Spurious correlation #5,501 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the 'expanding brain' meme and the second variable is Liquefied petroleum gas used in Kyrgyzstan. The chart goes from 2006 to 2021, 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 Popularity of the 'expanding brain' meme and the second variable is Liquefied petroleum gas used in Kyrgyzstan. The chart goes from 2006 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the 'expanding brain' meme gained popularity, more people were exposed to larger and larger brain images. This led to a collective increase in brain size perception, ultimately causing a spike in innovative thinking. One of these big ideas was to harness the power of memes to promote the use of liquefied petroleum gas in Kyrgyzstan, leading to a surge in its usage. So, in a truly mind-blowing chain of events, you could say that the meme literally expanded minds and ignited a fiery interest in LPG in Kyrgyzstan!

^{Show image generation prompt} Create a meme inspired by the expanding brain meme that in some way references Liquefied petroleum gas used in Kyrgyzstan. Try to emulate the style of the meme - don’t violate the copyright, just make it look and feel like the original meme.
^{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 increases in Popularity of the 'expanding brain' meme positively influenced Liquefied petroleum gas used in Kyrgyzstan. Make it feel plausible.

AI academic paper

(Because p < 0.01)

From Small Brain to Big Gas: Uncovering the Link Between 'Expanding Brain' Meme Popularity and Liquefied Petroleum Gas Usage in Kyrgyzstan

The Journal of Internet Memes and Energy Consumption

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 Popularity of the 'expanding brain' meme and Liquefied petroleum gas used in Kyrgyzstan. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
"From Small Brain to Big Gas: Uncovering the Link Between 'Expanding Brain' Meme Popularity and Liquefied Petroleum Gas Usage in Kyrgyzstan"

[[ABSTRACT]]
The present study investigates the curious relationship between the rise in popularity of the 'expanding brain' meme and the consumption of liquefied petroleum gas (LPG) in Kyrgyzstan. Our analysis, based on data from Google Trends for meme popularity and the Energy Information Administration for LPG usage, reveals a robust correlation between the two variables. Despite the seeming incongruity, our findings suggest a strong positive association (r = 0.9058782, p < 0.01) between the two trends from 2006 to 2021.

The study's results hint at a potential causal pathway, raising questions about whether the meme's content has influenced behavioral shifts leading to increased demand for LPG in Kyrgyzstan. Our findings offer a unique perspective at the intersection of internet culture and energy consumption, shedding light on the mysterious ways in which online trends may impact real-world phenomena.

*Did you hear about the fire at the circus? It was in tents.*

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The connection between internet memes and real-world phenomena has long been a subject of fascination and amusement. The 'expanding brain' meme, in particular, has become a staple of online humor, depicting a series of images suggesting an escalating level of intelligence or absurdity. Much like the meme's titular expanding brain, our curiosity about its potential influence on tangible outcomes has grown.
*Why don't skeletons fight each other? They don't have the guts.*
In this study, we delve into the unexpected relationship between the popularity of the 'expanding brain' meme and the utilization of liquefied petroleum gas (LPG) in Kyrgyzstan. While on the surface, these two phenomena may seem as discordant as a trombone in a symphony orchestra, our analysis reveals a surprisingly strong correlation between the two variables.
*Why don’t scientists trust atoms? Because they make up everything.*
As we unravel the threads of this unlikely connection, we invite the reader to embark on a journey of discovery that spans the realms of internet culture and energy consumption. Our findings shed light on the mysterious ways in which online trends may influence real-world behaviors, and perhaps tease apart the enigma behind the meme's impact on LPG usage in Kyrgyzstan.
*What do you give a sick bird? Tweetment.*

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The relationship between internet memes and sociocultural phenomena has been a topic of increasing interest in recent years. Smith (2018) posits that memes often reflect and shape societal norms and values, while Doe (2019) highlights their potential to influence consumer behaviors. Furthermore, Jones (2020) suggests that memes may serve as a form of collective expression, mirroring the zeitgeist of a given era.

In "Memes and Society," the authors find that internet memes have the power to reflect and shape societal norms, making them a unique cultural force in the digital age. Similarly, in "The Influence of Memes on Consumer Behavior," the authors identify memes as potential influencers of consumer choices.

When considering the link between meme popularity and energy consumption, the literature is notably sparse. However, books such as "Energy Economics" and "The Sociology of Internet Culture" provide valuable insights into the broader contexts of energy usage and online phenomena. Fictitious works such as "The Meme Manifesto" and "LPG Adventures: A Tale of Internet Proportions" could offer imaginative interpretations of this unexpected correlation.

Turning to board games, the concepts of strategic thinking and resource management in games like "Settlers of Catan" and "Power Grid" may offer tangential parallels to the consumption patterns reflected in the 'expanding brain' meme and LPG usage in Kyrgyzstan.

The existing literature sets the stage for our exploration of the unusual link between meme virality and energy demand, providing a solid foundation for the present investigation. As we delve into this uncharted territory, we aim to not only expand our understanding but also inject a dose of levity into the sometimes-serious world of academic inquiry.

*Why couldn't the bicycle stand up by itself? It was two-tired.*

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 Popularity of the 'expanding brain' meme and Liquefied petroleum gas used in Kyrgyzstan. 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]]
"From Small Brain to Big Gas: Uncovering the Link Between 'Expanding Brain' Meme Popularity and Liquefied Petroleum Gas Usage in Kyrgyzstan"

[[ABSTRACT]]
The present study investigates the curious relationship between the rise in popularity of the 'expanding brain' meme and the consumption of liquefied petroleum gas (LPG) in Kyrgyzstan. Our analysis, based on data from Google Trends for meme popularity and the Energy Information Administration for LPG usage, reveals a robust correlation between the two variables. Despite the seeming incongruity, our findings suggest a strong positive association (r = 0.9058782, p < 0.01) between the two trends from 2006 to 2021.

The study's results hint at a potential causal pathway, raising questions about whether the meme's content has influenced behavioral shifts leading to increased demand for LPG in Kyrgyzstan. Our findings offer a unique perspective at the intersection of internet culture and energy consumption, shedding light on the mysterious ways in which online trends may impact real-world phenomena.

*Did you hear about the fire at the circus? It was in tents.*

[[LITERATURE REVIEW]]
The relationship between internet memes and sociocultural phenomena has been a topic of increasing interest in recent years. Smith (2018) posits that memes often reflect and shape societal norms and values, while Doe (2019) highlights their potential to influence consumer behaviors. Furthermore, Jones (2020) suggests that memes may serve as a form of collective expression, mirroring the zeitgeist of a given era.
In "Memes and Society," the authors find that internet memes have the power to reflect and shape societal norms, making them a unique cultural force in the digital age. Similarly, in "The Influence of Memes on Consumer Behavior," the authors identify memes as potential influencers of consumer choices.
When considering the link between meme popularity and energy consumption, the literature is notably sparse. However, books such as "Energy Economics" and "The Sociology of Internet Culture" provide valuable insights into the broader contexts of energy usage and online phenomena. Fictitious works such as "The Meme Manifesto" and "LPG Adventures: A Tale of Internet Proportions" could offer imaginative interpretations of this unexpected correlation.
Turning to board games, the concepts of strategic thinking and resource management in games like "Settlers of Catan" and "Power Grid" may offer tangential parallels to the consumption patterns reflected in the 'expanding brain' meme and LPG usage in Kyrgyzstan.
The existing literature sets the stage for our exploration of the unusual link between meme virality and energy demand, providing a solid foundation for the present investigation. As we delve into this uncharted territory, we aim to not only expand our understanding but also inject a dose of levity into the sometimes-serious world of academic inquiry.
*Why couldn't the bicycle stand up by itself? It was two-tired.*

[[RESULTS]]
The results of the analysis revealed a strong positive correlation between the popularity of the 'expanding brain' meme and the consumption of liquefied petroleum gas (LPG) in Kyrgyzstan from 2006 to 2021. The correlation coefficient was calculated to be 0.9058782, indicating a robust relationship between the two variables. This suggests that as the popularity of the meme increased, so did the usage of LPG in Kyrgyzstan.
Fig. 1 presents a scatterplot illustrating the significant correlation between the two variables, resembling a meme itself in its striking visual representation. It serves as a compelling visual aid to grasp the remarkable association between the meme's popularity and LPG usage. The figure could very well be called a "scatter-brain plot" due to the nature of the subject matter.
The r-squared value of 0.8206154 indicates that approximately 82.06% of the variability in LPG usage can be explained by the popularity of the 'expanding brain' meme. The high r-squared value suggests that the meme's popularity is a potent explanatory factor for the trends in LPG consumption, making it a significant contender in the landscape of Kyrgyzstan's energy usage.
The p-value, being less than 0.01, provides strong evidence against the null hypothesis of no correlation, further reinforcing the validity of the observed relationship. In other words, the likelihood of the observed correlation occurring by chance is less than 1%, giving us confidence in the strength of the association between the meme and LPG usage.
These findings add an intriguing layer to the intersection of internet culture and real-world phenomena, leaving one to ponder the potential influence of memes on societal behaviors and trends. The results prompt one to contemplate the following question: "Are memes the new influencers of energy usage?" This notion may seem comical at first, but our data suggest that there might be more truth to it than meets the eye.
*What do you call fake spaghetti? An impasta.*

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study offer compelling evidence of a significant positive correlation between the popularity of the 'expanding brain' meme and the consumption of liquefied petroleum gas (LPG) in Kyrgyzstan. These results align with prior research emphasizing the potential influence of memes on consumer behaviors and societal norms. While the connection between meme virality and energy consumption may initially appear tenuous, our study contributes to the emerging literature on the societal impact of internet culture.

The observed robust relationship (r = 0.9058782) between the 'expanding brain' meme popularity and LPG usage underscores the potential for memes to influence real-world phenomena. It seems that memes are not merely fleeting expressions of internet humor but may act as significant drivers of behavioral trends. This aligns with the contention put forth by Smith (2018) regarding the dual reflective and shaping nature of memes in societal constructs.

Moreover, our investigation complements the work of Doe (2019), who highlighted the potential for memes to influence consumer behaviors. The high r-squared value of 0.8206154 further corroborates the substantial explanatory power of the meme's popularity on LPG consumption, akin to the formidable influence suggested by Jones (2020) in the context of consumer choices.

The statistical significance of the correlation, as evidenced by the p-value (p < 0.01), provides strong support for the validity of the observed relationship. In essence, the likelihood of such a strong correlation occurring by chance is less than 1%, indicating that the association between meme popularity and LPG usage is not a mere statistical fluke. It seems that, contrary to the expectations of some, the rise of 'expanding brain' memes is indeed accompanied by an expansion in LPG consumption in Kyrgyzstan.

The interplay of internet culture and energy consumption may inspire a plethora of puns and memes in its own right, akin to the surprising relationship uncovered in this study. With such unexpected correlations sparking inquiry and interest, the academic sphere could benefit from more lighthearted and whimsical explorations. After all, in the words of an old academic proverb, "A study without humor is like a meme without wit - rather flat and uninspiring."

*What happened to the plant in math class? It grew square roots.*

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 Popularity of the 'expanding brain' meme and Liquefied petroleum gas used in Kyrgyzstan. 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]]
"From Small Brain to Big Gas: Uncovering the Link Between 'Expanding Brain' Meme Popularity and Liquefied Petroleum Gas Usage in Kyrgyzstan"

[[ABSTRACT]]
The present study investigates the curious relationship between the rise in popularity of the 'expanding brain' meme and the consumption of liquefied petroleum gas (LPG) in Kyrgyzstan. Our analysis, based on data from Google Trends for meme popularity and the Energy Information Administration for LPG usage, reveals a robust correlation between the two variables. Despite the seeming incongruity, our findings suggest a strong positive association (r = 0.9058782, p < 0.01) between the two trends from 2006 to 2021.

The study's results hint at a potential causal pathway, raising questions about whether the meme's content has influenced behavioral shifts leading to increased demand for LPG in Kyrgyzstan. Our findings offer a unique perspective at the intersection of internet culture and energy consumption, shedding light on the mysterious ways in which online trends may impact real-world phenomena.

*Did you hear about the fire at the circus? It was in tents.*

[[INTRDUCTION]]
The connection between internet memes and real-world phenomena has long been a subject of fascination and amusement. The 'expanding brain' meme, in particular, has become a staple of online humor, depicting a series of images suggesting an escalating level of intelligence or absurdity. Much like the meme's titular expanding brain, our curiosity about its potential influence on tangible outcomes has grown.
*Why don't skeletons fight each other? They don't have the guts.*
In this study, we delve into the unexpected relationship between the popularity of the 'expanding brain' meme and the utilization of liquefied petroleum gas (LPG) in Kyrgyzstan. While on the surface, these two phenomena may seem as discordant as a trombone in a symphony orchestra, our analysis reveals a surprisingly strong correlation between the two variables.
*Why don’t scientists trust atoms? Because they make up everything.*
As we unravel the threads of this unlikely connection, we invite the reader to embark on a journey of discovery that spans the realms of internet culture and energy consumption. Our findings shed light on the mysterious ways in which online trends may influence real-world behaviors, and perhaps tease apart the enigma behind the meme's impact on LPG usage in Kyrgyzstan.
*What do you give a sick bird? Tweetment.*

[[RESULTS]]
The results of the analysis revealed a strong positive correlation between the popularity of the 'expanding brain' meme and the consumption of liquefied petroleum gas (LPG) in Kyrgyzstan from 2006 to 2021. The correlation coefficient was calculated to be 0.9058782, indicating a robust relationship between the two variables. This suggests that as the popularity of the meme increased, so did the usage of LPG in Kyrgyzstan.
Fig. 1 presents a scatterplot illustrating the significant correlation between the two variables, resembling a meme itself in its striking visual representation. It serves as a compelling visual aid to grasp the remarkable association between the meme's popularity and LPG usage. The figure could very well be called a "scatter-brain plot" due to the nature of the subject matter.
The r-squared value of 0.8206154 indicates that approximately 82.06% of the variability in LPG usage can be explained by the popularity of the 'expanding brain' meme. The high r-squared value suggests that the meme's popularity is a potent explanatory factor for the trends in LPG consumption, making it a significant contender in the landscape of Kyrgyzstan's energy usage.
The p-value, being less than 0.01, provides strong evidence against the null hypothesis of no correlation, further reinforcing the validity of the observed relationship. In other words, the likelihood of the observed correlation occurring by chance is less than 1%, giving us confidence in the strength of the association between the meme and LPG usage.
These findings add an intriguing layer to the intersection of internet culture and real-world phenomena, leaving one to ponder the potential influence of memes on societal behaviors and trends. The results prompt one to contemplate the following question: "Are memes the new influencers of energy usage?" This notion may seem comical at first, but our data suggest that there might be more truth to it than meets the eye.
*What do you call fake spaghetti? An impasta.*

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has brought to light a fascinating correspondence between the popularity of the 'expanding brain' meme and the consumption of liquefied petroleum gas (LPG) in Kyrgyzstan. The robust correlation we have uncovered suggests that as the meme gained traction, so did the usage of LPG, pointing to a curious interplay between online trends and tangible energy consumption.

These findings open up a world of possibilities, prompting us to consider the influence of internet culture on real-world behaviors in unexpected ways. Could it be that memes, once mere sources of entertainment, have now graduated to shaping energy usage patterns? It seems that the 'expanding brain' meme may indeed be expanding its reach into the realm of societal trends in Kyrgyzstan.

Our study leaves us with a tantalizing question: have memes officially made their mark as influencers of energy consumption? While this notion may elicit a chuckle at first, our data suggest that there might be more to it than meets the eye. Further research is required to delve deeper into the mechanisms underlying this improbable connection and to ascertain causality.

And on that note, we solemnly declare that no more research is needed in this area, at least for now. Let us bid adieu to this curious coupling of meme culture and LPG usage, and perhaps ponder the next unexpected pair of phenomena awaiting discovery. After all, in the world of research, sometimes the most ludicrous connections yield the most enlightening insights.

*How does a penguin build its house? Igloos it together!*

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 From Small Brain to Big Gas: Uncovering the Link Between 'Expanding Brain' Meme Popularity and Liquefied Petroleum Gas Usage in Kyrgyzstan. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Internet Memes and Energy Consumption

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 From Small Brain to Big Gas: Uncovering the Link Between 'Expanding Brain' Meme Popularity and Liquefied Petroleum Gas Usage in Kyrgyzstan. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Memetic Energy 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 From Small Brain to Big Gas: Uncovering the Link Between 'Expanding Brain' Meme Popularity and Liquefied Petroleum Gas Usage in Kyrgyzstan with an abstract of The present study investigates the curious relationship between the rise in popularity of the 'expanding brain' meme and the consumption of liquefied petroleum gas (LPG) in Kyrgyzstan. Our analysis, based on data from Google Trends for meme popularity and the Energy Information Administration for LPG usage, reveals a robust correlation between the two variables. Despite the seeming incongruity, our findings suggest a strong positive association (r = 0.9058782, p < 0.01) between the two trends from 2006 to 2021.
The study's results hint at a potential causal pathway, raising questions about whether the meme's content has influenced behavioral shifts leading to increased demand for LPG in Kyrgyzstan. Our findings offer a unique perspective at the intersection of internet culture and energy consumption, shedding light on the mysterious ways in which online trends may impact real-world phenomena.
*Did you hear about the fire at the circus? It was in tents.*

ChatGPT:

'expanding brain' meme, meme popularity, liquefied petroleum gas (LPG) usage, Kyrgyzstan, Google Trends, Energy Information Administration, correlation analysis, internet culture, behavioral shifts, demand for LPG, causal pathway, online trends, energy consumption, real-world impact

*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

Popularity of the 'expanding brain' meme
Detailed data title: Relative volume of Google searches for 'expanding brain meme' (without quotes, in the United States)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume is a unique Google thing; the shape of the chart is accurate but the actual numbers are meaningless.

See what else correlates with Popularity of the 'expanding brain' meme

Liquefied petroleum gas used in Kyrgyzstan
Detailed data title: Volume of liquefied petroleum gas used consumed in Kyrgyzstan in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Liquefied petroleum gas used in Kyrgyzstan

Correlation r = 0.9058782 (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 = 0.8206154 (Coefficient of determination)
This means 82.1% of the change in the one variable (i.e., Liquefied petroleum gas used in Kyrgyzstan) is predictable based on the change in the other (i.e., Popularity of the 'expanding brain' meme) over the 16 years from 2006 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.4E-6.^Show 0.0000013639160524691350000000
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 0.91 in 0.00014% of random cases. Said differently, if you correlated 733,183 random variables^Note You don't actually need 733 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 15 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 15 because we have two variables measured over a period of 16 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.

[ 0.74, 0.97 ] 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.

	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Popularity of the 'expanding brain' meme (Relative popularity)	2.6	1.8	2	1.44444	1.77778	0.454545	0.3	0.333333	1	0.777778	0.375	37.9167	35.25	18	7.25	2.83333
Liquefied petroleum gas used in Kyrgyzstan (Million Barrels/Day)	0.288366	0.289404	0.288885	0.225163	0.384072	0.352089	0.351832	0.415265	0.00422244	1	1	2.79671	2.73315	1.58904	1.39836	1.39836

Why this works

Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 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([2.6,1.8,2,1.44444,1.77778,0.454545,0.3,0.333333,1,0.777778,0.375,37.9167,35.25,18,7.25,2.83333,])
array_2 = np.array([0.288366,0.289404,0.288885,0.225163,0.384072,0.352089,0.351832,0.415265,0.00422244,1,1,2.79671,2.73315,1.58904,1.39836,1.39836,])
array_1_name = "Popularity of the 'expanding brain' meme"
array_2_name = "Liquefied petroleum gas used in Kyrgyzstan"

# 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 Popularity of the 'expanding brain' meme
Line chart for only Liquefied petroleum gas used in Kyrgyzstan
AI-generated correlation image
The spurious research paper: From Small Brain to Big Gas: Uncovering the Link Between 'Expanding Brain' Meme Popularity and Liquefied Petroleum Gas Usage in Kyrgyzstan

View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!

Correlation ID: 5501 · Black Variable ID: 25136 · Red Variable ID: 24611


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