Spurious correlation #4,525 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Republican Presidential candidate in North Dakota and the second variable is Liquefied petroleum gas used in Turkmenistan. The chart goes from 1992 to 2020, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Republican Presidential candidate in North Dakota and the second variable is Liquefied petroleum gas used in Turkmenistan. The chart goes from 1992 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The strong support for the Republican candidate in North Dakota led to a surge in enthusiasm. This increase in collective excitement somehow altered the atmospheric pressure patterns, creating a domino effect that ultimately boosted the production and distribution of liquefied petroleum gas in Turkmenistan. It's as if the political fervor ignited a chain reaction of events, culminating in a random but remarkable connection between American voting preferences and Central Asian energy resources. Who knew that the road to the White House could have a pit stop in the land of flammable gas?

^{Show image generation prompt} Model: dalle-3
Prompt: [A TIME magazine cover image] Show a bustling voting station in North Dakota, with proud voters casting their ballots for the Republican Presidential candidate. Capture the excitement and enthusiasm in their expressions as they exercise their democratic right. Additionally, depict atmospheric pressure patterns shifting above the scene, visually connecting the voter fervor to a global impact. Illustrate a subtle ripple effect traveling from North Dakota to Turkmenistan, symbolizing the unexpected connection between American voting preferences and Central Asian energy resources. The image should visually convey the excitement of voting and the far-reaching effects of human actions on a global scale. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Votes for the Republican Presidential candidate in North Dakota and Liquefied petroleum gas used in Turkmenistan. 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: Psychedelic Data cyber art Cyberpunk Cybernetic art A TIME magazine cover image
ChatGPT: A TIME magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for the Republican Presidential candidate in North Dakota and Liquefied petroleum gas used in Turkmenistan, in the following situation: The strong support for the Republican candidate in North Dakota led to a surge in enthusiasm. This increase in collective excitement somehow altered the atmospheric pressure patterns, creating a domino effect that ultimately boosted the production and distribution of liquefied petroleum gas in Turkmenistan. It's as if the political fervor ignited a chain reaction of events, culminating in a random but remarkable connection between American voting preferences and Central Asian energy resources. Who knew that the road to the White House could have a pit stop in the land of flammable gas?. Keep the description simple.
ChatGPT: In North Dakota, voters proudly cast their ballots for the Republican Presidential candidate, creating an atmosphere of excitement and enthusiasm. As the collective fervor grew, the atmospheric pressure patterns shifted, causing a ripple effect across the globe. In Turkmenistan, the surge in atmospheric pressure somehow boosted the production and distribution of liquefied petroleum gas, leading to an unexpected connection between American voting preferences and Central Asian energy resources.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A TIME magazine cover image ] and depicting this scene: In North Dakota, voters proudly cast their ballots for the Republican Presidential candidate, creating an atmosphere of excitement and enthusiasm. As the collective fervor grew, the atmospheric pressure patterns shifted, causing a ripple effect across the globe. In Turkmenistan, the surge in atmospheric pressure somehow boosted the production and distribution of liquefied petroleum gas, leading to an unexpected connection between American voting preferences and Central Asian energy resources. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [A TIME magazine cover image] Show a bustling voting station in North Dakota, with proud voters casting their ballots for the Republican Presidential candidate. Capture the excitement and enthusiasm in their expressions as they exercise their democratic right. Additionally, depict atmospheric pressure patterns shifting above the scene, visually connecting the voter fervor to a global impact. Illustrate a subtle ripple effect traveling from North Dakota to Turkmenistan, symbolizing the unexpected connection between American voting preferences and Central Asian energy resources. The image should visually convey the excitement of voting and the far-reaching effects of human actions on a global scale.

*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.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Votes for the Republican Presidential candidate in North Dakota caused Liquefied petroleum gas used in Turkmenistan to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study

The Journal of Political Gas Dynamics

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} 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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Dakota and Liquefied petroleum gas used in Turkmenistan. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
"Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study"

[[ABSTRACT]]
This research paper delves into the unexpected and often overlooked relationship between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in the distant land of Turkmenistan. Despite initial skepticism, our research team utilized data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this peculiar connection. To our surprise, a significant correlation coefficient of 0.9089128 with p < 0.01 emerged from our analysis, covering the period from 1992 to 2020. The findings herein challenge conventional wisdom and are sure to ignite lively discussion among academics and political pundits alike.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between political preferences in one part of the world and energy consumption in another may at first glance seem like an odd couple, akin to an oil and water mixture. However, as the saying goes, "opposites attract" – and in the world of statistical analysis, sometimes the most unexpected pairings yield fascinating insights.
In the current political landscape, where discussions about energy policy and international relations abound, it is important to explore the potential interplay between seemingly disparate factors. Thus, this study delves into the curious correlation between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan. While this connection may appear as unlikely as a polar bear sunbathing in the desert, our findings reveal a surprising level of statistical significance.
This paper aims to shed light on this intriguing relationship, employing rigorous statistical methodologies to unearth the potential factors at play. Through the analysis of extensive datasets spanning nearly three decades, we endeavor to offer a fresh perspective that challenges traditional assumptions and inspires further investigation.
The findings of this research not only contribute to the academic understanding of political behavior and energy consumption patterns but also serve as a reminder that in the world of data analysis, one should always expect the unexpected – much like receiving a bouquet of statistical significance from an unlikely pair of variables.
The exploratory nature of this study is intended to provoke curiosity and spark discussions, much like the sudden realization that two seemingly unrelated entities may indeed dance to the same statistical tune. Therefore, without further ado, let us embark on this journey of uncovering the mystique behind the convergence of gas in Turkmenistan and votes for a Republican.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Numerous scholarly works have examined the political landscape and energy consumption patterns, albeit independently, providing valuable insights into both domains. For instance, in "The Political Landscape in Modern America," Smith delves into the complexities of regional voting trends, offering meticulous analyses of state-level political preferences. Similarly, Doe's "Energy Consumption Patterns in Central Asia" presents a comprehensive overview of energy usage in the region, emphasizing the role of liquefied petroleum gas in Turkmenistan. Furthermore, Jones' "Election Dynamics and Political Behavior" explores the myriad factors that shape voting patterns in the United States, establishing a robust theoretical framework for understanding electoral behavior.

Transitioning from these weighty tomes, one cannot overlook the contributions of non-fiction works addressing related themes. A notable example is "The Energy Chronicles: A Global Perspective," which delves into the intricacies of energy consumption across diverse geographical locations. Another compelling read, "Politics Unveiled: An Insider's Account," provides a gripping portrayal of the machinations underlying political decision-making, offering valuable context for understanding electoral dynamics. Not to be discounted are the perennial classics such as "Gas, Grit, and Glory: A Historical Perspective," which intertwines the tale of energy with the tapestry of human endeavor.

Moving into the realm of fiction, the influence of literature on our understanding of interconnected global phenomena cannot be underestimated. Through the lens of fiction, authors often subtly weave threads of truth into the fabric of their narratives, shedding light on aspects of reality that may otherwise remain obscured. Titles such as "The Petroleum Paradox" and "Republican Rhapsody" beckon readers into worlds where the unexpected converges, challenging perceptions and beckoning one to contemplate the improbable.

While the pursuit of knowledge often finds its roots in the erudite, one must not discount the potential for insight from more unconventional sources. In the pursuit of understanding the enigmatic relationship between votes for a Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan, even seemingly whimsical media forms have not been entirely disregarded. Cartoons such as "Gasoline Gus and the Political Pals" and children's shows featuring political themes have provided unexpected moments of clarity, reminding researchers that knowledge does not always adhere to conventional boundaries.

Thus, as we navigate the landscape of literature pertinent to our investigation, it becomes evident that the undercurrents of our research findings may have been subtly hinted at across a diverse array of sources. This diverse spectrum of material has not only informed the conversation surrounding our study but has also provided moments of levity and surprise along the way.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Dakota and Liquefied petroleum gas used in Turkmenistan. Make lots of jokes, goofy observations, and puns. 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 1992 to 2020

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study"

[[ABSTRACT]]
This research paper delves into the unexpected and often overlooked relationship between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in the distant land of Turkmenistan. Despite initial skepticism, our research team utilized data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this peculiar connection. To our surprise, a significant correlation coefficient of 0.9089128 with p < 0.01 emerged from our analysis, covering the period from 1992 to 2020. The findings herein challenge conventional wisdom and are sure to ignite lively discussion among academics and political pundits alike.

[[INTRODUCTION]]
The relationship between political preferences in one part of the world and energy consumption in another may at first glance seem like an odd couple, akin to an oil and water mixture. However, as the saying goes, "opposites attract" – and in the world of statistical analysis, sometimes the most unexpected pairings yield fascinating insights.
In the current political landscape, where discussions about energy policy and international relations abound, it is important to explore the potential interplay between seemingly disparate factors. Thus, this study delves into the curious correlation between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan. While this connection may appear as unlikely as a polar bear sunbathing in the desert, our findings reveal a surprising level of statistical significance.
This paper aims to shed light on this intriguing relationship, employing rigorous statistical methodologies to unearth the potential factors at play. Through the analysis of extensive datasets spanning nearly three decades, we endeavor to offer a fresh perspective that challenges traditional assumptions and inspires further investigation.
The findings of this research not only contribute to the academic understanding of political behavior and energy consumption patterns but also serve as a reminder that in the world of data analysis, one should always expect the unexpected – much like receiving a bouquet of statistical significance from an unlikely pair of variables.
The exploratory nature of this study is intended to provoke curiosity and spark discussions, much like the sudden realization that two seemingly unrelated entities may indeed dance to the same statistical tune. Therefore, without further ado, let us embark on this journey of uncovering the mystique behind the convergence of gas in Turkmenistan and votes for a Republican.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To investigate the perplexing correlation between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan, an extensive and meticulous approach was undertaken. The data utilized for this analysis was collected from various reputable sources, including the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, covering the period from 1992 to 2020.

Initially, to address the complexity of this unorthodox inquiry, our research team attempted a traditional approach involving straightforward statistical modeling. However, given the whimsical nature of the relationship being explored, it became evident that a more innovative and adaptable method was imperative.

Therefore, a unique hybrid model was devised, blending elements of multivariate regression analysis with a touch of astrological alignment to capture the cosmic confluence of these seemingly disparate variables. This approach allowed for the examination of the relationship between votes for the Republican candidate and liquefied petroleum gas consumption, while also considering the celestial positioning of key astrological signs, as an attempt to align the statistical analysis with the cosmic energy fields.

Furthermore, recognizing the inherent spatial separation between North Dakota and Turkmenistan, a geographic dispersion analysis was performed to account for the geospatial influences on the observed correlation. The geospatial analysis involved mapping the distribution of Republican votes in North Dakota and comparing it to the spatial distribution of liquefied petroleum gas usage in Turkmenistan, with careful consideration for the curvature of the Earth and the potential impact of solar flares on the data integrity.

Additionally, in a lighthearted attempt to integrate the whimsy of this unconventional inquiry, a brief foray into anthropological contemplation was ventured. By exploring the cultural and historical contexts of North Dakota and Turkmenistan, the research sought to uncover potential socio-cultural factors that could underpin the statistical relationship between Republican votes and liquefied petroleum gas consumption.

Moreover, to ensure the robustness of the analysis and to account for the potential autocorrelation and endogeneity of the dataset, a series of robustness checks and sensitivity analyses were conducted. These checks involved subjecting the data to a battery of stringent tests, including but not limited to variations in statistical specifications and the introduction of control variables, such as global coffee consumption and the number of UFO sightings in the vicinity of polling stations.

Finally, to maintain the integrity and authenticity of the findings, a blind review process was undertaken, where renowned statisticians and astrologers were invited to peer into the cosmic conjunction of the data and provide their invaluable insights.

Overall, the methodological approach taken in this study reflects a balance between rigorous empirical analysis and a whimsical spirit of inquiry. The conjunction of traditional statistical methodologies and adventurous experimentation encapsulates the essence of this unconventional journey to unravel the enigmatic correlation between the votes for a Republican and the consumption of liquefied petroleum gas in Turkmenistan.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Dakota and Liquefied petroleum gas used in Turkmenistan. Make lots of jokes, goofy observations, and puns. 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]]
"Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study"

[[ABSTRACT]]
This research paper delves into the unexpected and often overlooked relationship between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in the distant land of Turkmenistan. Despite initial skepticism, our research team utilized data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this peculiar connection. To our surprise, a significant correlation coefficient of 0.9089128 with p < 0.01 emerged from our analysis, covering the period from 1992 to 2020. The findings herein challenge conventional wisdom and are sure to ignite lively discussion among academics and political pundits alike.

[[LITERATURE REVIEW]]
Numerous scholarly works have examined the political landscape and energy consumption patterns, albeit independently, providing valuable insights into both domains. For instance, in "The Political Landscape in Modern America," Smith delves into the complexities of regional voting trends, offering meticulous analyses of state-level political preferences. Similarly, Doe's "Energy Consumption Patterns in Central Asia" presents a comprehensive overview of energy usage in the region, emphasizing the role of liquefied petroleum gas in Turkmenistan. Furthermore, Jones' "Election Dynamics and Political Behavior" explores the myriad factors that shape voting patterns in the United States, establishing a robust theoretical framework for understanding electoral behavior.
Transitioning from these weighty tomes, one cannot overlook the contributions of non-fiction works addressing related themes. A notable example is "The Energy Chronicles: A Global Perspective," which delves into the intricacies of energy consumption across diverse geographical locations. Another compelling read, "Politics Unveiled: An Insider's Account," provides a gripping portrayal of the machinations underlying political decision-making, offering valuable context for understanding electoral dynamics. Not to be discounted are the perennial classics such as "Gas, Grit, and Glory: A Historical Perspective," which intertwines the tale of energy with the tapestry of human endeavor.
Moving into the realm of fiction, the influence of literature on our understanding of interconnected global phenomena cannot be underestimated. Through the lens of fiction, authors often subtly weave threads of truth into the fabric of their narratives, shedding light on aspects of reality that may otherwise remain obscured. Titles such as "The Petroleum Paradox" and "Republican Rhapsody" beckon readers into worlds where the unexpected converges, challenging perceptions and beckoning one to contemplate the improbable.
While the pursuit of knowledge often finds its roots in the erudite, one must not discount the potential for insight from more unconventional sources. In the pursuit of understanding the enigmatic relationship between votes for a Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan, even seemingly whimsical media forms have not been entirely disregarded. Cartoons such as "Gasoline Gus and the Political Pals" and children's shows featuring political themes have provided unexpected moments of clarity, reminding researchers that knowledge does not always adhere to conventional boundaries.
Thus, as we navigate the landscape of literature pertinent to our investigation, it becomes evident that the undercurrents of our research findings may have been subtly hinted at across a diverse array of sources. This diverse spectrum of material has not only informed the conversation surrounding our study but has also provided moments of levity and surprise along the way.

[[RESULTS]]
The analysis of the data revealed a surprisingly strong correlation between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan. The correlation coefficient of 0.9089128 indicates a robust positive relationship between these seemingly unrelated variables. This finding, to put it simply, is as unexpected as finding a polar bear in the desert, or perhaps as unpredictably humorous as a statistical punchline.
The high r-squared value of 0.8261224 further confirms the substantial proportion of the variance in Republican votes in North Dakota explained by the consumption of liquefied petroleum gas in Turkmenistan. In the world of statistical modeling, this level of explicative power is akin to witnessing a perfectly orchestrated dance between two partners who were thought to have very little in common.
The statistical significance, with a p-value of less than 0.01, underscores the reliability of the observed relationship. This level of significance is as compelling as a magician pulling a statistically significant rabbit out of a hat, leaving even the most skeptical observers in awe.
The scatterplot in Fig. 1 visually encapsulates the strength of the relationship, as the points form a tight, upward-sloping pattern that could rival the precision of a well-executed statistical theorem. The metaphorical dance of the data points on the graph could easily be mistaken for a well-rehearsed ballet performance, gracefully illustrating the unexpected harmony between gas consumption in Turkmenistan and political voting patterns in North Dakota.
In conclusion, the results of this study provide compelling evidence of a noteworthy association between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan. This correlation, though initially perplexing, has emerged as a captivating revelation in the world of statistical analysis, reminding researchers that even the most unlikely pairings can sometimes yield remarkable insights. This unexpected statistical love story highlights the potential for unanticipated connections to be found in the most unlikely of places, much like stumbling upon a statistically meaningful reference in an unlikely dataset.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our findings have brought to light an intriguing relationship that defies conventional expectations, comparable to encountering a penguin in the tropics or stumbling upon a statistical epiphany in an unexpected dataset. Building on the whimsical insights gleaned from the literature review, our study has not only validated the suppositions hinted at in seemingly fanciful works but has also underscored the potential for lighthearted sources to contribute unexpectedly to scientific inquiry.

The substantial correlation coefficient of 0.9089128 between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan not only echoes the surprise of finding a clown at a scientific symposium but also challenges the boundaries of traditional scholarly discourse. This robust correlation reaffirms the significance of integrating seemingly unrelated facets into our analytical purview, as accentuated by the amusing references to fictional works and unorthodox media forms in the literature review. Our results provide empirical support for the adage that reality can be stranger than fiction, and that scholarly inquiry should be open to insights from even the most unconventional sources.

Furthermore, the high r-squared value of 0.8261224 demonstrates that a substantial proportion of the variance in Republican votes in North Dakota can be attributed to the consumption of liquefied petroleum gas in Turkmenistan, akin to witnessing the fusion of contrasting dance styles into a harmonious performance. This statistical dance, so to speak, elucidates the unexpected synchronicity between geographically disparate variables and emphasizes the importance of embracing the unexpected in scientific exploration.

The statistical significance of the observed relationship, with a p-value of less than 0.01, accentuates the reliability of our results, perhaps akin to an improbable magic trick leaving onlookers in awe. This level of statistical significance reinforces the unexpected nature of our findings, akin to a surprising plot twist in a grand narrative, and underscores the potential for unconventional variables to exert an influential role in political dynamics.

In conclusion, our research has not only unveiled a statistically significant relationship between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan, but has also endeavored to highlight the unexpected and often whimsical aspects of scientific inquiry. This unanticipated statistical liaison serves as a reminder of the serendipitous nature of scholarly discovery, akin to stumbling upon a hidden joke in a weighty academic text. Our findings encourage researchers to remain open to the possibilities of unprecedented interconnections, reminding us that even the most seemingly incongruous pairings may hold the key to unlocking new realms of knowledge.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Dakota and Liquefied petroleum gas used in Turkmenistan. Make lots of jokes, goofy observations, and puns. 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]]
"Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study"

[[ABSTRACT]]
This research paper delves into the unexpected and often overlooked relationship between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in the distant land of Turkmenistan. Despite initial skepticism, our research team utilized data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this peculiar connection. To our surprise, a significant correlation coefficient of 0.9089128 with p < 0.01 emerged from our analysis, covering the period from 1992 to 2020. The findings herein challenge conventional wisdom and are sure to ignite lively discussion among academics and political pundits alike.

[[INTRDUCTION]]
The relationship between political preferences in one part of the world and energy consumption in another may at first glance seem like an odd couple, akin to an oil and water mixture. However, as the saying goes, "opposites attract" – and in the world of statistical analysis, sometimes the most unexpected pairings yield fascinating insights.
In the current political landscape, where discussions about energy policy and international relations abound, it is important to explore the potential interplay between seemingly disparate factors. Thus, this study delves into the curious correlation between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan. While this connection may appear as unlikely as a polar bear sunbathing in the desert, our findings reveal a surprising level of statistical significance.
This paper aims to shed light on this intriguing relationship, employing rigorous statistical methodologies to unearth the potential factors at play. Through the analysis of extensive datasets spanning nearly three decades, we endeavor to offer a fresh perspective that challenges traditional assumptions and inspires further investigation.
The findings of this research not only contribute to the academic understanding of political behavior and energy consumption patterns but also serve as a reminder that in the world of data analysis, one should always expect the unexpected – much like receiving a bouquet of statistical significance from an unlikely pair of variables.
The exploratory nature of this study is intended to provoke curiosity and spark discussions, much like the sudden realization that two seemingly unrelated entities may indeed dance to the same statistical tune. Therefore, without further ado, let us embark on this journey of uncovering the mystique behind the convergence of gas in Turkmenistan and votes for a Republican.

[[RESULTS]]
The analysis of the data revealed a surprisingly strong correlation between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan. The correlation coefficient of 0.9089128 indicates a robust positive relationship between these seemingly unrelated variables. This finding, to put it simply, is as unexpected as finding a polar bear in the desert, or perhaps as unpredictably humorous as a statistical punchline.
The high r-squared value of 0.8261224 further confirms the substantial proportion of the variance in Republican votes in North Dakota explained by the consumption of liquefied petroleum gas in Turkmenistan. In the world of statistical modeling, this level of explicative power is akin to witnessing a perfectly orchestrated dance between two partners who were thought to have very little in common.
The statistical significance, with a p-value of less than 0.01, underscores the reliability of the observed relationship. This level of significance is as compelling as a magician pulling a statistically significant rabbit out of a hat, leaving even the most skeptical observers in awe.
The scatterplot in Fig. 1 visually encapsulates the strength of the relationship, as the points form a tight, upward-sloping pattern that could rival the precision of a well-executed statistical theorem. The metaphorical dance of the data points on the graph could easily be mistaken for a well-rehearsed ballet performance, gracefully illustrating the unexpected harmony between gas consumption in Turkmenistan and political voting patterns in North Dakota.
In conclusion, the results of this study provide compelling evidence of a noteworthy association between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan. This correlation, though initially perplexing, has emerged as a captivating revelation in the world of statistical analysis, reminding researchers that even the most unlikely pairings can sometimes yield remarkable insights. This unexpected statistical love story highlights the potential for unanticipated connections to be found in the most unlikely of places, much like stumbling upon a statistically meaningful reference in an unlikely dataset.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In light of the robust correlation uncovered between Republican votes in North Dakota and the consumption of liquefied petroleum gas in Turkmenistan, it is clear that these two variables are more than mere statistical acquaintances. This unexpected statistical romance between the American Midwest and the Central Asian steppes is as captivating as an unpredictable plot twist in a statistical thriller.

The significant correlation coefficient and high r-squared value suggest a level of interdependence that is as remarkable as finding statistical treasure in a most unlikely place. The statistical significance, with a p-value of less than 0.01, serves as a compelling reminder that even the most improbable pairings can yield valuable insights, much like discovering a diamond in the rough of a vast dataset.

The findings of this study not only challenge conventional wisdom but also serve as a playful reminder that in the world of data analysis, one should always expect the unexpected – much like receiving a bouquet of statistical significance from an unlikely pair of variables. However, the unexpected delight of this statistical waltz between gas and votes does not necessitate further investigation. The statistical mystery of this unusual pairing has been sufficiently unraveled, and no more research is needed in this area.

In conclusion, this statistical love story between North Dakota and Turkmenistan underscores the potential for remarkable connections to be found in the most unexpected of places. As we bid adieu to this delightful statistical rendezvous, we are reminded that in the world of data analysis, the most compelling discoveries may emerge from the most unlikely of pairings.

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 Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Gas Dynamics

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 Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Geopolitical Analysis and Voter Behavior

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 Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study with an abstract of This research paper delves into the unexpected and often overlooked relationship between the votes for the Republican presidential candidate in North Dakota and the consumption of liquefied petroleum gas in the distant land of Turkmenistan. Despite initial skepticism, our research team utilized data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this peculiar connection. To our surprise, a significant correlation coefficient of 0.9089128 with p < 0.01 emerged from our analysis, covering the period from 1992 to 2020. The findings herein challenge conventional wisdom and are sure to ignite lively discussion among academics and political pundits alike.

ChatGPT:

Gas consumption, Turkmenistan, Republican votes, Republican presidential candidate, North Dakota, liquefied petroleum gas, correlation coefficient, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, statistical study

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

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

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

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

Correlation r = 0.9089128 (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 = 0.8261224 (Coefficient of determination)
This means 82.6% of the change in the one variable (i.e., Liquefied petroleum gas used in Turkmenistan) is predictable based on the change in the other (i.e., Votes for the Republican Presidential candidate in North Dakota) over the 8 years from 1992 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0018.^Show 0.0017626307100965784000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.18% of random cases. Said differently, if you correlated 567 random variables^Note Which I absolutely did.
with the same 7 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 7 because we have two variables measured over a period of 8 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.57, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	1992	1996	2000	2004	2008	2012	2016	2020
Votes for the Republican Presidential candidate in North Dakota (Percentage of votes)	44.216	46.9388	60.6586	62.8613	53.2501	58.3157	62.9556	65.1141
Liquefied petroleum gas used in Turkmenistan (Million Barrels/Day)	6.5	9.4	21.0054	26.8541	25.8093	24.5675	32	37.9463

Why this works

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.
Lack of causal connection: There is probably^Note 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.
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^Note 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.
Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} 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([44.216,46.9388,60.6586,62.8613,53.2501,58.3157,62.9556,65.1141,])
array_2 = np.array([6.5,9.4,21.0054,26.8541,25.8093,24.5675,32,37.9463,])
array_1_name = "Votes for the Republican Presidential candidate in North Dakota"
array_2_name = "Liquefied petroleum gas used in Turkmenistan"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Votes for the Republican Presidential candidate in North Dakota
Line chart for only Liquefied petroleum gas used in Turkmenistan
AI-generated correlation image
The spurious research paper: Gas in Turkmenistan and Votes for a Republican, Oh My! A Statistical Study

View another random correlation

How fun was this correlation?

I'm grateful for your review!

Correlation ID: 4525 · Black Variable ID: 26150 · Red Variable ID: 25022


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: