about · email me · subscribe
Spurious correlation #5,158 · 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 Democratic Presidential candidate in North Dakota and the second variable is Petroluem consumption in Czechia.  The chart goes from 1993 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The high-energy debates sparked a surge in political interest, leading North Dakotans to hit the polls in droves. This surge in democratic participation created a literal power struggle, as the increased voter turnout indirectly revved up the demand for petroleum in the state. As the saying goes, when it comes to political preference and petrol, it's all about that democratic octane boost for North Dakota. And as the wheels of democracy turned, so did the need for fuel, ultimately leading to a surprising connection between the US election and Czechia's petroleum consumption.

Model: dalle-3
Prompt: Generate an image of a futuristic cityscape in North Dakota, with sleek, electric-powered vehicles weaving through the streets, juxtaposed against towering, high-tech fuel stations surrounded by lines of voters waiting to cast their ballots. The scene should exude an atmosphere of political fervor and technological advancement, capturing the surprising connection between high voter turnout and increased petroleum consumption. The image should convey the unexpected link between the US election and the demand for petroleum in an innovative and thought-provoking manner. 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 Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia. 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: Concept art Parallax art Cubism Futuristic Whimsical illustration
ChatGPT: Futuristic

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 Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia, in the following situation: The high-energy debates sparked a surge in political interest, leading North Dakotans to hit the polls in droves. This surge in democratic participation created a literal power struggle, as the increased voter turnout indirectly revved up the demand for petroleum in the state. As the saying goes, when it comes to political preference and petrol, it's all about that democratic octane boost for North Dakota. And as the wheels of democracy turned, so did the need for fuel, ultimately leading to a surprising connection between the US election and Czechia's petroleum consumption.. Keep the description simple.
ChatGPT: In North Dakota, long lines of voters snake through the streets as people eagerly cast their ballots for the Democratic presidential candidate. The surge of political participation creates a buzz of excitement, almost palpable in the air. As the democratic fervor grows, the demand for petroleum in the state peaks, with more cars filling up at gas stations. The correlation between the high voter turnout and increased petrol consumption becomes a surprising outcome, highlighting the unexpected connection between the US election and Czechia's petroleum usage.

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: [ Futuristic ] and depicting this scene: In North Dakota, long lines of voters snake through the streets as people eagerly cast their ballots for the Democratic presidential candidate. The surge of political participation creates a buzz of excitement, almost palpable in the air. As the democratic fervor grows, the demand for petroleum in the state peaks, with more cars filling up at gas stations. The correlation between the high voter turnout and increased petrol consumption becomes a surprising outcome, highlighting the unexpected connection between the US election and Czechia's petroleum usage. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a futuristic cityscape in North Dakota, with sleek, electric-powered vehicles weaving through the streets, juxtaposed against towering, high-tech fuel stations surrounded by lines of voters waiting to cast their ballots. The scene should exude an atmosphere of political fervor and technological advancement, capturing the surprising connection between high voter turnout and increased petroleum consumption. The image should convey the unexpected link between the US election and the demand for petroleum in an innovative and thought-provoking manner.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Votes for the Democrat Presidential candidate in North Dakota positively influenced Petroluem consumption in Czechia.\Make it sound serious until the end.

AI academic paper

(Because p < 0.05)
Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia

The International Journal of Geopolitical Energy Dynamics

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 witty academic researcher. Your writing sounds like it belongs in a statistics 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 Votes for the Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia. Make lots of jokes, goofy observations, and puns.

Include a pun 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 0.8287283 and p < 0.05 for 1993 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]]
"Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia"

[[ABSTRACT]]
In this study, we examined the intriguing relationship between voting preferences in North Dakota for the Democrat presidential candidate and petroleum consumption in Czechia. Our research team delved deep into the data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this enigmatic connection. Employing rigorous statistical analyses, we arrived at a correlation coefficient of 0.8287283, with a p-value less than 0.05 for the period spanning 1993 to 2020. Our findings provide a humorous and unexpected twist to the conventional wisdom, proving that even in the realm of electoral and energy matters, there can be humorous correlations that leave one pondering the comic potential of statistical quirks. Our results, while entertaining, also serve as a reminder to approach correlations with caution and skepticism, lest we fall prey to the perils of spurious relationships.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Votes for the Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia. 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]]
"Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia"

[[ABSTRACT]]
In this study, we examined the intriguing relationship between voting preferences in North Dakota for the Democrat presidential candidate and petroleum consumption in Czechia. Our research team delved deep into the data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this enigmatic connection. Employing rigorous statistical analyses, we arrived at a correlation coefficient of 0.8287283, with a p-value less than 0.05 for the period spanning 1993 to 2020. Our findings provide a humorous and unexpected twist to the conventional wisdom, proving that even in the realm of electoral and energy matters, there can be humorous correlations that leave one pondering the comic potential of statistical quirks. Our results, while entertaining, also serve as a reminder to approach correlations with caution and skepticism, lest we fall prey to the perils of spurious relationships.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of politics and petroleum has long been a subject of fascination and contention. However, it is rarely conceived that the quixotic polling preferences of voters in North Dakota could hold any sway over the gaseous predilections of citizens in Czechia. Yet, such is the intriguing puzzle on which this study is premised. Like a gusher of statistical curiosity, our research aims to shed light on the unexpected and, dare we say, whimsical relationship between the votive leanings of North Dakotans and the fuel appetite of Czechians.

The conventional wisdom tells us that political decisions are often influenced by considerations of socioeconomic status, education, or regional factors. Meanwhile, energy consumption patterns are typically driven by economic indicators, climate conditions, and cultural proclivities. Linking the two might seem as improbable as finding a vegan at a ribfest, but as our research unfolds, the surprising correlations we uncover will prompt one to ponder the seemingly implausible comedic potential of statistical quirks.

This study is particularly pertinent in the current era, where political discussions and debates over energy policy dominate the public discourse. The empirical evidence presented here not only tickles the intellect with its unexpected connection but also serves as a cautionary tale about the perils of drawing causal inferences from mere correlations. It is with a twinkle in our eye and a data-driven rigor in our approach that we unveil the peculiar and, we dare say, amusing relationship between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Let the analysis commence, and may the statistical mirth commence!


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia. 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 a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
"Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia"

[[ABSTRACT]]
In this study, we examined the intriguing relationship between voting preferences in North Dakota for the Democrat presidential candidate and petroleum consumption in Czechia. Our research team delved deep into the data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this enigmatic connection. Employing rigorous statistical analyses, we arrived at a correlation coefficient of 0.8287283, with a p-value less than 0.05 for the period spanning 1993 to 2020. Our findings provide a humorous and unexpected twist to the conventional wisdom, proving that even in the realm of electoral and energy matters, there can be humorous correlations that leave one pondering the comic potential of statistical quirks. Our results, while entertaining, also serve as a reminder to approach correlations with caution and skepticism, lest we fall prey to the perils of spurious relationships.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of politics and petroleum has long been a subject of fascination and contention. However, it is rarely conceived that the quixotic polling preferences of voters in North Dakota could hold any sway over the gaseous predilections of citizens in Czechia. Yet, such is the intriguing puzzle on which this study is premised. Like a gusher of statistical curiosity, our research aims to shed light on the unexpected and, dare we say, whimsical relationship between the votive leanings of North Dakotans and the fuel appetite of Czechians.
The conventional wisdom tells us that political decisions are often influenced by considerations of socioeconomic status, education, or regional factors. Meanwhile, energy consumption patterns are typically driven by economic indicators, climate conditions, and cultural proclivities. Linking the two might seem as improbable as finding a vegan at a ribfest, but as our research unfolds, the surprising correlations we uncover will prompt one to ponder the seemingly implausible comedic potential of statistical quirks.
This study is particularly pertinent in the current era, where political discussions and debates over energy policy dominate the public discourse. The empirical evidence presented here not only tickles the intellect with its unexpected connection but also serves as a cautionary tale about the perils of drawing causal inferences from mere correlations. It is with a twinkle in our eye and a data-driven rigor in our approach that we unveil the peculiar and, we dare say, amusing relationship between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Let the analysis commence, and may the statistical mirth commence!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al." (2015), the authors find a groundbreaking association between the votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Their study lays the groundwork for our investigation into this whimsical yet compelling correlation. Similarly, Doe and Jones (2017) expound upon the intricate interplay of political inclinations in North Dakota and energy habits in Czechia, setting the stage for our light-hearted foray into the statistical realm of unconventional relationships.

Building upon these foundational works, we venture into the world of non-fiction literature related to our topic. "The Petroleum Industry and Czech Politics" (Brown, 2018) offers valuable insights into the socio-political landscape of Czechia, although it regrettably fails to uncover the comical dimensions of petroleum consumption. Meanwhile, "Elections and Energy: A Comparative Analysis" (Miller, 2019) provides a sober assessment of the electoral dynamics in North Dakota and energy trends in Czechia but overlooks the opportunity to infuse statistical analysis with a dash of comedic revelation.

Turning our attention to the realm of fiction, "Crude Intentions" (Black, 2020) presents an enthralling narrative of political intrigue and energy machinations, although its relevance to our statistical exploration remains tenuous at best. Similarly, "The Petrol Plot" (White, 2016) weaves a captivating tale of electoral shenanigans and surreptitious petroleum dealings, offering a delightful diversion from the seriousness of our research pursuits.

In our quest for inspiration, we also ventured into the realm of popular culture, conducting in-depth analysis of television shows with potential relevance to our subject matter. "Fossil Fuels and Political Fiascos" sheds light on the interplay between energy politics and electoral maneuvering, providing a satirical take on the confluence of voting behavior and petroleum preferences. Furthermore, "Democracy and Diesel" presents a compelling narrative of political drama and fuel-related escapades, serving as a lighthearted source of anecdotal evidence for our research endeavors.

As we immerse ourselves in the scholarly discourse and explore the amusing dimensions of political and energy correlations, we seek to unravel the peculiar bond between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Our inquiry promises not only to entertain but also to provoke contemplation on the whimsical potential of statistical relationships.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia. 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 1993 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]]
"Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia"

[[ABSTRACT]]
In this study, we examined the intriguing relationship between voting preferences in North Dakota for the Democrat presidential candidate and petroleum consumption in Czechia. Our research team delved deep into the data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this enigmatic connection. Employing rigorous statistical analyses, we arrived at a correlation coefficient of 0.8287283, with a p-value less than 0.05 for the period spanning 1993 to 2020. Our findings provide a humorous and unexpected twist to the conventional wisdom, proving that even in the realm of electoral and energy matters, there can be humorous correlations that leave one pondering the comic potential of statistical quirks. Our results, while entertaining, also serve as a reminder to approach correlations with caution and skepticism, lest we fall prey to the perils of spurious relationships.

[[INTRODUCTION]]
The intersection of politics and petroleum has long been a subject of fascination and contention. However, it is rarely conceived that the quixotic polling preferences of voters in North Dakota could hold any sway over the gaseous predilections of citizens in Czechia. Yet, such is the intriguing puzzle on which this study is premised. Like a gusher of statistical curiosity, our research aims to shed light on the unexpected and, dare we say, whimsical relationship between the votive leanings of North Dakotans and the fuel appetite of Czechians.
The conventional wisdom tells us that political decisions are often influenced by considerations of socioeconomic status, education, or regional factors. Meanwhile, energy consumption patterns are typically driven by economic indicators, climate conditions, and cultural proclivities. Linking the two might seem as improbable as finding a vegan at a ribfest, but as our research unfolds, the surprising correlations we uncover will prompt one to ponder the seemingly implausible comedic potential of statistical quirks.
This study is particularly pertinent in the current era, where political discussions and debates over energy policy dominate the public discourse. The empirical evidence presented here not only tickles the intellect with its unexpected connection but also serves as a cautionary tale about the perils of drawing causal inferences from mere correlations. It is with a twinkle in our eye and a data-driven rigor in our approach that we unveil the peculiar and, we dare say, amusing relationship between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Let the analysis commence, and may the statistical mirth commence!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Our research embarked on a whimsical journey into the realm of statistical inquiry, aiming to unravel the improbable relationship between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. The methodology we employed harnessed the power of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, capturing the years from 1993 to 2020.

To undertake this audacious task, we first gathered voting data from North Dakota, meticulously sifting through the electoral records with the fervor of a prospector seeking a gold nugget in the political landscape. With an ardent commitment to accuracy, we collated the number of votes cast for the Democrat presidential candidate in each election cycle, ensuring that no ballot was left uncounted.

Simultaneously, our intrepid expedition led us to the Czech Republic, where we eagerly scavenged data on petroleum consumption. We stared at barrels, liters, and kilometers of pipes with the intensity of a detective solving a mystery. We meticulously collected information on the consumption of petroleum products, including the merrily guzzled gasoline and the industriously consumed diesel, per capita over the study period.

Once we had amassed this peculiar assortment of data, we employed a bewildering array of mathematical tools and statistical techniques to illuminate the ostensibly bizarre connection between these disparate variables. Through rigorous regression analyses, we endeavored to disentangle the enigmatic web of correlation between the voting habits of citizens in North Dakota and the petroleum proclivities of our Czechian counterparts.

Our statistical journey was not without its treacherous twists and turns, but with steely resolve and a healthy dose of lightheartedness, we arrived at a correlation coefficient of 0.8287283, accompanied by a p-value that gleefully persisted below the esteemed threshold of 0.05. These findings, while seemingly impish in their nature, hinted at a link between the electoral choices of North Dakotans and the consumption of petroleum in Czechia that left us pleasantly befuddled.

In closing, our methodology, like any good vaudeville act, combined the serious precision of statistical analysis with a sprinkle of levity, providing a mirthful journey through the curious correlations that dot the landscape of social and economic phenomena.

Stay tuned for the uproarious unveiling of our findings in the subsequent sections, where we shall unravel the comedic conundrum of this improbable connection.

"Analyzing data is serious work, but that doesn't mean we can't have a bit of statistical fun along the way!"


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Votes for the Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia. 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 1993 to 2020, you found a correlation 0.8287283, r-squared of 0.6867906, and p < 0.05.

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]]
"Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia"

[[ABSTRACT]]
In this study, we examined the intriguing relationship between voting preferences in North Dakota for the Democrat presidential candidate and petroleum consumption in Czechia. Our research team delved deep into the data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this enigmatic connection. Employing rigorous statistical analyses, we arrived at a correlation coefficient of 0.8287283, with a p-value less than 0.05 for the period spanning 1993 to 2020. Our findings provide a humorous and unexpected twist to the conventional wisdom, proving that even in the realm of electoral and energy matters, there can be humorous correlations that leave one pondering the comic potential of statistical quirks. Our results, while entertaining, also serve as a reminder to approach correlations with caution and skepticism, lest we fall prey to the perils of spurious relationships.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of politics and petroleum has long been a subject of fascination and contention. However, it is rarely conceived that the quixotic polling preferences of voters in North Dakota could hold any sway over the gaseous predilections of citizens in Czechia. Yet, such is the intriguing puzzle on which this study is premised. Like a gusher of statistical curiosity, our research aims to shed light on the unexpected and, dare we say, whimsical relationship between the votive leanings of North Dakotans and the fuel appetite of Czechians.
The conventional wisdom tells us that political decisions are often influenced by considerations of socioeconomic status, education, or regional factors. Meanwhile, energy consumption patterns are typically driven by economic indicators, climate conditions, and cultural proclivities. Linking the two might seem as improbable as finding a vegan at a ribfest, but as our research unfolds, the surprising correlations we uncover will prompt one to ponder the seemingly implausible comedic potential of statistical quirks.
This study is particularly pertinent in the current era, where political discussions and debates over energy policy dominate the public discourse. The empirical evidence presented here not only tickles the intellect with its unexpected connection but also serves as a cautionary tale about the perils of drawing causal inferences from mere correlations. It is with a twinkle in our eye and a data-driven rigor in our approach that we unveil the peculiar and, we dare say, amusing relationship between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Let the analysis commence, and may the statistical mirth commence!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data spanning from 1993 to 2020 revealed a surprisingly strong correlation of 0.8287283 between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. This correlation was found to be statistically significant, with a p-value less than 0.05, indicating that the relationship between these two seemingly unrelated variables is highly unlikely to have occurred by random chance.

Furthermore, the coefficient of determination (r-squared) was calculated to be 0.6867906, suggesting that approximately 68.7% of the variability in petroleum consumption in Czechia can be explained by the voting preferences of North Dakotans for the Democrat presidential candidate. This high r-squared value reinforces the robustness of the correlation and implies a substantial level of predictability in the petroleum consumption patterns based on the political inclinations of voters in North Dakota.

The strength of the relationship is visually depicted in Figure 1, which illustrates a strikingly clear positive linear association between the percentage of votes for the Democrat presidential candidate in North Dakota and the volume of petroleum consumption in Czechia. The scatterplot portrays a tight clustering of data points along the upward trendline, emphasizing the coherence of the relationship and dispelling any notions of randomness.

Overall, these findings not only challenge conventional wisdom but also inject a dose of statistical humor into the often stern and serious domain of research. The unexpected correlation between the political landscape in North Dakota and the energy preferences in Czechia serves as a reminder of the whimsical and unpredictable nature of statistical analyses. As we delve into the depths of data, we must maintain a keen awareness of the potential for amusing relationships to emerge and the necessity of approaching correlations with caution and critical scrutiny.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia. 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]]
"Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia"

[[ABSTRACT]]
In this study, we examined the intriguing relationship between voting preferences in North Dakota for the Democrat presidential candidate and petroleum consumption in Czechia. Our research team delved deep into the data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this enigmatic connection. Employing rigorous statistical analyses, we arrived at a correlation coefficient of 0.8287283, with a p-value less than 0.05 for the period spanning 1993 to 2020. Our findings provide a humorous and unexpected twist to the conventional wisdom, proving that even in the realm of electoral and energy matters, there can be humorous correlations that leave one pondering the comic potential of statistical quirks. Our results, while entertaining, also serve as a reminder to approach correlations with caution and skepticism, lest we fall prey to the perils of spurious relationships.

[[LITERATURE REVIEW]]
In "Smith et al." (2015), the authors find a groundbreaking association between the votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Their study lays the groundwork for our investigation into this whimsical yet compelling correlation. Similarly, Doe and Jones (2017) expound upon the intricate interplay of political inclinations in North Dakota and energy habits in Czechia, setting the stage for our light-hearted foray into the statistical realm of unconventional relationships.
Building upon these foundational works, we venture into the world of non-fiction literature related to our topic. "The Petroleum Industry and Czech Politics" (Brown, 2018) offers valuable insights into the socio-political landscape of Czechia, although it regrettably fails to uncover the comical dimensions of petroleum consumption. Meanwhile, "Elections and Energy: A Comparative Analysis" (Miller, 2019) provides a sober assessment of the electoral dynamics in North Dakota and energy trends in Czechia but overlooks the opportunity to infuse statistical analysis with a dash of comedic revelation.
Turning our attention to the realm of fiction, "Crude Intentions" (Black, 2020) presents an enthralling narrative of political intrigue and energy machinations, although its relevance to our statistical exploration remains tenuous at best. Similarly, "The Petrol Plot" (White, 2016) weaves a captivating tale of electoral shenanigans and surreptitious petroleum dealings, offering a delightful diversion from the seriousness of our research pursuits.
In our quest for inspiration, we also ventured into the realm of popular culture, conducting in-depth analysis of television shows with potential relevance to our subject matter. "Fossil Fuels and Political Fiascos" sheds light on the interplay between energy politics and electoral maneuvering, providing a satirical take on the confluence of voting behavior and petroleum preferences. Furthermore, "Democracy and Diesel" presents a compelling narrative of political drama and fuel-related escapades, serving as a lighthearted source of anecdotal evidence for our research endeavors.
As we immerse ourselves in the scholarly discourse and explore the amusing dimensions of political and energy correlations, we seek to unravel the peculiar bond between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Our inquiry promises not only to entertain but also to provoke contemplation on the whimsical potential of statistical relationships.

[[RESULTS]]
The analysis of the data spanning from 1993 to 2020 revealed a surprisingly strong correlation of 0.8287283 between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. This correlation was found to be statistically significant, with a p-value less than 0.05, indicating that the relationship between these two seemingly unrelated variables is highly unlikely to have occurred by random chance.
Furthermore, the coefficient of determination (r-squared) was calculated to be 0.6867906, suggesting that approximately 68.7% of the variability in petroleum consumption in Czechia can be explained by the voting preferences of North Dakotans for the Democrat presidential candidate. This high r-squared value reinforces the robustness of the correlation and implies a substantial level of predictability in the petroleum consumption patterns based on the political inclinations of voters in North Dakota.
The strength of the relationship is visually depicted in Figure 1, which illustrates a strikingly clear positive linear association between the percentage of votes for the Democrat presidential candidate in North Dakota and the volume of petroleum consumption in Czechia. The scatterplot portrays a tight clustering of data points along the upward trendline, emphasizing the coherence of the relationship and dispelling any notions of randomness.
Overall, these findings not only challenge conventional wisdom but also inject a dose of statistical humor into the often stern and serious domain of research. The unexpected correlation between the political landscape in North Dakota and the energy preferences in Czechia serves as a reminder of the whimsical and unpredictable nature of statistical analyses. As we delve into the depths of data, we must maintain a keen awareness of the potential for amusing relationships to emerge and the necessity of approaching correlations with caution and critical scrutiny.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our investigation into the correlation between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia has yielded fascinating results that both amuse and astonish. The robust correlation coefficient of 0.8287283, complemented by a statistically significant p-value, echoes the findings of prior research, such as the groundbreaking work of Smith et al. (2015) and the whimsical ramblings of "Fossil Fuels and Political Fiascos." These results not only confirm the unexpected connection between seemingly unrelated variables but also add a delightful twist to the scholarly discourse on statistical relationships.

The high coefficient of determination (r-squared) of 0.6867906 reaffirms the potent predictive power inherent in the relationship between voting preferences in North Dakota and petroleum consumption in Czechia. One might even jest that the electoral whims of North Dakotans exert a considerable influence over the fuel consumption habits of Czechs, shaping the energy landscape in ways previously unimagined. These findings provide ample evidence to support the notion that statistical quirks can indeed be both hilarious and thought-provoking, challenging researchers to acknowledge the comic potential of correlations while remaining steadfast in their pursuit of rigorous analysis.

The visually compelling scatterplot depicted in Figure 1 encapsulates the strikingly clear positive linear association between the variables, leaving no room for doubt regarding the coherence of the relationship. The tightly clustered data points along the upward trendline serve as a visual testament to the intriguing bond between political inclinations in North Dakota and energy preferences in Czechia, underscoring the nontrivial nature of this comical yet meaningful statistical revelation.

While our results bring a lighthearted touch to the often somber realm of research, they also serve as a cautionary reminder of the need for skepticism in interpreting statistical correlations, lest we succumb to the allure of spurious relationships in pursuit of comic relief. This study encourages future researchers to embrace the entertaining potential of statistical analyses, while bearing in mind the necessity of approaching correlations with critical scrutiny and an appreciation for the unexpected humor that may arise from seemingly unrelated phenomena.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in North Dakota and Petroluem consumption in Czechia. 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]]
"Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia"

[[ABSTRACT]]
In this study, we examined the intriguing relationship between voting preferences in North Dakota for the Democrat presidential candidate and petroleum consumption in Czechia. Our research team delved deep into the data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this enigmatic connection. Employing rigorous statistical analyses, we arrived at a correlation coefficient of 0.8287283, with a p-value less than 0.05 for the period spanning 1993 to 2020. Our findings provide a humorous and unexpected twist to the conventional wisdom, proving that even in the realm of electoral and energy matters, there can be humorous correlations that leave one pondering the comic potential of statistical quirks. Our results, while entertaining, also serve as a reminder to approach correlations with caution and skepticism, lest we fall prey to the perils of spurious relationships.

[[INTRDUCTION]]
The intersection of politics and petroleum has long been a subject of fascination and contention. However, it is rarely conceived that the quixotic polling preferences of voters in North Dakota could hold any sway over the gaseous predilections of citizens in Czechia. Yet, such is the intriguing puzzle on which this study is premised. Like a gusher of statistical curiosity, our research aims to shed light on the unexpected and, dare we say, whimsical relationship between the votive leanings of North Dakotans and the fuel appetite of Czechians.
The conventional wisdom tells us that political decisions are often influenced by considerations of socioeconomic status, education, or regional factors. Meanwhile, energy consumption patterns are typically driven by economic indicators, climate conditions, and cultural proclivities. Linking the two might seem as improbable as finding a vegan at a ribfest, but as our research unfolds, the surprising correlations we uncover will prompt one to ponder the seemingly implausible comedic potential of statistical quirks.
This study is particularly pertinent in the current era, where political discussions and debates over energy policy dominate the public discourse. The empirical evidence presented here not only tickles the intellect with its unexpected connection but also serves as a cautionary tale about the perils of drawing causal inferences from mere correlations. It is with a twinkle in our eye and a data-driven rigor in our approach that we unveil the peculiar and, we dare say, amusing relationship between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. Let the analysis commence, and may the statistical mirth commence!

[[RESULTS]]
The analysis of the data spanning from 1993 to 2020 revealed a surprisingly strong correlation of 0.8287283 between votes for the Democrat presidential candidate in North Dakota and petroleum consumption in Czechia. This correlation was found to be statistically significant, with a p-value less than 0.05, indicating that the relationship between these two seemingly unrelated variables is highly unlikely to have occurred by random chance.
Furthermore, the coefficient of determination (r-squared) was calculated to be 0.6867906, suggesting that approximately 68.7% of the variability in petroleum consumption in Czechia can be explained by the voting preferences of North Dakotans for the Democrat presidential candidate. This high r-squared value reinforces the robustness of the correlation and implies a substantial level of predictability in the petroleum consumption patterns based on the political inclinations of voters in North Dakota.
The strength of the relationship is visually depicted in Figure 1, which illustrates a strikingly clear positive linear association between the percentage of votes for the Democrat presidential candidate in North Dakota and the volume of petroleum consumption in Czechia. The scatterplot portrays a tight clustering of data points along the upward trendline, emphasizing the coherence of the relationship and dispelling any notions of randomness.
Overall, these findings not only challenge conventional wisdom but also inject a dose of statistical humor into the often stern and serious domain of research. The unexpected correlation between the political landscape in North Dakota and the energy preferences in Czechia serves as a reminder of the whimsical and unpredictable nature of statistical analyses. As we delve into the depths of data, we must maintain a keen awareness of the potential for amusing relationships to emerge and the necessity of approaching correlations with caution and critical scrutiny.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unearthed a confounding correlation between Democratic votes in North Dakota and petroleum consumption in Czechia, leaving us scratching our heads in amusement and bemusement simultaneously. While it may seem as unlikely as finding a unicorn in a petting zoo, the statistical relationship we have uncovered is undeniable. The magnitude of the correlation coefficient, with a p-value less than 0.05, leaves us in a statistical stupor, pondering the sheer absurdity of the association.

Our findings not only add a whimsical twist to the nexus of electoral and energy matters but also serve as a gentle reminder that correlation does not imply causation – unless, of course, your ideology is the root of all gasoline consumption evils! The r-squared value of approximately 68.7% further cements the robustness of this inexplicable link, infusing an air of predictability into the enigmatic dance between political preferences in North Dakota and petrol proclivities in Czechia.

In the spirit of statistical quirkiness, we leave no pun unturned in emphasizing that further research in this area may not just be unnecessary - it might be akin to searching for the Loch Ness Monster in a bathtub. Nonetheless, as we bid adieu to this comically perplexing correlation, we remind ourselves to approach statistical relationships with caution and a generous dash of humor, for in the infinite realm of data, truths may be stranger than fiction.


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 Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Geopolitical Energy Dynamics


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Global Energy Studies and Political Analysis


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 Crude Politics: Unconventional Correlations Between Democrat Votes in North Dakota and Petroleum Consumption in Czechia with an abstract of In this study, we examined the intriguing relationship between voting preferences in North Dakota for the Democrat presidential candidate and petroleum consumption in Czechia. Our research team delved deep into the data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to unravel this enigmatic connection. Employing rigorous statistical analyses, we arrived at a correlation coefficient of 0.8287283, with a p-value less than 0.05 for the period spanning 1993 to 2020. Our findings provide a humorous and unexpected twist to the conventional wisdom, proving that even in the realm of electoral and energy matters, there can be humorous correlations that leave one pondering the comic potential of statistical quirks. Our results, while entertaining, also serve as a reminder to approach correlations with caution and skepticism, lest we fall prey to the perils of spurious relationships.

ChatGPT:

Democrat votes North Dakota, petroleum consumption Czechia, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, correlation coefficient, statistical analyses, electoral energy correlation, humorous correlations, spurious relationships

*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 Democratic Presidential candidate in North Dakota
Detailed data title: Total votes cast for the Democrat Presidential candidate in North Dakota
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Democratic Presidential candidate in North Dakota

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

Correlation r = 0.8287283 (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 = 0.6867906 (Coefficient of determination)
This means 68.7% of the change in the one variable (i.e., Petroluem consumption in Czechia) is predictable based on the change in the other (i.e., Votes for the Democratic Presidential candidate in North Dakota) over the 7 years from 1993 through 2020.

p < 0.05, which statistically significant(Null hypothesis significance test)
The p-value is 0.021. 0.0212134259124390630000000000
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 0.83 in 2.1% of random cases. Said differently, if you correlated 47 random variables Which I absolutely did.
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.

[ 0.2, 0.97 ] 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.
1996200020042008201220162020
Votes for the Democratic Presidential candidate in North Dakota (Total votes)1069059528411105214127812496693758114902
Petroluem consumption in Czechia (Million Barrels/Day)173.347169.817206.097215.181195.51180.183192.71




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([106905,95284,111052,141278,124966,93758,114902,])
array_2 = np.array([173.347,169.817,206.097,215.181,195.51,180.183,192.71,])
array_1_name = "Votes for the Democratic Presidential candidate in North Dakota"
array_2_name = "Petroluem consumption in Czechia"

# 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?

You're the rating guru we've been waiting for!


Correlation ID: 5158 · Black Variable ID: 26016 · Red Variable ID: 24343
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0