about · email me · subscribe
Spurious correlation #4,368 · 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 Libertarian Presidential candidate in Utah and the second variable is Petroluem consumption in Mozambique.  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

The spike in demand for diesel trucks adorned with "Taxation is Theft" bumper stickers led to a domino effect of increased fuel imports in Mozambique. Who knew that the road to a small government ran right through a big oil boom in Southern Africa?

Model: dalle-3
Prompt: [ Whimsical illustration ] Generate an image of a bustling street in Maputo, Mozambique, portraying a scene where diesel trucks with "Taxation is Theft" bumper stickers line up at a fuel station. In the background, there's a polling station set up under a large tree where proud individuals, wearing "Libertarian for President" shirts, are casting their votes. The illustration should capture the juxtaposition of the libertarian trucks and the petroleum imports, emphasizing the interplay between diesel truck demand and petroleum consumption in Mozambique due to the small government ideology. Emphasize the vibrant colors and add a touch of whimsical charm to the overall scene. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Votes for the Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique. 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: Glitch art Whimsical illustration Art nouveau Pop art Oragami
ChatGPT: Whimsical illustration

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 Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique, in the following situation: The spike in demand for diesel trucks adorned with "Taxation is Theft" bumper stickers led to a domino effect of increased fuel imports in Mozambique. Who knew that the road to a small government ran right through a big oil boom in Southern Africa?. Keep the description simple.
ChatGPT: In a bustling street in Maputo, Mozambique, diesel trucks with "Taxation is Theft" bumper stickers are lined up at a fuel station, waiting for their turn to fill up with petroleum. Nearby, a group of people proudly wearing "Libertarian for President" shirts are casting their votes at a polling station set up under a large tree. The juxtaposition of the libertarian trucks and the petroleum imports highlights the interplay between the spike in diesel truck demand and petroleum consumption in Mozambique due to the small government ideology.

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: [ Whimsical illustration ] and depicting this scene: In a bustling street in Maputo, Mozambique, diesel trucks with "Taxation is Theft" bumper stickers are lined up at a fuel station, waiting for their turn to fill up with petroleum. Nearby, a group of people proudly wearing "Libertarian for President" shirts are casting their votes at a polling station set up under a large tree. The juxtaposition of the libertarian trucks and the petroleum imports highlights the interplay between the spike in diesel truck demand and petroleum consumption in Mozambique due to the small government ideology. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Whimsical illustration ] Generate an image of a bustling street in Maputo, Mozambique, portraying a scene where diesel trucks with "Taxation is Theft" bumper stickers line up at a fuel station. In the background, there's a polling station set up under a large tree where proud individuals, wearing "Libertarian for President" shirts, are casting their votes. The illustration should capture the juxtaposition of the libertarian trucks and the petroleum imports, emphasizing the interplay between diesel truck demand and petroleum consumption in Mozambique due to the small government ideology. Emphasize the vibrant colors and add a touch of whimsical charm to the overall scene.

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

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

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 Libertarian Presidential candidate in Utah caused Petroluem consumption in Mozambique to increase.

AI academic paper

(Because p < 0.01)
Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique

The Journal of Unlikely Correlations

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 Votes for the Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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 0.9577515 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]]
"Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
In this study, we explore the eyebrow-raising correlation between the votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in the African nation of Mozambique. While these two seem as unrelated as a penguin in the desert, our analysis, utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, uncovers a striking correlation coefficient of 0.9577515 (p < 0.01) for the years spanning 1980 to 2020. This unexpected linkage prompts us to delve into the nuanced relationship between voter ideology in a U.S. state known for its stunning landscapes and a country on the southeastern coast of Africa, renowned for its vibrant culture and resilient spirit. Our findings raise questions that may leave some scratching their heads, but undoubtedly, they also shed light on the intricate interconnectedness of the global political and economic landscape. Join us as we unravel this curious conundrum and take a journey from the mountains of Utah to the plains of Mozambique, all while pondering the peculiar paths that data can pave.


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 Votes for the Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
In this study, we explore the eyebrow-raising correlation between the votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in the African nation of Mozambique. While these two seem as unrelated as a penguin in the desert, our analysis, utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, uncovers a striking correlation coefficient of 0.9577515 (p < 0.01) for the years spanning 1980 to 2020. This unexpected linkage prompts us to delve into the nuanced relationship between voter ideology in a U.S. state known for its stunning landscapes and a country on the southeastern coast of Africa, renowned for its vibrant culture and resilient spirit. Our findings raise questions that may leave some scratching their heads, but undoubtedly, they also shed light on the intricate interconnectedness of the global political and economic landscape. Join us as we unravel this curious conundrum and take a journey from the mountains of Utah to the plains of Mozambique, all while pondering the peculiar paths that data can pave.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The world of political and economic research is rife with surprises and curiosities. It is a realm where the seemingly disparate and unrelated can come together in a statistical dance, leaving researchers and readers alike scratching their heads in bemusement. In this paper, we examine the peculiar correlation between votes for the Libertarian presidential candidate in the picturesque state of Utah and petroleum consumption in the vibrant nation of Mozambique. On the surface, one might mistakenly think that these two variables have no more in common than a lab rat and a chef at a gourmet restaurant. However, our meticulous analysis, guided by data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, exposes an astonishing correlation coefficient of 0.9577515 (p < 0.01) over the period from 1980 to 2020. This eyebrow-raising relationship beckons us to embark on a journey through the twisty paths of statistical significance, causation versus correlation, and the timeless pursuit of understanding the underlying mechanisms at play.

The state of Utah, with its breathtaking scenery and a population known for its zeal for individual liberty, provides a fitting backdrop for the investigation of libertarian voting patterns. On the other hand, Mozambique, nestled in the southeastern corner of Africa, stands as a beacon of culture, resilience, and energy production. Indeed, the study of petroleum consumption in Mozambique allows us to explore a different facet of the global economic landscape. It is in this complex tapestry of political ideologies and energy demands that we find ourselves entangled, searching for the threads that tie these seemingly distant locales and variables together.

As we embark on this scholarly quest, we are reminded of the words of the great physicist, Richard Feynman, who remarked, "It doesn't matter how beautiful your theory is, it doesn't matter how smart you are. If it doesn't agree with experiment, it's wrong." With this mantra as our guide, we set out to dissect the enigma laid before us and reveal the surprising and perhaps, whimsical insights that empirical inquiry can yield. So, fasten your seatbelts and ready your scientific spectacles as we navigate the intriguing intersection of political ideologies and energy landscapes, all while maintaining our sense of humor amidst the mysteries of statistical analysis.


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 Votes for the Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
In this study, we explore the eyebrow-raising correlation between the votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in the African nation of Mozambique. While these two seem as unrelated as a penguin in the desert, our analysis, utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, uncovers a striking correlation coefficient of 0.9577515 (p < 0.01) for the years spanning 1980 to 2020. This unexpected linkage prompts us to delve into the nuanced relationship between voter ideology in a U.S. state known for its stunning landscapes and a country on the southeastern coast of Africa, renowned for its vibrant culture and resilient spirit. Our findings raise questions that may leave some scratching their heads, but undoubtedly, they also shed light on the intricate interconnectedness of the global political and economic landscape. Join us as we unravel this curious conundrum and take a journey from the mountains of Utah to the plains of Mozambique, all while pondering the peculiar paths that data can pave.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of political and economic research is rife with surprises and curiosities. It is a realm where the seemingly disparate and unrelated can come together in a statistical dance, leaving researchers and readers alike scratching their heads in bemusement. In this paper, we examine the peculiar correlation between votes for the Libertarian presidential candidate in the picturesque state of Utah and petroleum consumption in the vibrant nation of Mozambique. On the surface, one might mistakenly think that these two variables have no more in common than a lab rat and a chef at a gourmet restaurant. However, our meticulous analysis, guided by data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, exposes an astonishing correlation coefficient of 0.9577515 (p < 0.01) over the period from 1980 to 2020. This eyebrow-raising relationship beckons us to embark on a journey through the twisty paths of statistical significance, causation versus correlation, and the timeless pursuit of understanding the underlying mechanisms at play.
The state of Utah, with its breathtaking scenery and a population known for its zeal for individual liberty, provides a fitting backdrop for the investigation of libertarian voting patterns. On the other hand, Mozambique, nestled in the southeastern corner of Africa, stands as a beacon of culture, resilience, and energy production. Indeed, the study of petroleum consumption in Mozambique allows us to explore a different facet of the global economic landscape. It is in this complex tapestry of political ideologies and energy demands that we find ourselves entangled, searching for the threads that tie these seemingly distant locales and variables together.
As we embark on this scholarly quest, we are reminded of the words of the great physicist, Richard Feynman, who remarked, "It doesn't matter how beautiful your theory is, it doesn't matter how smart you are. If it doesn't agree with experiment, it's wrong." With this mantra as our guide, we set out to dissect the enigma laid before us and reveal the surprising and perhaps, whimsical insights that empirical inquiry can yield. So, fasten your seatbelts and ready your scientific spectacles as we navigate the intriguing intersection of political ideologies and energy landscapes, all while maintaining our sense of humor amidst the mysteries of statistical analysis.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their groundbreaking study, Smith et al. (2016) uncover the intricate relationship between libertarian voting behavior in the United States and its potential impact on global energy consumption patterns. Doe and Jones (2018) further delve into the nuances of petroleum usage in developing nations, shedding light on the complex interplay of political, economic, and environmental factors. The findings from these seminal works lay the foundation for our investigation into the unexpected correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique.

Turning our attention to relevant non-fiction literature, the works of "Energy: A Human History" by Richard Rhodes and "Libertarianism: A Primer" by David Boaz provide valuable insight into the historical context and philosophical underpinnings that may offer a semblance of understanding to our seemingly absurd correlation. Additionally, the fictional narratives of "Atlas Shrugged" by Ayn Rand and "Petroleum Man" by J.G. Ballard, while not directly related to our study, serve to ignite the imagination and spark creative contemplation on the intersections of individualism, energy, and societal structures.

In a slightly different vein, the cinematic experiences of "There Will Be Blood" and "Office Space" act as tangentially relevant stimuli for our analytical journey, offering glimpses into the idiosyncrasies of human behavior and the unpredictable ways in which economic and political dynamics unfold.

With this eclectic mix of scholarly endeavors, philosophical musings, and cultural reflections, we embark on our quest to untangle the bizarre correlation between libertarian votes in Utah and petroleum consumption in Mozambique. Let the chase begin! And may the data be ever in our favor.


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 Votes for the Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
In this study, we explore the eyebrow-raising correlation between the votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in the African nation of Mozambique. While these two seem as unrelated as a penguin in the desert, our analysis, utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, uncovers a striking correlation coefficient of 0.9577515 (p < 0.01) for the years spanning 1980 to 2020. This unexpected linkage prompts us to delve into the nuanced relationship between voter ideology in a U.S. state known for its stunning landscapes and a country on the southeastern coast of Africa, renowned for its vibrant culture and resilient spirit. Our findings raise questions that may leave some scratching their heads, but undoubtedly, they also shed light on the intricate interconnectedness of the global political and economic landscape. Join us as we unravel this curious conundrum and take a journey from the mountains of Utah to the plains of Mozambique, all while pondering the peculiar paths that data can pave.

[[INTRODUCTION]]
The world of political and economic research is rife with surprises and curiosities. It is a realm where the seemingly disparate and unrelated can come together in a statistical dance, leaving researchers and readers alike scratching their heads in bemusement. In this paper, we examine the peculiar correlation between votes for the Libertarian presidential candidate in the picturesque state of Utah and petroleum consumption in the vibrant nation of Mozambique. On the surface, one might mistakenly think that these two variables have no more in common than a lab rat and a chef at a gourmet restaurant. However, our meticulous analysis, guided by data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, exposes an astonishing correlation coefficient of 0.9577515 (p < 0.01) over the period from 1980 to 2020. This eyebrow-raising relationship beckons us to embark on a journey through the twisty paths of statistical significance, causation versus correlation, and the timeless pursuit of understanding the underlying mechanisms at play.
The state of Utah, with its breathtaking scenery and a population known for its zeal for individual liberty, provides a fitting backdrop for the investigation of libertarian voting patterns. On the other hand, Mozambique, nestled in the southeastern corner of Africa, stands as a beacon of culture, resilience, and energy production. Indeed, the study of petroleum consumption in Mozambique allows us to explore a different facet of the global economic landscape. It is in this complex tapestry of political ideologies and energy demands that we find ourselves entangled, searching for the threads that tie these seemingly distant locales and variables together.
As we embark on this scholarly quest, we are reminded of the words of the great physicist, Richard Feynman, who remarked, "It doesn't matter how beautiful your theory is, it doesn't matter how smart you are. If it doesn't agree with experiment, it's wrong." With this mantra as our guide, we set out to dissect the enigma laid before us and reveal the surprising and perhaps, whimsical insights that empirical inquiry can yield. So, fasten your seatbelts and ready your scientific spectacles as we navigate the intriguing intersection of political ideologies and energy landscapes, all while maintaining our sense of humor amidst the mysteries of statistical analysis.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic connection between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique, we employed a hodgepodge of statistical techniques and data manipulation reminiscent of a mad scientist's laboratory. Our data collection involved a deep dive into the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration, where we scavenged for every data point from the cobweb-covered corners of the internet. The years 1980 to 2020 served as our canvas for this artistic symphony of numbers and variables.

The first step in our convoluted odyssey was to wrangle the data into submission. Like cowboys in a wild data west, we corralled and cleansed the libertarian vote counts from the state of Utah, meticulously ensuring that no stray ballots or whimsical write-in candidates found their way into our analysis. Simultaneously, we tamed the capricious data on petroleum consumption in Mozambique, massaging it into a form palatable for our statistical appetites.

Next, with the precision of a watchmaker and the flair of a circus performer, we engaged in the delicate dance of statistical analysis. Our trusty software tools, akin to loyal companions on a treacherous voyage, crunched numbers with the gusto of a hungry mathematician at an all-you-can-solve buffet. We computed correlation coefficients, confident intervals, and regression models, all in the pursuit of uncovering the deep-seated connection between these seemingly disparate variables.

While donning our metaphorical Sherlock Holmes hats, we audited the data for potential confounding variables, outliers, and other statistical saboteurs that might seek to derail our noble quest for truth. Once satisfied that our data were free from mischief, we bravely ventured into the realm of hypothesis testing, where p-values sprouted like daisies in a statistical garden, signifying the significance of our findings.

In our analysis, we also delved into time series modeling, treating the data as a captivating narrative of fluctuations and trends. With the finesse of a seasoned storyteller, we interpreted the ebb and flow of libertarian votes in Utah and petroleum consumption in Mozambique over the decades, unraveling the intricate plot twists and unexpected character developments that emerged from our statistical saga.

Furthermore, to bolster the robustness of our findings, we engaged in sensitivity analysis and validation procedures, ensuring that our results stood firm against the battering winds of skepticism and scholarly scrutiny. Like a medieval knight fortifying a castle against siege, we fortified our statistical edifice with the impregnability of empirical evidence and analytical rigor.

Ultimately, our methodological escapade culminated in revealing the astonishing correlation coefficient of 0.9577515 (p < 0.01) between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique. This revelation, akin to stumbling upon a hidden treasure in the vast expanse of statistical wilderness, propelled us into the realm of speculation and interpretation, setting the stage for the grand unveiling of our findings in the following sections. So, with our statistical toolbox emptied and our hypotheses tested, we invite you, dear reader, to join us on this comical quest through the enthralling intersection of political fervor and liquid energy consumption.

(And remember, always handle statistics with care; they tend to multiply when you least expect it!)


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 Votes for the Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 1980 to 2020, you found a correlation 0.9577515, r-squared of 0.9172880, 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]]
"Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
In this study, we explore the eyebrow-raising correlation between the votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in the African nation of Mozambique. While these two seem as unrelated as a penguin in the desert, our analysis, utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, uncovers a striking correlation coefficient of 0.9577515 (p < 0.01) for the years spanning 1980 to 2020. This unexpected linkage prompts us to delve into the nuanced relationship between voter ideology in a U.S. state known for its stunning landscapes and a country on the southeastern coast of Africa, renowned for its vibrant culture and resilient spirit. Our findings raise questions that may leave some scratching their heads, but undoubtedly, they also shed light on the intricate interconnectedness of the global political and economic landscape. Join us as we unravel this curious conundrum and take a journey from the mountains of Utah to the plains of Mozambique, all while pondering the peculiar paths that data can pave.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The world of political and economic research is rife with surprises and curiosities. It is a realm where the seemingly disparate and unrelated can come together in a statistical dance, leaving researchers and readers alike scratching their heads in bemusement. In this paper, we examine the peculiar correlation between votes for the Libertarian presidential candidate in the picturesque state of Utah and petroleum consumption in the vibrant nation of Mozambique. On the surface, one might mistakenly think that these two variables have no more in common than a lab rat and a chef at a gourmet restaurant. However, our meticulous analysis, guided by data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, exposes an astonishing correlation coefficient of 0.9577515 (p < 0.01) over the period from 1980 to 2020. This eyebrow-raising relationship beckons us to embark on a journey through the twisty paths of statistical significance, causation versus correlation, and the timeless pursuit of understanding the underlying mechanisms at play.
The state of Utah, with its breathtaking scenery and a population known for its zeal for individual liberty, provides a fitting backdrop for the investigation of libertarian voting patterns. On the other hand, Mozambique, nestled in the southeastern corner of Africa, stands as a beacon of culture, resilience, and energy production. Indeed, the study of petroleum consumption in Mozambique allows us to explore a different facet of the global economic landscape. It is in this complex tapestry of political ideologies and energy demands that we find ourselves entangled, searching for the threads that tie these seemingly distant locales and variables together.
As we embark on this scholarly quest, we are reminded of the words of the great physicist, Richard Feynman, who remarked, "It doesn't matter how beautiful your theory is, it doesn't matter how smart you are. If it doesn't agree with experiment, it's wrong." With this mantra as our guide, we set out to dissect the enigma laid before us and reveal the surprising and perhaps, whimsical insights that empirical inquiry can yield. So, fasten your seatbelts and ready your scientific spectacles as we navigate the intriguing intersection of political ideologies and energy landscapes, all while maintaining our sense of humor amidst the mysteries of statistical analysis.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our investigation into the perplexing association between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique have left us both astounded and amused. Our analysis revealed an eye-popping correlation coefficient of 0.9577515 (p < 0.01) for the period from 1980 to 2020, signifying a remarkably robust relationship between these seemingly incongruous variables. The r-squared of 0.9172880 further attests to the strength of this correlation, leaving little room for skepticism. It appears that the connection between libertarianism and petroleum consumption is not as diffuse as trying to mix oil and water; rather, it emerges as a compelling and coherent phenomenon.

Figure 1 depicts the scatterplot illustrating the noteworthy correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique. The unmistakable trend apparent in the data points serves as a visual testament to the intriguing relationship we have uncovered. The plot, while devoid of dazzling colors or intricate designs, nonetheless captivates the eye with its depiction of the intricate bond between political leanings in a U.S. state and energy demands in a far-flung African nation.

The strength of the correlation coefficient, coupled with the visual representation in Figure 1, firmly establishes the linkage between these disparate variables. It is as if the statistical gods themselves conspired to draw these seemingly unrelated entities together in a statistical waltz, leaving us mere mortals to marvel at the complexity and whimsy inherent in the world of data analysis. Indeed, the findings not only serve to bolster our understanding of the interplay between political ideologies and energy consumption but also add a touch of merriment to the often sober domain of statistical inquiry.

In conclusion, our results unveil a surprising and amusing correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique. This discovery underscores the whimsical nature of statistical relationships and the profound, if somewhat enigmatic, interconnectedness of global political and economic dynamics. As we continue to uncover such unexpected links, it behooves us to approach our research with a blend of skepticism and good humor, for in the nebulous world of data, just as in life, there may well be more than meets the eye.



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 Votes for the Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
In this study, we explore the eyebrow-raising correlation between the votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in the African nation of Mozambique. While these two seem as unrelated as a penguin in the desert, our analysis, utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, uncovers a striking correlation coefficient of 0.9577515 (p < 0.01) for the years spanning 1980 to 2020. This unexpected linkage prompts us to delve into the nuanced relationship between voter ideology in a U.S. state known for its stunning landscapes and a country on the southeastern coast of Africa, renowned for its vibrant culture and resilient spirit. Our findings raise questions that may leave some scratching their heads, but undoubtedly, they also shed light on the intricate interconnectedness of the global political and economic landscape. Join us as we unravel this curious conundrum and take a journey from the mountains of Utah to the plains of Mozambique, all while pondering the peculiar paths that data can pave.

[[LITERATURE REVIEW]]
In their groundbreaking study, Smith et al. (2016) uncover the intricate relationship between libertarian voting behavior in the United States and its potential impact on global energy consumption patterns. Doe and Jones (2018) further delve into the nuances of petroleum usage in developing nations, shedding light on the complex interplay of political, economic, and environmental factors. The findings from these seminal works lay the foundation for our investigation into the unexpected correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique.
Turning our attention to relevant non-fiction literature, the works of "Energy: A Human History" by Richard Rhodes and "Libertarianism: A Primer" by David Boaz provide valuable insight into the historical context and philosophical underpinnings that may offer a semblance of understanding to our seemingly absurd correlation. Additionally, the fictional narratives of "Atlas Shrugged" by Ayn Rand and "Petroleum Man" by J.G. Ballard, while not directly related to our study, serve to ignite the imagination and spark creative contemplation on the intersections of individualism, energy, and societal structures.
In a slightly different vein, the cinematic experiences of "There Will Be Blood" and "Office Space" act as tangentially relevant stimuli for our analytical journey, offering glimpses into the idiosyncrasies of human behavior and the unpredictable ways in which economic and political dynamics unfold.
With this eclectic mix of scholarly endeavors, philosophical musings, and cultural reflections, we embark on our quest to untangle the bizarre correlation between libertarian votes in Utah and petroleum consumption in Mozambique. Let the chase begin! And may the data be ever in our favor.

[[RESULTS]]
The results of our investigation into the perplexing association between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique have left us both astounded and amused. Our analysis revealed an eye-popping correlation coefficient of 0.9577515 (p < 0.01) for the period from 1980 to 2020, signifying a remarkably robust relationship between these seemingly incongruous variables. The r-squared of 0.9172880 further attests to the strength of this correlation, leaving little room for skepticism. It appears that the connection between libertarianism and petroleum consumption is not as diffuse as trying to mix oil and water; rather, it emerges as a compelling and coherent phenomenon.
Figure 1 depicts the scatterplot illustrating the noteworthy correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique. The unmistakable trend apparent in the data points serves as a visual testament to the intriguing relationship we have uncovered. The plot, while devoid of dazzling colors or intricate designs, nonetheless captivates the eye with its depiction of the intricate bond between political leanings in a U.S. state and energy demands in a far-flung African nation.
The strength of the correlation coefficient, coupled with the visual representation in Figure 1, firmly establishes the linkage between these disparate variables. It is as if the statistical gods themselves conspired to draw these seemingly unrelated entities together in a statistical waltz, leaving us mere mortals to marvel at the complexity and whimsy inherent in the world of data analysis. Indeed, the findings not only serve to bolster our understanding of the interplay between political ideologies and energy consumption but also add a touch of merriment to the often sober domain of statistical inquiry.
In conclusion, our results unveil a surprising and amusing correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique. This discovery underscores the whimsical nature of statistical relationships and the profound, if somewhat enigmatic, interconnectedness of global political and economic dynamics. As we continue to uncover such unexpected links, it behooves us to approach our research with a blend of skepticism and good humor, for in the nebulous world of data, just as in life, there may well be more than meets the eye.


-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of our study reveal a remarkably robust association between votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in Mozambique, a connection that is as puzzling as a statistical outlier at first glance. However, our results align with previous research by Smith et al. (2016) and Doe and Jones (2018) in demonstrating the potential impact of libertarian voting behavior on global energy consumption patterns. It seems that the libertarian spirit, much like the petroleum itself, may have a far-reaching influence that transcends geographical and ideological boundaries.

The eyebrow-raising correlation coefficient of 0.9577515 (p < 0.01) between the two seemingly unrelated variables echoes the work of Smith et al. (2016), who hinted at the intricate relationship between political ideologies and energy dynamics. While some may find this correlation as unlikely as finding a needle in a data haystack, our results provide empirical support for the captivating notion that political leanings in one part of the world might reverberate in the energy consumption patterns of another.

Our findings not only illustrate the unexpected interconnectedness of political and economic landscapes but also hint at the complexity of human behavior and societal dynamics. It's as if we've stumbled upon a statistical Rosetta Stone, deciphering the cryptic messages hidden within the data to uncover the peculiar interplay between libertarianism and petroleum consumption. This correlation, with its strength and statistical significance, beckons researchers and observers alike to reconsider the boundaries of influence and the peculiar ways in which seemingly disparate variables can intertwine.

Much like the enigmatic forces that govern the subatomic particles in quantum physics, our study presents a curious conundrum that challenges conventional notions of causality. The statistical waltz depicted in our scatterplot is reminiscent of a whimsical dance, where the partners clearly move in tandem, despite the apparent mismatch of their identities.

In the grand scheme of scientific exploration, our discovery serves as a delightful reminder of the unexpected joys that can be unearthed in the realm of data analysis. As researchers, we must remain vigilant in our pursuit of knowledge, prepared to encounter the unexpected and embrace the inherent whimsy that lurks within the numerical depths of our analyses.

As we continue to peel back the layers of complexity in our statistical inquiries, we are reminded that the world of data is not governed solely by cold, hard facts, but also by the capricious nature of human interactions and societal dynamics. Our findings stand as a testament to the enduring mantra of statistical inquiry: expect the unexpected, and when in doubt, analyze with a healthy dose of humor and curiosity.


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 Votes for the Libertarian Presidential candidate in Utah and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
In this study, we explore the eyebrow-raising correlation between the votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in the African nation of Mozambique. While these two seem as unrelated as a penguin in the desert, our analysis, utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, uncovers a striking correlation coefficient of 0.9577515 (p < 0.01) for the years spanning 1980 to 2020. This unexpected linkage prompts us to delve into the nuanced relationship between voter ideology in a U.S. state known for its stunning landscapes and a country on the southeastern coast of Africa, renowned for its vibrant culture and resilient spirit. Our findings raise questions that may leave some scratching their heads, but undoubtedly, they also shed light on the intricate interconnectedness of the global political and economic landscape. Join us as we unravel this curious conundrum and take a journey from the mountains of Utah to the plains of Mozambique, all while pondering the peculiar paths that data can pave.

[[INTRDUCTION]]
The world of political and economic research is rife with surprises and curiosities. It is a realm where the seemingly disparate and unrelated can come together in a statistical dance, leaving researchers and readers alike scratching their heads in bemusement. In this paper, we examine the peculiar correlation between votes for the Libertarian presidential candidate in the picturesque state of Utah and petroleum consumption in the vibrant nation of Mozambique. On the surface, one might mistakenly think that these two variables have no more in common than a lab rat and a chef at a gourmet restaurant. However, our meticulous analysis, guided by data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, exposes an astonishing correlation coefficient of 0.9577515 (p < 0.01) over the period from 1980 to 2020. This eyebrow-raising relationship beckons us to embark on a journey through the twisty paths of statistical significance, causation versus correlation, and the timeless pursuit of understanding the underlying mechanisms at play.
The state of Utah, with its breathtaking scenery and a population known for its zeal for individual liberty, provides a fitting backdrop for the investigation of libertarian voting patterns. On the other hand, Mozambique, nestled in the southeastern corner of Africa, stands as a beacon of culture, resilience, and energy production. Indeed, the study of petroleum consumption in Mozambique allows us to explore a different facet of the global economic landscape. It is in this complex tapestry of political ideologies and energy demands that we find ourselves entangled, searching for the threads that tie these seemingly distant locales and variables together.
As we embark on this scholarly quest, we are reminded of the words of the great physicist, Richard Feynman, who remarked, "It doesn't matter how beautiful your theory is, it doesn't matter how smart you are. If it doesn't agree with experiment, it's wrong." With this mantra as our guide, we set out to dissect the enigma laid before us and reveal the surprising and perhaps, whimsical insights that empirical inquiry can yield. So, fasten your seatbelts and ready your scientific spectacles as we navigate the intriguing intersection of political ideologies and energy landscapes, all while maintaining our sense of humor amidst the mysteries of statistical analysis.

[[RESULTS]]
The results of our investigation into the perplexing association between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique have left us both astounded and amused. Our analysis revealed an eye-popping correlation coefficient of 0.9577515 (p < 0.01) for the period from 1980 to 2020, signifying a remarkably robust relationship between these seemingly incongruous variables. The r-squared of 0.9172880 further attests to the strength of this correlation, leaving little room for skepticism. It appears that the connection between libertarianism and petroleum consumption is not as diffuse as trying to mix oil and water; rather, it emerges as a compelling and coherent phenomenon.
Figure 1 depicts the scatterplot illustrating the noteworthy correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique. The unmistakable trend apparent in the data points serves as a visual testament to the intriguing relationship we have uncovered. The plot, while devoid of dazzling colors or intricate designs, nonetheless captivates the eye with its depiction of the intricate bond between political leanings in a U.S. state and energy demands in a far-flung African nation.
The strength of the correlation coefficient, coupled with the visual representation in Figure 1, firmly establishes the linkage between these disparate variables. It is as if the statistical gods themselves conspired to draw these seemingly unrelated entities together in a statistical waltz, leaving us mere mortals to marvel at the complexity and whimsy inherent in the world of data analysis. Indeed, the findings not only serve to bolster our understanding of the interplay between political ideologies and energy consumption but also add a touch of merriment to the often sober domain of statistical inquiry.
In conclusion, our results unveil a surprising and amusing correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique. This discovery underscores the whimsical nature of statistical relationships and the profound, if somewhat enigmatic, interconnectedness of global political and economic dynamics. As we continue to uncover such unexpected links, it behooves us to approach our research with a blend of skepticism and good humor, for in the nebulous world of data, just as in life, there may well be more than meets the eye.


-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unearthed a startlingly robust correlation between votes for the Libertarian presidential candidate in Utah and petroleum consumption in Mozambique, proving that statistical analysis can be as surprising as finding a clown at a funeral. The evidence of a correlation coefficient of 0.9577515 (p < 0.01) from 1980 to 2020 leaves little room for doubt, much like trying to argue that a square is a circle in a room full of mathematicians. Our findings, while initially as bewildering as a chicken trying to play chess, shed light on the interconnectedness of seemingly unrelated variables in the global political and economic landscape.

As we wrap up our exploration of this peculiar pair of variables, it is as clear as the nose on one's face that no more research is needed in this area. The statistical waltz between libertarianism and petroleum consumption has been uncovered, and it seems that the universe has played a clever trick on us, revealing an unexpected melody in the symphony of data. It is in this spirit of wonder and giggles that we bid adieu to this unconventional journey through the twists and turns of statistical exploration.


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 Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unlikely Correlations


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 Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique. Respond only with the name of a fictional organization.

ChatGPT:

Society for Quirky Global Relations and Interdisciplinary 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 Fueling Libertarianism: A Crude Connection Between Votes for the Libertarian Presidential Candidate in Utah and Petroleum Consumption in Mozambique with an abstract of In this study, we explore the eyebrow-raising correlation between the votes for the Libertarian presidential candidate in the state of Utah and petroleum consumption in the African nation of Mozambique. While these two seem as unrelated as a penguin in the desert, our analysis, utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, uncovers a striking correlation coefficient of 0.9577515 (p < 0.01) for the years spanning 1980 to 2020. This unexpected linkage prompts us to delve into the nuanced relationship between voter ideology in a U.S. state known for its stunning landscapes and a country on the southeastern coast of Africa, renowned for its vibrant culture and resilient spirit. Our findings raise questions that may leave some scratching their heads, but undoubtedly, they also shed light on the intricate interconnectedness of the global political and economic landscape. Join us as we unravel this curious conundrum and take a journey from the mountains of Utah to the plains of Mozambique, all while pondering the peculiar paths that data can pave.

ChatGPT:

Libertarian presidential candidate, Utah, petroleum consumption, Mozambique, correlation, voter ideology, global political landscape, economic interconnectedness, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, correlation coefficient, U.S. state, African nation, data analysis, political economy, democracy, petroleum demand, ideological voting patterns, cross-national voting behavior

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

Petroluem consumption in Mozambique
Detailed data title: Volume of petroluem consumption consumed in Mozambique in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Petroluem consumption in Mozambique

Correlation r = 0.9577515 (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 = 0.9172880 (Coefficient of determination)
This means 91.7% of the change in the one variable (i.e., Petroluem consumption in Mozambique) is predictable based on the change in the other (i.e., Votes for the Libertarian Presidential candidate in Utah) over the 11 years from 1980 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.61E-6. 0.0000036064799664102368000000
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 0.96 in 0.000361% of random cases. Said differently, if you correlated 277,279 random variables You don't actually need 277 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.84, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19801984198819921996200020042008201220162020
Votes for the Libertarian Presidential candidate in Utah (Percentage of votes)1.184470.3886251.155010.2553770.6203150.4691510.3637460.7314381.235653.501052.5833
Petroluem consumption in Mozambique (Million Barrels/Day)13129.76.884487.0844810.646510.96813.31117.513342.299130.2179




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([1.18447,0.388625,1.15501,0.255377,0.620315,0.469151,0.363746,0.731438,1.23565,3.50105,2.5833,])
array_2 = np.array([13,12,9.7,6.88448,7.08448,10.6465,10.968,13.311,17.5133,42.2991,30.2179,])
array_1_name = "Votes for the Libertarian Presidential candidate in Utah"
array_2_name = "Petroluem consumption in Mozambique"

# 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?

I'm genuinely thankful for your rating!


Correlation ID: 4368 · Black Variable ID: 26176 · Red Variable ID: 24717
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0