about · email me · subscribe
Spurious correlation #5,245 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Libertarian Senators in Minnesota and the second variable is Petroluem consumption in Chad.  The chart goes from 1980 to 2014, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The Senators were big fans of more oil-ternative energy sources, leading to a spike in Chad's petrol-eum production to meet the increased demand for libertarian-ium powered vehicles. They really fueled the fire for freedom on the road!

Model: dalle-3
Prompt: Generate an evocative image of contrasting scenes from Minnesota and Chad. In Minnesota, show a sleek, futuristic voting booth with individuals casting ballots for a "Libertarian Senator," set against a backdrop of advanced renewable energy technologies. In Chad, depict powerful, high-tech oil rigs extracting petroleum, while libertarian-ium powered vehicles cruise the roads, emitting minimal pollution. Capture the juxtaposition of modern energy innovation and traditional fossil fuel extraction in dynamic visual compositions. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Votes for Libertarian Senators in Minnesota and Petroluem consumption in Chad. 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: High-tech A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s 3D Pixar Style a meme Glitch art
ChatGPT: High-tech

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for Libertarian Senators in Minnesota and Petroluem consumption in Chad, in the following situation: The Senators were big fans of more oil-ternative energy sources, leading to a spike in Chad's petrol-eum production to meet the increased demand for libertarian-ium powered vehicles. They really fueled the fire for freedom on the road!. Keep the description simple.
ChatGPT: In Minnesota, people line up at the voting booths, marking their ballots with "Libertarian Senator" while a group of senators stand in front of a large banner that reads "More Oil-ternative Energy Sources." Meanwhile, in Chad, oil rigs work tirelessly to produce more petroleum as libertarian-ium powered vehicles drive along the roads, emitting less pollution into the air.

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: [ High-tech ] and depicting this scene: In Minnesota, people line up at the voting booths, marking their ballots with "Libertarian Senator" while a group of senators stand in front of a large banner that reads "More Oil-ternative Energy Sources." Meanwhile, in Chad, oil rigs work tirelessly to produce more petroleum as libertarian-ium powered vehicles drive along the roads, emitting less pollution into the air. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an evocative image of contrasting scenes from Minnesota and Chad. In Minnesota, show a sleek, futuristic voting booth with individuals casting ballots for a "Libertarian Senator," set against a backdrop of advanced renewable energy technologies. In Chad, depict powerful, high-tech oil rigs extracting petroleum, while libertarian-ium powered vehicles cruise the roads, emitting minimal pollution. Capture the juxtaposition of modern energy innovation and traditional fossil fuel extraction in dynamic visual compositions.

*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 Libertarian votes for Senators in Minnesota caused Petroluem consumption in Chad to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?

The International Journal of Ecological Economics and Political Behavior

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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Minnesota and Petroluem consumption in Chad. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9948679 and p < 0.01 for 1980 to 2014.

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]]
Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?

[[ABSTRACT]]
This study delves into the relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our research team rigorously examined this seemingly incongruous pairing. Through meticulous analysis, we discovered a remarkably high correlation coefficient of 0.9948679 and p < 0.01 for the period spanning 1980 to 2014. The implications of this unexpected linkage are certain to fuel robust discussions in both political and energy spheres.


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 introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Minnesota and Petroluem consumption in Chad. 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]]
Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?

[[ABSTRACT]]
This study delves into the relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our research team rigorously examined this seemingly incongruous pairing. Through meticulous analysis, we discovered a remarkably high correlation coefficient of 0.9948679 and p < 0.01 for the period spanning 1980 to 2014. The implications of this unexpected linkage are certain to fuel robust discussions in both political and energy spheres.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The curious juxtaposition of Libertarian votes in Minnesota and petroleum consumption in Chad has piqued the interest of our research team, prompting a thorough investigation into this seemingly incongruous pair. While one might speculate that these variables have as much in common as a hedgehog and a hairdryer, our rigorous analysis has uncovered an unexpected and robust correlation that simply cannot be brushed aside.

Drawing from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our team meticulously collected and processed data covering the period from 1980 to 2014. This period was chosen based on the availability and reliability of data, as well as the desire to delve into the historical nuances of both libertarian voting patterns and petroleum consumption in Chad. The resulting dataset underwent a battery of statistical tests, with our research team exercising the utmost caution to avoid spurious correlations or statistical shenanigans.

The initial skepticism that greeted our research endeavor was understandable. The notion that the voting preferences of Minnesotans, known for their love of lakes and loons, could be related to the petroleum consumption habits of Chadians may seem as unlikely as a penguin in the Sahara. However, as the results started to materialize, it became clear that there was more to this correlation than meets the eye.

Our investigation revealed a correlation coefficient of 0.9948679, a figure that, by statistical standards, is more eye-catching than a brightly colored peacock during mating season. Furthermore, with a p-value of less than 0.01, the strength of this association cannot be dismissed as mere statistical noise. The implications of such a high correlation are as intriguing as they are unexpected, unlocking a Pandora's box of questions and avenues for further inquiry.

As we embark on the journey to unravel the mystery behind this linkage, it is imperative to tread carefully and approach the findings with the necessary scientific skepticism. The potential far-reaching implications of these results demand a dispassionate and thorough exploration, one that goes beyond mere data points and ventures into the realm of nuanced interpretation and thoughtful speculation. In the pages that follow, we aim to dissect this correlation, teasing out the threads that connect libertarian votes in Minnesota to petroleum consumption in Chad, and illuminating the potential implications for both political and energy landscapes.


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 Libertarian votes for Senators in Minnesota and Petroluem consumption in Chad. 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]]
Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?

[[ABSTRACT]]
This study delves into the relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our research team rigorously examined this seemingly incongruous pairing. Through meticulous analysis, we discovered a remarkably high correlation coefficient of 0.9948679 and p < 0.01 for the period spanning 1980 to 2014. The implications of this unexpected linkage are certain to fuel robust discussions in both political and energy spheres.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The curious juxtaposition of Libertarian votes in Minnesota and petroleum consumption in Chad has piqued the interest of our research team, prompting a thorough investigation into this seemingly incongruous pair. While one might speculate that these variables have as much in common as a hedgehog and a hairdryer, our rigorous analysis has uncovered an unexpected and robust correlation that simply cannot be brushed aside.
Drawing from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our team meticulously collected and processed data covering the period from 1980 to 2014. This period was chosen based on the availability and reliability of data, as well as the desire to delve into the historical nuances of both libertarian voting patterns and petroleum consumption in Chad. The resulting dataset underwent a battery of statistical tests, with our research team exercising the utmost caution to avoid spurious correlations or statistical shenanigans.
The initial skepticism that greeted our research endeavor was understandable. The notion that the voting preferences of Minnesotans, known for their love of lakes and loons, could be related to the petroleum consumption habits of Chadians may seem as unlikely as a penguin in the Sahara. However, as the results started to materialize, it became clear that there was more to this correlation than meets the eye.
Our investigation revealed a correlation coefficient of 0.9948679, a figure that, by statistical standards, is more eye-catching than a brightly colored peacock during mating season. Furthermore, with a p-value of less than 0.01, the strength of this association cannot be dismissed as mere statistical noise. The implications of such a high correlation are as intriguing as they are unexpected, unlocking a Pandora's box of questions and avenues for further inquiry.
As we embark on the journey to unravel the mystery behind this linkage, it is imperative to tread carefully and approach the findings with the necessary scientific skepticism. The potential far-reaching implications of these results demand a dispassionate and thorough exploration, one that goes beyond mere data points and ventures into the realm of nuanced interpretation and thoughtful speculation. In the pages that follow, we aim to dissect this correlation, teasing out the threads that connect libertarian votes in Minnesota to petroleum consumption in Chad, and illuminating the potential implications for both political and energy landscapes.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Smith (2010) posits a rational political model to explain voting behavior, emphasizing individual preferences and economic self-interest. While Smith's work has been foundational in elucidating the complexities of voter decision-making, it does not directly address the specific confluence of Libertarian votes in Minnesota and petroleum consumption in Chad. Doe (2015) highlights the intricate interplay of energy geopolitics and economic development in Sub-Saharan Africa, shedding light on the dynamics of petroleum consumption in the region. Jones (2018) delves into the ideological landscape of American politics, offering insights into the emergence of third-party movements and their potential influence on the electoral arena. However, the intersection of these bodies of literature with the seemingly disparate variables under examination in this study is yet unexplored.

Turning to more general works that could shed some light on the matter, "The Libertarian Mind" by David Boaz and "Atlas Shrugged" by Ayn Rand offer foundational perspectives on Libertarian ideology and its potential sway in political landscapes. These sources, while not explicitly discussing the petroleum consumption habits of Chadians, contribute to our understanding of the ideological underpinnings of Libertarianism. Furthermore, "The Prize: The Epic Quest for Oil, Money, and Power" by Daniel Yergin and "Crude World: The Violent Twilight of Oil" by Peter Maass provide comprehensive analyses of the global petroleum industry, serving as valuable resources to comprehend the broader context of petroleum consumption and its implications.

Venturing into the realm of fiction, Ayn Rand's "Atlas Shrugged" and John Grisham's "The Appeal" may appear tangentially related to the topic at hand. While the former delves into philosophical discourse on individualism and societal contribution, the latter offers a legal drama that, despite its revolve around courtroom battles, fails to directly address the intriguing link between Libertarian votes in Minnesota and petroleum consumption in Chad. Furthermore, movies such as "There Will Be Blood" and "Syriana" invoke varying perspectives on the complexities of the petroleum industry and its influence on socio-political dynamics, though they do not specifically address the unique juxtaposition under scrutiny in this study.


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 Libertarian votes for Senators in Minnesota and Petroluem consumption in Chad. 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 2014

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]]
Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?

[[ABSTRACT]]
This study delves into the relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our research team rigorously examined this seemingly incongruous pairing. Through meticulous analysis, we discovered a remarkably high correlation coefficient of 0.9948679 and p < 0.01 for the period spanning 1980 to 2014. The implications of this unexpected linkage are certain to fuel robust discussions in both political and energy spheres.

[[INTRODUCTION]]
The curious juxtaposition of Libertarian votes in Minnesota and petroleum consumption in Chad has piqued the interest of our research team, prompting a thorough investigation into this seemingly incongruous pair. While one might speculate that these variables have as much in common as a hedgehog and a hairdryer, our rigorous analysis has uncovered an unexpected and robust correlation that simply cannot be brushed aside.
Drawing from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our team meticulously collected and processed data covering the period from 1980 to 2014. This period was chosen based on the availability and reliability of data, as well as the desire to delve into the historical nuances of both libertarian voting patterns and petroleum consumption in Chad. The resulting dataset underwent a battery of statistical tests, with our research team exercising the utmost caution to avoid spurious correlations or statistical shenanigans.
The initial skepticism that greeted our research endeavor was understandable. The notion that the voting preferences of Minnesotans, known for their love of lakes and loons, could be related to the petroleum consumption habits of Chadians may seem as unlikely as a penguin in the Sahara. However, as the results started to materialize, it became clear that there was more to this correlation than meets the eye.
Our investigation revealed a correlation coefficient of 0.9948679, a figure that, by statistical standards, is more eye-catching than a brightly colored peacock during mating season. Furthermore, with a p-value of less than 0.01, the strength of this association cannot be dismissed as mere statistical noise. The implications of such a high correlation are as intriguing as they are unexpected, unlocking a Pandora's box of questions and avenues for further inquiry.
As we embark on the journey to unravel the mystery behind this linkage, it is imperative to tread carefully and approach the findings with the necessary scientific skepticism. The potential far-reaching implications of these results demand a dispassionate and thorough exploration, one that goes beyond mere data points and ventures into the realm of nuanced interpretation and thoughtful speculation. In the pages that follow, we aim to dissect this correlation, teasing out the threads that connect libertarian votes in Minnesota to petroleum consumption in Chad, and illuminating the potential implications for both political and energy landscapes.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data utilized in this study originated primarily from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration. The choice of these sources was driven by the factors of data availability, credibility, and the desire to incorporate a diverse range of information for a comprehensive analysis. The data covered the period from 1980 to 2014, encompassing a timeframe that allowed for the exploration of historical shifts in both libertarian voting patterns and petroleum consumption in Chad.

The process of data collection resembled a scientific scavenger hunt, as the research team scoured through an eclectic assortment of datasets, navigating the labyrinthine corridors of digital archives and repositories. The careful curation of these datasets, akin to the selection of ingredients for an intricate culinary masterpiece, aimed to ensure a rich and flavorful exploration of the relationship between seemingly disparate variables.

Variable Selection:
In considering the variables for analysis, the research team took meticulous care to identify measures that encapsulated the essence of libertarian voting in Minnesota and petroleum consumption in Chad. The choice of these variables was guided by a desire to capture the essence of these phenomena, much like a skilled artist aims to convey the spirit of a subject through brushstrokes on canvas. The variables were then subjected to stringent scrutiny, akin to the discerning eye of a connoisseur evaluating fine wine, to ensure their relevance and reliability for the study.

Data Processing and Statistical Analysis:
Upon the acquisition of the datasets, our research team embarked on a journey through the labyrinth of statistical analysis, wielding an arsenal of mathematical tools and techniques. The data underwent rigorous processing and cleansing, akin to the meticulous grooming of a prized show dog, to ensure that inaccuracies and anomalies did not detract from the integrity of the analysis.

Statistical analyses, including but not limited to correlation coefficients and regression models, were employed to unravel the complex interplay between libertarian votes in Minnesota and petroleum consumption in Chad. These analytical methods, akin to the investigative prowess of a seasoned detective, sought to uncover the underlying patterns and connections hidden within the dataset, shedding light on the enigmatic relationship between the variables.

Validity Checks and Sensitivity Analysis:
In the pursuit of scientific rigor, the research team conducted a series of validity checks and sensitivity analyses to scrutinize the robustness of the findings. These exercises, resembling the stress tests undergone by architectural structures or the resilience assessments of space-bound machinery, provided a critical assessment of the stability and reliability of the results, guarding against the pitfalls of spurious correlations and statistical mirages.

The validation process involved an interrogation of the data from varied vantage points, akin to the examination of an enigmatic puzzle from different angles, to ascertain the consistency and coherence of the results. Sensitivity analyses, akin to exposing an artwork to different lighting conditions, probed the resilience of the findings against potential fluctuations and perturbations, ensuring that the conclusions stood firm in the face of scrutiny.

Limitations and Assumptions:
It is important to acknowledge the inherent limitations and assumptions that underpin this study. The analysis operates within the confines of observational data, and as such, the establishment of causality must be approached with caution. The assumptions inherent to statistical analyses, akin to the premises of a logical argument, serve as the foundation upon which the findings are built and warrant careful consideration.

Furthermore, the generalizability of the findings may be subject to constraints stemming from the specificity of the chosen variables and the temporal scope of the study. These limitations, akin to the boundaries of a theatrical stage, delineate the extent to which the findings can be extrapolated to broader contexts and underscore the importance of circumspect interpretation.

Ethical Considerations:
Throughout the research process, ethical considerations remained paramount, guiding the treatment of data and the dissemination of findings. The principles of integrity and transparency, akin to the moral compass of ethical conduct, steered the course of the study, ensuring that the pursuit of knowledge remained anchored in ethical responsibility.

In summary, the establishment of the methodological framework for this research endeavor encompassed a blend of meticulous data collection, scrupulous variable selection, rigorous statistical analyses, and careful consideration of limitations and ethical principles. These methodological pillars form the bedrock upon which the findings are presented and invite further scholarly discourse and inquiry into the unexpected relationship between libertarian votes in Minnesota and petroleum consumption in Chad.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Libertarian votes for Senators in Minnesota and Petroluem consumption in Chad. 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 2014, you found a correlation 0.9948679, r-squared of 0.9897621, 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]]
Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?

[[ABSTRACT]]
This study delves into the relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our research team rigorously examined this seemingly incongruous pairing. Through meticulous analysis, we discovered a remarkably high correlation coefficient of 0.9948679 and p < 0.01 for the period spanning 1980 to 2014. The implications of this unexpected linkage are certain to fuel robust discussions in both political and energy spheres.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The curious juxtaposition of Libertarian votes in Minnesota and petroleum consumption in Chad has piqued the interest of our research team, prompting a thorough investigation into this seemingly incongruous pair. While one might speculate that these variables have as much in common as a hedgehog and a hairdryer, our rigorous analysis has uncovered an unexpected and robust correlation that simply cannot be brushed aside.
Drawing from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our team meticulously collected and processed data covering the period from 1980 to 2014. This period was chosen based on the availability and reliability of data, as well as the desire to delve into the historical nuances of both libertarian voting patterns and petroleum consumption in Chad. The resulting dataset underwent a battery of statistical tests, with our research team exercising the utmost caution to avoid spurious correlations or statistical shenanigans.
The initial skepticism that greeted our research endeavor was understandable. The notion that the voting preferences of Minnesotans, known for their love of lakes and loons, could be related to the petroleum consumption habits of Chadians may seem as unlikely as a penguin in the Sahara. However, as the results started to materialize, it became clear that there was more to this correlation than meets the eye.
Our investigation revealed a correlation coefficient of 0.9948679, a figure that, by statistical standards, is more eye-catching than a brightly colored peacock during mating season. Furthermore, with a p-value of less than 0.01, the strength of this association cannot be dismissed as mere statistical noise. The implications of such a high correlation are as intriguing as they are unexpected, unlocking a Pandora's box of questions and avenues for further inquiry.
As we embark on the journey to unravel the mystery behind this linkage, it is imperative to tread carefully and approach the findings with the necessary scientific skepticism. The potential far-reaching implications of these results demand a dispassionate and thorough exploration, one that goes beyond mere data points and ventures into the realm of nuanced interpretation and thoughtful speculation. In the pages that follow, we aim to dissect this correlation, teasing out the threads that connect libertarian votes in Minnesota to petroleum consumption in Chad, and illuminating the potential implications for both political and energy landscapes.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data revealed a remarkably high correlation coefficient of 0.9948679 between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad for the period spanning 1980 to 2014. This correlation coefficient is as strong as a bull in a china shop, leaving little room for doubt about the robustness of the relationship between these seemingly disparate variables.

Furthermore, the r-squared value of 0.9897621 indicates that approximately 98.98% of the variance in petroleum consumption in Chad can be explained by the variance in Libertarian votes in Minnesota. To put it simply, the relationship between these two variables is as clear as a cloudless day in the desert.

With a p-value of less than 0.01, we can confidently reject the null hypothesis and assert that this correlation is not due to random chance or mere statistical flukes. This p-value is more decisive than a referee's whistle in a football match, signaling that the relationship we have uncovered is indeed statistically significant.

Figure 1 displays a scatterplot illustrating the strong positive correlation between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. The points on the plot are as tightly clustered as peas in a pod, showcasing the striking alignment between these two variables.

These findings challenge conventional wisdom and beckon for further scrutiny and inquiry into the unexpected interplay between political preferences and energy consumption patterns. The implications of this unlikely linkage are as intriguing as they are confounding, fueling discussions that are bound to ignite sparks across multiple fields of study.


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 Libertarian votes for Senators in Minnesota and Petroluem consumption in Chad. 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]]
Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?

[[ABSTRACT]]
This study delves into the relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our research team rigorously examined this seemingly incongruous pairing. Through meticulous analysis, we discovered a remarkably high correlation coefficient of 0.9948679 and p < 0.01 for the period spanning 1980 to 2014. The implications of this unexpected linkage are certain to fuel robust discussions in both political and energy spheres.

[[LITERATURE REVIEW]]
Smith (2010) posits a rational political model to explain voting behavior, emphasizing individual preferences and economic self-interest. While Smith's work has been foundational in elucidating the complexities of voter decision-making, it does not directly address the specific confluence of Libertarian votes in Minnesota and petroleum consumption in Chad. Doe (2015) highlights the intricate interplay of energy geopolitics and economic development in Sub-Saharan Africa, shedding light on the dynamics of petroleum consumption in the region. Jones (2018) delves into the ideological landscape of American politics, offering insights into the emergence of third-party movements and their potential influence on the electoral arena. However, the intersection of these bodies of literature with the seemingly disparate variables under examination in this study is yet unexplored.
Turning to more general works that could shed some light on the matter, "The Libertarian Mind" by David Boaz and "Atlas Shrugged" by Ayn Rand offer foundational perspectives on Libertarian ideology and its potential sway in political landscapes. These sources, while not explicitly discussing the petroleum consumption habits of Chadians, contribute to our understanding of the ideological underpinnings of Libertarianism. Furthermore, "The Prize: The Epic Quest for Oil, Money, and Power" by Daniel Yergin and "Crude World: The Violent Twilight of Oil" by Peter Maass provide comprehensive analyses of the global petroleum industry, serving as valuable resources to comprehend the broader context of petroleum consumption and its implications.
Venturing into the realm of fiction, Ayn Rand's "Atlas Shrugged" and John Grisham's "The Appeal" may appear tangentially related to the topic at hand. While the former delves into philosophical discourse on individualism and societal contribution, the latter offers a legal drama that, despite its revolve around courtroom battles, fails to directly address the intriguing link between Libertarian votes in Minnesota and petroleum consumption in Chad. Furthermore, movies such as "There Will Be Blood" and "Syriana" invoke varying perspectives on the complexities of the petroleum industry and its influence on socio-political dynamics, though they do not specifically address the unique juxtaposition under scrutiny in this study.

[[RESULTS]]
The analysis of the data revealed a remarkably high correlation coefficient of 0.9948679 between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad for the period spanning 1980 to 2014. This correlation coefficient is as strong as a bull in a china shop, leaving little room for doubt about the robustness of the relationship between these seemingly disparate variables.
Furthermore, the r-squared value of 0.9897621 indicates that approximately 98.98% of the variance in petroleum consumption in Chad can be explained by the variance in Libertarian votes in Minnesota. To put it simply, the relationship between these two variables is as clear as a cloudless day in the desert.
With a p-value of less than 0.01, we can confidently reject the null hypothesis and assert that this correlation is not due to random chance or mere statistical flukes. This p-value is more decisive than a referee's whistle in a football match, signaling that the relationship we have uncovered is indeed statistically significant.
Figure 1 displays a scatterplot illustrating the strong positive correlation between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. The points on the plot are as tightly clustered as peas in a pod, showcasing the striking alignment between these two variables.
These findings challenge conventional wisdom and beckon for further scrutiny and inquiry into the unexpected interplay between political preferences and energy consumption patterns. The implications of this unlikely linkage are as intriguing as they are confounding, fueling discussions that are bound to ignite sparks across multiple fields of study.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The remarkably high correlation coefficient of 0.9948679 between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad, as indicated by our study, sheds light on a previously unexplored relationship. The results not only reaffirm the relevance of individual preferences and economic self-interest in political behavior, as posited by Smith (2010), but they also highlight the potential for unexpected connections between geographically distant variables. Our findings, like a bolt out of the blue, challenge conventional assumptions and call for a reevaluation of the complex interplay between political ideologies and energy dynamics.

Drawing from the literature, although seemingly tangential, "Atlas Shrugged" by Ayn Rand and "The Appeal" by John Grisham indirectly contribute to our understanding of Libertarian ideology and the legal complexities that underpin modern political landscapes. The unexpected nature of our findings resonates with the twists and turns in Grisham's legal drama, leaving scholars and policymakers alike in anticipation of the next chapter in the story of this peculiar correlation. Furthermore, the valuable insights offered by "The Prize: The Epic Quest for Oil, Money, and Power" by Daniel Yergin and "Crude World: The Violent Twilight of Oil" by Peter Maass contribute to a deeper appreciation of the broader context within which the unprecedented linkage between political preferences in Minnesota and energy consumption in Chad has emerged.

The robust statistical significance of our results, akin to a pulsating beat in a musical masterpiece, underscores the need for further research to unravel the intricacies of this unexpected association. As such, our study, much like a captivating cliffhanger, invites future investigations to delve into the nuanced mechanisms underlying this intriguing correlation. This unlikely pairing of variables provokes a well-deserved eyebrow raise in the scientific community, emphasizing the importance of remaining open to unanticipated connections and serendipitous discoveries in research.


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 Libertarian votes for Senators in Minnesota and Petroluem consumption in Chad. 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]]
Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?

[[ABSTRACT]]
This study delves into the relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our research team rigorously examined this seemingly incongruous pairing. Through meticulous analysis, we discovered a remarkably high correlation coefficient of 0.9948679 and p < 0.01 for the period spanning 1980 to 2014. The implications of this unexpected linkage are certain to fuel robust discussions in both political and energy spheres.

[[INTRDUCTION]]
The curious juxtaposition of Libertarian votes in Minnesota and petroleum consumption in Chad has piqued the interest of our research team, prompting a thorough investigation into this seemingly incongruous pair. While one might speculate that these variables have as much in common as a hedgehog and a hairdryer, our rigorous analysis has uncovered an unexpected and robust correlation that simply cannot be brushed aside.
Drawing from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our team meticulously collected and processed data covering the period from 1980 to 2014. This period was chosen based on the availability and reliability of data, as well as the desire to delve into the historical nuances of both libertarian voting patterns and petroleum consumption in Chad. The resulting dataset underwent a battery of statistical tests, with our research team exercising the utmost caution to avoid spurious correlations or statistical shenanigans.
The initial skepticism that greeted our research endeavor was understandable. The notion that the voting preferences of Minnesotans, known for their love of lakes and loons, could be related to the petroleum consumption habits of Chadians may seem as unlikely as a penguin in the Sahara. However, as the results started to materialize, it became clear that there was more to this correlation than meets the eye.
Our investigation revealed a correlation coefficient of 0.9948679, a figure that, by statistical standards, is more eye-catching than a brightly colored peacock during mating season. Furthermore, with a p-value of less than 0.01, the strength of this association cannot be dismissed as mere statistical noise. The implications of such a high correlation are as intriguing as they are unexpected, unlocking a Pandora's box of questions and avenues for further inquiry.
As we embark on the journey to unravel the mystery behind this linkage, it is imperative to tread carefully and approach the findings with the necessary scientific skepticism. The potential far-reaching implications of these results demand a dispassionate and thorough exploration, one that goes beyond mere data points and ventures into the realm of nuanced interpretation and thoughtful speculation. In the pages that follow, we aim to dissect this correlation, teasing out the threads that connect libertarian votes in Minnesota to petroleum consumption in Chad, and illuminating the potential implications for both political and energy landscapes.

[[RESULTS]]
The analysis of the data revealed a remarkably high correlation coefficient of 0.9948679 between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad for the period spanning 1980 to 2014. This correlation coefficient is as strong as a bull in a china shop, leaving little room for doubt about the robustness of the relationship between these seemingly disparate variables.
Furthermore, the r-squared value of 0.9897621 indicates that approximately 98.98% of the variance in petroleum consumption in Chad can be explained by the variance in Libertarian votes in Minnesota. To put it simply, the relationship between these two variables is as clear as a cloudless day in the desert.
With a p-value of less than 0.01, we can confidently reject the null hypothesis and assert that this correlation is not due to random chance or mere statistical flukes. This p-value is more decisive than a referee's whistle in a football match, signaling that the relationship we have uncovered is indeed statistically significant.
Figure 1 displays a scatterplot illustrating the strong positive correlation between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. The points on the plot are as tightly clustered as peas in a pod, showcasing the striking alignment between these two variables.
These findings challenge conventional wisdom and beckon for further scrutiny and inquiry into the unexpected interplay between political preferences and energy consumption patterns. The implications of this unlikely linkage are as intriguing as they are confounding, fueling discussions that are bound to ignite sparks across multiple fields of study.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In concluding our exploration of the perplexing relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad, it is evident that the strength of the correlation between these variables is as undeniable as the force of gravity. This unexpected linkage, akin to discovering a pineapple on a pizza, has sparked discussions that are as lively as a caffeinated laboratory mouse.

The robust correlation coefficient of 0.9948679 has left little room for doubt, standing out like a bright beacon in the night sky of statistical analysis. The r-squared value of 0.9897621 further emphasizes the tight grip that Libertarian votes in Minnesota seem to have on petroleum consumption in Chad, like a vise clamping down on a reluctant jar lid.

The p-value of less than 0.01 is as conclusive as a period at the end of a sentence, leaving no room for doubting the statistical significance of this unexpected relationship. The scatterplot, with points as tightly clustered as sardines in a can, vividly illustrates the striking alignment between these seemingly incongruous variables, leaving us with a sense of awe akin to witnessing a synchronized swimming team of statisticians.

Exploring the implications of this linkage has been as enlightening as stumbling upon a hidden treasure trove in the world of research. It is clear that the potential impact of these findings spans far beyond the realms of political and energy landscapes, reaching into the uncharted territories of interdisciplinary inquiry.

In conclusion, we assert with a confidence as firm as a well-anchored ship that no further research into this area is necessary. The unexpected nexus between Libertarian votes in Minnesota and petroleum consumption in Chad has been thoroughly explored, and the implications of our findings are as vast as the night sky, paving the way for new avenues of thought and inquiry. Therefore, it is with a sense of accomplishment and amusement that we bid adieu to this surprising confluence of variables, leaving it to tantalize and perplex future scholars and enthusiasts alike.


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 Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Ecological Economics and Political Behavior


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 Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad?. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Interdisciplinary Research on Global Energy and Political Economy


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 Libertarian Votes in Minnesota: A Link to Petroleum Consumption in Chad? with an abstract of This study delves into the relationship between Libertarian votes for Senators in Minnesota and petroleum consumption in Chad. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, our research team rigorously examined this seemingly incongruous pairing. Through meticulous analysis, we discovered a remarkably high correlation coefficient of 0.9948679 and p < 0.01 for the period spanning 1980 to 2014. The implications of this unexpected linkage are certain to fuel robust discussions in both political and energy spheres.

ChatGPT:

Libertarian votes, Minnesota, petroleum consumption, Chad, correlation coefficient, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, political implications, energy implications, data analysis

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

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

Correlation r = 0.9948679 (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 = 0.9897621 (Coefficient of determination)
This means 99% of the change in the one variable (i.e., Petroluem consumption in Chad) is predictable based on the change in the other (i.e., Votes for Libertarian Senators in Minnesota) over the 7 years from 1980 through 2014.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.6E-6. 0.0000036141049969759642000000
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 0.99 in 0.00036% of random cases. Said differently, if you correlated 276,694 random variables You don't actually need 276 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 6 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 6 because we have two variables measured over a period of 7 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.

[ 0.96, 1 ] 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.
1982198419881996200020082014
Votes for Libertarian Senators in Minnesota (Percentage of votes)0.3252660.2252020.1928890.2486590.2722850.4821571.49809
Petroluem consumption in Chad (Million Barrels/Day)1.90.91.012771.21.691232.131647.16348




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.325266,0.225202,0.192889,0.248659,0.272285,0.482157,1.49809,])
array_2 = np.array([1.9,0.9,1.01277,1.2,1.69123,2.13164,7.16348,])
array_1_name = "Votes for Libertarian Senators in Minnesota"
array_2_name = "Petroluem consumption in Chad"

# 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?

Bravo! Your evaluation rocks!


Correlation ID: 5245 · Black Variable ID: 26408 · Red Variable ID: 24286
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0