about · email me · subscribe
Spurious correlation #1,070 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'zombies' and the second variable is The number of real estate agents in North Dakota.  The chart goes from 2004 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As more people prepared for a potential zombie apocalypse, the demand for underground bunkers in North Dakota skyrocketed, leading to a boom in the real estate market and a sudden need for more agents to facilitate these unconventional property transactions. "Even the undead can't resist that North Dakota charm!"

Model: dalle-3
Prompt: Generate an image of a serene small town street in North Dakota, lined with charming houses on either side. On one side of the street, imagine a gathering of people dressed in elaborate zombie costumes and setting up spooky decorations. They exude an otherworldly atmosphere as they enthusiastically engage in the zombie craze. On the opposite side of the street, visualize a group of real estate agents interacting with potential buyers. They are positioning "open house" signs and engaging in conversations, discussing the unique advantages of properties near cemeteries. The scene should convey an intriguing juxtaposition of the surreal and the everyday, blending elements of magic realism with a touch of the uncanny. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: An increase in zombies (Google searches for 'zombies') caused the number of real estate agents in North Dakota to also increase due to the rising demand for properties with "graveyard adjacency" as people seek more secure homes with "dead-end" neighborhoods and potential "tomb with a view" opportunities.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Psychedelic Cute cartoon An image that looks like it is a scene from A Disney Movie Realistic Magic realism
ChatGPT: Magic realism

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. An increase in zombies (Google searches for 'zombies') caused the number of real estate agents in North Dakota to also increase due to the rising demand for properties with "graveyard adjacency" as people seek more secure homes with "dead-end" neighborhoods and potential "tomb with a view" opportunities.
ChatGPT: Sure! Imagine a small town in North Dakota with a row of quaint houses. On one side of the street, you see an uptick in zombie costumes and decorations as more people search for "zombies" online. On the other side of the street, you notice a group of real estate agents setting up open house signs and speaking with potential buyers. They're discussing the benefits of properties located near cemeteries and explaining how these homes provide a sense of security in a "dead-end" neighborhood, while also highlighting the potential for a "tomb with a view."

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: [ Magic realism ] and depicting this scene: Sure! Imagine a small town in North Dakota with a row of quaint houses. On one side of the street, you see an uptick in zombie costumes and decorations as more people search for "zombies" online. On the other side of the street, you notice a group of real estate agents setting up open house signs and speaking with potential buyers. They're discussing the benefits of properties located near cemeteries and explaining how these homes provide a sense of security in a "dead-end" neighborhood, while also highlighting the potential for a "tomb with a view." Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a serene small town street in North Dakota, lined with charming houses on either side. On one side of the street, imagine a gathering of people dressed in elaborate zombie costumes and setting up spooky decorations. They exude an otherworldly atmosphere as they enthusiastically engage in the zombie craze. On the opposite side of the street, visualize a group of real estate agents interacting with potential buyers. They are positioning "open house" signs and engaging in conversations, discussing the unique advantages of properties near cemeteries. The scene should convey an intriguing juxtaposition of the surreal and the everyday, blending elements of magic realism with a touch of the uncanny.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in zombies (Google searches for 'zombies') positively influenced The number of real estate agents in North Dakota. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones

Journal of Quirky Real Estate Research

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Google searches for 'zombies' and The number of real estate agents in North Dakota. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title an alliteration.

Your research team used data from Google Trends and Bureau of Larbor Statistics to assess this nagging question. You found a correlation coefficient of 0.9361148 and p < 0.01 for 2004 to 2022.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones

[[ABSTRACT]]
This paper investigates the unexpected and seemingly unrelated connection between Google searches for 'zombies' and the number of real estate agents in the charming and enigmatic state of North Dakota. Utilizing data from Google Trends and the Bureau of Labor Statistics, our research team sought to shed light on this peculiar correlation. Surprisingly, our analysis revealed a remarkable correlation coefficient of 0.9361148 and a statistically significant p-value of less than 0.01 for the period spanning from 2004 to 2022. Our findings not only raise eyebrows but also prompt contemplation on the whimsical interplay between an apocalyptic pop culture phenomenon and the ever-evolving real estate market landscape. We propose that this unexpected correlation may reveal a deeper, yet to be unearthed, relationship between the fascination with the undead and the thriving real estate industry in the captivating realm of North Dakota. This zany juxtaposition invites further exploration and elicits a playful nod to the peculiar, unforeseen connections that underlie the tapestry of socio-economic phenomena.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Google searches for 'zombies' and The number of real estate agents in North Dakota. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones

[[ABSTRACT]]
This paper investigates the unexpected and seemingly unrelated connection between Google searches for 'zombies' and the number of real estate agents in the charming and enigmatic state of North Dakota. Utilizing data from Google Trends and the Bureau of Labor Statistics, our research team sought to shed light on this peculiar correlation. Surprisingly, our analysis revealed a remarkable correlation coefficient of 0.9361148 and a statistically significant p-value of less than 0.01 for the period spanning from 2004 to 2022. Our findings not only raise eyebrows but also prompt contemplation on the whimsical interplay between an apocalyptic pop culture phenomenon and the ever-evolving real estate market landscape. We propose that this unexpected correlation may reveal a deeper, yet to be unearthed, relationship between the fascination with the undead and the thriving real estate industry in the captivating realm of North Dakota. This zany juxtaposition invites further exploration and elicits a playful nod to the peculiar, unforeseen connections that underlie the tapestry of socio-economic phenomena.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
**[[INTRODUCTION]]**

The enigmatic allure of zombies has long captured the fascination of popular culture, from classic horror films to contemporary television series. Meanwhile, the real estate market embodies the ever-changing landscape of economic activity, characterized by its dynamism and adaptability to external forces. Our study delves into the whimsical intersection of these seemingly unrelated phenomena, aiming to unravel the unexpected correlation between Google searches for 'zombies' and the number of real estate agents in the picturesque state of North Dakota.

As researchers, we are no strangers to the undead – data that is. We sought to unearth potential relationships between these peculiar variables, embarking on a statistical journey that more closely resembles navigating a zombie-infested labyrinth than perusing traditional socio-economic correlations. The eerie glow of statistical significance beckons us forth, as we venture into the uncharted territory of unconventional research connections.

Amidst the sea of mundane statistical analyses, we found ourselves diving head-first into the abyss of zombified Google search data, armed with robust statistical tools and a healthy dose of skepticism. Much like intrepid explorers in search of a mythical treasure, we valiantly charted a course through the murky waters of data analysis, undeterred by the undead distractions that threatened to feast on our precious p-values.

Our research is not merely a quirky exercise in statistical exploration, but a testament to the audacious spirit of inquiry that drives the pursuit of knowledge. As we unveil the enthralling relationship between 'zombie' searches and real estate agents, we invite readers to embark on this whimsical journey with an open mind and a readiness to embrace the unexpected – much like a real estate agent navigating a property in post-apocalyptic fiction.

In the pages that follow, we dissect the bizarre linkage between the undead and the real estate workforce, shedding light on a correlation that defies conventional wisdom and injects a dose of levity into the solemn realm of academic inquiry. Our findings not only prompt contemplation but also establish a foundation for further exploration into the intricate tapestry of socio-economic peculiarities. Join us as we navigate the zany zombieland of statistics and real estate, shedding light on the unexpected correlations that lurk beneath the surface.


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 Google searches for 'zombies' and The number of real estate agents in North Dakota. 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]]
Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones

[[ABSTRACT]]
This paper investigates the unexpected and seemingly unrelated connection between Google searches for 'zombies' and the number of real estate agents in the charming and enigmatic state of North Dakota. Utilizing data from Google Trends and the Bureau of Labor Statistics, our research team sought to shed light on this peculiar correlation. Surprisingly, our analysis revealed a remarkable correlation coefficient of 0.9361148 and a statistically significant p-value of less than 0.01 for the period spanning from 2004 to 2022. Our findings not only raise eyebrows but also prompt contemplation on the whimsical interplay between an apocalyptic pop culture phenomenon and the ever-evolving real estate market landscape. We propose that this unexpected correlation may reveal a deeper, yet to be unearthed, relationship between the fascination with the undead and the thriving real estate industry in the captivating realm of North Dakota. This zany juxtaposition invites further exploration and elicits a playful nod to the peculiar, unforeseen connections that underlie the tapestry of socio-economic phenomena.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The enigmatic allure of zombies has long captured the fascination of popular culture, from classic horror films to contemporary television series. Meanwhile, the real estate market embodies the ever-changing landscape of economic activity, characterized by its dynamism and adaptability to external forces. Our study delves into the whimsical intersection of these seemingly unrelated phenomena, aiming to unravel the unexpected correlation between Google searches for 'zombies' and the number of real estate agents in the picturesque state of North Dakota.
As researchers, we are no strangers to the undead – data that is. We sought to unearth potential relationships between these peculiar variables, embarking on a statistical journey that more closely resembles navigating a zombie-infested labyrinth than perusing traditional socio-economic correlations. The eerie glow of statistical significance beckons us forth, as we venture into the uncharted territory of unconventional research connections.
Amidst the sea of mundane statistical analyses, we found ourselves diving head-first into the abyss of zombified Google search data, armed with robust statistical tools and a healthy dose of skepticism. Much like intrepid explorers in search of a mythical treasure, we valiantly charted a course through the murky waters of data analysis, undeterred by the undead distractions that threatened to feast on our precious p-values.
Our research is not merely a quirky exercise in statistical exploration, but a testament to the audacious spirit of inquiry that drives the pursuit of knowledge. As we unveil the enthralling relationship between 'zombie' searches and real estate agents, we invite readers to embark on this whimsical journey with an open mind and a readiness to embrace the unexpected – much like a real estate agent navigating a property in post-apocalyptic fiction.
In the pages that follow, we dissect the bizarre linkage between the undead and the real estate workforce, shedding light on a correlation that defies conventional wisdom and injects a dose of levity into the solemn realm of academic inquiry. Our findings not only prompt contemplation but also establish a foundation for further exploration into the intricate tapestry of socio-economic peculiarities. Join us as we navigate the zany zombieland of statistics and real estate, shedding light on the unexpected correlations that lurk beneath the surface.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The unexpected correlation between Google searches for 'zombies' and the number of real estate agents in North Dakota has prompted a flurry of academic and non-academic inquiries alike. Smith et al. (2015) conducted a comprehensive analysis of internet search patterns and their potential implications for niche industries. Their study, while not directly addressing zombies or real estate, laid the groundwork for understanding the enigmatic relationship between seemingly unrelated variables in the digital age.

In another study, Doe (2018) delved into the sociocultural impact of zombie narratives and their influence on consumer behavior. While not specifically focused on real estate agents, Doe’s work provides intriguing insights into the psychological underpinnings of fascination with the undead, insights that may have implications for the real estate industry.

Adding a twist to the discourse, Jones (2020) explored the potential parallels between survival strategies in a zombie apocalypse and the competitive landscape of real estate agent markets. Though the study was framed as a fictional narrative, it offers curious parallels that might shed light on the unexpected affinity between zombie-related searches and real estate agent numbers in North Dakota.

Turning to non-academic literature, "The Zombie Survival Guide: Complete Protection from the Living Dead" by Max Brooks presents a comprehensive – albeit tongue-in-cheek – examination of survival tactics in a hypothetical zombie outbreak, inspiring tangential contemplations on the preparedness of real estate agents in facing unforeseen challenges.

Furthermore, the renowned fiction series "The Walking Dead" by Robert Kirkman weaves an intricate narrative of survival in a post-apocalyptic world, offering a fictitious yet thought-provoking portrayal of how societal dynamics – including the real estate industry – might evolve in the wake of a zombie uprising.

Lastly, the board game "Zombies!!!," a light-hearted foray into apocalyptic scenarios, sparks amusement and curiosity around the intersection of survival and strategic decision-making, an allegory that tickles the boundaries of our research inquiry and teases the subtleties of real estate agent proliferation in North Dakota.

As we traverse the realm of literature pertaining to zombies and real estate, we find ourselves oscillating between scholarly rigor and the whimsical allure of fictional narratives, a journey that mirrors the kaleidoscopic nature of our research pursuit. With these diverse sources in mind, we commence our exploration of the uncharted, curious correlation that underpins the enthralling interplay between 'zombies' and the real estate workforce in North Dakota.


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 Google searches for 'zombies' and The number of real estate agents in North Dakota. 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 Google Trends and Bureau of Larbor Statistics . You used data from 2004 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]]
Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones

[[ABSTRACT]]
This paper investigates the unexpected and seemingly unrelated connection between Google searches for 'zombies' and the number of real estate agents in the charming and enigmatic state of North Dakota. Utilizing data from Google Trends and the Bureau of Labor Statistics, our research team sought to shed light on this peculiar correlation. Surprisingly, our analysis revealed a remarkable correlation coefficient of 0.9361148 and a statistically significant p-value of less than 0.01 for the period spanning from 2004 to 2022. Our findings not only raise eyebrows but also prompt contemplation on the whimsical interplay between an apocalyptic pop culture phenomenon and the ever-evolving real estate market landscape. We propose that this unexpected correlation may reveal a deeper, yet to be unearthed, relationship between the fascination with the undead and the thriving real estate industry in the captivating realm of North Dakota. This zany juxtaposition invites further exploration and elicits a playful nod to the peculiar, unforeseen connections that underlie the tapestry of socio-economic phenomena.

[[INTRODUCTION]]
The enigmatic allure of zombies has long captured the fascination of popular culture, from classic horror films to contemporary television series. Meanwhile, the real estate market embodies the ever-changing landscape of economic activity, characterized by its dynamism and adaptability to external forces. Our study delves into the whimsical intersection of these seemingly unrelated phenomena, aiming to unravel the unexpected correlation between Google searches for 'zombies' and the number of real estate agents in the picturesque state of North Dakota.
As researchers, we are no strangers to the undead – data that is. We sought to unearth potential relationships between these peculiar variables, embarking on a statistical journey that more closely resembles navigating a zombie-infested labyrinth than perusing traditional socio-economic correlations. The eerie glow of statistical significance beckons us forth, as we venture into the uncharted territory of unconventional research connections.
Amidst the sea of mundane statistical analyses, we found ourselves diving head-first into the abyss of zombified Google search data, armed with robust statistical tools and a healthy dose of skepticism. Much like intrepid explorers in search of a mythical treasure, we valiantly charted a course through the murky waters of data analysis, undeterred by the undead distractions that threatened to feast on our precious p-values.
Our research is not merely a quirky exercise in statistical exploration, but a testament to the audacious spirit of inquiry that drives the pursuit of knowledge. As we unveil the enthralling relationship between 'zombie' searches and real estate agents, we invite readers to embark on this whimsical journey with an open mind and a readiness to embrace the unexpected – much like a real estate agent navigating a property in post-apocalyptic fiction.
In the pages that follow, we dissect the bizarre linkage between the undead and the real estate workforce, shedding light on a correlation that defies conventional wisdom and injects a dose of levity into the solemn realm of academic inquiry. Our findings not only prompt contemplation but also establish a foundation for further exploration into the intricate tapestry of socio-economic peculiarities. Join us as we navigate the zany zombieland of statistics and real estate, shedding light on the unexpected correlations that lurk beneath the surface.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To embark on our peculiar quest to unravel the connection between the mesmerizing allure of zombies and the bustling world of real estate, we devised a labyrinthine methodology befitting of the enigmatic nature of our research question.

Data Collection:
We scoured the digital realm, akin to intrepid explorers searching for buried treasure, for Google search trends related to 'zombies' from the year 2004 to 2022. Our team diligently combed through the cryptic corridors of Google Trends, capturing the ebb and flow of zombie-related searches with meticulous precision, despite the occasional distracting urge to stock up on survival gear for an impending zombie apocalypse.

Simultaneously, our pursuit led us to the Bureau of Labor Statistics, where we sought to identify the number of real estate agents in the captivating and often underrated land of North Dakota. Like skilled cartographers mapping uncharted territories, we navigated through the dense statistical underbrush to capture the essence of the real estate workforce, avoiding the occasional statistical zombie lurking in the shadows of data deficiencies.

Data Analysis:
Armed with this enigmatic amalgamation of data, we harnessed the formidable power of statistical tools, casting an analytical gaze through the misty veil of probability and correlation. We engaged in rigorous statistical analyses, akin to navigating a labyrinth of undead distractions, to discern the underlying relationship between the rise of zombie searches and the flourishing presence of real estate agents. While we did not encounter any actual zombies during this process, we did fend off the occasional statistical outlier that lurked in the shadows, threatening to disrupt the harmony of our findings.

Correlation Coefficient and Significance Testing:
With bated breath and an unwavering resolve, we calculated the correlation coefficient between 'zombie' searches and the number of real estate agents, unveiling a remarkable coefficient of 0.9361148. As we confronted this unexpected revelation, we turned to the hallowed ground of hypothesis testing, where our p-value of less than 0.01 resolutely asserted the statistical significance of our findings. This discovery not only raised our eyebrows but also prompted us to consider the whimsical interplay between these two seemingly unrelated phenomena, much like a real estate agent pondering the unexpected allure of a property in a zombie-infested world.

Qualitative Analysis:
Amidst the quantitative bedlam, we delved into the realm of qualitative analysis, not with scalpels and test tubes, but with a discerning eye for the underlying narratives and peculiarities that underscored the surge of zombie searches and the real estate landscape. We sought to capture the evocative essence of this indelible connection, much like a master storyteller weaving a tale of unexpected correlations and uncanny revelations.

In summary, our methodology embraced the labyrinthine twists and turns of the unconventional, revealing a correlation that defies conventional wisdom and reinvigorates the scholarly pursuit with a dose of levity 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 Google searches for 'zombies' and The number of real estate agents in North Dakota. 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 Google Trends and Bureau of Larbor Statistics .

For the time period 2004 to 2022, you found a correlation 0.9361148, r-squared of 0.8763109, 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]]
Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones

[[ABSTRACT]]
This paper investigates the unexpected and seemingly unrelated connection between Google searches for 'zombies' and the number of real estate agents in the charming and enigmatic state of North Dakota. Utilizing data from Google Trends and the Bureau of Labor Statistics, our research team sought to shed light on this peculiar correlation. Surprisingly, our analysis revealed a remarkable correlation coefficient of 0.9361148 and a statistically significant p-value of less than 0.01 for the period spanning from 2004 to 2022. Our findings not only raise eyebrows but also prompt contemplation on the whimsical interplay between an apocalyptic pop culture phenomenon and the ever-evolving real estate market landscape. We propose that this unexpected correlation may reveal a deeper, yet to be unearthed, relationship between the fascination with the undead and the thriving real estate industry in the captivating realm of North Dakota. This zany juxtaposition invites further exploration and elicits a playful nod to the peculiar, unforeseen connections that underlie the tapestry of socio-economic phenomena.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The enigmatic allure of zombies has long captured the fascination of popular culture, from classic horror films to contemporary television series. Meanwhile, the real estate market embodies the ever-changing landscape of economic activity, characterized by its dynamism and adaptability to external forces. Our study delves into the whimsical intersection of these seemingly unrelated phenomena, aiming to unravel the unexpected correlation between Google searches for 'zombies' and the number of real estate agents in the picturesque state of North Dakota.
As researchers, we are no strangers to the undead – data that is. We sought to unearth potential relationships between these peculiar variables, embarking on a statistical journey that more closely resembles navigating a zombie-infested labyrinth than perusing traditional socio-economic correlations. The eerie glow of statistical significance beckons us forth, as we venture into the uncharted territory of unconventional research connections.
Amidst the sea of mundane statistical analyses, we found ourselves diving head-first into the abyss of zombified Google search data, armed with robust statistical tools and a healthy dose of skepticism. Much like intrepid explorers in search of a mythical treasure, we valiantly charted a course through the murky waters of data analysis, undeterred by the undead distractions that threatened to feast on our precious p-values.
Our research is not merely a quirky exercise in statistical exploration, but a testament to the audacious spirit of inquiry that drives the pursuit of knowledge. As we unveil the enthralling relationship between 'zombie' searches and real estate agents, we invite readers to embark on this whimsical journey with an open mind and a readiness to embrace the unexpected – much like a real estate agent navigating a property in post-apocalyptic fiction.
In the pages that follow, we dissect the bizarre linkage between the undead and the real estate workforce, shedding light on a correlation that defies conventional wisdom and injects a dose of levity into the solemn realm of academic inquiry. Our findings not only prompt contemplation but also establish a foundation for further exploration into the intricate tapestry of socio-economic peculiarities. Join us as we navigate the zany zombieland of statistics and real estate, shedding light on the unexpected correlations that lurk beneath the surface.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data revealed a remarkably strong correlation between Google searches for 'zombies' and the number of real estate agents in North Dakota, with a correlation coefficient of 0.9361148. This finding indicates a robust relationship between these seemingly disparate variables, raising questions that are as compelling as they are perplexing.

The strength of the correlation is further supported by an r-squared value of 0.8763109, signifying that approximately 87.63% of the variability in the number of real estate agents can be explained by variations in 'zombie' searches. It seems that the allure of the undead exerts a significant influence on the dynamics of the real estate market in North Dakota, a revelation that undoubtedly adds a touch of whimsy to the field of socio-economic research.

Furthermore, the p-value of less than 0.01 provides compelling evidence that this correlation is not a mere coincidental fluke. It seems that the relationship between 'zombie' searches and the real estate industry is as real as the dystopian scenarios depicted in zombie fiction. We must resist the temptation to dismiss this finding as a statistical anomaly and instead embrace the peculiar charm of this unexpected correlation.

The scatterplot (Fig. 1) visually depicts the strong positive relationship between Google searches for 'zombies' and the number of real estate agents in North Dakota. Each data point in the plot serves as a testament to the uncanny dance between the undead and the domain of property transactions. It appears that while zombies may not be interested in buying real estate themselves, their spectral presence has a palpable impact on the real estate workforce in this unique corner of the world.

In light of these findings, we are left to marvel at the inexplicable harmony between the macabre fascination with zombies and the intricate dynamics of the real estate market. It is clear that our research has unearthed a correlation that transcends common expectations and adds a touch of wit to the realm of empirical inquiry. This unexpected link between 'zombies' and real estate agents not only invites further exploration but also serves as a reminder that the tapestry of socio-economic phenomena is sprinkled with delightful and enigmatic connections waiting to be discovered.


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 Google searches for 'zombies' and The number of real estate agents in North Dakota. 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]]
Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones

[[ABSTRACT]]
This paper investigates the unexpected and seemingly unrelated connection between Google searches for 'zombies' and the number of real estate agents in the charming and enigmatic state of North Dakota. Utilizing data from Google Trends and the Bureau of Labor Statistics, our research team sought to shed light on this peculiar correlation. Surprisingly, our analysis revealed a remarkable correlation coefficient of 0.9361148 and a statistically significant p-value of less than 0.01 for the period spanning from 2004 to 2022. Our findings not only raise eyebrows but also prompt contemplation on the whimsical interplay between an apocalyptic pop culture phenomenon and the ever-evolving real estate market landscape. We propose that this unexpected correlation may reveal a deeper, yet to be unearthed, relationship between the fascination with the undead and the thriving real estate industry in the captivating realm of North Dakota. This zany juxtaposition invites further exploration and elicits a playful nod to the peculiar, unforeseen connections that underlie the tapestry of socio-economic phenomena.

[[LITERATURE REVIEW]]
The unexpected correlation between Google searches for 'zombies' and the number of real estate agents in North Dakota has prompted a flurry of academic and non-academic inquiries alike. Smith et al. (2015) conducted a comprehensive analysis of internet search patterns and their potential implications for niche industries. Their study, while not directly addressing zombies or real estate, laid the groundwork for understanding the enigmatic relationship between seemingly unrelated variables in the digital age.
In another study, Doe (2018) delved into the sociocultural impact of zombie narratives and their influence on consumer behavior. While not specifically focused on real estate agents, Doe’s work provides intriguing insights into the psychological underpinnings of fascination with the undead, insights that may have implications for the real estate industry.
Adding a twist to the discourse, Jones (2020) explored the potential parallels between survival strategies in a zombie apocalypse and the competitive landscape of real estate agent markets. Though the study was framed as a fictional narrative, it offers curious parallels that might shed light on the unexpected affinity between zombie-related searches and real estate agent numbers in North Dakota.
Turning to non-academic literature, "The Zombie Survival Guide: Complete Protection from the Living Dead" by Max Brooks presents a comprehensive – albeit tongue-in-cheek – examination of survival tactics in a hypothetical zombie outbreak, inspiring tangential contemplations on the preparedness of real estate agents in facing unforeseen challenges.
Furthermore, the renowned fiction series "The Walking Dead" by Robert Kirkman weaves an intricate narrative of survival in a post-apocalyptic world, offering a fictitious yet thought-provoking portrayal of how societal dynamics – including the real estate industry – might evolve in the wake of a zombie uprising.
Lastly, the board game "Zombies!!!," a light-hearted foray into apocalyptic scenarios, sparks amusement and curiosity around the intersection of survival and strategic decision-making, an allegory that tickles the boundaries of our research inquiry and teases the subtleties of real estate agent proliferation in North Dakota.
As we traverse the realm of literature pertaining to zombies and real estate, we find ourselves oscillating between scholarly rigor and the whimsical allure of fictional narratives, a journey that mirrors the kaleidoscopic nature of our research pursuit. With these diverse sources in mind, we commence our exploration of the uncharted, curious correlation that underpins the enthralling interplay between 'zombies' and the real estate workforce in North Dakota.

[[RESULTS]]
The analysis of the data revealed a remarkably strong correlation between Google searches for 'zombies' and the number of real estate agents in North Dakota, with a correlation coefficient of 0.9361148. This finding indicates a robust relationship between these seemingly disparate variables, raising questions that are as compelling as they are perplexing.
The strength of the correlation is further supported by an r-squared value of 0.8763109, signifying that approximately 87.63% of the variability in the number of real estate agents can be explained by variations in 'zombie' searches. It seems that the allure of the undead exerts a significant influence on the dynamics of the real estate market in North Dakota, a revelation that undoubtedly adds a touch of whimsy to the field of socio-economic research.
Furthermore, the p-value of less than 0.01 provides compelling evidence that this correlation is not a mere coincidental fluke. It seems that the relationship between 'zombie' searches and the real estate industry is as real as the dystopian scenarios depicted in zombie fiction. We must resist the temptation to dismiss this finding as a statistical anomaly and instead embrace the peculiar charm of this unexpected correlation.
The scatterplot (Fig. 1) visually depicts the strong positive relationship between Google searches for 'zombies' and the number of real estate agents in North Dakota. Each data point in the plot serves as a testament to the uncanny dance between the undead and the domain of property transactions. It appears that while zombies may not be interested in buying real estate themselves, their spectral presence has a palpable impact on the real estate workforce in this unique corner of the world.
In light of these findings, we are left to marvel at the inexplicable harmony between the macabre fascination with zombies and the intricate dynamics of the real estate market. It is clear that our research has unearthed a correlation that transcends common expectations and adds a touch of wit to the realm of empirical inquiry. This unexpected link between 'zombies' and real estate agents not only invites further exploration but also serves as a reminder that the tapestry of socio-economic phenomena is sprinkled with delightful and enigmatic connections waiting to be discovered.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our investigation into the peculiar correlation between Google searches for 'zombies' and the number of real estate agents in North Dakota has unveiled unexpected revelations that parallel the captivating whimsy found in the satirical musings of Max Brooks and the survival tactics of "The Walking Dead" series. The remarkably robust correlation coefficient of 0.9361148 appears to validate the seemingly zany hypothesis that an infatuation with the undead intertwines with the ebbs and flows of the real estate market.

These findings echo the prior work of Smith et al. (2015), who, while not directly examining zombies or real estate, hinted at the looming enigma of seemingly unrelated variables in the digital age. Additionally, the sociocultural impact explored by Doe (2018) and the survival strategies in a zombie apocalypse expounded upon by Jones (2020) elicit contemplation on the profound yet comical interplay between human psychology and the socio-economic landscape, reminiscent of a zombie-themed board game night.

The substantial r-squared value of 0.8763109 illuminates the extent to which variations in 'zombie' searches explain the flux in the number of real estate agents, akin to a zombie horde's inexplicable influence over its environment. The minuscule p-value further solidifies the authenticity of this connection, emphasizing that the allure of the undead is as real as the statistical significance that underpins it. The visual representation of our findings, the scatterplot (Fig. 1), serves as a light-hearted yet compelling testament to the spectral dance between 'zombies' and real estate professionals.

In the realm of socio-economic inquiry, our research unearths a reminder that the tapestry of empirical investigation is adorned with puzzles that enigmatically weave together the serious and the lighthearted. This correlation between 'zombies' and real estate agents invites us to revel in the delightful unpredictability of statistical relationships, injecting a playful twist into the often stoic world of data analytics. As we continue our pursuit of comically curious correlations, let us not lose sight of the potential for whimsy and lightheartedness in juxtaposing seemingly unrelated phenomena.


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 Google searches for 'zombies' and The number of real estate agents in North Dakota. 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]]
Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones

[[ABSTRACT]]
This paper investigates the unexpected and seemingly unrelated connection between Google searches for 'zombies' and the number of real estate agents in the charming and enigmatic state of North Dakota. Utilizing data from Google Trends and the Bureau of Labor Statistics, our research team sought to shed light on this peculiar correlation. Surprisingly, our analysis revealed a remarkable correlation coefficient of 0.9361148 and a statistically significant p-value of less than 0.01 for the period spanning from 2004 to 2022. Our findings not only raise eyebrows but also prompt contemplation on the whimsical interplay between an apocalyptic pop culture phenomenon and the ever-evolving real estate market landscape. We propose that this unexpected correlation may reveal a deeper, yet to be unearthed, relationship between the fascination with the undead and the thriving real estate industry in the captivating realm of North Dakota. This zany juxtaposition invites further exploration and elicits a playful nod to the peculiar, unforeseen connections that underlie the tapestry of socio-economic phenomena.

[[INTRDUCTION]]
The enigmatic allure of zombies has long captured the fascination of popular culture, from classic horror films to contemporary television series. Meanwhile, the real estate market embodies the ever-changing landscape of economic activity, characterized by its dynamism and adaptability to external forces. Our study delves into the whimsical intersection of these seemingly unrelated phenomena, aiming to unravel the unexpected correlation between Google searches for 'zombies' and the number of real estate agents in the picturesque state of North Dakota.
As researchers, we are no strangers to the undead – data that is. We sought to unearth potential relationships between these peculiar variables, embarking on a statistical journey that more closely resembles navigating a zombie-infested labyrinth than perusing traditional socio-economic correlations. The eerie glow of statistical significance beckons us forth, as we venture into the uncharted territory of unconventional research connections.
Amidst the sea of mundane statistical analyses, we found ourselves diving head-first into the abyss of zombified Google search data, armed with robust statistical tools and a healthy dose of skepticism. Much like intrepid explorers in search of a mythical treasure, we valiantly charted a course through the murky waters of data analysis, undeterred by the undead distractions that threatened to feast on our precious p-values.
Our research is not merely a quirky exercise in statistical exploration, but a testament to the audacious spirit of inquiry that drives the pursuit of knowledge. As we unveil the enthralling relationship between 'zombie' searches and real estate agents, we invite readers to embark on this whimsical journey with an open mind and a readiness to embrace the unexpected – much like a real estate agent navigating a property in post-apocalyptic fiction.
In the pages that follow, we dissect the bizarre linkage between the undead and the real estate workforce, shedding light on a correlation that defies conventional wisdom and injects a dose of levity into the solemn realm of academic inquiry. Our findings not only prompt contemplation but also establish a foundation for further exploration into the intricate tapestry of socio-economic peculiarities. Join us as we navigate the zany zombieland of statistics and real estate, shedding light on the unexpected correlations that lurk beneath the surface.

[[RESULTS]]
The analysis of the data revealed a remarkably strong correlation between Google searches for 'zombies' and the number of real estate agents in North Dakota, with a correlation coefficient of 0.9361148. This finding indicates a robust relationship between these seemingly disparate variables, raising questions that are as compelling as they are perplexing.
The strength of the correlation is further supported by an r-squared value of 0.8763109, signifying that approximately 87.63% of the variability in the number of real estate agents can be explained by variations in 'zombie' searches. It seems that the allure of the undead exerts a significant influence on the dynamics of the real estate market in North Dakota, a revelation that undoubtedly adds a touch of whimsy to the field of socio-economic research.
Furthermore, the p-value of less than 0.01 provides compelling evidence that this correlation is not a mere coincidental fluke. It seems that the relationship between 'zombie' searches and the real estate industry is as real as the dystopian scenarios depicted in zombie fiction. We must resist the temptation to dismiss this finding as a statistical anomaly and instead embrace the peculiar charm of this unexpected correlation.
The scatterplot (Fig. 1) visually depicts the strong positive relationship between Google searches for 'zombies' and the number of real estate agents in North Dakota. Each data point in the plot serves as a testament to the uncanny dance between the undead and the domain of property transactions. It appears that while zombies may not be interested in buying real estate themselves, their spectral presence has a palpable impact on the real estate workforce in this unique corner of the world.
In light of these findings, we are left to marvel at the inexplicable harmony between the macabre fascination with zombies and the intricate dynamics of the real estate market. It is clear that our research has unearthed a correlation that transcends common expectations and adds a touch of wit to the realm of empirical inquiry. This unexpected link between 'zombies' and real estate agents not only invites further exploration but also serves as a reminder that the tapestry of socio-economic phenomena is sprinkled with delightful and enigmatic connections waiting to be discovered.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the enthralling linkage between Google searches for 'zombies' and the number of real estate agents in North Dakota has unfurled a whimsical narrative that dances between statistical significance and surreal peculiarity. The striking correlation coefficient of 0.9361148 and the resolute p-value of less than 0.01 have thrust this peculiar relationship into the spotlight, akin to a zombie horde stumbling into a real estate open house with ghoulish enthusiasm.

The robust r-squared value of 0.8763109 further underscores the profound influence of 'zombie' searches on the ebb and flow of the real estate workforce, evoking visions of undead realtors brokering deals in a post-apocalyptic market. The scatterplot, with its eerie data points, serves as a testament to the harmonious albeit unorthodox waltz between the spectral allure of zombies and the bustling world of property transactions.

As we bid adieu to this zany exploration, we cannot help but revel in the wondrous absurdity of the socio-economic landscape. The tangible impact of 'zombie' searches on the real estate industry not only challenges conventional wisdom but also embodies the delightful caprice that infuses the tapestry of empirical inquiry.

In light of these findings, we assert that no further research is needed in this area. After all, we have already unraveled the mystery of the undead's influence on North Dakota's real estate market, leaving us with a tale as amusing as it is enlightening. It seems that in the wild realm of statistical exploration, even the most unconventional correlations can yield astonishing revelations – much like stumbling upon a hidden treasure in a forsaken cemetery.

Journeying through the zany zombieland of statistics has rewarded us with a deeper appreciation for the whimsical interplay of inexplicable relationships in our intricate socio-economic world. As we lay this peculiar topic to rest, we do so with the knowledge that our research has peered into the quirkier corners of empirical inquiry, treading where few venture but where the undead may roam.


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 Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Real Estate Research


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 Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones. Respond only with the name of a fictional organization.

ChatGPT:

The International Society for Paranormal and Supernatural Studies


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 Zombie Zeal and Real Estate: A Zany Zombieland Zest for Zombie Searches and Zesty Zillow Zones with an abstract of This paper investigates the unexpected and seemingly unrelated connection between Google searches for 'zombies' and the number of real estate agents in the charming and enigmatic state of North Dakota. Utilizing data from Google Trends and the Bureau of Labor Statistics, our research team sought to shed light on this peculiar correlation. Surprisingly, our analysis revealed a remarkable correlation coefficient of 0.9361148 and a statistically significant p-value of less than 0.01 for the period spanning from 2004 to 2022. Our findings not only raise eyebrows but also prompt contemplation on the whimsical interplay between an apocalyptic pop culture phenomenon and the ever-evolving real estate market landscape. We propose that this unexpected correlation may reveal a deeper, yet to be unearthed, relationship between the fascination with the undead and the thriving real estate industry in the captivating realm of North Dakota. This zany juxtaposition invites further exploration and elicits a playful nod to the peculiar, unforeseen connections that underlie the tapestry of socio-economic phenomena.

ChatGPT:

"zombies and real estate," "zombie searches," "real estate agents North Dakota," "Google Trends," "Bureau of Labor Statistics," "correlation coefficient," "p-value," "apocalyptic pop culture phenomenon," "real estate market landscape," "undead fascination," "North Dakota real estate," "socio-economic phenomena"

*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

Google searches for 'zombies'
Detailed data title: Relative volume of Google searches for 'zombies' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'zombies'

The number of real estate agents in North Dakota
Detailed data title: BLS estimate of real estate sales agents in North Dakota
Source: Bureau of Larbor Statistics
See what else correlates with The number of real estate agents in North Dakota

Correlation r = 0.9361148 (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 = 0.8763109 (Coefficient of determination)
This means 87.6% of the change in the one variable (i.e., The number of real estate agents in North Dakota) is predictable based on the change in the other (i.e., Google searches for 'zombies') over the 19 years from 2004 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.9E-9. 0.0000000038962358095387400000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.94 in 3.9E-7% of random cases. Said differently, if you correlated 256,657,977 random variables You don't actually need 256 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 18 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 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.

[ 0.84, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
2004200520062007200820092010201120122013201420152016201720182019202020212022
Google searches for 'zombies' (Rel. search volume)3.666674.083334.083335.083336.0833317.916736.7559.416767.583383.255948.7539.083328.252417.7523.66671919.5
The number of real estate agents in North Dakota (Real Estate Sales Agents)140120160160190260330580630630460480440350260240260230460




Why this works

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

    For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

    (This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
    They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([3.66667,4.08333,4.08333,5.08333,6.08333,17.9167,36.75,59.4167,67.5833,83.25,59,48.75,39.0833,28.25,24,17.75,23.6667,19,19.5,])
array_2 = np.array([140,120,160,160,190,260,330,580,630,630,460,480,440,350,260,240,260,230,460,])
array_1_name = "Google searches for 'zombies'"
array_2_name = "The number of real estate agents in North Dakota"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!


Correlation ID: 1070 · Black Variable ID: 1380 · Red Variable ID: 12662
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0