correlation is as irresistible as a plate of free donuts in the break room, prompting our rigorous investigation into this unexpected and seemingly unrelated pair of variables. The statistical strength of this correlation beckons us to explore its underpinnings with the curiosity of a cat who just discovered a new cardboard box – except, in our case, the box is filled with data and not catnip.
As we delve into this uncharted territory, we must resist the temptation to fuel the fire with kerosene puns, as tempting as it may be. So remember, folks, stay lit-erary, even when discussing illuminating correlations between political preferences and energy consumption.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To investigate the peculiar correlation between the votes for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in Togo, we utilized a combination of quantitative research methods, statistical analyses, and a dash of good old-fashioned detective work – think Sherlock Holmes with a spreadsheet. Our data collection involved scouring the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration, akin to a diligent scavenger hunt looking for clues.

First, we compiled historical voting data for Libertarian candidates in Senate elections in Illinois from 1980 to 2020, meticulously analyzing the electoral outcomes over the decades. This involved sifting through more numbers than an accountant at a jigsaw puzzle company – though we promise, it was more exhilarating than it sounds.

Next, we turned our attention to kerosene consumption in Togo during the same time period, diving into the Energy Information Administration data like enthusiastic submarine explorers, albeit with fewer sea creatures and more spreadsheets. We cross-referenced kerosene usage with socioeconomic and geopolitical factors impacting Togo, pondering the relationship between political leanings in Illinois and energy choices in Togo, much like pondering whether chickens or eggs have a future in politics.

Statistical analyses were our trusty sidekicks in this academic adventure. We calculated the correlation coefficient using sophisticated mathematical models, feeling a bit like Dumbledore examining the stars for prophecies – except, of course, we were conjuring statistical significance instead of spells. The significance tests were as crucial as reading the fine print in a contract, ensuring that our findings weren't as fleeting as a magician's trick.

Additionally, we employed regression analyses to unravel the potential causal pathways underlying this unexpected correlation, just like unraveling a mysterious ball of yarn. We delved into the depths of multivariate analyses, navigating the statistical seas to reveal the hidden currents explaining the interplay between political preferences and energy consumption, like intrepid sailors charting unfamiliar waters.

We must note that although our investigation was as serious as a heart attack, we didn't skimp on the dad jokes. Because who can resist the allure of puns? Just like a book about eye-rolling humor, we sprinkled this section with a healthy dose of wordplay, reminding ourselves not to take everything too seriously. But fear not, dear readers, for although we employed humor sporadically, our commitment to rigorous scientific inquiry never wavered—unlike that friend who's always late, no matter the occasion.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Illinois and Kerosene used in Togo. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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 0.9145332, r-squared of 0.8363709, 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]]
From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo

[[ABSTRACT]]
In this research, we delve into the intriguing correlation between the votes cast for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in the West African country of Togo. Our investigation utilizes data from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration to unravel this unlikely but statistically significant association, much like the bond between two atoms - unlikely but still electric.

Our study spans the years 1980 to 2020 and reveals a strong correlation coefficient of 0.9145332 and p < 0.01, leaving us more surprised than a kid who thought he got socks for Christmas but found out there's a video game hidden inside the box. As we sifted through the numbers, just like sifting through a box of assorted chocolates, we discovered a link that may seem as puzzling as a riddle – yet, the data won't let us ignore it, like a persistent knock-knock joke.

This connection is as unexpected as finding a unicorn at a petting zoo, but as researchers, it's our duty to shed light on the most unforeseen of correlations. As much as we're tempted to make a kerosene-related pun here, we need to keep our excitement in check, just like controlling the urge to blurt out a dad joke in serious conversations. Our findings may seem as surreal as a unicorn sighting, but they demand further exploration to uncover the underlying factors contributing to this astonishing correlation.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As we embark on this scholarly expedition into the realms of political voting behavior and international energy consumption, we are confronted with a correlation that may raise eyebrows as much as it raises questions. The connection between the votes for Libertarian candidates in the Senate elections in Illinois and the kerosene consumption in Togo is a puzzle as perplexing as the chicken or the egg causality dilemma – except in this case, it's more like deciding between a donkey or an elephant at the zoo.
This eyebrow-raising correlation begs the question: Are the voting trends in the Land of Lincoln somehow influencing the usage of kerosene in the faraway lands of Togo, or is there a clandestine kerosene trade agreement being negotiated over the Lake Shore Drive? It's as puzzling a mystery as trying to figure out why the man who invested in a belt didn't make any money – because he claimed it was a "waist" of money.
The allure of this correlation is as irresistible as a plate of free donuts in the break room, prompting our rigorous investigation into this unexpected and seemingly unrelated pair of variables. The statistical strength of this correlation beckons us to explore its underpinnings with the curiosity of a cat who just discovered a new cardboard box – except, in our case, the box is filled with data and not catnip.
As we delve into this uncharted territory, we must resist the temptation to fuel the fire with kerosene puns, as tempting as it may be. So remember, folks, stay lit-erary, even when discussing illuminating correlations between political preferences and energy consumption.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data gathered between the years 1980 and 2020 from various sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration revealed a striking correlation between Libertarian votes for Senators in Illinois and kerosene consumption in Togo. The correlation coefficient was found to be 0.9145332, with an r-squared value of 0.8363709, and p < 0.01. This strong correlation is akin to finding a needle in a haystack, except in this case, the needle is made of kerosene and the haystack is a giant ballot box.

The results depicted in Fig. 1 provide a visual representation of the relationship between these seemingly disparate variables. The scatterplot showcases a clear, upward-trending pattern, illustrating the impressive alignment of the two datasets. It's like finding out that the pen you've been looking for was behind your ear the whole time – unexpected yet oddly satisfying, much like this correlation itself.

The robustness of this correlation prompts further investigation into its potential causative factors. It's a bit like a detective investigating a case with unexpected clues – or in this case, a statistical Sherlock Holmes uncovering the mystery behind strikingly correlated voting patterns and kerosene consumption in a far-off land. The correlation is as mysterious as a locked room in a mansion, with only statistical analysis and a keen eye for data revealing the hidden truths, much like the secrets unraveled in a thrilling detective novel.

As the research team grappled with these findings, it was hard to ignore the enormity of this correlation. The connection, although unexpected, demands exploration and examination akin to the quest of a researcher seeking the elusive white rabbit, or in this case, a Libertarian kerosene-fueled hare of exceptional statistical significance. This unexpected correlation challenges conventional wisdom and beckons researchers to seek its underlying rationale, much like a riddle waiting to be unraveled – we just hope it's not a kerosene-soaked enigma.

In conclusion, the results of this study highlight a surprising and substantial correlation between the votes for Libertarian candidates in Illinois and the consumption of kerosene in Togo. This enigmatic connection calls for further investigation and analysis, shedding light on a seemingly improbable relationship that, much like a good dad joke, deserves a second look and a chuckle of acknowledgement.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Illinois and Kerosene used in Togo. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo

[[ABSTRACT]]
In this research, we delve into the intriguing correlation between the votes cast for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in the West African country of Togo. Our investigation utilizes data from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration to unravel this unlikely but statistically significant association, much like the bond between two atoms - unlikely but still electric.

Our study spans the years 1980 to 2020 and reveals a strong correlation coefficient of 0.9145332 and p < 0.01, leaving us more surprised than a kid who thought he got socks for Christmas but found out there's a video game hidden inside the box. As we sifted through the numbers, just like sifting through a box of assorted chocolates, we discovered a link that may seem as puzzling as a riddle – yet, the data won't let us ignore it, like a persistent knock-knock joke.

This connection is as unexpected as finding a unicorn at a petting zoo, but as researchers, it's our duty to shed light on the most unforeseen of correlations. As much as we're tempted to make a kerosene-related pun here, we need to keep our excitement in check, just like controlling the urge to blurt out a dad joke in serious conversations. Our findings may seem as surreal as a unicorn sighting, but they demand further exploration to uncover the underlying factors contributing to this astonishing correlation.

[[LITERATURE REVIEW]]
Numerous academic studies have delved into the intricate relationship between political voting behavior and various global phenomena. Smith et al. explored the impact of political ideology on consumer behavior, while Doe and Jones conducted a comprehensive analysis of the socio-economic factors influencing energy consumption patterns. Additionally, the work of Smith and Johnson sheds light on the interplay between international trade agreements and political dynamics.
Turning our attention to literature beyond the academic realm, books such as "The Libertarian Mind" by David Boaz and "Kerosene" by Chris Wooding offer insightful perspectives on the respective subjects. Furthermore, fictional works like "Atlas Shrugged" by Ayn Rand and "Kerosene" by Gwyneth Jones provide fictionalized accounts that intertwine political ideologies and energy sources in compelling narratives.
In the realm of internet culture, memes such as the "Libertarian Kerosene Conundrum" and "Togo's Kerosene Senate" humorously blend the two seemingly distant concepts, reminding us that even the most unlikely pairings can spark humor and creativity. Just like a good dad joke, these memes find humor in unexpected connections, prompting us to consider the unlikely correlations with a chuckle amidst our scholarly pursuits.
Speaking of dad jokes, did you hear about the guy who invented Lifesavers? They say he made a mint. This unexpected pairing of political votes and kerosene consumption in Togo may seem as amusing as that joke, but our research aims to uncover the underlying mechanisms driving this surprising correlation.

[[RESULTS]]
The analysis of the data gathered between the years 1980 and 2020 from various sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration revealed a striking correlation between Libertarian votes for Senators in Illinois and kerosene consumption in Togo. The correlation coefficient was found to be 0.9145332, with an r-squared value of 0.8363709, and p < 0.01. This strong correlation is akin to finding a needle in a haystack, except in this case, the needle is made of kerosene and the haystack is a giant ballot box.
The results depicted in Fig. 1 provide a visual representation of the relationship between these seemingly disparate variables. The scatterplot showcases a clear, upward-trending pattern, illustrating the impressive alignment of the two datasets. It's like finding out that the pen you've been looking for was behind your ear the whole time – unexpected yet oddly satisfying, much like this correlation itself.
The robustness of this correlation prompts further investigation into its potential causative factors. It's a bit like a detective investigating a case with unexpected clues – or in this case, a statistical Sherlock Holmes uncovering the mystery behind strikingly correlated voting patterns and kerosene consumption in a far-off land. The correlation is as mysterious as a locked room in a mansion, with only statistical analysis and a keen eye for data revealing the hidden truths, much like the secrets unraveled in a thrilling detective novel.
As the research team grappled with these findings, it was hard to ignore the enormity of this correlation. The connection, although unexpected, demands exploration and examination akin to the quest of a researcher seeking the elusive white rabbit, or in this case, a Libertarian kerosene-fueled hare of exceptional statistical significance. This unexpected correlation challenges conventional wisdom and beckons researchers to seek its underlying rationale, much like a riddle waiting to be unraveled – we just hope it's not a kerosene-soaked enigma.
In conclusion, the results of this study highlight a surprising and substantial correlation between the votes for Libertarian candidates in Illinois and the consumption of kerosene in Togo. This enigmatic connection calls for further investigation and analysis, shedding light on a seemingly improbable relationship that, much like a good dad joke, deserves a second look and a chuckle of acknowledgement.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The remarkable correlation uncovered in this study between Libertarian votes for Senators in Illinois and kerosene consumption in Togo has left us pondering over the intriguing interplay of variables that seem as different as chalk and cheese – or perhaps, as different as kerosene and libertarianism. The results of our analysis support the prior research that has delved into the complex relationship between political ideologies and consumer behaviors, as well as the socio-economic factors influencing energy consumption patterns. The unexpected yet robust correlation coefficient of 0.9145332 provides empirical evidence for an association that, much like a dad joke, initially raises eyebrows but ultimately leaves a lasting impression.

Our findings align with the work of Smith et al., who explored the impact of political ideology on consumer behavior, and similarly, with the comprehensive analysis by Doe and Jones of the socio-economic factors influencing energy consumption patterns. The statistical significance of the correlation coefficient reflects the interplay between international trade agreements and political dynamics highlighted in the work of Smith and Johnson. It's like the punchline of a well-told joke – it ties everything together in a surprising yet satisfying manner.

Just as memes humorously blend unlikely concepts, our research brings to light an unexpected linkage between seemingly disparate variables that warrants further investigation. The strong correlation coefficient mirrors the unexpected humor found in these memes, leaving us pondering over the underlying mechanisms that drive this unexpected alignment. It's like a good dad joke – you don't see it coming, but once it hits, you can't help but appreciate the cleverness behind it.

Our results not only provide empirical support for prior research but also prompt a re-evaluation of the factors influencing political voting behavior and energy consumption patterns. The statistical robustness of this surprising correlation is akin to a good dad joke that stands the test of time, prompting us to reconsider our preconceived notions and delve into the underlying rationale driving this unexpected relationship.

In unraveling this enigmatic correlation, our study not only adds to the body of knowledge regarding the interplay between political dynamics and energy consumption but also highlights the importance of considering unconventional relationships that may initially appear as puzzling as a riddle. Our research, much like a well-timed dad joke, challenges convention and beckons further exploration, driving us to seek the underlying truths behind seemingly improbable connections that deserve both scholarly scrutiny and a nod of appreciation.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Illinois and Kerosene used in Togo. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo

[[ABSTRACT]]
In this research, we delve into the intriguing correlation between the votes cast for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in the West African country of Togo. Our investigation utilizes data from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration to unravel this unlikely but statistically significant association, much like the bond between two atoms - unlikely but still electric.

Our study spans the years 1980 to 2020 and reveals a strong correlation coefficient of 0.9145332 and p < 0.01, leaving us more surprised than a kid who thought he got socks for Christmas but found out there's a video game hidden inside the box. As we sifted through the numbers, just like sifting through a box of assorted chocolates, we discovered a link that may seem as puzzling as a riddle – yet, the data won't let us ignore it, like a persistent knock-knock joke.

This connection is as unexpected as finding a unicorn at a petting zoo, but as researchers, it's our duty to shed light on the most unforeseen of correlations. As much as we're tempted to make a kerosene-related pun here, we need to keep our excitement in check, just like controlling the urge to blurt out a dad joke in serious conversations. Our findings may seem as surreal as a unicorn sighting, but they demand further exploration to uncover the underlying factors contributing to this astonishing correlation.

[[INTRDUCTION]]
As we embark on this scholarly expedition into the realms of political voting behavior and international energy consumption, we are confronted with a correlation that may raise eyebrows as much as it raises questions. The connection between the votes for Libertarian candidates in the Senate elections in Illinois and the kerosene consumption in Togo is a puzzle as perplexing as the chicken or the egg causality dilemma – except in this case, it's more like deciding between a donkey or an elephant at the zoo.
This eyebrow-raising correlation begs the question: Are the voting trends in the Land of Lincoln somehow influencing the usage of kerosene in the faraway lands of Togo, or is there a clandestine kerosene trade agreement being negotiated over the Lake Shore Drive? It's as puzzling a mystery as trying to figure out why the man who invested in a belt didn't make any money – because he claimed it was a "waist" of money.
The allure of this correlation is as irresistible as a plate of free donuts in the break room, prompting our rigorous investigation into this unexpected and seemingly unrelated pair of variables. The statistical strength of this correlation beckons us to explore its underpinnings with the curiosity of a cat who just discovered a new cardboard box – except, in our case, the box is filled with data and not catnip.
As we delve into this uncharted territory, we must resist the temptation to fuel the fire with kerosene puns, as tempting as it may be. So remember, folks, stay lit-erary, even when discussing illuminating correlations between political preferences and energy consumption.

[[RESULTS]]
The analysis of the data gathered between the years 1980 and 2020 from various sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration revealed a striking correlation between Libertarian votes for Senators in Illinois and kerosene consumption in Togo. The correlation coefficient was found to be 0.9145332, with an r-squared value of 0.8363709, and p < 0.01. This strong correlation is akin to finding a needle in a haystack, except in this case, the needle is made of kerosene and the haystack is a giant ballot box.
The results depicted in Fig. 1 provide a visual representation of the relationship between these seemingly disparate variables. The scatterplot showcases a clear, upward-trending pattern, illustrating the impressive alignment of the two datasets. It's like finding out that the pen you've been looking for was behind your ear the whole time – unexpected yet oddly satisfying, much like this correlation itself.
The robustness of this correlation prompts further investigation into its potential causative factors. It's a bit like a detective investigating a case with unexpected clues – or in this case, a statistical Sherlock Holmes uncovering the mystery behind strikingly correlated voting patterns and kerosene consumption in a far-off land. The correlation is as mysterious as a locked room in a mansion, with only statistical analysis and a keen eye for data revealing the hidden truths, much like the secrets unraveled in a thrilling detective novel.
As the research team grappled with these findings, it was hard to ignore the enormity of this correlation. The connection, although unexpected, demands exploration and examination akin to the quest of a researcher seeking the elusive white rabbit, or in this case, a Libertarian kerosene-fueled hare of exceptional statistical significance. This unexpected correlation challenges conventional wisdom and beckons researchers to seek its underlying rationale, much like a riddle waiting to be unraveled – we just hope it's not a kerosene-soaked enigma.
In conclusion, the results of this study highlight a surprising and substantial correlation between the votes for Libertarian candidates in Illinois and the consumption of kerosene in Togo. This enigmatic connection calls for further investigation and analysis, shedding light on a seemingly improbable relationship that, much like a good dad joke, deserves a second look and a chuckle of acknowledgement.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has uncovered an unexpected yet robust correlation between Libertarian votes for Senators in Illinois and kerosene consumption in Togo. This finding, much like a surprising punchline, demands further scrutiny and analysis to unravel the underlying mechanisms at play.

As we wrap up this paper, it's clear that this correlation is as intriguing as a political debate at a magic show – unexpected, but undeniably captivating. Our analysis has highlighted the need for a deeper exploration of the factors driving this unlikely association, much like a math problem that just keeps multiplying.

Therefore, in the immortal words of every dad ever, it's time to wrap this up before it starts to feel like a bad sitcom that just won't end. In other words, we’re putting a lid on this kerosene can and calling it a day. It’s clear that no more research is needed in this area – we’ll leave that to someone else while we sit back and wait for the inevitable "I told you so" from our statistical models.


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 From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Comparative Political Fire Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo. Respond only with the name of a fictional organization.

ChatGPT:

Society for Ethical and Democratic Policy Analysis (SEDPA)


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 From Libertarian Leanings to Luminous Light: A Correlation Analysis of Senatorial Votes in Illinois and Kerosene Consumption in Togo with an abstract of In this research, we delve into the intriguing correlation between the votes cast for Libertarian candidates in the Senate elections in Illinois and the consumption of kerosene in the West African country of Togo. Our investigation utilizes data from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration to unravel this unlikely but statistically significant association, much like the bond between two atoms - unlikely but still electric.
Our study spans the years 1980 to 2020 and reveals a strong correlation coefficient of 0.9145332 and p < 0.01, leaving us more surprised than a kid who thought he got socks for Christmas but found out there's a video game hidden inside the box. As we sifted through the numbers, just like sifting through a box of assorted chocolates, we discovered a link that may seem as puzzling as a riddle – yet, the data won't let us ignore it, like a persistent knock-knock joke.
This connection is as unexpected as finding a unicorn at a petting zoo, but as researchers, it's our duty to shed light on the most unforeseen of correlations. As much as we're tempted to make a kerosene-related pun here, we need to keep our excitement in check, just like controlling the urge to blurt out a dad joke in serious conversations. Our findings may seem as surreal as a unicorn sighting, but they demand further exploration to uncover the underlying factors contributing to this astonishing correlation.

ChatGPT:

Senate elections, Illinois, Libertarian candidate, kerosene consumption, Togo, correlation analysis, data analysis, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, statistical significance, correlation coefficient, 1980-2020, unexpected correlation, underlying factors, research paper

*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 Libertarian Senators in Illinois
Detailed data title: Percentage of votes cast for Federal Libertarian Senate candidates in Illinois
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for Libertarian Senators in Illinois

Kerosene used in Togo
Detailed data title: Volume of kerosene used consumed in Togo in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Togo

Correlation r = 0.9145332 (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 = 0.8363709 (Coefficient of determination)
This means 83.6% of the change in the one variable (i.e., Kerosene used in Togo) is predictable based on the change in the other (i.e., Votes for Libertarian Senators in Illinois) over the 12 years from 1980 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.11E-5. 0.0000310705741347956260000000
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 0.91 in 0.00311% of random cases. Said differently, if you correlated 32,185 random variables You don't actually need 32 thousand variables to find a correlation like this one. 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.

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 11 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 11 because we have two variables measured over a period of 12 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.

[ 0.72, 0.98 ] 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.
198019841986199219962002200420082010201420162020
Votes for Libertarian Senators in Illinois (Percentage of votes)0.6403451.248650.4448130.698990.9696711.645671.346940.9423092.355183.755113.204511.26779
Kerosene used in Togo (Million Barrels/Day)0.2277780.2611110.20.30.40.8259450.8448090.8236891.080081.412191.564270.539389




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 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([0.640345,1.24865,0.444813,0.69899,0.969671,1.64567,1.34694,0.942309,2.35518,3.75511,3.20451,1.26779,])
array_2 = np.array([0.227778,0.261111,0.2,0.3,0.4,0.825945,0.844809,0.823689,1.08008,1.41219,1.56427,0.539389,])
array_1_name = "Votes for Libertarian Senators in Illinois"
array_2_name = "Kerosene used in Togo"

# 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?

Thanks for shining a light on this correlation!


Correlation ID: 5755 · Black Variable ID: 26379 · Red Variable ID: 24996
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0