about · email me · subscribe
Spurious correlation #5,454 · 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 New York and the second variable is Petroluem consumption in Somalia.  The chart goes from 1980 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the saying goes, "less GOP votes in NY means more Soma-ralia for Somalia"! It seems that as the Republican support in New York dwindled, so did the demand for petroleum in Somalia. Perhaps it's because there were fewer political rallies needing fuel, or maybe it's simply a case of trickle-down non-economics.

Model: dalle-3
Prompt: A futuristic New York voting booth with sleek, glowing panels displays fewer ballots marked for the Republican candidate. The booth is surrounded by advanced holographic projections of data analysis. Meanwhile, outside the booth, a high-tech fuel station in Somalia showcases fewer vehicles filling up with petroleum. The scene is illuminated with modern digital signage and sophisticated fuel dispensers. The connection between the two scenes is subtly conveyed through advanced visual data streams linking the decreased Republican support in New York with the reduced petroleum consumption in Somalia. 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 New York and Petroluem consumption in Somalia. 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: Magic realism High-tech Whimsical illustration Cute cartoon Low poly
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 the Republican Presidential candidate in New York and Petroluem consumption in Somalia, in the following situation: As the saying goes, "less GOP votes in NY means more Soma-ralia for Somalia"! It seems that as the Republican support in New York dwindled, so did the demand for petroleum in Somalia. Perhaps it's because there were fewer political rallies needing fuel, or maybe it's simply a case of trickle-down non-economics.. Keep the description simple.
ChatGPT: In a New York voting booth, there are fewer ballots marked for the Republican candidate. Outside the booth, a fuel station in Somalia shows fewer vehicles filling up with petroleum. The connection between the two scenes suggests that decreased Republican support in New York correlates with reduced petroleum consumption in Somalia.

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 a New York voting booth, there are fewer ballots marked for the Republican candidate. Outside the booth, a fuel station in Somalia shows fewer vehicles filling up with petroleum. The connection between the two scenes suggests that decreased Republican support in New York correlates with reduced petroleum consumption in Somalia. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: A futuristic New York voting booth with sleek, glowing panels displays fewer ballots marked for the Republican candidate. The booth is surrounded by advanced holographic projections of data analysis. Meanwhile, outside the booth, a high-tech fuel station in Somalia showcases fewer vehicles filling up with petroleum. The scene is illuminated with modern digital signage and sophisticated fuel dispensers. The connection between the two scenes is subtly conveyed through advanced visual data streams linking the decreased Republican support in New York with the reduced petroleum consumption in Somalia.

*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 a decrease in Votes for the Republican Presidential candidate in New York caused Petroluem consumption in Somalia to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)
Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia

The Journal of Energized Politics

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in New York and Petroluem consumption in Somalia. Make lots of jokes, goofy observations, and puns.

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

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9287825 and p < 0.01 for 1980 to 2020.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia

[[ABSTRACT]]
This study presents an unexpected correlation between the votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team calculated a correlation coefficient of 0.9287825, with a p-value less than 0.01. Despite the geographical and cultural disparities between New York and Somalia, our findings suggest a surprising linkage between the political inclinations of New Yorkers and the petrol preferences of Somalians. The pun-intended "gas-tacular" relationship uncovered by our research sheds light on the interconnectedness of global politics and energy consumption. This correlation may seem as unlikely as finding a snowstorm in the Sahara, but the data speaks for itself in this quirky intersection of geopolitics and energy trends.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in New York and Petroluem consumption in Somalia. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia

[[ABSTRACT]]
This study presents an unexpected correlation between the votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team calculated a correlation coefficient of 0.9287825, with a p-value less than 0.01. Despite the geographical and cultural disparities between New York and Somalia, our findings suggest a surprising linkage between the political inclinations of New Yorkers and the petrol preferences of Somalians. The pun-intended "gas-tacular" relationship uncovered by our research sheds light on the interconnectedness of global politics and energy consumption. This correlation may seem as unlikely as finding a snowstorm in the Sahara, but the data speaks for itself in this quirky intersection of geopolitics and energy trends.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

The intersection of politics and energy consumption has often been a source of heated debates, but few could have predicted the surprising relationship uncovered in this study. The correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia has left many scratching their heads and wondering if they missed the turn at the intersection of geopolitics and energy trends.

This study may have begun as a mere curiosity, an off-hand remark about the possibility of a connection between the political leanings of New Yorkers and the petrol preferences of Somalians, but the data spoke volumes – not quite as loud as a revving engine, but close. As unlikely as finding a snowstorm in the Sahara, the correlation coefficient of 0.9287825 has us asking, “What in the world?”

While it's common to hear about oil influencing international relations, who would have thought that it might also influence political inclinations across an ocean? It seems oil has been hiding some political aspirations under its slippery surface, fueling the political spectrum in ways we never expected. We may need some gasoline to fuel these theories.

Our study delves into the data from 1980 to 2020 to unravel this puzzling connection, utilizing the reputable MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration. We didn't expect to find ourselves comparing the illuminated Statue of Liberty with the desert expanse of Somalia, but here we are, discussing petrol and politics with a straight face – well, mostly straight-faced.

Whether you find this correlation to be as bewildering as a politician without a prepared speech or as clear as day, the “gas-tacular” connection we've unearthed serves as a reminder that in the world of research, even the most unexpected findings can sometimes be the most enlightening. So, join us as we navigate this unexpected detour on the road of scholarly inquiry and attempt to unpack this political-petroleum enigma. Let's hope we don't run out of fuel before we reach our conclusion.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in New York and Petroluem consumption in Somalia. 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia

[[ABSTRACT]]
This study presents an unexpected correlation between the votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team calculated a correlation coefficient of 0.9287825, with a p-value less than 0.01. Despite the geographical and cultural disparities between New York and Somalia, our findings suggest a surprising linkage between the political inclinations of New Yorkers and the petrol preferences of Somalians. The pun-intended "gas-tacular" relationship uncovered by our research sheds light on the interconnectedness of global politics and energy consumption. This correlation may seem as unlikely as finding a snowstorm in the Sahara, but the data speaks for itself in this quirky intersection of geopolitics and energy trends.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The intersection of politics and energy consumption has often been a source of heated debates, but few could have predicted the surprising relationship uncovered in this study. The correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia has left many scratching their heads and wondering if they missed the turn at the intersection of geopolitics and energy trends.
This study may have begun as a mere curiosity, an off-hand remark about the possibility of a connection between the political leanings of New Yorkers and the petrol preferences of Somalians, but the data spoke volumes – not quite as loud as a revving engine, but close. As unlikely as finding a snowstorm in the Sahara, the correlation coefficient of 0.9287825 has us asking, “What in the world?”
While it's common to hear about oil influencing international relations, who would have thought that it might also influence political inclinations across an ocean? It seems oil has been hiding some political aspirations under its slippery surface, fueling the political spectrum in ways we never expected. We may need some gasoline to fuel these theories.
Our study delves into the data from 1980 to 2020 to unravel this puzzling connection, utilizing the reputable MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration. We didn't expect to find ourselves comparing the illuminated Statue of Liberty with the desert expanse of Somalia, but here we are, discussing petrol and politics with a straight face – well, mostly straight-faced.
Whether you find this correlation to be as bewildering as a politician without a prepared speech or as clear as day, the “gas-tacular” connection we've unearthed serves as a reminder that in the world of research, even the most unexpected findings can sometimes be the most enlightening. So, join us as we navigate this unexpected detour on the road of scholarly inquiry and attempt to unpack this political-petroleum enigma. Let's hope we don't run out of fuel before we reach our conclusion.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The intersection of politics and energy consumption has indeed been an area of growing interest in the academic world. Smith et al. (2015) found a fascinating correlation between voting behaviors and regional energy consumption in their study, "Political Pumps and Ballot Boxes." Their analysis of state-level voting patterns and petroleum usage hinted at a nuanced relationship between political events and energy trends. However, little did they know that their findings would pale in comparison to the gas-tacular saga we are about to unravel.

Turning to the social and cultural aspects of energy consumption, Doe and Jones (2018) delved into the societal implications of petroleum usage in their work, "Oil and Society: An Interdisciplinary Analysis." Their exploration of the nuanced connections between oil, culture, and politics shed light on the often uncharted territories of energy's influence on human behaviors and societal structures. Little did they know that our study would take this exploration to a whole new level, revealing a connection as unexpected as finding a penguin in the Sahara.

As we dig deeper into the intersection of politics and energy, one cannot overlook the influence of popular non-fiction works such as "The Prize: The Epic Quest for Oil, Money, and Power" by Daniel Yergin and "Private Empire: ExxonMobil and American Power" by Steve Coll. These insightful works highlight the complex dynamics of energy politics, showcasing the intricate web of interests, power struggles, and global dynamics that revolve around oil. Little did they anticipate that a comparison between New York votes and Somali petroleum consumption would be on par with a subplot from a science fiction novel.

Speaking of which, the fictional world has also dabbled in the realms of energy and politics with works like "The Handmaid's Fuel" by Margaret Atwood and "A Dance with Gasoline" by George R.R. Martin. These fictional narratives, while purely speculative, offer an intriguing parallel to our unexpected findings, portraying worlds where energy sources shape political landscapes in ways that are as mind-bending as a political debate between a unicorn and a centaur.

Moreover, our research draws inspiration from cinematic tales such as "There Will Be Fuel," where oil prospecting and political maneuvering collide in a dramatic narrative. The storyline takes unexpected turns, much like our own study's findings, emphasizing how energy and politics can intertwine in ways as unpredictable as a summer hailstorm.

In the following sections, we delve into the uncharted territory of the seemingly unrelated yet strangely intertwined realms of New York votes and Somali petrol consumption. Our findings are as surprising as finding a clownfish driving a car – a delightful twist in the narrative of energy and politics.



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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in New York and Petroluem consumption in Somalia. 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 1980 to 2020

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia

[[ABSTRACT]]
This study presents an unexpected correlation between the votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team calculated a correlation coefficient of 0.9287825, with a p-value less than 0.01. Despite the geographical and cultural disparities between New York and Somalia, our findings suggest a surprising linkage between the political inclinations of New Yorkers and the petrol preferences of Somalians. The pun-intended "gas-tacular" relationship uncovered by our research sheds light on the interconnectedness of global politics and energy consumption. This correlation may seem as unlikely as finding a snowstorm in the Sahara, but the data speaks for itself in this quirky intersection of geopolitics and energy trends.

[[INTRODUCTION]]
INTRODUCTION
The intersection of politics and energy consumption has often been a source of heated debates, but few could have predicted the surprising relationship uncovered in this study. The correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia has left many scratching their heads and wondering if they missed the turn at the intersection of geopolitics and energy trends.
This study may have begun as a mere curiosity, an off-hand remark about the possibility of a connection between the political leanings of New Yorkers and the petrol preferences of Somalians, but the data spoke volumes – not quite as loud as a revving engine, but close. As unlikely as finding a snowstorm in the Sahara, the correlation coefficient of 0.9287825 has us asking, “What in the world?”
While it's common to hear about oil influencing international relations, who would have thought that it might also influence political inclinations across an ocean? It seems oil has been hiding some political aspirations under its slippery surface, fueling the political spectrum in ways we never expected. We may need some gasoline to fuel these theories.
Our study delves into the data from 1980 to 2020 to unravel this puzzling connection, utilizing the reputable MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration. We didn't expect to find ourselves comparing the illuminated Statue of Liberty with the desert expanse of Somalia, but here we are, discussing petrol and politics with a straight face – well, mostly straight-faced.
Whether you find this correlation to be as bewildering as a politician without a prepared speech or as clear as day, the “gas-tacular” connection we've unearthed serves as a reminder that in the world of research, even the most unexpected findings can sometimes be the most enlightening. So, join us as we navigate this unexpected detour on the road of scholarly inquiry and attempt to unpack this political-petroleum enigma. Let's hope we don't run out of fuel before we reach our conclusion.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

METHODOLOGY

To uncover the peculiar connection between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia, our research team employed a range of data collection and analysis methods. We utilized data from 1980 to 2020 sourced from reputable databases, including the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration.

Given the inherently unusual nature of our research question, we had to get creative with our data collection methods. In a nod to the diverse and eclectic nature of our investigation, we scoured the depths of the internet, conducting searches across multiple platforms and dusting off long-forgotten data repositories. It was as if we were navigating a treasure map with a big X that read "Demographics and Petroleum" in New York and Somalia.

Our approach to analyzing the data involved some unconventional techniques as well. We may or may not have consulted a Magic 8-Ball for guidance, but the majority of our analysis was far more conventional. We calculated a correlation coefficient using advanced statistical methods that, on occasion, had us feeling like mathematical wizards. Our calculations spanned multiple spreadsheets and featured more formulas than a chemist's lab, all in pursuit of truth and, in this case, some unexpected correlations.

Additionally, in the spirit of total transparency, we want to acknowledge that our research involved more double-takes and head-scratching moments than we had initially anticipated. The juxtaposition of electoral data from the hustle and bustle of New York with petroleum consumption figures from the sunbaked expanse of Somalia certainly raised a few eyebrows, but also led to some unexpected "Eureka!" moments.

This novel research quest also required us to embrace the unconventional while maintaining methodological rigor. It was a bit like trying to juggle apples and oranges – quite the balancing act, but in the end, it made for a refreshing and unexpected finale.

In summary, our approach to unraveling the enigmatic correlation between Republican votes in New York and petroleum consumption in Somalia was, in a word, adventurous. We emerged with findings that left us both elated and a tad bewildered, realizing that sometimes it's worth venturing into the unknown to uncover the unexpected.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in New York and Petroluem consumption in Somalia. 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 .

For the time period 1980 to 2020, you found a correlation 0.9287825, r-squared of 0.8626369, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia

[[ABSTRACT]]
This study presents an unexpected correlation between the votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team calculated a correlation coefficient of 0.9287825, with a p-value less than 0.01. Despite the geographical and cultural disparities between New York and Somalia, our findings suggest a surprising linkage between the political inclinations of New Yorkers and the petrol preferences of Somalians. The pun-intended "gas-tacular" relationship uncovered by our research sheds light on the interconnectedness of global politics and energy consumption. This correlation may seem as unlikely as finding a snowstorm in the Sahara, but the data speaks for itself in this quirky intersection of geopolitics and energy trends.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The intersection of politics and energy consumption has often been a source of heated debates, but few could have predicted the surprising relationship uncovered in this study. The correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia has left many scratching their heads and wondering if they missed the turn at the intersection of geopolitics and energy trends.
This study may have begun as a mere curiosity, an off-hand remark about the possibility of a connection between the political leanings of New Yorkers and the petrol preferences of Somalians, but the data spoke volumes – not quite as loud as a revving engine, but close. As unlikely as finding a snowstorm in the Sahara, the correlation coefficient of 0.9287825 has us asking, “What in the world?”
While it's common to hear about oil influencing international relations, who would have thought that it might also influence political inclinations across an ocean? It seems oil has been hiding some political aspirations under its slippery surface, fueling the political spectrum in ways we never expected. We may need some gasoline to fuel these theories.
Our study delves into the data from 1980 to 2020 to unravel this puzzling connection, utilizing the reputable MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration. We didn't expect to find ourselves comparing the illuminated Statue of Liberty with the desert expanse of Somalia, but here we are, discussing petrol and politics with a straight face – well, mostly straight-faced.
Whether you find this correlation to be as bewildering as a politician without a prepared speech or as clear as day, the “gas-tacular” connection we've unearthed serves as a reminder that in the world of research, even the most unexpected findings can sometimes be the most enlightening. So, join us as we navigate this unexpected detour on the road of scholarly inquiry and attempt to unpack this political-petroleum enigma. Let's hope we don't run out of fuel before we reach our conclusion.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The data analysis revealed a remarkably strong correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. The correlation coefficient of 0.9287825 and an r-squared value of 0.8626369 pointed to a robust relationship, capturing the attention of our research team like a shiny, well-maintained sports car at a car show. Certainly an unexpected pit stop on the road of academic inquiry.

Fig. 1 displays a scatterplot illustrating the direct relationship between the two variables. The points on the graph align as smoothly as gears in a well-oiled machine, highlighting the coherence between the seemingly unrelated entities. It's not every day that one gets to witness such an intriguing tandem between political voting patterns and petroleum consumption, but time and time again, the data demonstrated a close-knit association that wouldn't loosen its grip.

The p-value less than 0.01 left little room for doubt, signaling a statistically significant connection akin to a bright red stop sign at the intersection of politics and energy consumption. The strength of the association left us gazing at the results as if we stumbled upon a treasure map in the unlikeliest of places.

This gas-tacular relationship challenges conventional wisdom and offers a peculiar lens through which to view the global intricacies of politics and energy. The unexpected connection may be as surprising as finding a clown at an oil refinery, but it serves as a reminder that scholarly inquiry can uncover the most unexpected and thought-provoking insights.

In conclusion, these findings add a curious twist to the tapestry of global political and energy dynamics, leaving our research team with more questions than answers, much like a riddle that begs to be solved. We invite fellow scholars and inquisitive minds to join us in unwrapping this enigmatic correlation, as we shift gears and navigate the uncharted territory at the crossroads of Republican votes in New York and petroleum consumption in Somalia.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in New York and Petroluem consumption in Somalia. 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]]
Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia

[[ABSTRACT]]
This study presents an unexpected correlation between the votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team calculated a correlation coefficient of 0.9287825, with a p-value less than 0.01. Despite the geographical and cultural disparities between New York and Somalia, our findings suggest a surprising linkage between the political inclinations of New Yorkers and the petrol preferences of Somalians. The pun-intended "gas-tacular" relationship uncovered by our research sheds light on the interconnectedness of global politics and energy consumption. This correlation may seem as unlikely as finding a snowstorm in the Sahara, but the data speaks for itself in this quirky intersection of geopolitics and energy trends.

[[LITERATURE REVIEW]]
The intersection of politics and energy consumption has indeed been an area of growing interest in the academic world. Smith et al. (2015) found a fascinating correlation between voting behaviors and regional energy consumption in their study, "Political Pumps and Ballot Boxes." Their analysis of state-level voting patterns and petroleum usage hinted at a nuanced relationship between political events and energy trends. However, little did they know that their findings would pale in comparison to the gas-tacular saga we are about to unravel.
Turning to the social and cultural aspects of energy consumption, Doe and Jones (2018) delved into the societal implications of petroleum usage in their work, "Oil and Society: An Interdisciplinary Analysis." Their exploration of the nuanced connections between oil, culture, and politics shed light on the often uncharted territories of energy's influence on human behaviors and societal structures. Little did they know that our study would take this exploration to a whole new level, revealing a connection as unexpected as finding a penguin in the Sahara.
As we dig deeper into the intersection of politics and energy, one cannot overlook the influence of popular non-fiction works such as "The Prize: The Epic Quest for Oil, Money, and Power" by Daniel Yergin and "Private Empire: ExxonMobil and American Power" by Steve Coll. These insightful works highlight the complex dynamics of energy politics, showcasing the intricate web of interests, power struggles, and global dynamics that revolve around oil. Little did they anticipate that a comparison between New York votes and Somali petroleum consumption would be on par with a subplot from a science fiction novel.
Speaking of which, the fictional world has also dabbled in the realms of energy and politics with works like "The Handmaid's Fuel" by Margaret Atwood and "A Dance with Gasoline" by George R.R. Martin. These fictional narratives, while purely speculative, offer an intriguing parallel to our unexpected findings, portraying worlds where energy sources shape political landscapes in ways that are as mind-bending as a political debate between a unicorn and a centaur.
Moreover, our research draws inspiration from cinematic tales such as "There Will Be Fuel," where oil prospecting and political maneuvering collide in a dramatic narrative. The storyline takes unexpected turns, much like our own study's findings, emphasizing how energy and politics can intertwine in ways as unpredictable as a summer hailstorm.
In the following sections, we delve into the uncharted territory of the seemingly unrelated yet strangely intertwined realms of New York votes and Somali petrol consumption. Our findings are as surprising as finding a clownfish driving a car – a delightful twist in the narrative of energy and politics.


[[RESULTS]]
The data analysis revealed a remarkably strong correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. The correlation coefficient of 0.9287825 and an r-squared value of 0.8626369 pointed to a robust relationship, capturing the attention of our research team like a shiny, well-maintained sports car at a car show. Certainly an unexpected pit stop on the road of academic inquiry.
Fig. 1 displays a scatterplot illustrating the direct relationship between the two variables. The points on the graph align as smoothly as gears in a well-oiled machine, highlighting the coherence between the seemingly unrelated entities. It's not every day that one gets to witness such an intriguing tandem between political voting patterns and petroleum consumption, but time and time again, the data demonstrated a close-knit association that wouldn't loosen its grip.
The p-value less than 0.01 left little room for doubt, signaling a statistically significant connection akin to a bright red stop sign at the intersection of politics and energy consumption. The strength of the association left us gazing at the results as if we stumbled upon a treasure map in the unlikeliest of places.
This gas-tacular relationship challenges conventional wisdom and offers a peculiar lens through which to view the global intricacies of politics and energy. The unexpected connection may be as surprising as finding a clown at an oil refinery, but it serves as a reminder that scholarly inquiry can uncover the most unexpected and thought-provoking insights.
In conclusion, these findings add a curious twist to the tapestry of global political and energy dynamics, leaving our research team with more questions than answers, much like a riddle that begs to be solved. We invite fellow scholars and inquisitive minds to join us in unwrapping this enigmatic correlation, as we shift gears and navigate the uncharted territory at the crossroads of Republican votes in New York and petroleum consumption in Somalia.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

The gas-tacular saga we've uncovered in this study brings to light a fascinating yet unexpected connection between Republican votes in New York and petroleum consumption in Somalia. It's as surprising as finding a soap opera in a car engine – an unlikely fusion that keeps audiences engrossed.

Our findings not only supported but also surpassed the nuances uncovered by Smith et al. (2015) in their exploration of political pumps and ballot boxes. The robust correlation coefficient we calculated echoed their hints at a nuanced relationship, but our results brought the connection to the forefront, shining as bright as a newly polished diamond in an oil field. This unexpected revelation is a testament to the uncharted territories within the realm of energy's influence on political events, offering a perspective as captivating as a thriller set in a gas station.

Furthermore, our study takes the exploration of energy's societal implications to a whole new level, building upon the work of Doe and Jones (2018). Much like our surprising findings, their work peeled back the layers of the complex connections between oil, culture, and politics. Little did they know that our study would unveil a connection as unexpected as finding a penguin in the Sahara, solidifying the notion that the unexpected can lead to profound scholarly breakthroughs.

The insights from popular non-fiction works such as "The Prize: The Epic Quest for Oil, Money, and Power" by Daniel Yergin and "Private Empire: ExxonMobil and American Power" by Steve Coll have laid the groundwork for understanding the intricate web of interests and global dynamics involving oil. Our study's unexpected comparison between New York votes and Somali petroleum consumption showcases a narrative as captivating as a subplot from a science fiction novel. It's a reminder that even the most unexpected data can unveil unforeseen connections, much like stumbling upon a unicorn amidst a herd of wild buffalo.

These findings challenge conventional wisdom and offer a peculiar lens through which to view the global intricacies of politics and energy. This gas-tacular relationship is as quirky as finding a clownfish driving a car but is a reminder that scholarly inquiry can uncover the most unexpected and thought-provoking insights. Our findings further exemplify the unpredictability of scholarly inquiry, urging us to delve deeper into the riddle waiting for us at the crossroads of Republican votes in New York and petroleum consumption in Somalia.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in New York and Petroluem consumption in Somalia. 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]]
Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia

[[ABSTRACT]]
This study presents an unexpected correlation between the votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team calculated a correlation coefficient of 0.9287825, with a p-value less than 0.01. Despite the geographical and cultural disparities between New York and Somalia, our findings suggest a surprising linkage between the political inclinations of New Yorkers and the petrol preferences of Somalians. The pun-intended "gas-tacular" relationship uncovered by our research sheds light on the interconnectedness of global politics and energy consumption. This correlation may seem as unlikely as finding a snowstorm in the Sahara, but the data speaks for itself in this quirky intersection of geopolitics and energy trends.

[[INTRDUCTION]]
INTRODUCTION
The intersection of politics and energy consumption has often been a source of heated debates, but few could have predicted the surprising relationship uncovered in this study. The correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia has left many scratching their heads and wondering if they missed the turn at the intersection of geopolitics and energy trends.
This study may have begun as a mere curiosity, an off-hand remark about the possibility of a connection between the political leanings of New Yorkers and the petrol preferences of Somalians, but the data spoke volumes – not quite as loud as a revving engine, but close. As unlikely as finding a snowstorm in the Sahara, the correlation coefficient of 0.9287825 has us asking, “What in the world?”
While it's common to hear about oil influencing international relations, who would have thought that it might also influence political inclinations across an ocean? It seems oil has been hiding some political aspirations under its slippery surface, fueling the political spectrum in ways we never expected. We may need some gasoline to fuel these theories.
Our study delves into the data from 1980 to 2020 to unravel this puzzling connection, utilizing the reputable MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration. We didn't expect to find ourselves comparing the illuminated Statue of Liberty with the desert expanse of Somalia, but here we are, discussing petrol and politics with a straight face – well, mostly straight-faced.
Whether you find this correlation to be as bewildering as a politician without a prepared speech or as clear as day, the “gas-tacular” connection we've unearthed serves as a reminder that in the world of research, even the most unexpected findings can sometimes be the most enlightening. So, join us as we navigate this unexpected detour on the road of scholarly inquiry and attempt to unpack this political-petroleum enigma. Let's hope we don't run out of fuel before we reach our conclusion.

[[RESULTS]]
The data analysis revealed a remarkably strong correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. The correlation coefficient of 0.9287825 and an r-squared value of 0.8626369 pointed to a robust relationship, capturing the attention of our research team like a shiny, well-maintained sports car at a car show. Certainly an unexpected pit stop on the road of academic inquiry.
Fig. 1 displays a scatterplot illustrating the direct relationship between the two variables. The points on the graph align as smoothly as gears in a well-oiled machine, highlighting the coherence between the seemingly unrelated entities. It's not every day that one gets to witness such an intriguing tandem between political voting patterns and petroleum consumption, but time and time again, the data demonstrated a close-knit association that wouldn't loosen its grip.
The p-value less than 0.01 left little room for doubt, signaling a statistically significant connection akin to a bright red stop sign at the intersection of politics and energy consumption. The strength of the association left us gazing at the results as if we stumbled upon a treasure map in the unlikeliest of places.
This gas-tacular relationship challenges conventional wisdom and offers a peculiar lens through which to view the global intricacies of politics and energy. The unexpected connection may be as surprising as finding a clown at an oil refinery, but it serves as a reminder that scholarly inquiry can uncover the most unexpected and thought-provoking insights.
In conclusion, these findings add a curious twist to the tapestry of global political and energy dynamics, leaving our research team with more questions than answers, much like a riddle that begs to be solved. We invite fellow scholars and inquisitive minds to join us in unwrapping this enigmatic correlation, as we shift gears and navigate the uncharted territory at the crossroads of Republican votes in New York and petroleum consumption in Somalia.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

As we come to a screeching halt at the end of this gas-tacular journey, our findings have left us in a bit of a conundrum. The unexpected correlation between votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020 has sparked more puzzlement than a Rubik's Cube in a room full of philosophers.

The robust correlation coefficient and eyebrow-raising r-squared value have us contemplating the geopolitics of petrol with the fervor of a tireless car enthusiast. The statistical significance of this connection is akin to stumbling upon a diamond in the rough of academic research – or perhaps, a pristine vintage car in a junkyard of data.

While it may seem as improbable as finding a polar bear in a desert, our study undeniably underscores the entwined nature of global political inclinations and energy consumption. It's like discovering a hidden compartment in a vehicle that makes you question everything you thought you knew about its design.

In the realm of scholarly inquiries, this unexpected correlation serves as a beacon of curiosity, beckoning us to explore the uncharted terrain and unravel the mysteries of these seemingly disparate entities. We have hit the brakes, opened the hood, and taken a long, hard look at this odd pairing, but the journey has left us with more questions than answers – somewhat like searching for a specific car in a packed parking lot.

In the grand scheme of academic research, these findings hold their own in the realm of unexpected discoveries, much like stumbling upon a pearl in an oyster that you never intended to open.

But as much as we've enjoyed this wild ride, we dare say, in the spirit of academic zaniness and scholarly whimsy, that further research in this area is like trying to reinvent the wheel – unnecessary. This peculiar correlation, gas-tacular as it may be, has already revved its engine in the annals of quirky scholarly inquiries.

Let's park this peculiar study in the lot of academic oddities and bid adieu to the unusual intersection of Republican votes in New York and petroleum consumption in Somalia, a journey we won't soon forget.


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Energized Politics


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Eclectic Political Analysis and Petroleum Research


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Fueling the Political Spectrum: A Gas-tacular Comparison of Republican Votes in New York and Petroleum Consumption in Somalia with an abstract of This study presents an unexpected correlation between the votes for the Republican presidential candidate in New York and petroleum consumption in Somalia from 1980 to 2020. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team calculated a correlation coefficient of 0.9287825, with a p-value less than 0.01. Despite the geographical and cultural disparities between New York and Somalia, our findings suggest a surprising linkage between the political inclinations of New Yorkers and the petrol preferences of Somalians. The pun-intended "gas-tacular" relationship uncovered by our research sheds light on the interconnectedness of global politics and energy consumption. This correlation may seem as unlikely as finding a snowstorm in the Sahara, but the data speaks for itself in this quirky intersection of geopolitics and energy trends.

ChatGPT:

Republican votes New York, petroleum consumption Somalia, political correlation, New York presidential candidate votes, petroleum consumption 1980-2020, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, political inclinations New Yorkers, petrol preferences Somalians, global politics energy consumption, geopolitical correlation energy trends

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

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

Correlation r = 0.9287825 (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 = 0.8626369 (Coefficient of determination)
This means 86.3% of the change in the one variable (i.e., Petroluem consumption in Somalia) is predictable based on the change in the other (i.e., Votes for the Republican Presidential candidate in New York) over the 11 years from 1980 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.6E-5. 0.0000362385426685066150000000
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 0.93 in 0.0036% of random cases. Said differently, if you correlated 27,595 random variables You don't actually need 27 thousand variables to find a correlation like this one. You can also correlate variables that are not independent. I do this a lot.

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

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

[ 0.74, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19801984198819921996200020042008201220162020
Votes for the Republican Presidential candidate in New York (Percentage of votes)42.530149.60543.764328.839727.002232.449837.686531.317231.241632.390637.4613
Petroluem consumption in Somalia (Million Barrels/Day)7.99.27.206593.703163.903194.823825.353015.461995.574865.893015.61757




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([42.5301,49.605,43.7643,28.8397,27.0022,32.4498,37.6865,31.3172,31.2416,32.3906,37.4613,])
array_2 = np.array([7.9,9.2,7.20659,3.70316,3.90319,4.82382,5.35301,5.46199,5.57486,5.89301,5.61757,])
array_1_name = "Votes for the Republican Presidential candidate in New York"
array_2_name = "Petroluem consumption in Somalia"

# 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?

Kudos for rating!


Correlation ID: 5454 · Black Variable ID: 26144 · Red Variable ID: 24915
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0