Spurious correlation #4,127 · 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 pipelayers in Nevada and the second variable is Google searches for 'Nintendo'. The chart goes from 2008 to 2022, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of pipelayers in Nevada and the second variable is Google searches for 'Nintendo'. The chart goes from 2008 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of pipelayers in Nevada decreased, so did the availability of laying the groundwork for Nintendo's success. It seems the plumber shortage really put a wrench in Nintendo's search results! Remember, when it comes to pipelines and gaming icons, it's all about having the right connections.

^{Show image generation prompt} Model: dalle-3
Prompt: Image Generation Prompt: Style: A scene from Skyrim Scene Description: A vast, mountainous landscape dominated by rugged terrain and towering peaks. In the foreground, a group of construction workers in heavy gear are skillfully laying pipes across the rocky terrain of Nevada. Their machinery and tools blend seamlessly with the natural surroundings as they work diligently. In the middle ground, a large computer screen with the Google search bar prominently displayed, set against the backdrop of the Nevada landscape. The search bar shows a decline in searches for 'Nintendo', leading to a sad-faced Mario icon looking perplexed. The screen's glow illuminates the surroundings, contrasting with the twilight sky. Instructions: Generate an image that combines the rugged beauty of Skyrim's landscapes with the industrious work of construction crews laying pipes in Nevada. Incorporate a computer screen displaying a declining search for 'Nintendo', along with a perplexed Mario icon, to symbolize the impact of the dwindling number of pipelayers on the success of Nintendo. 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 pipelayers in Nevada and Google searches for 'Nintendo'. 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: Photorealism Cutsy graphics Surrealism Pop art A scene from Skyrim
ChatGPT: A scene from Skyrim

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 pipelayers in Nevada and Google searches for 'Nintendo', in the following situation: As the number of pipelayers in Nevada decreased, so did the availability of laying the groundwork for Nintendo's success. It seems the plumber shortage really put a wrench in Nintendo's search results! Remember, when it comes to pipelines and gaming icons, it's all about having the right connections.. Keep the description simple.
ChatGPT: In Nevada, as the number of pipelayers decreased, we see fewer people in construction gear working on laying pipes. Meanwhile, on a computer screen, the Google search bar shows a drop in searches for 'Nintendo', with a sad-faced Mario icon looking perplexed. The lack of pipelayers in Nevada seems to have caused a shortage in laying the groundwork for Nintendo's success, as depicted by the dwindling search results.

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 scene from Skyrim ] and depicting this scene: In Nevada, as the number of pipelayers decreased, we see fewer people in construction gear working on laying pipes. Meanwhile, on a computer screen, the Google search bar shows a drop in searches for 'Nintendo', with a sad-faced Mario icon looking perplexed. The lack of pipelayers in Nevada seems to have caused a shortage in laying the groundwork for Nintendo's success, as depicted by the dwindling search results. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Image Generation Prompt: Style: A scene from Skyrim Scene Description: A vast, mountainous landscape dominated by rugged terrain and towering peaks. In the foreground, a group of construction workers in heavy gear are skillfully laying pipes across the rocky terrain of Nevada. Their machinery and tools blend seamlessly with the natural surroundings as they work diligently. In the middle ground, a large computer screen with the Google search bar prominently displayed, set against the backdrop of the Nevada landscape. The search bar shows a decline in searches for 'Nintendo', leading to a sad-faced Mario icon looking perplexed. The screen's glow illuminates the surroundings, contrasting with the twilight sky. Instructions: Generate an image that combines the rugged beauty of Skyrim's landscapes with the industrious work of construction crews laying pipes in Nevada. Incorporate a computer screen displaying a declining search for 'Nintendo', along with a perplexed Mario icon, to symbolize the impact of the dwindling number of pipelayers on the success of Nintendo.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in The number of pipelayers in Nevada caused Nintendo (Google searches for 'Nintendo') to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Pipe Dreams: The Piping Hot Relationship Between Pipelayers in Nevada and Google Searches for Nintendo

The Journal of Quirky Cross-Cultural Connections

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of pipelayers in Nevada and Google searches for 'Nintendo'. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Pipe Dreams: The Piping Hot Relationship Between Pipelayers in Nevada and Google Searches for Nintendo"

[[ABSTRACT]]
This research delves into the unexpected and whimsical relationship between the number of pipelayers in the state of Nevada and the frequency of Google searches for the beloved video game company, Nintendo. The study employs data from the Bureau of Labor Statistics and Google Trends to analyze this seemingly unrelated pair. Contrary to conventional wisdom, our findings reveal a surprisingly robust correlation coefficient of 0.8701921, with statistical significance at p < 0.01, spanning from 2008 to 2022. This paper aims to not only unveil the statistical connection but also to provoke further inquiry into the quirky dynamics of occupational choices and consumer interests.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the realm of research, we often seek out relationships between variables that are as seemingly unrelated as a cat at a dog show. But just as we revel in the delightful surprise of a unicorn sighting, sometimes our data presents us with unexpected correlations that leave us scratching our heads and reaching for the nearest statistical textbook. Such is the case with the peculiar pairing of pipelayers in Nevada and Google searches for Nintendo.
One might initially question what pipelayers, those stalwart individuals working underground to ensure the free flow of that most precious resource, water, have to do with the virtual playgrounds and pixelated adventures of Nintendo. Yet, as we delved into the data from the Bureau of Labor Statistics and Google Trends, we found ourselves tumbling down a rabbit hole into a world where plumbing and video games dance a statistical tango.
To our surprise, we uncovered a correlation coefficient that would make even the stodgiest of statisticians raise an eyebrow – a piping hot 0.8701921, with a cheeky little p-value of p < 0.01. The relationship, much like Mario in his quest to rescue Princess Peach, spanned from 2008 to 2022, defying expectations and inviting us to embrace the whimsical side of quantitative analysis.
This paper not only aims to unveil this offbeat statistical romance but also to implore fellow academics to join us in our mirthful curiosity. After all, who wouldn't want to be part of unraveling the enigmatic ties between the workforce beneath the Silver State and the yearning for virtual adventure? So, with pipes of all kinds and pixelated heroes in mind, let us embark on a quest to explore this unexpected and strangely delightful correlation.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

As the search for understanding the unlikely bond between the number of pipelayers in Nevada and Google searches for Nintendo continues, we turn to the existing literature for insights into this peculiar correlation.

In "Plumbing and Play: Uncovering Surprising Connections in Occupational Choices and Consumer Behavior," Smith et al. propose a theoretical framework for examining the intersection of plumbing professions and the love for virtual gaming. The authors find that individuals drawn to careers in pipelaying may possess a latent affinity for the intricate networks and systems found in video games, leading to an unconscious attraction to Nintendo's digital landscapes.

Building on this notion, Doe and Jones present a quantitative analysis in "On Pipe Dreams and Power-Ups: Exploring the Statistical Association Between Pipelayers in Nevada and Google Searches for Nintendo." Their study reveals a statistically significant correlation between the two seemingly disparate variables, prompting further investigation into the underlying mechanisms driving this peculiar relationship.

However, the literature also draws attention to the wider societal implications of these findings. In "Pipes and Pixels: The Socioeconomic Impact of Nintendo Obsession Among Pipelayers," the authors delve into the potential effects of video game immersion on occupational performance, with intriguing implications for workplace dynamics and productivity.

Turning to related non-fiction works for additional insight, "The Secret Life of Pipes" by John Pipeston and "The Art of Mario: A Historical Analysis of the Nintendo Phenomenon" by Louise G. Console provide valuable background information on the history and cultural significance of both pipelaying and Nintendo, shedding light on the potential intersection between these realms.

On a slightly more whimsical note, fiction literature also offers intriguing perspectives. From "The Plumber's Portal" by Alice Tubeinsky to "Super Mario and the Chamber of Pipeline Secrets" by J.K. Plumb, these titles, though not directly related to the empirical research at hand, infuse the scholarly landscape with a dollop of playful imagination.

Additionally, while not canonical sources in academic research, board games such as "Pipeline Puzzles" and "Super Mario Monopoly" inspire musings on the playful interplay between the physical world of pipelayers and the virtual realm of Nintendo.

As we wade through this literature, it becomes evident that the correlation between pipelayers in Nevada and Google searches for Nintendo is more than just a statistical anomaly – it is a conduit to a world of theoretical intrigue and whimsical wonder.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of pipelayers in Nevada and Google searches for 'Nintendo'. Make lots of 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]]
"Pipe Dreams: The Piping Hot Relationship Between Pipelayers in Nevada and Google Searches for Nintendo"

[[ABSTRACT]]
This research delves into the unexpected and whimsical relationship between the number of pipelayers in the state of Nevada and the frequency of Google searches for the beloved video game company, Nintendo. The study employs data from the Bureau of Labor Statistics and Google Trends to analyze this seemingly unrelated pair. Contrary to conventional wisdom, our findings reveal a surprisingly robust correlation coefficient of 0.8701921, with statistical significance at p < 0.01, spanning from 2008 to 2022. This paper aims to not only unveil the statistical connection but also to provoke further inquiry into the quirky dynamics of occupational choices and consumer interests.

[[LITERATURE REVIEW]]
As the search for understanding the unlikely bond between the number of pipelayers in Nevada and Google searches for Nintendo continues, we turn to the existing literature for insights into this peculiar correlation.
In "Plumbing and Play: Uncovering Surprising Connections in Occupational Choices and Consumer Behavior," Smith et al. propose a theoretical framework for examining the intersection of plumbing professions and the love for virtual gaming. The authors find that individuals drawn to careers in pipelaying may possess a latent affinity for the intricate networks and systems found in video games, leading to an unconscious attraction to Nintendo's digital landscapes.
Building on this notion, Doe and Jones present a quantitative analysis in "On Pipe Dreams and Power-Ups: Exploring the Statistical Association Between Pipelayers in Nevada and Google Searches for Nintendo." Their study reveals a statistically significant correlation between the two seemingly disparate variables, prompting further investigation into the underlying mechanisms driving this peculiar relationship.
However, the literature also draws attention to the wider societal implications of these findings. In "Pipes and Pixels: The Socioeconomic Impact of Nintendo Obsession Among Pipelayers," the authors delve into the potential effects of video game immersion on occupational performance, with intriguing implications for workplace dynamics and productivity.
Turning to related non-fiction works for additional insight, "The Secret Life of Pipes" by John Pipeston and "The Art of Mario: A Historical Analysis of the Nintendo Phenomenon" by Louise G. Console provide valuable background information on the history and cultural significance of both pipelaying and Nintendo, shedding light on the potential intersection between these realms.
On a slightly more whimsical note, fiction literature also offers intriguing perspectives. From "The Plumber's Portal" by Alice Tubeinsky to "Super Mario and the Chamber of Pipeline Secrets" by J.K. Plumb, these titles, though not directly related to the empirical research at hand, infuse the scholarly landscape with a dollop of playful imagination.
Additionally, while not canonical sources in academic research, board games such as "Pipeline Puzzles" and "Super Mario Monopoly" inspire musings on the playful interplay between the physical world of pipelayers and the virtual realm of Nintendo.
As we wade through this literature, it becomes evident that the correlation between pipelayers in Nevada and Google searches for Nintendo is more than just a statistical anomaly – it is a conduit to a world of theoretical intrigue and whimsical wonder.

[[RESULTS]]
The results of our analysis unveil a remarkably strong correlation between the number of pipelayers in Nevada and Google searches for Nintendo, which will surely make even the most stoic of researchers crack a smile. The correlation coefficient of 0.8701921 suggests a robust relationship between these two seemingly disparate entities, akin to the curious kinship between a wrench and a Wii controller.
Furthermore, the r-squared value of 0.7572343 indicates that a considerable 75.72% of the variance in Google searches for Nintendo can be explained by the variation in the number of pipelayers in Nevada. This statistical association, much like a well-executed video game combo, demonstrates a surprisingly compelling link that defies traditional expectations.
The p-value of less than 0.01 underscores the statistical significance of this relationship, emphasizing that the likelihood of such a strong association occurring by mere chance is rarer than a shiny Pokémon. This finding prompts us to not only reconsider the often-unexpected web of interconnected variables but also to appreciate the whimsical and delightful nature of statistical inquiry.
In support of our findings, Fig. 1 illustrates a scatterplot showcasing the evident correlation between the two variables. The scatterplot, much like a level in a Nintendo game, paints a vivid picture of the interconnectedness between the number of pipelayers in Nevada and the frequency of Google searches for Nintendo, inviting both awe and mirth in its revelatory nature.
Ultimately, our results not only attest to the tantalizing nature of statistical anomalies but also beckon to fellow researchers to embrace the enchanting dance of quantitative analysis, where even the most unlikely pairs can captivate with their statistical harmony.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The unexpected and enigmatic relationship between the number of pipelayers in Nevada and Google searches for Nintendo has left us pondering the whimsical interplay of occupational choices and consumer interests. Our robust correlation coefficient of 0.8701921, with statistical significance at p < 0.01, serves as a clarion call to behold the seemingly unrelated with fresh eyes and an ardent spirit of inquiry.

In aligning with prior research by Smith et al. and Doe and Jones, our findings bolster the notion that individuals in the plumbing profession may harbor an underlying penchant for the intricate networks and systems prevalent in immersive video games, instigating an unconscious attraction to Nintendo's digital domain. This illuminating discovery adds a new level of depth to the concept of occupational passions and dovetails with the "Pipe Dreams and Power-Ups" study, solidifying the statistical association as more than just a statistical oddity but a tangible representation of the captivating relationship between the physical and virtual worlds.

The r-squared value of 0.7572343 admirably elucidates that a considerable 75.72% of the fluctuation in Google searches for Nintendo can be elucidated by the nuanced variances in the number of pipelayers in Nevada. This significant explanatory power poignantly underscores the captivating harmony shared between these seemingly disparate variables, akin to a well-crafted visual puzzle awaiting interpretation.

Moreover, as potentiated by the p-value of less than 0.01, the likelihood of such a compelling correlation occurring by chance is as rare as capturing a shiny Pokémon, reaffirming the statistical significance of this curious relationship. This serves as a triumphant testament to the captivating allure of serendipitous statistical discoveries, stirring a heady blend of laughter and insight among the scholarly community.

In light of our results, we implore fellow researchers to embrace the enchanting waltz of quantitative analysis, where even the most improbably matched pairs can evoke fascination and mirth. Our study highlights the charm of statistical inquiry, inviting scholars to revel in the delightful dance of variables and the joyous unraveling of unexpected connections, much like stumbling upon a hidden power-up in a video game.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of pipelayers in Nevada and Google searches for 'Nintendo'. Make lots of 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]]
"Pipe Dreams: The Piping Hot Relationship Between Pipelayers in Nevada and Google Searches for Nintendo"

[[ABSTRACT]]
This research delves into the unexpected and whimsical relationship between the number of pipelayers in the state of Nevada and the frequency of Google searches for the beloved video game company, Nintendo. The study employs data from the Bureau of Labor Statistics and Google Trends to analyze this seemingly unrelated pair. Contrary to conventional wisdom, our findings reveal a surprisingly robust correlation coefficient of 0.8701921, with statistical significance at p < 0.01, spanning from 2008 to 2022. This paper aims to not only unveil the statistical connection but also to provoke further inquiry into the quirky dynamics of occupational choices and consumer interests.

[[INTRDUCTION]]
In the realm of research, we often seek out relationships between variables that are as seemingly unrelated as a cat at a dog show. But just as we revel in the delightful surprise of a unicorn sighting, sometimes our data presents us with unexpected correlations that leave us scratching our heads and reaching for the nearest statistical textbook. Such is the case with the peculiar pairing of pipelayers in Nevada and Google searches for Nintendo.
One might initially question what pipelayers, those stalwart individuals working underground to ensure the free flow of that most precious resource, water, have to do with the virtual playgrounds and pixelated adventures of Nintendo. Yet, as we delved into the data from the Bureau of Labor Statistics and Google Trends, we found ourselves tumbling down a rabbit hole into a world where plumbing and video games dance a statistical tango.
To our surprise, we uncovered a correlation coefficient that would make even the stodgiest of statisticians raise an eyebrow – a piping hot 0.8701921, with a cheeky little p-value of p < 0.01. The relationship, much like Mario in his quest to rescue Princess Peach, spanned from 2008 to 2022, defying expectations and inviting us to embrace the whimsical side of quantitative analysis.
This paper not only aims to unveil this offbeat statistical romance but also to implore fellow academics to join us in our mirthful curiosity. After all, who wouldn't want to be part of unraveling the enigmatic ties between the workforce beneath the Silver State and the yearning for virtual adventure? So, with pipes of all kinds and pixelated heroes in mind, let us embark on a quest to explore this unexpected and strangely delightful correlation.

[[RESULTS]]
The results of our analysis unveil a remarkably strong correlation between the number of pipelayers in Nevada and Google searches for Nintendo, which will surely make even the most stoic of researchers crack a smile. The correlation coefficient of 0.8701921 suggests a robust relationship between these two seemingly disparate entities, akin to the curious kinship between a wrench and a Wii controller.
Furthermore, the r-squared value of 0.7572343 indicates that a considerable 75.72% of the variance in Google searches for Nintendo can be explained by the variation in the number of pipelayers in Nevada. This statistical association, much like a well-executed video game combo, demonstrates a surprisingly compelling link that defies traditional expectations.
The p-value of less than 0.01 underscores the statistical significance of this relationship, emphasizing that the likelihood of such a strong association occurring by mere chance is rarer than a shiny Pokémon. This finding prompts us to not only reconsider the often-unexpected web of interconnected variables but also to appreciate the whimsical and delightful nature of statistical inquiry.
In support of our findings, Fig. 1 illustrates a scatterplot showcasing the evident correlation between the two variables. The scatterplot, much like a level in a Nintendo game, paints a vivid picture of the interconnectedness between the number of pipelayers in Nevada and the frequency of Google searches for Nintendo, inviting both awe and mirth in its revelatory nature.
Ultimately, our results not only attest to the tantalizing nature of statistical anomalies but also beckon to fellow researchers to embrace the enchanting dance of quantitative analysis, where even the most unlikely pairs can captivate with their statistical harmony.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, this research sheds light on the unexpectedly whimsical connection between the number of pipelayers in Nevada and Google searches for Nintendo. The robust correlation coefficient of 0.8701921, akin to stumbling upon a warp zone in the world of statistics, defies conventional logic and beckons researchers to embrace the enigmatic allure of seemingly unrelated variables.

The r-squared value of 0.7572343 further emphasizes the surprisingly compelling link between these divergent entities, akin to a successful power-up in a video game that unlocks new levels of understanding. The p-value of less than 0.01 not only underscores the statistical significance of this relationship but also adds a touch of statistical humor, as rare as encountering a cheat code in the labyrinth of data analysis.

While one might be inclined to dismiss this peculiar association as a statistical fluke, the scatterplot in Fig. 1 vividly illustrates the undeniable interconnectedness between pipelayers and Nintendo searches, much like stumbling upon an unexpected Easter egg in a game.

Hence, it is evident that this research not only delights in unraveling statistical curiosities but also invites fellow academics to join in the merry pursuit of uncovering the tangled web of connections in the world of research. However, in the spirit of embracing the unexpected, it is our firm conclusion that further research in this area is as unnecessary as an extra life in a game with unlimited continues.

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 Pipe Dreams: The Piping Hot Relationship Between Pipelayers in Nevada and Google Searches for Nintendo. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Cross-Cultural Connections

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 Pipe Dreams: The Piping Hot Relationship Between Pipelayers in Nevada and Google Searches for Nintendo. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Applied Pipeology

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 Pipe Dreams: The Piping Hot Relationship Between Pipelayers in Nevada and Google Searches for Nintendo with an abstract of This research delves into the unexpected and whimsical relationship between the number of pipelayers in the state of Nevada and the frequency of Google searches for the beloved video game company, Nintendo. The study employs data from the Bureau of Labor Statistics and Google Trends to analyze this seemingly unrelated pair. Contrary to conventional wisdom, our findings reveal a surprisingly robust correlation coefficient of 0.8701921, with statistical significance at p < 0.01, spanning from 2008 to 2022. This paper aims to not only unveil the statistical connection but also to provoke further inquiry into the quirky dynamics of occupational choices and consumer interests.

ChatGPT:

Nevada, pipelayers, Google searches, Nintendo, video game company, Bureau of Labor Statistics, Google Trends, correlation coefficient, statistical significance, p-value, occupational choices, consumer interests, quirky dynamics

*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 pipelayers in Nevada
Detailed data title: BLS estimate of pipelayers in Nevada
Source: Bureau of Larbor Statistics
See what else correlates with The number of pipelayers in Nevada

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

See what else correlates with Google searches for 'Nintendo'

Correlation r = 0.8701921 (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 = 0.7572343 (Coefficient of determination)
This means 75.7% of the change in the one variable (i.e., Google searches for 'Nintendo') is predictable based on the change in the other (i.e., The number of pipelayers in Nevada) over the 15 years from 2008 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.5E-5.^Show 0.0000246512815553103100000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.87 in 0.0025% of random cases. Said differently, if you correlated 40,566 random variables^Note You don't actually need 40 thousand variables to find a correlation like this one. 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.

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 14 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 14 because we have two variables measured over a period of 15 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.

[ 0.65, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
The number of pipelayers in Nevada (Pipelayers)	840	720	510	330	130	160	140	110	70	80	430	600	1010	440	630
Google searches for 'Nintendo' (Rel. search volume)	62.4167	51.9167	40.75	34.5	26.25	24.0833	21.5833	21.1667	26.0833	39.5833	37.9167	39.5	52.5	39.6667	38.5

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([840,720,510,330,130,160,140,110,70,80,430,600,1010,440,630,])
array_2 = np.array([62.4167,51.9167,40.75,34.5,26.25,24.0833,21.5833,21.1667,26.0833,39.5833,37.9167,39.5,52.5,39.6667,38.5,])
array_1_name = "The number of pipelayers in Nevada"
array_2_name = "Google searches for 'Nintendo'"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only The number of pipelayers in Nevada
Line chart for only Google searches for 'Nintendo'
AI-generated correlation image
The spurious research paper: Pipe Dreams: The Piping Hot Relationship Between Pipelayers in Nevada and Google Searches for Nintendo

View another random correlation

How fun was this correlation?

You're a rater extraordinaire!

Correlation ID: 4127 · Black Variable ID: 11235 · Red Variable ID: 1415


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