Spurious correlation #4,644 · 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 Republican Senators in South Dakota and the second variable is Number of Earthquakes in the United States. The chart goes from 1990 to 2012, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Republican Senators in South Dakota and the second variable is Number of Earthquakes in the United States. The chart goes from 1990 to 2012, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As more Republicans voted for Senators in South Dakota, there was a surge in political rhetoric. This led to an increase in hot air production, creating a literal and figurative shift in the tectonic plates across the United States. Seismic activity couldn't help but rise as the political landscape became, quite literally, rockier.

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s, depicting a scene of seismic activity in South Dakota as Republican voters cast their ballots for Senators amid rising political tension. The illustration should show the ground rumbling and tectonic plates shifting, with a correlation to the political landscape. Keep the visual depiction simple without including any words or speech bubbles. 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: Republican votes for Senators in South Dakota and Number of Earthquakes in the United States. 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: Futuristic A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Cubism a funny image macro 3D Pixar Style
ChatGPT: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s

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 Republican votes for Senators in South Dakota and Number of Earthquakes in the United States, in the following situation: As more Republicans voted for Senators in South Dakota, there was a surge in political rhetoric. This led to an increase in hot air production, creating a literal and figurative shift in the tectonic plates across the United States. Seismic activity couldn't help but rise as the political landscape became, quite literally, rockier.. Keep the description simple.
ChatGPT: In South Dakota, Republican voters cast their ballots for Senators as political tension rose. As the hot air of political rhetoric increased, tectonic plates across the United States shifted. The ground rumbled and seismic activity surged in correlation with the political landscape.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s ] and depicting this scene: In South Dakota, Republican voters cast their ballots for Senators as political tension rose. As the hot air of political rhetoric increased, tectonic plates across the United States shifted. The ground rumbled and seismic activity surged in correlation with the political landscape. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s, depicting a scene of seismic activity in South Dakota as Republican voters cast their ballots for Senators amid rising political tension. The illustration should show the ground rumbling and tectonic plates shifting, with a correlation to the political landscape. Keep the visual depiction simple without including any words or speech bubbles.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Republican votes for Senators in South Dakota caused Number of Earthquakes in the United States to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States

The Journal of Unconventional Political Geophysics

Jan 2024

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

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Republican votes for Senators in South Dakota and Number of Earthquakes in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States

[[ABSTRACT]]
The present study aimed to investigate the relationship between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and the US Geological Survey, a thorough analysis was conducted to shed light on this surprising association. The findings revealed a substantial correlation coefficient of 0.8709042 and p < 0.01 for the period from 1990 to 2012.

Drawing on electoral and seismic data, the research team deciphered a noteworthy pattern, establishing a connection that was previously overlooked. The results indicate a positive relationship between Republican support in South Dakota and seismic activity across the nation, suggesting that political preferences in one part of the country could potentially influence tectonic movements elsewhere. This unexpected correlation prompts a seismic shift in our understanding of political and geological dynamics.

Furthermore, the study unearths a lighthearted yet revealing dad joke: Why did the conservative voter bring a map to the polling place? To show they're shaking things up - politically and geologically! This remarkable discovery adds a touch of levity to the often serious sphere of electoral and geological research, underscoring the interconnectedness of seemingly disparate phenomena.

In conclusion, this investigation not only demonstrates a statistically significant linkage between Republican votes in South Dakota and seismic events in the United States but also serves as a stark reminder that in the intricate web of causality, even the most unexpected factors can "quake" the foundations of our assumptions.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The coalescence of political events and geological phenomena has long captured the imagination of researchers and laymen alike. The intricate dance between seismic activity and political leanings invites contemplation of the interconnectedness of seemingly unrelated domains. The present study delves into this unexplored territory by examining the correlation between Republican votes for Senators in South Dakota and the number of earthquakes in the United States.
This unexpected confluence of electoral outcomes and tectonic movements gives new meaning to the phrase "political landslide." The seismic implications of voter preferences in one state reverberating across the nation offers a refreshingly unconventional lens through which to view the complex dynamics of American politics and geology.
As the data unfolds, it becomes clear that the association between Republican support in South Dakota and seismicity in the United States is rock-solid. This revelatory connection not only tantalizingly substantiates the adage "as South Dakota votes, so the earth shakes" but also highlights the seismic potential of political engagement.
The unexpected correlation uncovered in this study could inspire political pundits and geologists alike to adopt a novel perspective. One might even say the findings cause a "fault" in our previous understanding of the intricate interplay between voter behavior and tectonic restlessness.
The seismic interplay bridging political allegiances and geological events affords a pun-derful opportunity to unearth the unexpected ways in which human activities and natural phenomena collide. This research casts an affirmative ballot for the notion that seismic shifts in one domain can yield valuable insights into seemingly unconnected realities. Therefore, the significance of this study emanates not only from its statistical robustness but also from the levity it injects into the less light-hearted realms of electoral and geological discourse.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.," the authors find that there is a positive correlation between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. This surprising discovery has prompted a seismic shift in the field of political and geological research.

Doe and Jones also delve into this unexpected correlation, reinforcing the link between political preferences in South Dakota and seismic activity across the nation. The findings of these reputable studies demand further investigation and analysis.

Turning to the non-fiction literature, "The Earth is Always Moving" by Kathleen Weidner Zoehfeld offers valuable insights into the geological forces at play beneath the Earth's surface, while "Politics and Power" by David Kinsella provides a comprehensive overview of the political landscape in South Dakota. These works inform the present investigation by contextualizing the seismic and political phenomena under scrutiny.

On a more imaginative note, "Richter 10" by Arthur C. Clarke and Mike McQuay and "The Republican Playbook" by Leslie Knope present fictional narratives that subtly resonate with the unexpected correlation uncovered in this study. These entertaining yet tangentially relevant works add an element of whimsy to the investigation.

Moreover, the animated television series "The Magic School Bus" and "Dora the Explorer" subtly incorporate geological and geographic themes, providing an unconventional lens through which to contemplate the interplay between political voting patterns and seismic events. While these children's shows may not explicitly address the present research question, their thematic relevance merits acknowledgment.

The unexpected connection elucidated in this study underscores the interconnectedness of seemingly disparate domains. As the findings demonstrate a statistically significant link between Republican votes in South Dakota and seismic events in the United States, they also introduce a touch of levity to the often serious spheres of electoral and geological research.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the 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 Republican votes for Senators in South Dakota and Number of Earthquakes in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 US Geological Survey . You used data from 1990 to 2012

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]]
Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States

[[ABSTRACT]]
The present study aimed to investigate the relationship between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and the US Geological Survey, a thorough analysis was conducted to shed light on this surprising association. The findings revealed a substantial correlation coefficient of 0.8709042 and p < 0.01 for the period from 1990 to 2012.

Drawing on electoral and seismic data, the research team deciphered a noteworthy pattern, establishing a connection that was previously overlooked. The results indicate a positive relationship between Republican support in South Dakota and seismic activity across the nation, suggesting that political preferences in one part of the country could potentially influence tectonic movements elsewhere. This unexpected correlation prompts a seismic shift in our understanding of political and geological dynamics.

Furthermore, the study unearths a lighthearted yet revealing dad joke: Why did the conservative voter bring a map to the polling place? To show they're shaking things up - politically and geologically! This remarkable discovery adds a touch of levity to the often serious sphere of electoral and geological research, underscoring the interconnectedness of seemingly disparate phenomena.

In conclusion, this investigation not only demonstrates a statistically significant linkage between Republican votes in South Dakota and seismic events in the United States but also serves as a stark reminder that in the intricate web of causality, even the most unexpected factors can "quake" the foundations of our assumptions.

[[INTRODUCTION]]
The coalescence of political events and geological phenomena has long captured the imagination of researchers and laymen alike. The intricate dance between seismic activity and political leanings invites contemplation of the interconnectedness of seemingly unrelated domains. The present study delves into this unexplored territory by examining the correlation between Republican votes for Senators in South Dakota and the number of earthquakes in the United States.
This unexpected confluence of electoral outcomes and tectonic movements gives new meaning to the phrase "political landslide." The seismic implications of voter preferences in one state reverberating across the nation offers a refreshingly unconventional lens through which to view the complex dynamics of American politics and geology.
As the data unfolds, it becomes clear that the association between Republican support in South Dakota and seismicity in the United States is rock-solid. This revelatory connection not only tantalizingly substantiates the adage "as South Dakota votes, so the earth shakes" but also highlights the seismic potential of political engagement.
The unexpected correlation uncovered in this study could inspire political pundits and geologists alike to adopt a novel perspective. One might even say the findings cause a "fault" in our previous understanding of the intricate interplay between voter behavior and tectonic restlessness.
The seismic interplay bridging political allegiances and geological events affords a pun-derful opportunity to unearth the unexpected ways in which human activities and natural phenomena collide. This research casts an affirmative ballot for the notion that seismic shifts in one domain can yield valuable insights into seemingly unconnected realities. Therefore, the significance of this study emanates not only from its statistical robustness but also from the levity it injects into the less light-hearted realms of electoral and geological discourse.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection:
The research team gathered data on Republican votes for Senators in South Dakota from the MIT Election Data and Science Lab and harvested information about seismic activity in the United States from the US Geological Survey. The data collection process was as meticulous as a seismologist poring over tremor recordings, ensuring that the dataset was rock-solid.

Moreover, the team utilized the Harvard Dataverse to corroborate and supplement the primary data sources, creating a comprehensive repository that could stand the test of electoral and geological scrutiny. One might say the data collection process was so thorough, it left no (tectonic) plate unturned.

Variable Selection:
The selection of variables involved a judicious consideration of various factors that could potentially influence both Republican votes in South Dakota and seismic events across the United States. After extensive deliberation and analysis, the team identified the number of Republican votes for Senators in South Dakota and the frequency of earthquakes as the primary variables of interest. The selection process was as precise as a geologist’s measurement of fault displacement, aiming to capture the essence of political and seismic dynamics.

Data Analysis:
To unravel the connection between Republican votes in South Dakota and seismic activity in the United States, the research team employed a robust statistical approach. Firstly, the team calculated the correlation coefficient between the two variables, revealing a remarkably high correlation of 0.8709042. This finding surpassed expectations, prompting the team to exclaim, "Well, shake my data!"

Additionally, the team conducted a regression analysis to assess the strength and direction of the relationship between Republican votes in South Dakota and seismic activity. The analysis uncovered a significant influence, indicating that seismic activity in the United States is not immune to the sway of political outcomes in South Dakota. The results of the data analysis were so revealing, they caused a seismic shift in the team's prior assumptions.

Time Period Consideration:
The research focused on data from 1990 to 2012, encompassing a substantial timeframe that allowed for a comprehensive examination of the relationship between Republican votes in South Dakota and seismic events. By studying a range of electoral and geological occurrences, the research captured the evolutionary dynamics of both domains, uncovering unforeseen connections that shook the foundations of conventional wisdom.

Limitations:
While the research methodology and data analysis were meticulous and rigorous, certain limitations must be acknowledged. The study's scope was limited to a specific time period and geographic region, offering a snapshot of the complex interplay between political preferences and seismic phenomena. Additionally, the study did not delve into the underlying causal mechanisms driving the observed correlation. Nevertheless, the findings stand as a testament to the unforeseen ties that bind political dynamics in South Dakota to seismic reverberations across the United States.

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

Please make up the results section of an academic research paper presenting the findings of the connection between Republican votes for Senators in South Dakota and Number of Earthquakes in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 US Geological Survey .

For the time period 1990 to 2012, you found a correlation 0.8709042, r-squared of 0.7584741, 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]]
Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States

[[ABSTRACT]]
The present study aimed to investigate the relationship between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and the US Geological Survey, a thorough analysis was conducted to shed light on this surprising association. The findings revealed a substantial correlation coefficient of 0.8709042 and p < 0.01 for the period from 1990 to 2012.

Drawing on electoral and seismic data, the research team deciphered a noteworthy pattern, establishing a connection that was previously overlooked. The results indicate a positive relationship between Republican support in South Dakota and seismic activity across the nation, suggesting that political preferences in one part of the country could potentially influence tectonic movements elsewhere. This unexpected correlation prompts a seismic shift in our understanding of political and geological dynamics.

Furthermore, the study unearths a lighthearted yet revealing dad joke: Why did the conservative voter bring a map to the polling place? To show they're shaking things up - politically and geologically! This remarkable discovery adds a touch of levity to the often serious sphere of electoral and geological research, underscoring the interconnectedness of seemingly disparate phenomena.

In conclusion, this investigation not only demonstrates a statistically significant linkage between Republican votes in South Dakota and seismic events in the United States but also serves as a stark reminder that in the intricate web of causality, even the most unexpected factors can "quake" the foundations of our assumptions.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The coalescence of political events and geological phenomena has long captured the imagination of researchers and laymen alike. The intricate dance between seismic activity and political leanings invites contemplation of the interconnectedness of seemingly unrelated domains. The present study delves into this unexplored territory by examining the correlation between Republican votes for Senators in South Dakota and the number of earthquakes in the United States.
This unexpected confluence of electoral outcomes and tectonic movements gives new meaning to the phrase "political landslide." The seismic implications of voter preferences in one state reverberating across the nation offers a refreshingly unconventional lens through which to view the complex dynamics of American politics and geology.
As the data unfolds, it becomes clear that the association between Republican support in South Dakota and seismicity in the United States is rock-solid. This revelatory connection not only tantalizingly substantiates the adage "as South Dakota votes, so the earth shakes" but also highlights the seismic potential of political engagement.
The unexpected correlation uncovered in this study could inspire political pundits and geologists alike to adopt a novel perspective. One might even say the findings cause a "fault" in our previous understanding of the intricate interplay between voter behavior and tectonic restlessness.
The seismic interplay bridging political allegiances and geological events affords a pun-derful opportunity to unearth the unexpected ways in which human activities and natural phenomena collide. This research casts an affirmative ballot for the notion that seismic shifts in one domain can yield valuable insights into seemingly unconnected realities. Therefore, the significance of this study emanates not only from its statistical robustness but also from the levity it injects into the less light-hearted realms of electoral and geological discourse.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the relationship between Republican votes for Senators in South Dakota and seismic activity in the United States yielded a remarkable correlation coefficient of 0.8709042. This coefficient indicates a strong positive relationship between the two variables, providing compelling evidence that electoral outcomes in South Dakota are significantly associated with seismic events nationwide. This unexpected association is akin to a political aftershock felt across the geological landscape, challenging conventional understandings of the intersections between political preferences and geological phenomena.

The obtained r-squared value of 0.7584741 further reinforces the robustness of the correlation. This high r-squared value suggests that approximately 75.85% of the variance in seismic activity in the United States can be explained by variations in Republican votes for Senators in South Dakota. It appears that the political inclinations in South Dakota play a substantial role in influencing seismic events on a national scale, shaking up not only the political arena but also the geological domain.

The statistical significance of the correlation was confounded to a p-value of less than 0.01, underlining the reliability and strength of the relationship between the variables. This means that the likelihood of observing such a strong correlation due to random chance alone is less than 1%, providing compelling evidence for the substantial connection between Republican support in South Dakota and seismic activity across the United States.

Notably, the correlation being particularly pronounced from 1990 to 2012 prompts the thought-provoking observation that this period was truly a seismic time for both electoral and geological landscapes. It seems that during these years, the political vibrations from South Dakota were particularly resonant nationwide, resulting in a notable uptick in seismic occurrences. This unexpected alignment of political and geological phenomena extends an invitation for further explorations into the deep-seated interconnections between seemingly disparate domains.

Consequently, the presented findings not only corroborate the unexpected correlation but also infuse a touch of humor and levity into the otherwise serious discourse. This seismic revelation calls for a shift in our understanding of not only electoral and geological dynamics but also in our appreciation for the unexpected humor that can be found in the unlikeliest of places.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Republican votes for Senators in South Dakota and Number of Earthquakes in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States

[[ABSTRACT]]
The present study aimed to investigate the relationship between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and the US Geological Survey, a thorough analysis was conducted to shed light on this surprising association. The findings revealed a substantial correlation coefficient of 0.8709042 and p < 0.01 for the period from 1990 to 2012.

Drawing on electoral and seismic data, the research team deciphered a noteworthy pattern, establishing a connection that was previously overlooked. The results indicate a positive relationship between Republican support in South Dakota and seismic activity across the nation, suggesting that political preferences in one part of the country could potentially influence tectonic movements elsewhere. This unexpected correlation prompts a seismic shift in our understanding of political and geological dynamics.

Furthermore, the study unearths a lighthearted yet revealing dad joke: Why did the conservative voter bring a map to the polling place? To show they're shaking things up - politically and geologically! This remarkable discovery adds a touch of levity to the often serious sphere of electoral and geological research, underscoring the interconnectedness of seemingly disparate phenomena.

In conclusion, this investigation not only demonstrates a statistically significant linkage between Republican votes in South Dakota and seismic events in the United States but also serves as a stark reminder that in the intricate web of causality, even the most unexpected factors can "quake" the foundations of our assumptions.

[[LITERATURE REVIEW]]
In "Smith et al.," the authors find that there is a positive correlation between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. This surprising discovery has prompted a seismic shift in the field of political and geological research.
Doe and Jones also delve into this unexpected correlation, reinforcing the link between political preferences in South Dakota and seismic activity across the nation. The findings of these reputable studies demand further investigation and analysis.
Turning to the non-fiction literature, "The Earth is Always Moving" by Kathleen Weidner Zoehfeld offers valuable insights into the geological forces at play beneath the Earth's surface, while "Politics and Power" by David Kinsella provides a comprehensive overview of the political landscape in South Dakota. These works inform the present investigation by contextualizing the seismic and political phenomena under scrutiny.
On a more imaginative note, "Richter 10" by Arthur C. Clarke and Mike McQuay and "The Republican Playbook" by Leslie Knope present fictional narratives that subtly resonate with the unexpected correlation uncovered in this study. These entertaining yet tangentially relevant works add an element of whimsy to the investigation.
Moreover, the animated television series "The Magic School Bus" and "Dora the Explorer" subtly incorporate geological and geographic themes, providing an unconventional lens through which to contemplate the interplay between political voting patterns and seismic events. While these children's shows may not explicitly address the present research question, their thematic relevance merits acknowledgment.
The unexpected connection elucidated in this study underscores the interconnectedness of seemingly disparate domains. As the findings demonstrate a statistically significant link between Republican votes in South Dakota and seismic events in the United States, they also introduce a touch of levity to the often serious spheres of electoral and geological research.

[[RESULTS]]
The analysis of the relationship between Republican votes for Senators in South Dakota and seismic activity in the United States yielded a remarkable correlation coefficient of 0.8709042. This coefficient indicates a strong positive relationship between the two variables, providing compelling evidence that electoral outcomes in South Dakota are significantly associated with seismic events nationwide. This unexpected association is akin to a political aftershock felt across the geological landscape, challenging conventional understandings of the intersections between political preferences and geological phenomena.
The obtained r-squared value of 0.7584741 further reinforces the robustness of the correlation. This high r-squared value suggests that approximately 75.85% of the variance in seismic activity in the United States can be explained by variations in Republican votes for Senators in South Dakota. It appears that the political inclinations in South Dakota play a substantial role in influencing seismic events on a national scale, shaking up not only the political arena but also the geological domain.
The statistical significance of the correlation was confounded to a p-value of less than 0.01, underlining the reliability and strength of the relationship between the variables. This means that the likelihood of observing such a strong correlation due to random chance alone is less than 1%, providing compelling evidence for the substantial connection between Republican support in South Dakota and seismic activity across the United States.
Notably, the correlation being particularly pronounced from 1990 to 2012 prompts the thought-provoking observation that this period was truly a seismic time for both electoral and geological landscapes. It seems that during these years, the political vibrations from South Dakota were particularly resonant nationwide, resulting in a notable uptick in seismic occurrences. This unexpected alignment of political and geological phenomena extends an invitation for further explorations into the deep-seated interconnections between seemingly disparate domains.
Consequently, the presented findings not only corroborate the unexpected correlation but also infuse a touch of humor and levity into the otherwise serious discourse. This seismic revelation calls for a shift in our understanding of not only electoral and geological dynamics but also in our appreciation for the unexpected humor that can be found in the unlikeliest of places.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The present study has brought to light a truly seismic discovery: a substantial and statistically significant correlation between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. These findings corroborate prior research by Smith et al. and Doe and Jones, affirming the unexpected link between political preferences in South Dakota and seismic activity across the nation. The robust correlation coefficient of 0.8709042 and p < 0.01 align with the prior literature, signaling a seismic shift in our understanding of the interconnectedness of political and geological dynamics.

This unexpected correlation prompts the amusing yet insightful reflection - why did the conservative voter bring a map to the polling place? To show they're shaking things up - politically and geologically! This lighthearted jest resonates with the unexpected findings, underscoring the interconnectedness of seemingly disparate phenomena and infusing a touch of levity into the discourse. The present investigation not only upholds the statistically significant linkage between Republican votes in South Dakota and seismic events in the United States but also serves as a reminder that even the most unlikely factors can disrupt the foundations of our assumptions.

The literature review contributed to framing the unexpected correlation within a broader context. The non-fiction literature on geological forces and political landscapes provided valuable insights, while the tangentially relevant fictional narratives and children's shows introduced an element of whimsy to the investigation. The unexpected connection elucidated in this study underscores the nuanced interplay between political voting patterns and seismic events, shedding light on the lighthearted yet revealing aspects of this unconventional correlation.

The results further solidify the implications of the connection, with a high r-squared value of 0.7584741 suggesting that a substantial portion of the variance in seismic activity in the United States can be explained by variations in Republican votes for Senators in South Dakota. This unexpected revelation prompts the thought-provoking observation that the political vibrations from South Dakota during 1990 to 2012 were particularly resonant nationwide, resulting in a notable uptick in seismic occurrences.

In conclusion, the unexpected correlation between Republican votes in South Dakota and seismic events across the United States not only challenges conventional understandings of the intersections between political preferences and geological phenomena but also showcases the unexpected humor that can be found in the unlikeliest of places. This seismic discovery invites further exploration into the deep-seated interconnections between political and geological domains, highlighting the whimsical as well as the scholarly inferences that emerge from this surprising association.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Republican votes for Senators in South Dakota and Number of Earthquakes in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States

[[ABSTRACT]]
The present study aimed to investigate the relationship between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and the US Geological Survey, a thorough analysis was conducted to shed light on this surprising association. The findings revealed a substantial correlation coefficient of 0.8709042 and p < 0.01 for the period from 1990 to 2012.

Drawing on electoral and seismic data, the research team deciphered a noteworthy pattern, establishing a connection that was previously overlooked. The results indicate a positive relationship between Republican support in South Dakota and seismic activity across the nation, suggesting that political preferences in one part of the country could potentially influence tectonic movements elsewhere. This unexpected correlation prompts a seismic shift in our understanding of political and geological dynamics.

Furthermore, the study unearths a lighthearted yet revealing dad joke: Why did the conservative voter bring a map to the polling place? To show they're shaking things up - politically and geologically! This remarkable discovery adds a touch of levity to the often serious sphere of electoral and geological research, underscoring the interconnectedness of seemingly disparate phenomena.

In conclusion, this investigation not only demonstrates a statistically significant linkage between Republican votes in South Dakota and seismic events in the United States but also serves as a stark reminder that in the intricate web of causality, even the most unexpected factors can "quake" the foundations of our assumptions.

[[INTRDUCTION]]
The coalescence of political events and geological phenomena has long captured the imagination of researchers and laymen alike. The intricate dance between seismic activity and political leanings invites contemplation of the interconnectedness of seemingly unrelated domains. The present study delves into this unexplored territory by examining the correlation between Republican votes for Senators in South Dakota and the number of earthquakes in the United States.
This unexpected confluence of electoral outcomes and tectonic movements gives new meaning to the phrase "political landslide." The seismic implications of voter preferences in one state reverberating across the nation offers a refreshingly unconventional lens through which to view the complex dynamics of American politics and geology.
As the data unfolds, it becomes clear that the association between Republican support in South Dakota and seismicity in the United States is rock-solid. This revelatory connection not only tantalizingly substantiates the adage "as South Dakota votes, so the earth shakes" but also highlights the seismic potential of political engagement.
The unexpected correlation uncovered in this study could inspire political pundits and geologists alike to adopt a novel perspective. One might even say the findings cause a "fault" in our previous understanding of the intricate interplay between voter behavior and tectonic restlessness.
The seismic interplay bridging political allegiances and geological events affords a pun-derful opportunity to unearth the unexpected ways in which human activities and natural phenomena collide. This research casts an affirmative ballot for the notion that seismic shifts in one domain can yield valuable insights into seemingly unconnected realities. Therefore, the significance of this study emanates not only from its statistical robustness but also from the levity it injects into the less light-hearted realms of electoral and geological discourse.

[[RESULTS]]
The analysis of the relationship between Republican votes for Senators in South Dakota and seismic activity in the United States yielded a remarkable correlation coefficient of 0.8709042. This coefficient indicates a strong positive relationship between the two variables, providing compelling evidence that electoral outcomes in South Dakota are significantly associated with seismic events nationwide. This unexpected association is akin to a political aftershock felt across the geological landscape, challenging conventional understandings of the intersections between political preferences and geological phenomena.
The obtained r-squared value of 0.7584741 further reinforces the robustness of the correlation. This high r-squared value suggests that approximately 75.85% of the variance in seismic activity in the United States can be explained by variations in Republican votes for Senators in South Dakota. It appears that the political inclinations in South Dakota play a substantial role in influencing seismic events on a national scale, shaking up not only the political arena but also the geological domain.
The statistical significance of the correlation was confounded to a p-value of less than 0.01, underlining the reliability and strength of the relationship between the variables. This means that the likelihood of observing such a strong correlation due to random chance alone is less than 1%, providing compelling evidence for the substantial connection between Republican support in South Dakota and seismic activity across the United States.
Notably, the correlation being particularly pronounced from 1990 to 2012 prompts the thought-provoking observation that this period was truly a seismic time for both electoral and geological landscapes. It seems that during these years, the political vibrations from South Dakota were particularly resonant nationwide, resulting in a notable uptick in seismic occurrences. This unexpected alignment of political and geological phenomena extends an invitation for further explorations into the deep-seated interconnections between seemingly disparate domains.
Consequently, the presented findings not only corroborate the unexpected correlation but also infuse a touch of humor and levity into the otherwise serious discourse. This seismic revelation calls for a shift in our understanding of not only electoral and geological dynamics but also in our appreciation for the unexpected humor that can be found in the unlikeliest of places.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the present study illuminates a compelling correlation between Republican votes for Senators in South Dakota and the frequency of earthquakes across the United States. This unexpected connection underscores the seismic impact of political leanings in one part of the country on tectonic movements nationwide. The findings of this investigation reveal a seismic shift in our understanding of the interplay between electoral dynamics and geological occurrences, challenging conventional assumptions and paving the way for a fresh perspective on the nuanced relationship between political landscapes and geological phenomena.

The remarkable statistical robustness of the correlation coefficient and the high r-squared value not only shake up traditional research paradigms but also add a touch of unexpected humor to the otherwise solemn realm of electoral and geological discourse. As the seismic implications of conservative support in South Dakota reverberate across the nation, it seems that even Mother Earth can't help but cast her ballot.

To put it in dad joke terms: Why did the Republican voter bring a seismograph to the polling place? To "quake" the vote! This light-hearted yet revealing discovery underscores the quirkiness of interconnected realities and demonstrates that even in the most unlikely places, unexpected correlations can strike.

Therefore, the research team unequivocally asserts that no further investigations are warranted in this particular area, as the unexpectedly robust findings of the present study sufficiently shake up the status quo and encourage future exploration of lighthearted yet revealing interconnections in the world of research.

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 Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unconventional Political Geophysics

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 Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States. Respond only with the name of a fictional organization.

ChatGPT:

Foundation for Geological 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 Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States with an abstract of The present study aimed to investigate the relationship between Republican votes for Senators in South Dakota and the number of earthquakes in the United States. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and the US Geological Survey, a thorough analysis was conducted to shed light on this surprising association. The findings revealed a substantial correlation coefficient of 0.8709042 and p < 0.01 for the period from 1990 to 2012.
Drawing on electoral and seismic data, the research team deciphered a noteworthy pattern, establishing a connection that was previously overlooked. The results indicate a positive relationship between Republican support in South Dakota and seismic activity across the nation, suggesting that political preferences in one part of the country could potentially influence tectonic movements elsewhere. This unexpected correlation prompts a seismic shift in our understanding of political and geological dynamics.
Furthermore, the study unearths a lighthearted yet revealing dad joke: Why did the conservative voter bring a map to the polling place? To show they're shaking things up - politically and geologically! This remarkable discovery adds a touch of levity to the often serious sphere of electoral and geological research, underscoring the interconnectedness of seemingly disparate phenomena.
In conclusion, this investigation not only demonstrates a statistically significant linkage between Republican votes in South Dakota and seismic events in the United States but also serves as a stark reminder that in the intricate web of causality, even the most unexpected factors can "quake" the foundations of our assumptions.

ChatGPT:

Republican votes, Senators, South Dakota, seismic activity, United States, correlation, earthquakes, MIT Election Data and Science Lab, Harvard Dataverse, US Geological Survey, political preferences, tectonic movements, conservative voter, dad joke, electoral research, geological research, interconnectedness, causality

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

Number of Earthquakes in the United States
Source: US Geological Survey
See what else correlates with Number of Earthquakes in the United States

Correlation r = 0.8709042 (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 = 0.7584741 (Coefficient of determination)
This means 75.8% of the change in the one variable (i.e., Number of Earthquakes in the United States) is predictable based on the change in the other (i.e., Votes for Republican Senators in South Dakota) over the 8 years from 1990 through 2012.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0049.^Show 0.0048713640005378970000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.87 in 0.49% of random cases. Said differently, if you correlated 205 random variables^Note Which I absolutely did.
with the same 7 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 7 because we have two variables measured over a period of 8 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.43, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	1990	1992	1996	1998	2002	2004	2008	2010
Votes for Republican Senators in South Dakota (Percentage of votes)	52.3917	32.5066	48.6781	36.4086	49.4662	50.5762	37.5083	100
Number of Earthquakes in the United States (Earthquakes)	2268	3581	2807	2779	3876	3550	3618	8496

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([52.3917,32.5066,48.6781,36.4086,49.4662,50.5762,37.5083,100,])
array_2 = np.array([2268,3581,2807,2779,3876,3550,3618,8496,])
array_1_name = "Votes for Republican Senators in South Dakota"
array_2_name = "Number of Earthquakes in the United States"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Votes for Republican Senators in South Dakota
Line chart for only Number of Earthquakes in the United States
AI-generated correlation image
The spurious research paper: Shakin' Up the Ballot Box: The Correlation Between Republican Votes for Senators in South Dakota and Seismic Activity in the United States

View another random correlation

How fun was this correlation?

Kudos for rating!

Correlation ID: 4644 · Black Variable ID: 26462 · Red Variable ID: 223


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