about · email me · subscribe
Spurious correlation #3,798 · 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 athletes and sports competitors in Florida and the second variable is Google searches for 'zombies'.  The chart goes from 2004 to 2022, and the two variables track closely in value over that time. Small Image

AI explanation

More athletes and sports competitors in Florida means more people to outrun zombies when the inevitable zombie apocalypse hits. So, the increase in interest in zombies could be a subconscious preparation for an undead marathon in the Sunshine State. Remember, cardio is key to survival!

Model: dalle-3
Prompt: Prompt: [ A photo-realistic image ] Set on a radiant Florida beach, capture a vibrant scene where numerous athletes and sports competitors are assembled in preparation for a marathon. The beach is bathed in golden sunlight, with the runners stretching and warming up against a backdrop of gently rolling waves and clear blue skies. An unmistakable aura of excitement and anticipation envelops the scene as people gather to witness the event. Notably, amidst the poised competitors and spectators, depict a noticeable surge of individuals using their smartphones to search for 'zombies', their expressions reflecting a mix of puzzlement and concern. As they engage with their devices, subtly convey the presence of a prominent banner in the background, proudly showcasing the growing number of athletes and sports competitors in Florida. Capture the convergence of these intriguing elements within a simple and captivating composition. 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 athletes and sports competitors in Florida and Google searches for 'zombies'. 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: Art nouveau Art nouveau A photo-realistic image Glitch art Cyber folk
ChatGPT: A photo-realistic image

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 athletes and sports competitors in Florida and Google searches for 'zombies', in the following situation: As the number of athletes and sports competitors in Florida increases, so does the demand for brains! This leads to more people searching for zombies online as they seek to understand the undead's obsession with grey matter. It's a real "dead-end" situation for these athletes, but at least they're "running" with it!. Keep the description simple.
ChatGPT: On a sunny Florida beach, a large group of athletes and sports competitors gather for a marathon. As they stretch and prepare for the race, the beachgoers notice a sudden spike in Google searches for 'zombies'. On their phones, people are frantically typing 'zombies' and looking puzzled as they try to understand the sudden interest. Amidst this activity, a banner in the background proudly showcases the growing number of athletes and sports competitors in Florida.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A photo-realistic image ] and depicting this scene: On a sunny Florida beach, a large group of athletes and sports competitors gather for a marathon. As they stretch and prepare for the race, the beachgoers notice a sudden spike in Google searches for 'zombies'. On their phones, people are frantically typing 'zombies' and looking puzzled as they try to understand the sudden interest. Amidst this activity, a banner in the background proudly showcases the growing number of athletes and sports competitors in Florida. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: [ A photo-realistic image ] Set on a radiant Florida beach, capture a vibrant scene where numerous athletes and sports competitors are assembled in preparation for a marathon. The beach is bathed in golden sunlight, with the runners stretching and warming up against a backdrop of gently rolling waves and clear blue skies. An unmistakable aura of excitement and anticipation envelops the scene as people gather to witness the event. Notably, amidst the poised competitors and spectators, depict a noticeable surge of individuals using their smartphones to search for 'zombies', their expressions reflecting a mix of puzzlement and concern. As they engage with their devices, subtly convey the presence of a prominent banner in the background, proudly showcasing the growing number of athletes and sports competitors in Florida. Capture the convergence of these intriguing elements within a simple and captivating composition.

*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 The number of athletes and sports competitors in Florida positively influenced zombies (Google searches for 'zombies').

AI academic paper

(Because p < 0.01)
Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida

The Journal of Mysterious Sports Trends

Jan 2024
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 researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between The number of athletes and sports competitors in Florida and Google searches for 'zombies'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Include a pun in the title.

Your research team used data from Bureau of Larbor Statistics and Google Trends to assess this nagging question. You found a correlation coefficient of 0.8707066 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]]
"Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida"

[[ABSTRACT]]
We're breaking new ground in the world of quirky correlations as we delve into the relationship between the population of athletes and sports competitors in the Sunshine State and the frequency of Google searches for 'zombies'. It's no joke - we stumbled upon this curious connection when analyzing data from the Bureau of Labor Statistics and Google Trends. Armed with a correlation coefficient of 0.8707066 and a p-value of less than 0.01 for the time span from 2004 to 2022, we are confident that our findings reveal something truly captivating.

In our tongue-in-cheek investigation, we discovered that as the number of athletes and sports competitors in Florida rose, so did the searches for 'zombies' on Google. It seems like the residents of Florida might not only be interested in winning medals, but also in preparing for a potential zombie apocalypse! It's quite the paradox - they take fitness seriously, yet they also seem to have an eye on the undead. Maybe they just want to out-run the zombie crowd at the next marathon!

Our research not only sheds light on this offbeat relationship between athletic prowess and an unquenchable curiosity about the walking dead, but it also serves as a reminder that even in the serious world of academia, there’s always room to infuse a little levity. As the saying goes, "Where do zombies like to go swimming? The Dead Sea." Our study opens the door to further exploration of unexpected correlations and emphasizes the importance of keeping a sense of humor while analyzing data.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between The number of athletes and sports competitors in Florida and Google searches for 'zombies'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Here is the title and abstract of the paper:
[[TITLE]]
"Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida"

[[ABSTRACT]]
We're breaking new ground in the world of quirky correlations as we delve into the relationship between the population of athletes and sports competitors in the Sunshine State and the frequency of Google searches for 'zombies'. It's no joke - we stumbled upon this curious connection when analyzing data from the Bureau of Labor Statistics and Google Trends. Armed with a correlation coefficient of 0.8707066 and a p-value of less than 0.01 for the time span from 2004 to 2022, we are confident that our findings reveal something truly captivating.

In our tongue-in-cheek investigation, we discovered that as the number of athletes and sports competitors in Florida rose, so did the searches for 'zombies' on Google. It seems like the residents of Florida might not only be interested in winning medals, but also in preparing for a potential zombie apocalypse! It's quite the paradox - they take fitness seriously, yet they also seem to have an eye on the undead. Maybe they just want to out-run the zombie crowd at the next marathon!

Our research not only sheds light on this offbeat relationship between athletic prowess and an unquenchable curiosity about the walking dead, but it also serves as a reminder that even in the serious world of academia, there’s always room to infuse a little levity. As the saying goes, "Where do zombies like to go swimming? The Dead Sea." Our study opens the door to further exploration of unexpected correlations and emphasizes the importance of keeping a sense of humor while analyzing data.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

It's time to lace up our sneakers and limber up our funny bones because we're about to embark on a journey into the strange and captivating world of correlations. Here, we're not just talking about the usual suspects like the relationship between inflation and unemployment or the supply and demand of goods and services. No, we're diving headfirst into the murky waters of unexpectedly related phenomena - and in this case, that includes athletes and Google searches for 'zombies' in the great state of Florida.

As we navigate through this uncharted territory, it's only fitting to pause and ask: Why don't zombies eat comedians? Because they taste funny! Our research has uncovered a correlation coefficient of 0.8707066 and a p-value of less than 0.01, indicating a strong connection between the number of athletes and sports competitors in Florida and the frequency of Google searches for 'zombies' from 2004 to 2022. So, while we may be treading on bizarre ground, the numbers don't lie – there's something fascinating happening here.

The spark behind this investigation ignited when we stumbled upon this unlikely relationship in the data. It's as unexpected as finding a zombie at a dance party - you just never know when they'll show up and start doing the thriller dance! Our analysis reveals that as the population of athletes and sports competitors in Florida increased, so did the interest in 'zombies' on Google. It's a peculiar trend for sure, but it seems that the Sunshine State may have a penchant for embracing both physical excellence and preparation for the undead. It's like they're training for the race of their lives, running from zombies instead of their athletic rivals.

The findings of our study not only expose this quirky correlation but also remind us that even in the world of academia, there's room for a little levity. In the midst of dissecting data and crunching numbers, we're still able to appreciate the humor in unexpected connections. After all, who says academic research can't be a bit of a thriller? Speaking of which, did you hear about the zombie who joined a running club? He was a real dead sprinter!


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of athletes and sports competitors in Florida and Google searches for 'zombies'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
"Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida"

[[ABSTRACT]]
We're breaking new ground in the world of quirky correlations as we delve into the relationship between the population of athletes and sports competitors in the Sunshine State and the frequency of Google searches for 'zombies'. It's no joke - we stumbled upon this curious connection when analyzing data from the Bureau of Labor Statistics and Google Trends. Armed with a correlation coefficient of 0.8707066 and a p-value of less than 0.01 for the time span from 2004 to 2022, we are confident that our findings reveal something truly captivating.

In our tongue-in-cheek investigation, we discovered that as the number of athletes and sports competitors in Florida rose, so did the searches for 'zombies' on Google. It seems like the residents of Florida might not only be interested in winning medals, but also in preparing for a potential zombie apocalypse! It's quite the paradox - they take fitness seriously, yet they also seem to have an eye on the undead. Maybe they just want to out-run the zombie crowd at the next marathon!

Our research not only sheds light on this offbeat relationship between athletic prowess and an unquenchable curiosity about the walking dead, but it also serves as a reminder that even in the serious world of academia, there’s always room to infuse a little levity. As the saying goes, "Where do zombies like to go swimming? The Dead Sea." Our study opens the door to further exploration of unexpected correlations and emphasizes the importance of keeping a sense of humor while analyzing data.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
It's time to lace up our sneakers and limber up our funny bones because we're about to embark on a journey into the strange and captivating world of correlations. Here, we're not just talking about the usual suspects like the relationship between inflation and unemployment or the supply and demand of goods and services. No, we're diving headfirst into the murky waters of unexpectedly related phenomena - and in this case, that includes athletes and Google searches for 'zombies' in the great state of Florida.
As we navigate through this uncharted territory, it's only fitting to pause and ask: Why don't zombies eat comedians? Because they taste funny! Our research has uncovered a correlation coefficient of 0.8707066 and a p-value of less than 0.01, indicating a strong connection between the number of athletes and sports competitors in Florida and the frequency of Google searches for 'zombies' from 2004 to 2022. So, while we may be treading on bizarre ground, the numbers don't lie – there's something fascinating happening here.
The spark behind this investigation ignited when we stumbled upon this unlikely relationship in the data. It's as unexpected as finding a zombie at a dance party - you just never know when they'll show up and start doing the thriller dance! Our analysis reveals that as the population of athletes and sports competitors in Florida increased, so did the interest in 'zombies' on Google. It's a peculiar trend for sure, but it seems that the Sunshine State may have a penchant for embracing both physical excellence and preparation for the undead. It's like they're training for the race of their lives, running from zombies instead of their athletic rivals.
The findings of our study not only expose this quirky correlation but also remind us that even in the world of academia, there's room for a little levity. In the midst of dissecting data and crunching numbers, we're still able to appreciate the humor in unexpected connections. After all, who says academic research can't be a bit of a thriller? Speaking of which, did you hear about the zombie who joined a running club? He was a real dead sprinter!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

As we dive into the realm of unusual correlations, a review of existing literature unveils a surprising discover on the relationship between the number of athletes and sports competitors in Florida and the Google searches for 'zombies'. In a comprehensive study by Smith et al., titled "Athletic Engagement and Peculiar Internet Queries," the authors find an unexpected positive correlation between the two seemingly unrelated phenomena.

Doe and Jones, in their seminal work "Sporting Pursuits and Undead Interests," further elaborate on this intriguing association, delving into the potential societal implications of a populace interested in both athletic achievements and zombie-related content.

Beyond the academic realm, non-fiction works such as "Zombies in the Sunshine State: A Historical Overview" by Author A. Non and "Athletes and All Things Undead" by Researcher X. Treme contribute to our understanding of the Florida's unique fascination with both physical prowess and the undead.

In the realm of fiction, novels like "Marathon of the Dead" by Fictional Writer Z. Bie and "Zombie Blitz: The Ultimate Athletic Challenge" by Author Y. Not present fictional narratives that mirror the surprising correlation uncovered in our research.

Taking a less conventional approach, this literature review extends its scope to include sources of unconventional wisdom, such as the backs of shampoo bottles, where the hidden truths of the universe are rumored to be inscribed. Of course, one must approach these sources with a certain degree of skepticism, as their reliability may only be matched by the credibility of a zombie's career counselor.

Unearthing this unconventional relationship between athleticism and the allure of the undead serves as a reminder that even in the serious pursuit of knowledge, there's always room for a well-timed dad joke. Did you hear about the athlete who was training for a zombie marathon? She wanted to make sure she had a running start in case the undead decided to join the race!


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of athletes and sports competitors in Florida and Google searches for 'zombies'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Google Trends . 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]]
"Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida"

[[ABSTRACT]]
We're breaking new ground in the world of quirky correlations as we delve into the relationship between the population of athletes and sports competitors in the Sunshine State and the frequency of Google searches for 'zombies'. It's no joke - we stumbled upon this curious connection when analyzing data from the Bureau of Labor Statistics and Google Trends. Armed with a correlation coefficient of 0.8707066 and a p-value of less than 0.01 for the time span from 2004 to 2022, we are confident that our findings reveal something truly captivating.

In our tongue-in-cheek investigation, we discovered that as the number of athletes and sports competitors in Florida rose, so did the searches for 'zombies' on Google. It seems like the residents of Florida might not only be interested in winning medals, but also in preparing for a potential zombie apocalypse! It's quite the paradox - they take fitness seriously, yet they also seem to have an eye on the undead. Maybe they just want to out-run the zombie crowd at the next marathon!

Our research not only sheds light on this offbeat relationship between athletic prowess and an unquenchable curiosity about the walking dead, but it also serves as a reminder that even in the serious world of academia, there’s always room to infuse a little levity. As the saying goes, "Where do zombies like to go swimming? The Dead Sea." Our study opens the door to further exploration of unexpected correlations and emphasizes the importance of keeping a sense of humor while analyzing data.

[[INTRODUCTION]]
It's time to lace up our sneakers and limber up our funny bones because we're about to embark on a journey into the strange and captivating world of correlations. Here, we're not just talking about the usual suspects like the relationship between inflation and unemployment or the supply and demand of goods and services. No, we're diving headfirst into the murky waters of unexpectedly related phenomena - and in this case, that includes athletes and Google searches for 'zombies' in the great state of Florida.
As we navigate through this uncharted territory, it's only fitting to pause and ask: Why don't zombies eat comedians? Because they taste funny! Our research has uncovered a correlation coefficient of 0.8707066 and a p-value of less than 0.01, indicating a strong connection between the number of athletes and sports competitors in Florida and the frequency of Google searches for 'zombies' from 2004 to 2022. So, while we may be treading on bizarre ground, the numbers don't lie – there's something fascinating happening here.
The spark behind this investigation ignited when we stumbled upon this unlikely relationship in the data. It's as unexpected as finding a zombie at a dance party - you just never know when they'll show up and start doing the thriller dance! Our analysis reveals that as the population of athletes and sports competitors in Florida increased, so did the interest in 'zombies' on Google. It's a peculiar trend for sure, but it seems that the Sunshine State may have a penchant for embracing both physical excellence and preparation for the undead. It's like they're training for the race of their lives, running from zombies instead of their athletic rivals.
The findings of our study not only expose this quirky correlation but also remind us that even in the world of academia, there's room for a little levity. In the midst of dissecting data and crunching numbers, we're still able to appreciate the humor in unexpected connections. After all, who says academic research can't be a bit of a thriller? Speaking of which, did you hear about the zombie who joined a running club? He was a real dead sprinter!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To illuminate the perplexing connection between athletes and Google searches for 'zombies' in Florida, our research team embarked on a data collection journey that could rival a quest for buried treasure - or, in this case, buried athlete-zombie correlations. Our primary sources of data were the Bureau of Labor Statistics and Google Trends, where we diligently scoured information from the years 2004 to 2022. It was a veritable digital expedition, akin to hunting for clues in a haunted mansion – only this time, the specters were statistical anomalies.

To start off, we donned our metaphorical detective hats and harnessed the power of the Bureau of Labor Statistics to identify the number of athletes and sports competitors in Florida. We employed a top-secret algorithm that involved counting virtual jumping jacks and calculating the collective sweat droplets of sports enthusiasts. Through this convoluted process, which could rival the complexity of a multi-tiered puzzle in a video game, we unearthed the data depicting the fluctuations in the athletic population over the years. It was like unearthing a hidden treasure chest, only instead of gold doubloons, we found stacks of digits and numbers pointing towards a curious correlation.

With the athletic data securely in our grasp, we set sail for the uncharted waters of Google Trends. Here, we navigated the treacherous terrain of search queries and keyword frequencies, all while keeping an eye out for the telltale signals of an impending zombie apocalypse. Our quest resembled the journey of a group of intrepid adventurers seeking ancient relics, except our prizes were digital footprints and the occasional snippet of spooky search patterns. We wielded statistical tools with the adeptness of seasoned treasure hunters, mapping out the rise and fall of 'zombie' searches in Florida over the years.

Once we had gathered our bounty of data, we proceeded to channel our inner alchemists and employed the mystical arts of statistical analysis to distill the essence of our findings. This involved donning robes and muttering incantations – just kidding! In reality, we utilized complex mathematical models and software to calculate correlation coefficients and p-values, all while resisting the urge to animate our spreadsheets into peculiar golems. Our analysis would put the most elaborate magic show to shame, as we conjured the numbers into meaningful patterns and relationships, albeit without the assistance of smoke and mirrors.

Lastly, we engaged in the ancient tradition of peer review, presenting our findings to illustrious colleagues and subjecting them to rigorous scrutiny. Picture a council of wise sages debating the significance of arcane prophecies, except in our case, the prophecies were statistics and the sages were fellow researchers with a penchant for uncovering enigmatic connections. Their feedback and critiques were as invaluable as the counsel of seasoned wizards, helping to hone our insights and ensure the robustness of our conclusions.

With our methods navigating the tumultuous currents of data collection, statistical analysis, and peer review, we emerged with a set of findings that shed light on the curious relationship between athletes and 'zombies' in Florida. It's as if we've uncovered a treasure map leading to unexpected revelations – and perhaps a few more zombie jokes along the way!


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

Please make up the results section of an academic research paper presenting the findings of the connection between The number of athletes and sports competitors in Florida and Google searches for 'zombies'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

For the time period 2004 to 2022, you found a correlation 0.8707066, r-squared of 0.7581299, 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]]
"Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida"

[[ABSTRACT]]
We're breaking new ground in the world of quirky correlations as we delve into the relationship between the population of athletes and sports competitors in the Sunshine State and the frequency of Google searches for 'zombies'. It's no joke - we stumbled upon this curious connection when analyzing data from the Bureau of Labor Statistics and Google Trends. Armed with a correlation coefficient of 0.8707066 and a p-value of less than 0.01 for the time span from 2004 to 2022, we are confident that our findings reveal something truly captivating.

In our tongue-in-cheek investigation, we discovered that as the number of athletes and sports competitors in Florida rose, so did the searches for 'zombies' on Google. It seems like the residents of Florida might not only be interested in winning medals, but also in preparing for a potential zombie apocalypse! It's quite the paradox - they take fitness seriously, yet they also seem to have an eye on the undead. Maybe they just want to out-run the zombie crowd at the next marathon!

Our research not only sheds light on this offbeat relationship between athletic prowess and an unquenchable curiosity about the walking dead, but it also serves as a reminder that even in the serious world of academia, there’s always room to infuse a little levity. As the saying goes, "Where do zombies like to go swimming? The Dead Sea." Our study opens the door to further exploration of unexpected correlations and emphasizes the importance of keeping a sense of humor while analyzing data.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
It's time to lace up our sneakers and limber up our funny bones because we're about to embark on a journey into the strange and captivating world of correlations. Here, we're not just talking about the usual suspects like the relationship between inflation and unemployment or the supply and demand of goods and services. No, we're diving headfirst into the murky waters of unexpectedly related phenomena - and in this case, that includes athletes and Google searches for 'zombies' in the great state of Florida.
As we navigate through this uncharted territory, it's only fitting to pause and ask: Why don't zombies eat comedians? Because they taste funny! Our research has uncovered a correlation coefficient of 0.8707066 and a p-value of less than 0.01, indicating a strong connection between the number of athletes and sports competitors in Florida and the frequency of Google searches for 'zombies' from 2004 to 2022. So, while we may be treading on bizarre ground, the numbers don't lie – there's something fascinating happening here.
The spark behind this investigation ignited when we stumbled upon this unlikely relationship in the data. It's as unexpected as finding a zombie at a dance party - you just never know when they'll show up and start doing the thriller dance! Our analysis reveals that as the population of athletes and sports competitors in Florida increased, so did the interest in 'zombies' on Google. It's a peculiar trend for sure, but it seems that the Sunshine State may have a penchant for embracing both physical excellence and preparation for the undead. It's like they're training for the race of their lives, running from zombies instead of their athletic rivals.
The findings of our study not only expose this quirky correlation but also remind us that even in the world of academia, there's room for a little levity. In the midst of dissecting data and crunching numbers, we're still able to appreciate the humor in unexpected connections. After all, who says academic research can't be a bit of a thriller? Speaking of which, did you hear about the zombie who joined a running club? He was a real dead sprinter!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis revealed a strong positive correlation between the number of athletes and sports competitors in Florida and the frequency of Google searches for 'zombies' over the time period from 2004 to 2022. The correlation coefficient of 0.8707066 and the r-squared value of 0.7581299 suggest that approximately 76% of the variation in Google searches for 'zombies' can be explained by the variation in the number of athletes and sports competitors in Florida. This finding indicates a robust relationship between these seemingly unrelated variables, akin to a marathon runner's endurance in the face of a zombie apocalypse.

As depicted in Figure 1, the scatterplot visually illustrates the positive trend between these variables, with the number of athletes and sports competitors on the x-axis and the Google searches for 'zombies' on the y-axis. The points on the plot form a distinct pattern, resembling a group of runners trying to outpace a growing horde of zombies. The correlation is so strong that you might say it's a "dead-heat" between the two variables!

Our findings suggest that as the population of athletes and sports competitors in Florida increased, there was a corresponding surge in the interest in 'zombies' on Google. It's as if the residents of Florida are gearing up for a race filled with obstacles, including dodging the undead. This curious phenomenon prompts us to consider the possibility of a "zombie marathon," where the participants not only compete against each other but also strive to outrun the zombies on the course. One might say it's a race against time and the undead!

In conclusion, our research uncovers a fascinating link between athleticism and the fascination with zombies, highlighting the unexpected ways in which diverse interests intersect. This offbeat correlation serves as a reminder that in the realm of academic inquiry, there's always room for a touch of whimsy – and in this case, perhaps a dash of "zombie dash"!


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of athletes and sports competitors in Florida and Google searches for 'zombies'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida"

[[ABSTRACT]]
We're breaking new ground in the world of quirky correlations as we delve into the relationship between the population of athletes and sports competitors in the Sunshine State and the frequency of Google searches for 'zombies'. It's no joke - we stumbled upon this curious connection when analyzing data from the Bureau of Labor Statistics and Google Trends. Armed with a correlation coefficient of 0.8707066 and a p-value of less than 0.01 for the time span from 2004 to 2022, we are confident that our findings reveal something truly captivating.

In our tongue-in-cheek investigation, we discovered that as the number of athletes and sports competitors in Florida rose, so did the searches for 'zombies' on Google. It seems like the residents of Florida might not only be interested in winning medals, but also in preparing for a potential zombie apocalypse! It's quite the paradox - they take fitness seriously, yet they also seem to have an eye on the undead. Maybe they just want to out-run the zombie crowd at the next marathon!

Our research not only sheds light on this offbeat relationship between athletic prowess and an unquenchable curiosity about the walking dead, but it also serves as a reminder that even in the serious world of academia, there’s always room to infuse a little levity. As the saying goes, "Where do zombies like to go swimming? The Dead Sea." Our study opens the door to further exploration of unexpected correlations and emphasizes the importance of keeping a sense of humor while analyzing data.

[[LITERATURE REVIEW]]
As we dive into the realm of unusual correlations, a review of existing literature unveils a surprising discover on the relationship between the number of athletes and sports competitors in Florida and the Google searches for 'zombies'. In a comprehensive study by Smith et al., titled "Athletic Engagement and Peculiar Internet Queries," the authors find an unexpected positive correlation between the two seemingly unrelated phenomena.
Doe and Jones, in their seminal work "Sporting Pursuits and Undead Interests," further elaborate on this intriguing association, delving into the potential societal implications of a populace interested in both athletic achievements and zombie-related content.
Beyond the academic realm, non-fiction works such as "Zombies in the Sunshine State: A Historical Overview" by Author A. Non and "Athletes and All Things Undead" by Researcher X. Treme contribute to our understanding of the Florida's unique fascination with both physical prowess and the undead.
In the realm of fiction, novels like "Marathon of the Dead" by Fictional Writer Z. Bie and "Zombie Blitz: The Ultimate Athletic Challenge" by Author Y. Not present fictional narratives that mirror the surprising correlation uncovered in our research.
Taking a less conventional approach, this literature review extends its scope to include sources of unconventional wisdom, such as the backs of shampoo bottles, where the hidden truths of the universe are rumored to be inscribed. Of course, one must approach these sources with a certain degree of skepticism, as their reliability may only be matched by the credibility of a zombie's career counselor.
Unearthing this unconventional relationship between athleticism and the allure of the undead serves as a reminder that even in the serious pursuit of knowledge, there's always room for a well-timed dad joke. Did you hear about the athlete who was training for a zombie marathon? She wanted to make sure she had a running start in case the undead decided to join the race!

[[RESULTS]]
The results of our analysis revealed a strong positive correlation between the number of athletes and sports competitors in Florida and the frequency of Google searches for 'zombies' over the time period from 2004 to 2022. The correlation coefficient of 0.8707066 and the r-squared value of 0.7581299 suggest that approximately 76% of the variation in Google searches for 'zombies' can be explained by the variation in the number of athletes and sports competitors in Florida. This finding indicates a robust relationship between these seemingly unrelated variables, akin to a marathon runner's endurance in the face of a zombie apocalypse.
As depicted in Figure 1, the scatterplot visually illustrates the positive trend between these variables, with the number of athletes and sports competitors on the x-axis and the Google searches for 'zombies' on the y-axis. The points on the plot form a distinct pattern, resembling a group of runners trying to outpace a growing horde of zombies. The correlation is so strong that you might say it's a "dead-heat" between the two variables!
Our findings suggest that as the population of athletes and sports competitors in Florida increased, there was a corresponding surge in the interest in 'zombies' on Google. It's as if the residents of Florida are gearing up for a race filled with obstacles, including dodging the undead. This curious phenomenon prompts us to consider the possibility of a "zombie marathon," where the participants not only compete against each other but also strive to outrun the zombies on the course. One might say it's a race against time and the undead!
In conclusion, our research uncovers a fascinating link between athleticism and the fascination with zombies, highlighting the unexpected ways in which diverse interests intersect. This offbeat correlation serves as a reminder that in the realm of academic inquiry, there's always room for a touch of whimsy – and in this case, perhaps a dash of "zombie dash"!

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings posit a compelling connection between the number of athletes and sports competitors in Florida and the public interest in 'zombies'. As our research presented a correlation coefficient of 0.8707066 and a p-value of less than 0.01, we've seen compelling evidence to support the hypothesis that there is indeed a noteworthy relationship between these seemingly disparate variables. It's almost as if the athletes are training for the ultimate zombie sports event – the "undead-athlon", if you will.

To our surprise, our results align with previous studies investigating the unexpected intersection of athletic pursuits and fascination with the undead. Smith et al.'s work shed light on the positive correlation we uncovered, reinforcing the notion that there's genuine curiosity in the link between athleticism and zombies. It's as if our findings are the result of a relentless pursuit, much like a zombie tirelessly chasing after its next meal.

Furthermore, the peculiar findings from Doe and Jones emphasize the societal implications of this correlation – it's akin to a marathon where the finish line is constantly moving, not unlike the scenario one might encounter in a zombie-infested world. This perfectly underscores the fascinating connection we have unraveled, showing that in Florida, the interest in athleticism and zombies is not merely a passing fad. It's like the saying goes, "Why did the zombie join the track team? He wanted to improve his dead-lift!"

Delving into unconventional sources of wisdom, such as the fictitious works of Z. Bie and Y. Not, served as an unorthodox yet surprisingly relevant piece of the puzzle. These sources echo the synergy between athleticism and the undead, demonstrating that even outside the realms of empirical research, there's an undeniable fascination with this correlation, much like the allure of a zombie feast at a track meet.

The scatterplot in our results not only illustrates the strong positive trend between the variables but also serves as a visual representation of the potential race against time and zombies that the Florida residents seem to be preparing for. It's almost as if the athletes are gearing up for a "zombie triathlon" – swim, run, and flee from the undead!

In conclusion, our study has added a quirky yet thought-provoking layer to the understanding of human behavior. It gives new meaning to the phrase "running with the dead," showing that the pursuit of knowledge can illuminate the most unexpected connections, be it in sports, internet searches, or the infamously mysterious field of zombie enthusiasm. As the saying goes, "Why don't zombies like fast food? Because they can't catch it!"


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of athletes and sports competitors in Florida and Google searches for 'zombies'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida"

[[ABSTRACT]]
We're breaking new ground in the world of quirky correlations as we delve into the relationship between the population of athletes and sports competitors in the Sunshine State and the frequency of Google searches for 'zombies'. It's no joke - we stumbled upon this curious connection when analyzing data from the Bureau of Labor Statistics and Google Trends. Armed with a correlation coefficient of 0.8707066 and a p-value of less than 0.01 for the time span from 2004 to 2022, we are confident that our findings reveal something truly captivating.

In our tongue-in-cheek investigation, we discovered that as the number of athletes and sports competitors in Florida rose, so did the searches for 'zombies' on Google. It seems like the residents of Florida might not only be interested in winning medals, but also in preparing for a potential zombie apocalypse! It's quite the paradox - they take fitness seriously, yet they also seem to have an eye on the undead. Maybe they just want to out-run the zombie crowd at the next marathon!

Our research not only sheds light on this offbeat relationship between athletic prowess and an unquenchable curiosity about the walking dead, but it also serves as a reminder that even in the serious world of academia, there’s always room to infuse a little levity. As the saying goes, "Where do zombies like to go swimming? The Dead Sea." Our study opens the door to further exploration of unexpected correlations and emphasizes the importance of keeping a sense of humor while analyzing data.

[[INTRDUCTION]]
It's time to lace up our sneakers and limber up our funny bones because we're about to embark on a journey into the strange and captivating world of correlations. Here, we're not just talking about the usual suspects like the relationship between inflation and unemployment or the supply and demand of goods and services. No, we're diving headfirst into the murky waters of unexpectedly related phenomena - and in this case, that includes athletes and Google searches for 'zombies' in the great state of Florida.
As we navigate through this uncharted territory, it's only fitting to pause and ask: Why don't zombies eat comedians? Because they taste funny! Our research has uncovered a correlation coefficient of 0.8707066 and a p-value of less than 0.01, indicating a strong connection between the number of athletes and sports competitors in Florida and the frequency of Google searches for 'zombies' from 2004 to 2022. So, while we may be treading on bizarre ground, the numbers don't lie – there's something fascinating happening here.
The spark behind this investigation ignited when we stumbled upon this unlikely relationship in the data. It's as unexpected as finding a zombie at a dance party - you just never know when they'll show up and start doing the thriller dance! Our analysis reveals that as the population of athletes and sports competitors in Florida increased, so did the interest in 'zombies' on Google. It's a peculiar trend for sure, but it seems that the Sunshine State may have a penchant for embracing both physical excellence and preparation for the undead. It's like they're training for the race of their lives, running from zombies instead of their athletic rivals.
The findings of our study not only expose this quirky correlation but also remind us that even in the world of academia, there's room for a little levity. In the midst of dissecting data and crunching numbers, we're still able to appreciate the humor in unexpected connections. After all, who says academic research can't be a bit of a thriller? Speaking of which, did you hear about the zombie who joined a running club? He was a real dead sprinter!

[[RESULTS]]
The results of our analysis revealed a strong positive correlation between the number of athletes and sports competitors in Florida and the frequency of Google searches for 'zombies' over the time period from 2004 to 2022. The correlation coefficient of 0.8707066 and the r-squared value of 0.7581299 suggest that approximately 76% of the variation in Google searches for 'zombies' can be explained by the variation in the number of athletes and sports competitors in Florida. This finding indicates a robust relationship between these seemingly unrelated variables, akin to a marathon runner's endurance in the face of a zombie apocalypse.
As depicted in Figure 1, the scatterplot visually illustrates the positive trend between these variables, with the number of athletes and sports competitors on the x-axis and the Google searches for 'zombies' on the y-axis. The points on the plot form a distinct pattern, resembling a group of runners trying to outpace a growing horde of zombies. The correlation is so strong that you might say it's a "dead-heat" between the two variables!
Our findings suggest that as the population of athletes and sports competitors in Florida increased, there was a corresponding surge in the interest in 'zombies' on Google. It's as if the residents of Florida are gearing up for a race filled with obstacles, including dodging the undead. This curious phenomenon prompts us to consider the possibility of a "zombie marathon," where the participants not only compete against each other but also strive to outrun the zombies on the course. One might say it's a race against time and the undead!
In conclusion, our research uncovers a fascinating link between athleticism and the fascination with zombies, highlighting the unexpected ways in which diverse interests intersect. This offbeat correlation serves as a reminder that in the realm of academic inquiry, there's always room for a touch of whimsy – and in this case, perhaps a dash of "zombie dash"!

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In closing, our investigation into the relationship between the number of athletes and sports competitors in Florida and Google searches for 'zombies' has revealed a compelling correlation that raises intriguing questions about the intersection of athleticism and a fascination with the undead. It's as if the Sunshine State is gearing up for a "Zombie Olympics" – after all, who wouldn't want to witness an undead 100-meter dash?

Our findings not only highlight this unexpected connection but also emphasize the importance of maintaining a sense of humor in the rigorous world of data analysis. As demonstrated by our study, academic research can absolutely have its "ha-ha" moments, and this correlation between athletic pursuits and zombie inquiries serves as a testament to the unpredictable and entertaining nature of statistical analysis.

As we wrap up, it's safe to say that our exploration of this peculiar correlation has left us both amused and enlightened. It's akin to finding zombies at a track meet – unexpected, humorous, and undeniably captivating. So, the next time someone questions the whimsy of academic research, we can confidently respond with, "Why did the zombie join the track team? Because he wanted to improve his dead-lifts!"

And with that, we assert that no further research is needed in this area. After all, we wouldn't want to beat a dead horse – or should we say, a dead zombie?


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 Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Mysterious Sports Trends


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 Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Sports 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 Dead Ringers: The Correlation Between Athletes and Google Searches for 'Zombies' in Florida with an abstract of We're breaking new ground in the world of quirky correlations as we delve into the relationship between the population of athletes and sports competitors in the Sunshine State and the frequency of Google searches for 'zombies'. It's no joke - we stumbled upon this curious connection when analyzing data from the Bureau of Labor Statistics and Google Trends. Armed with a correlation coefficient of 0.8707066 and a p-value of less than 0.01 for the time span from 2004 to 2022, we are confident that our findings reveal something truly captivating.
In our tongue-in-cheek investigation, we discovered that as the number of athletes and sports competitors in Florida rose, so did the searches for 'zombies' on Google. It seems like the residents of Florida might not only be interested in winning medals, but also in preparing for a potential zombie apocalypse! It's quite the paradox - they take fitness seriously, yet they also seem to have an eye on the undead. Maybe they just want to out-run the zombie crowd at the next marathon!
Our research not only sheds light on this offbeat relationship between athletic prowess and an unquenchable curiosity about the walking dead, but it also serves as a reminder that even in the serious world of academia, there’s always room to infuse a little levity. As the saying goes, "Where do zombies like to go swimming? The Dead Sea." Our study opens the door to further exploration of unexpected correlations and emphasizes the importance of keeping a sense of humor while analyzing data.

ChatGPT:

athletes, sports competitors, Google searches, zombies, Florida, correlation coefficient, p-value, data analysis, Bureau of Labor Statistics, Google Trends, quirky correlations, relationship between athletic prowess and curiosity about zombies

*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 athletes and sports competitors in Florida
Detailed data title: BLS estimate of athletes and sports competitors in Florida
Source: Bureau of Larbor Statistics
See what else correlates with The number of athletes and sports competitors in Florida

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'

Correlation r = 0.8707066 (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 = 0.7581299 (Coefficient of determination)
This means 75.8% of the change in the one variable (i.e., Google searches for 'zombies') is predictable based on the change in the other (i.e., The number of athletes and sports competitors in Florida) over the 19 years from 2004 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.2E-6. 0.0000012412826927439854000000
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 0.87 in 0.00012% of random cases. Said differently, if you correlated 805,618 random variables You don't actually need 805 thousand 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.

[ 0.69, 0.95 ] 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
The number of athletes and sports competitors in Florida (Laborers)1090770980114015002190215029302920386032002840134013101320125055020101650
Google searches for 'zombies' (Rel. search volume)3.666674.083334.083335.083336.0833317.916736.7559.416767.583383.255948.7539.083328.252417.7523.66671919.5




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([1090,770,980,1140,1500,2190,2150,2930,2920,3860,3200,2840,1340,1310,1320,1250,550,2010,1650,])
array_2 = 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_1_name = "The number of athletes and sports competitors in Florida"
array_2_name = "Google searches for 'zombies'"

# 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?

Big thanks for reviewing!


Correlation ID: 3798 · Black Variable ID: 6487 · Red Variable ID: 1380
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0