Spurious correlation #4,243 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of transportation security screeners in West Virginia and the second variable is Google searches for 'how to build a bunker'. The chart goes from 2012 to 2022, 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 The number of transportation security screeners in West Virginia and the second variable is Google searches for 'how to build a bunker'. The chart goes from 2012 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

With fewer screeners around, the TSA implemented a new "Bring Your Own Bunker" policy, prompting a surge in West Virginians constructing their personal underground fortresses to ensure their own security. As a result, the demand for internet tutorials on bunker construction plummeted, as people realized that they were already experts in home fortification. Who needs a how-to guide when you can just repurpose your old fallout shelter blueprints from the 1950s? It was a real grassroots movement, or rather, an underground movement, in the Mountain State!

^{Show image generation prompt} Model: dalle-3
Prompt: Generating prompt... Title: Airport Bunker Rush Description: In a bustling airport in West Virginia, travelers anxiously wait to pass through a visibly understaffed security checkpoint. The line is filled with people clutching bags overflowing with bunker-building supplies, creating a bottleneck. Additionally, outside the airport, a group of individuals huddle around a smartphone, furiously typing 'how to build a bunker' into the Google search bar. In the background, the looming figures of Bigfoot and the Mothman can be seen, sparking a sense of urgency among the would-be bunker builders. The scene seamlessly blends a sense of chaos and urgency with the mythical presence of Bigfoot and the Mothman. Note: The prompt aims to create a visual depiction of a bustling airport scene in West Virginia, combining the chaos of travelers preparing for potential disasters with the looming presence of mythical creatures. 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: The number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker'. 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: Cyberpunk Parallax art Hyper-realistic Parallax art Low poly
ChatGPT: Parallax art

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 The number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker', in the following situation: People are worried the TSA screeners are going to confiscate all the bunker-building supplies as potential security threats. It's a race to build the ultimate underground fortress before Bigfoot and the Mothman team up to wreak havoc in West Virginia. "Because nothing ruins a bunker-building project like a shortage of TSA screeners.". Keep the description simple.
ChatGPT: In a bustling airport in West Virginia, a line of people anxiously waits to go through security. The number of transportation security screeners is visibly low, causing a bottleneck of travelers clutching bags filled with bunker-building supplies. Meanwhile, outside the airport, a group of individuals huddle around a smartphone, furiously typing 'how to build a bunker' into the Google search bar. In the background, the looming figures of Bigfoot and the Mothman can be seen, sparking a sense of urgency among the would-be bunker builders.

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: [ Parallax art ] and depicting this scene: In a bustling airport in West Virginia, a line of people anxiously waits to go through security. The number of transportation security screeners is visibly low, causing a bottleneck of travelers clutching bags filled with bunker-building supplies. Meanwhile, outside the airport, a group of individuals huddle around a smartphone, furiously typing 'how to build a bunker' into the Google search bar. In the background, the looming figures of Bigfoot and the Mothman can be seen, sparking a sense of urgency among the would-be bunker builders. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generating prompt... Title: Airport Bunker Rush Description: In a bustling airport in West Virginia, travelers anxiously wait to pass through a visibly understaffed security checkpoint. The line is filled with people clutching bags overflowing with bunker-building supplies, creating a bottleneck. Additionally, outside the airport, a group of individuals huddle around a smartphone, furiously typing 'how to build a bunker' into the Google search bar. In the background, the looming figures of Bigfoot and the Mothman can be seen, sparking a sense of urgency among the would-be bunker builders. The scene seamlessly blends a sense of chaos and urgency with the mythical presence of Bigfoot and the Mothman. Note: The prompt aims to create a visual depiction of a bustling airport scene in West Virginia, combining the chaos of travelers preparing for potential disasters with the looming presence of mythical creatures.

*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 a decrease in The number of transportation security screeners in West Virginia caused how to build a bunker (Google searches for 'how to build a bunker') to decrease.

AI academic paper

(Because p < 0.01)

Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'

International Journal of Behavioral Economics and Public Safety

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
"Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'"

[[ABSTRACT]]
In this research paper, we explore the intriguing relationship between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. Through rigorous analysis of data obtained from the Bureau of Labor Statistics and Google Trends, our research team uncovered a statistically significant correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8651587 and an impressively low p-value of less than 0.01 for the period from 2012 to 2022. The implications of this correlation are both thought-provoking and bewilderin—perhaps shedding light on the peculiar intrigues of the human psyche during times of perceived uncertainty. Our paper delves into the potential factors driving this unexpected connection, offering a whimsical dive into the underbelly of bunker-building ambitions and the labor force that stands guard.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
The whimsical world of correlation analysis often leads researchers down unexpected paths, uncovering peculiar connections between seemingly unrelated variables. In a quest to unravel the mysteries of human behavior and societal trends, our research team embarked on a journey to explore the correlation between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. As we delved into this peculiar pairing of variables, our initial skepticism was quickly overshadowed by the surprising strength of the association we discovered.
As the guardians of statistical rigor, we took on the challenge of examining this correlation with all the seriousness of a cat chasing a laser pointer – that is, with acute focus and occasional moments of delightful confusion. Our endeavor involved meticulous data collection from the Bureau of Labor Statistics, as well as a deep dive into the enigmatic realm of Google Trends. With a twinkle in our eyes and a healthy skepticism of correlation-causation fallacies, we began to unravel an unexpected tapestry of interconnectedness between employment figures and the curious interest in subterranean construction.
The title of our study, "Guardians of the Galaxy," not only pays tribute to the valiant efforts of the transportation security screeners but also hints at the cosmic scale of the correlation we have unearthed. Yes, we couldn't resist an astronomy-themed pun – after all, correlation analysis is a universe of its own, where stars (or data points) align in strange and wonderful ways.
Armed with statistical tools and an unyielding curiosity for the absurd, our research aims to shed light on the peculiar dance between workforce dynamics and clandestine construction aspirations. Prepare to embark on a statistical odyssey through the quirky corridors of correlation, where the unexpected rules and curiosity reigns supreme.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The investigation into the correlation between the number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker' has prompted a thorough review of existing literature on related topics. Smith et al. (2015) provide valuable insights into the labor market dynamics of security personnel, shedding light on the intricacies of employment patterns in the security sector. Furthermore, Doe's (2018) study delves into the psychological underpinnings of interest in do-it-yourself construction projects, albeit with a focus on above-ground structures.

Moving beyond the realm of non-fiction research, the works of renowned authors such as "The Prepper's Blueprint" by Tess Pennington and "How to Build a Bunker" by Benjamin Chasteen offer anecdotal evidence of the burgeoning interest in underground fortifications. On a more fictional note, publications like "The Road" by Cormac McCarthy and "The Tunnel" by Ernesto Sabato inexplicably capture the enigmatic allure of subterranean refuge-seeking in the face of uncertain times.

In the world of board games, "Pandemic" may not directly relate to bunker-building, but its portrayal of societal resilience in the face of dire global threats provides a tangential link to the underlying motivations that drive individuals to seek information on constructing protective shelters.

As we wade through this diverse array of literature, we cannot overlook the peculiar threads that seem to weave together the otherwise disparate realms of security employment, doomsday preparation, and underground construction aspirations. While the relationship between these elements may seem as improbable as finding a four-leaf clover in a haystack, our research endeavors to unearth the underlying patterns that tie them together – no matter how labyrinthine or cryptic they may be.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Google Trends . You used data from 2012 to 2022

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]]
"Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'"

[[ABSTRACT]]
In this research paper, we explore the intriguing relationship between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. Through rigorous analysis of data obtained from the Bureau of Labor Statistics and Google Trends, our research team uncovered a statistically significant correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8651587 and an impressively low p-value of less than 0.01 for the period from 2012 to 2022. The implications of this correlation are both thought-provoking and bewilderin—perhaps shedding light on the peculiar intrigues of the human psyche during times of perceived uncertainty. Our paper delves into the potential factors driving this unexpected connection, offering a whimsical dive into the underbelly of bunker-building ambitions and the labor force that stands guard.

[[INTRODUCTION]]
Introduction
The whimsical world of correlation analysis often leads researchers down unexpected paths, uncovering peculiar connections between seemingly unrelated variables. In a quest to unravel the mysteries of human behavior and societal trends, our research team embarked on a journey to explore the correlation between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. As we delved into this peculiar pairing of variables, our initial skepticism was quickly overshadowed by the surprising strength of the association we discovered.
As the guardians of statistical rigor, we took on the challenge of examining this correlation with all the seriousness of a cat chasing a laser pointer – that is, with acute focus and occasional moments of delightful confusion. Our endeavor involved meticulous data collection from the Bureau of Labor Statistics, as well as a deep dive into the enigmatic realm of Google Trends. With a twinkle in our eyes and a healthy skepticism of correlation-causation fallacies, we began to unravel an unexpected tapestry of interconnectedness between employment figures and the curious interest in subterranean construction.
The title of our study, "Guardians of the Galaxy," not only pays tribute to the valiant efforts of the transportation security screeners but also hints at the cosmic scale of the correlation we have unearthed. Yes, we couldn't resist an astronomy-themed pun – after all, correlation analysis is a universe of its own, where stars (or data points) align in strange and wonderful ways.
Armed with statistical tools and an unyielding curiosity for the absurd, our research aims to shed light on the peculiar dance between workforce dynamics and clandestine construction aspirations. Prepare to embark on a statistical odyssey through the quirky corridors of correlation, where the unexpected rules and curiosity reigns supreme.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection
Our methodological journey began with the acquisition of employment data for transportation security screeners in West Virginia obtained from the Bureau of Labor Statistics. We meticulously combed through employment figures, exercising the diligence of a squirrel storing nuts for winter – ensuring that no data nugget was left unturned. To bolster our analysis, we then ventured into the labyrinthine expanse of Google Trends, where we tracked the frequency of searches for 'how to build a bunker' with the fervor of a treasure hunter seeking elusive booty.

Statistical Analysis
With our repository of data in hand, we embarked on the treacherous seas of statistical analysis, armed with the compass of correlation and the sextant of significance. Our journey led us to harness the power of various statistical techniques, wielding them with the finesse of a seasoned chef creating the perfect soufflé – careful measurement and an occasional sprinkle of intuition. The correlation coefficient, akin to the North Star guiding sailors home, illuminated the strength of the relationship between the number of security screeners and the burgeoning curiosity for bunker-building endeavors. Meanwhile, the p-value stood as a vigilant gatekeeper, guarding against spurious relationships and upholding the sanctity of statistical inference.

Temporal Considerations
As we voyaged through the temporal landscape of our data spanning the years 2012 to 2022, we encountered the ebb and flow of societal currents – akin to a flotilla navigating through the tides of human interests and economic shifts. Our analysis considered the possibility of temporal lags, with an understanding that changes in employment dynamics may sow seeds that blossom into peculiar Google searches at unforeseen moments, much like a surprise birthday gift arriving after the confetti has settled.

Limitations
Though our endeavor was marked by resolve and scientific spirit, it was not without perils. We acknowledge that our data, akin to a map of uncharted territories, bore limitations in its scope and granularity. While we aimed to paint a vivid portrait of the connection between transportation security screeners and bunker-building queries, our canvas was not without its blank spaces. Future research endeavors may employ additional variables and more refined data sources to enrich the tapestry of understanding in this domain.

Ethical Considerations
As intrepid explorers of statistical phenomena, we remained steadfast in our commitment to ethical research conduct. Our pursuit of knowledge was guided by the twin beacons of integrity and respect for privacy, ensuring that the treasure troves of data were handled with the care of a museum curator tending to ancient relics.

In summary, our methodology stood as a sailing vessel navigating the choppy waters of correlation analysis, charting a course through data seas and statistical storms. With the wind of curiosity propelling our sails, we endeavored to unravel the enigmatic bond between the sentinels of security and the whispers of subterranean construction, all while maintaining a steady supply of puns and whimsy.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Google Trends .

For the time period 2012 to 2022, you found a correlation 0.8651587, r-squared of 0.7484996, 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]]
"Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'"

[[ABSTRACT]]
In this research paper, we explore the intriguing relationship between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. Through rigorous analysis of data obtained from the Bureau of Labor Statistics and Google Trends, our research team uncovered a statistically significant correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8651587 and an impressively low p-value of less than 0.01 for the period from 2012 to 2022. The implications of this correlation are both thought-provoking and bewilderin—perhaps shedding light on the peculiar intrigues of the human psyche during times of perceived uncertainty. Our paper delves into the potential factors driving this unexpected connection, offering a whimsical dive into the underbelly of bunker-building ambitions and the labor force that stands guard.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
The whimsical world of correlation analysis often leads researchers down unexpected paths, uncovering peculiar connections between seemingly unrelated variables. In a quest to unravel the mysteries of human behavior and societal trends, our research team embarked on a journey to explore the correlation between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. As we delved into this peculiar pairing of variables, our initial skepticism was quickly overshadowed by the surprising strength of the association we discovered.
As the guardians of statistical rigor, we took on the challenge of examining this correlation with all the seriousness of a cat chasing a laser pointer – that is, with acute focus and occasional moments of delightful confusion. Our endeavor involved meticulous data collection from the Bureau of Labor Statistics, as well as a deep dive into the enigmatic realm of Google Trends. With a twinkle in our eyes and a healthy skepticism of correlation-causation fallacies, we began to unravel an unexpected tapestry of interconnectedness between employment figures and the curious interest in subterranean construction.
The title of our study, "Guardians of the Galaxy," not only pays tribute to the valiant efforts of the transportation security screeners but also hints at the cosmic scale of the correlation we have unearthed. Yes, we couldn't resist an astronomy-themed pun – after all, correlation analysis is a universe of its own, where stars (or data points) align in strange and wonderful ways.
Armed with statistical tools and an unyielding curiosity for the absurd, our research aims to shed light on the peculiar dance between workforce dynamics and clandestine construction aspirations. Prepare to embark on a statistical odyssey through the quirky corridors of correlation, where the unexpected rules and curiosity reigns supreme.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The statistical analysis of the relationship between the number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker' yielded intriguing results. Our exploration of this unorthodox correlation revealed a striking correlation coefficient of 0.8651587, indicating a strong positive association between the two variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.7484996, signifying that approximately 74.85% of the variability in bunker-building searches can be explained by the number of vigilant screeners in the transportation security sector. Furthermore, the p-value of less than 0.01 provides compelling evidence against the null hypothesis of no correlation, affirming the statistical significance of our findings.

The visually appealing scatterplot (Fig. 1) exemplifies the robust correlation observed between transportation security screeners and searches for bunker construction guidance. Each data point in the scatterplot represents a unique juxtaposition of screeners and bunker-related searches, forming a delightful constellation of statistical intrigue. It's almost as if the data points are engaging in a dance of correlation, twirling around each other in a harmonious display of quantitative elegance.

As we navigate through the labyrinth of statistics, it becomes evident that the alliance between transportation security and bunker curiosity is not merely a chance encounter in the vast realm of data. Instead, it symbolizes a bond between the protectors of public transit and the esoteric yearning for subterranean sanctuaries – a connection that transcends conventional logic and ventures into the whimsical domain of statistical serendipity.

In conclusion, our research unearths an unanticipated relationship between transportation security screeners and the inquisitive pursuit of bunker construction knowledge. This unexpected correlation serves as a testament to the inexplicable ways in which human interests intersect with labor dynamics, inviting further exploration into the enigmatic landscapes of societal trends and statistical curiosities.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
"Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'"

[[ABSTRACT]]
In this research paper, we explore the intriguing relationship between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. Through rigorous analysis of data obtained from the Bureau of Labor Statistics and Google Trends, our research team uncovered a statistically significant correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8651587 and an impressively low p-value of less than 0.01 for the period from 2012 to 2022. The implications of this correlation are both thought-provoking and bewilderin—perhaps shedding light on the peculiar intrigues of the human psyche during times of perceived uncertainty. Our paper delves into the potential factors driving this unexpected connection, offering a whimsical dive into the underbelly of bunker-building ambitions and the labor force that stands guard.

[[LITERATURE REVIEW]]
The investigation into the correlation between the number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker' has prompted a thorough review of existing literature on related topics. Smith et al. (2015) provide valuable insights into the labor market dynamics of security personnel, shedding light on the intricacies of employment patterns in the security sector. Furthermore, Doe's (2018) study delves into the psychological underpinnings of interest in do-it-yourself construction projects, albeit with a focus on above-ground structures.
Moving beyond the realm of non-fiction research, the works of renowned authors such as "The Prepper's Blueprint" by Tess Pennington and "How to Build a Bunker" by Benjamin Chasteen offer anecdotal evidence of the burgeoning interest in underground fortifications. On a more fictional note, publications like "The Road" by Cormac McCarthy and "The Tunnel" by Ernesto Sabato inexplicably capture the enigmatic allure of subterranean refuge-seeking in the face of uncertain times.
In the world of board games, "Pandemic" may not directly relate to bunker-building, but its portrayal of societal resilience in the face of dire global threats provides a tangential link to the underlying motivations that drive individuals to seek information on constructing protective shelters.
As we wade through this diverse array of literature, we cannot overlook the peculiar threads that seem to weave together the otherwise disparate realms of security employment, doomsday preparation, and underground construction aspirations. While the relationship between these elements may seem as improbable as finding a four-leaf clover in a haystack, our research endeavors to unearth the underlying patterns that tie them together – no matter how labyrinthine or cryptic they may be.

[[RESULTS]]
The statistical analysis of the relationship between the number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker' yielded intriguing results. Our exploration of this unorthodox correlation revealed a striking correlation coefficient of 0.8651587, indicating a strong positive association between the two variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.7484996, signifying that approximately 74.85% of the variability in bunker-building searches can be explained by the number of vigilant screeners in the transportation security sector. Furthermore, the p-value of less than 0.01 provides compelling evidence against the null hypothesis of no correlation, affirming the statistical significance of our findings.
The visually appealing scatterplot (Fig. 1) exemplifies the robust correlation observed between transportation security screeners and searches for bunker construction guidance. Each data point in the scatterplot represents a unique juxtaposition of screeners and bunker-related searches, forming a delightful constellation of statistical intrigue. It's almost as if the data points are engaging in a dance of correlation, twirling around each other in a harmonious display of quantitative elegance.
As we navigate through the labyrinth of statistics, it becomes evident that the alliance between transportation security and bunker curiosity is not merely a chance encounter in the vast realm of data. Instead, it symbolizes a bond between the protectors of public transit and the esoteric yearning for subterranean sanctuaries – a connection that transcends conventional logic and ventures into the whimsical domain of statistical serendipity.
In conclusion, our research unearths an unanticipated relationship between transportation security screeners and the inquisitive pursuit of bunker construction knowledge. This unexpected correlation serves as a testament to the inexplicable ways in which human interests intersect with labor dynamics, inviting further exploration into the enigmatic landscapes of societal trends and statistical curiosities.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have brought to light a captivating and, dare I say, seismic correlation between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. These findings not only align with prior research into the peculiarities of human behavior during uncertain times but also unveil a novel connection that transcends the conventional realms of statistical exploration.

The literature review, which initially appeared to be a mere supporting act in this academic extravaganza, subtly elevates our understanding of the multidimensional facets of our investigation. The psychological underpinnings of do-it-yourself construction projects, as expounded upon by Doe (2018), find resonance in the clandestine allure of bunker-building. Similarly, the tangential link to societal resilience in facing global threats, as exemplified in the world of board games with "Pandemic," hints at the nuanced motivators driving individuals to seek refuge knowledge. These seemingly disparate strands weave together into a narrative that not only captivates the imagination but also elucidates the symbiotic relationship between the protectors of public transit and the desire for subterranean havens.

Our statistical analysis, akin to a Sherlock Holmes unraveling the mysteries of correlation, has not only validated the existence of this captivating bond but also quantitatively confirmed its robustness. The correlation coefficient, reminiscent of a steadfast compass guiding us through uncharted waters, exudes a sense of dependability in navigating the enigmatic landscape of societal trends. The visually appealing scatterplot, akin to a ballroom adorned with data points gracefully waltzing with one another, presents a compelling spectacle of statistical elegance, transcending the mundane realms of regression analysis.

In summary, our research has not only uncovered a statistically significant relationship between transportation security screeners and the pursuit of bunker construction knowledge but has also lifted the veil on the intricate dance of variables, intricately intertwined in the tapestry of statistical serendipity. As we tread the uncharted territories of statistical curiosity, let us not forget to revel in the humorous unpredictability of scientific exploration and the intriguing dance of correlation that captures the essences of human curiosity and labor dynamics.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'"

[[ABSTRACT]]
In this research paper, we explore the intriguing relationship between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. Through rigorous analysis of data obtained from the Bureau of Labor Statistics and Google Trends, our research team uncovered a statistically significant correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8651587 and an impressively low p-value of less than 0.01 for the period from 2012 to 2022. The implications of this correlation are both thought-provoking and bewilderin—perhaps shedding light on the peculiar intrigues of the human psyche during times of perceived uncertainty. Our paper delves into the potential factors driving this unexpected connection, offering a whimsical dive into the underbelly of bunker-building ambitions and the labor force that stands guard.

[[INTRDUCTION]]
Introduction
The whimsical world of correlation analysis often leads researchers down unexpected paths, uncovering peculiar connections between seemingly unrelated variables. In a quest to unravel the mysteries of human behavior and societal trends, our research team embarked on a journey to explore the correlation between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. As we delved into this peculiar pairing of variables, our initial skepticism was quickly overshadowed by the surprising strength of the association we discovered.
As the guardians of statistical rigor, we took on the challenge of examining this correlation with all the seriousness of a cat chasing a laser pointer – that is, with acute focus and occasional moments of delightful confusion. Our endeavor involved meticulous data collection from the Bureau of Labor Statistics, as well as a deep dive into the enigmatic realm of Google Trends. With a twinkle in our eyes and a healthy skepticism of correlation-causation fallacies, we began to unravel an unexpected tapestry of interconnectedness between employment figures and the curious interest in subterranean construction.
The title of our study, "Guardians of the Galaxy," not only pays tribute to the valiant efforts of the transportation security screeners but also hints at the cosmic scale of the correlation we have unearthed. Yes, we couldn't resist an astronomy-themed pun – after all, correlation analysis is a universe of its own, where stars (or data points) align in strange and wonderful ways.
Armed with statistical tools and an unyielding curiosity for the absurd, our research aims to shed light on the peculiar dance between workforce dynamics and clandestine construction aspirations. Prepare to embark on a statistical odyssey through the quirky corridors of correlation, where the unexpected rules and curiosity reigns supreme.

[[RESULTS]]
The statistical analysis of the relationship between the number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker' yielded intriguing results. Our exploration of this unorthodox correlation revealed a striking correlation coefficient of 0.8651587, indicating a strong positive association between the two variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.7484996, signifying that approximately 74.85% of the variability in bunker-building searches can be explained by the number of vigilant screeners in the transportation security sector. Furthermore, the p-value of less than 0.01 provides compelling evidence against the null hypothesis of no correlation, affirming the statistical significance of our findings.
The visually appealing scatterplot (Fig. 1) exemplifies the robust correlation observed between transportation security screeners and searches for bunker construction guidance. Each data point in the scatterplot represents a unique juxtaposition of screeners and bunker-related searches, forming a delightful constellation of statistical intrigue. It's almost as if the data points are engaging in a dance of correlation, twirling around each other in a harmonious display of quantitative elegance.
As we navigate through the labyrinth of statistics, it becomes evident that the alliance between transportation security and bunker curiosity is not merely a chance encounter in the vast realm of data. Instead, it symbolizes a bond between the protectors of public transit and the esoteric yearning for subterranean sanctuaries – a connection that transcends conventional logic and ventures into the whimsical domain of statistical serendipity.
In conclusion, our research unearths an unanticipated relationship between transportation security screeners and the inquisitive pursuit of bunker construction knowledge. This unexpected correlation serves as a testament to the inexplicable ways in which human interests intersect with labor dynamics, inviting further exploration into the enigmatic landscapes of societal trends and statistical curiosities.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In closing, our investigation into the correlation between the number of transportation security screeners in West Virginia and Google searches for 'how to build a bunker' has illuminated a compelling tale of statistical entanglement. The robust correlation coefficient of 0.8651587 serves as a testament to the intertwined nature of these seemingly unrelated phenomena. It's almost as if the vigilant screeners are standing guard not only at transportation checkpoints but also over the expansive domain of statistical quirks and whimsy.

The coefficient of determination (r-squared) of 0.7484996 further reinforces the notion that approximately 74.85% of bunker-building search behavior can be explained by the diligent presence of our guardians of transit security. It's as though the statistical narrative unfolds with the precision of a well-orchestrated symphony, with the transportation security screeners and bunker enthusiasts performing an unexpected duet of data-driven harmony.

The visually captivating scatterplot (Fig. 1) depicts the playful waltz of data points, twirling and pirouetting in a mesmerizing display of correlation choreography. Not to anthropomorphize the data, but one could almost imagine the data points exchanging statistical pleasantries and sharing the occasional numerical joke as they form constellations of correlation brilliance.

In pondering the implications of our findings, we are left with a sense of awe at the delightful confluence of labor dynamics and subterranean aspirations. The narrative that emerges from our research is not merely one of statistical analysis but an engaging tale of human curiosity and the intricate dance of data.

In light of these compelling revelations, we assert that no further research endeavors are needed to explore this particular correlation. The peculiar charm and statistical allure of this association stand as a testament to the enchanting idiosyncrasies of correlation exploration. It seems the data has spoken, and its symphony of statistical serendipity is a masterpiece worth admiring from afar.

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 Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'. Respond only with the name of a fictional academic journal.

ChatGPT:

International Journal of Behavioral Economics and Public Safety

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 Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Unusual Behavioral Trends and Security Measures

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 Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker' with an abstract of In this research paper, we explore the intriguing relationship between the number of transportation security screeners in West Virginia and the frequency of Google searches for 'how to build a bunker'. Through rigorous analysis of data obtained from the Bureau of Labor Statistics and Google Trends, our research team uncovered a statistically significant correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8651587 and an impressively low p-value of less than 0.01 for the period from 2012 to 2022. The implications of this correlation are both thought-provoking and bewilderin—perhaps shedding light on the peculiar intrigues of the human psyche during times of perceived uncertainty. Our paper delves into the potential factors driving this unexpected connection, offering a whimsical dive into the underbelly of bunker-building ambitions and the labor force that stands guard.

ChatGPT:

Transportation security screeners, West Virginia, Google searches, 'how to build a bunker', correlation, Bureau of Labor Statistics, Google Trends, correlation coefficient, p-value, human psyche, uncertainty, bunker-building ambitions, labor force

*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

The number of transportation security screeners in West Virginia
Detailed data title: BLS estimate of transportation security screeners in West Virginia
Source: Bureau of Larbor Statistics
See what else correlates with The number of transportation security screeners in West Virginia

Google searches for 'how to build a bunker'
Detailed data title: Relative volume of Google searches for 'how to build a bunker' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'how to build a bunker'

Correlation r = 0.8651587 (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 = 0.7484996 (Coefficient of determination)
This means 74.8% of the change in the one variable (i.e., Google searches for 'how to build a bunker') is predictable based on the change in the other (i.e., The number of transportation security screeners in West Virginia) over the 11 years from 2012 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00058.^Show 0.0005828946416799983000000000
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 0.058% of random cases. Said differently, if you correlated 1,716 random variables^Note Which I absolutely did.
with the same 10 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.55, 0.96 ] 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.

	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
The number of transportation security screeners in West Virginia (Laborers)	120	100	90	90	90	90	80	90	100	90	100
Google searches for 'how to build a bunker' (Rel. search volume)	60.4167	42.8333	32.9167	33.5833	36.75	42.9167	31.4167	27.0833	45.1667	37.5833	54

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.

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([120,100,90,90,90,90,80,90,100,90,100,])
array_2 = np.array([60.4167,42.8333,32.9167,33.5833,36.75,42.9167,31.4167,27.0833,45.1667,37.5833,54,])
array_1_name = "The number of transportation security screeners in West Virginia"
array_2_name = "Google searches for 'how to build a bunker'"

# 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 The number of transportation security screeners in West Virginia
Line chart for only Google searches for 'how to build a bunker'
AI-generated correlation image
The spurious research paper: Guardians of the Galaxy: The Correlation between Transportation Security Screeners in West Virginia and Google Searches for 'How to Build a Bunker'

View another random correlation

How fun was this correlation?

Your correlation rating is out of this world!

Correlation ID: 4243 · Black Variable ID: 19601 · Red Variable ID: 1377


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