Spurious correlation #4,083 · 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 first name Henry and the second variable is Wind power generated in Italy. The chart goes from 1989 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 first name Henry and the second variable is Wind power generated in Italy. The chart goes from 1989 to 2021, and the two variables track closely in value over that time.

AI explanation

Every time someone named Henry was born, a tiny gust of celebratory wind would sweep across Italy, giving the wind turbines a little extra oomph. It turns out, babies named Henry were inadvertently the key to Italy's booming wind power industry. Who would have thought that a popular baby name could have such a breezy impact on renewable energy?

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of rolling hills in Italy with wind turbines scattered across the landscape. In the foreground, create a representation of a newborn baby named Henry taking his first breath, with a gentle gust of wind swirling around him and adding energy to the spinning turbines. Use a Cubist style to depict the scene, with fragmented shapes and overlapping elements to convey a sense of movement and interconnectedness. Capture the celebration of new life and its impact on the renewable energy industry in a visually compelling manner. 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: Popularity of the first name Henry and Wind power generated in Italy. 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: Charcoal 3D Pixar Style a funny image macro Cubism Symbolism
ChatGPT: Cubism

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 Popularity of the first name Henry and Wind power generated in Italy, in the following situation: Every time someone named Henry was born, a tiny gust of celebratory wind would sweep across Italy, giving the wind turbines a little extra oomph. It turns out, babies named Henry were inadvertently the key to Italy's booming wind power industry. Who would have thought that a popular baby name could have such a breezy impact on renewable energy?. Keep the description simple.
ChatGPT: In Italy, the wind turbines spin peacefully across the rolling hills. As the sun rises, a newborn baby named Henry takes his first breath, and a gentle, celebratory gust of wind sweeps across the land, adding a little extra energy to the spinning turbines. The popularity of the name Henry has become intricately intertwined with the renewable energy industry in Italy, as the tiny gusts generated by each Henry born give the wind power industry a breezy boost.

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: [ Cubism ] and depicting this scene: In Italy, the wind turbines spin peacefully across the rolling hills. As the sun rises, a newborn baby named Henry takes his first breath, and a gentle, celebratory gust of wind sweeps across the land, adding a little extra energy to the spinning turbines. The popularity of the name Henry has become intricately intertwined with the renewable energy industry in Italy, as the tiny gusts generated by each Henry born give the wind power industry a breezy boost. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of rolling hills in Italy with wind turbines scattered across the landscape. In the foreground, create a representation of a newborn baby named Henry taking his first breath, with a gentle gust of wind swirling around him and adding energy to the spinning turbines. Use a Cubist style to depict the scene, with fragmented shapes and overlapping elements to convey a sense of movement and interconnectedness. Capture the celebration of new life and its impact on the renewable energy industry in a visually compelling manner.

*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 an increase in Popularity of the first name Henry caused Wind power generated in Italy to increase.

AI academic paper

(Because p < 0.01)

Blowin' in the Henry: Exploring the Breezy Connection Between the Popularity of the Name Henry and Wind Power Generation in Italy

Journal of Whimsical Linguistics

Jan 2024

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

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft 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 first name Henry and Wind power generated in Italy. 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]]
"Blowin' in the Henry: Exploring the Breezy Connection Between the Popularity of the Name Henry and Wind Power Generation in Italy"

[[ABSTRACT]]
In this study, we embark on an unusual exploration of the correlation between the popularity of the first name "Henry" and the generation of wind power in Italy. Utilizing data from the US Social Security Administration and the Energy Information Administration, we conducted a comprehensive analysis spanning the years 1989 to 2021. Our findings revealed a surprising correlation coefficient of 0.9000961 and a statistically significant p-value of less than 0.01, providing compelling evidence for the influence of the name "Henry" on wind power generation. This peculiar correlation invites us to consider the whimsical yet intriguing possibility that the gusts and zephyrs of wind may be swayed, at least in part, by the popularity of a name. We hope this research sparks a breeze of curiosity and entertainment while shedding light on this unexpectedly captivating connection.

[[LITERATURE REVIEW]]
The exploratory nature of our study led us to delve into a variety of sources, from serious academic studies to popular culture references, in an effort to uncover any hints of the airy connection between the popularity of the name "Henry" and wind power generation in Italy. While the initial search yielded scholarly works by Smith, Doe, and Jones, the journey soon took an unexpected turn, much like a sudden gust of wind on a tranquil day.
In "The Influence of Name Popularity on Environmental Phenomena," Smith et al. explored the potential impact of popular names on natural occurrences, drawing intriguing parallels between nomenclature and planetary rhythms. Mirroring this, Doe's "Eolian Euphony: A Study of Wind Power and Cultural Trends" delved into the cultural significance of wind power and its relationship to societal trends, presenting a thought-provoking backdrop for our unconventional investigation. Jones' work, "Nameology: Unearthing the Secrets of Moniker Influence," provided a theoretical framework for the influence of names on various aspects of human existence, invoking curiosity about the potential influences that names could exert on the forces of nature.
Venturing deeper into the realm of literature, we stumbled upon non-fiction works that seemed to brush against the edges of our quirky inquiry. "Wind Energy for Dummies" by Doe and Smith, though intended to demystify wind power for the layperson, unexpectedly hinted at the arcane interplay between the name "Henry" and the generation of renewable energy. Similarly, "Henry's Windy Adventures: A Tale of Renewable Energy" by Jane E. Jones drew parallels between the eponymous character's endeavors and the gusty currents of wind power, teasing at the very conundrum we sought to unravel.
As we navigated the sea of literary offerings, we couldn't help but notice fictional works that, although not directly related to our subject matter, carried a hint of airy allusion. "Gone with the Wind" by Margaret Mitchell, a timeless classic set against the backdrop of a turbulent era, playfully danced on the periphery of our study, offering a nod to the winds that feature prominently in both the novel's title and its narrative. Meanwhile, "The Name of the Wind" by Patrick Rothfuss, though a work of fantasy fiction, whispered a tantalizing hint of how names might hold sway over the unseen currents of the world—a notion that tiptoed alongside our inquiry into the influence of "Henry" on wind power.
In a lighthearted nod to the digital age, we couldn't overlook the role of internet memes that playfully reference the winds and the name "Henry." The viral phenomenon of "Henry, the Wind Whisperer" memes offered a tongue-in-cheek portrayal of an individual seemingly able to communicate with the wind, serving as a quirky reminder of the unexpected twists that nature and nomenclature can take.
With each turn of the proverbial page, our literature review journey veered further into whimsy and wonder, encompassing a dizzying array of references that underscore the breadth of this singularly breezy conundrum. As we move forward in our analysis, we hold onto the hope that these diverse sources will offer both insight and entertainment, underscoring our aim to straddle the line between the empirical and the entertaining.

[[RESULTS]]
The analysis of the data gleaned from the US Social Security Administration and the Energy Information Administration yielded winds of statistical significance, as we uncovered a remarkable correlation between the popularity of the first name "Henry" and wind power generation in Italy from 1989 to 2021. Our research leaves no gust unturned, as we present the compelling results that flutter at the intersection of nomenclature and nature.
The correlation coefficient of 0.9000961 speaks volumes, gusting with a force that cannot be ignored. This strong correlation suggests that the popularity of the name "Henry" is indeed blowing in the wind alongside the generation of wind power in Italy. It's as if the statistical zephyrs have conspired to reveal this surprising relationship, providing evidence that the winds of change may bear the imprint of a popular moniker.
Furthermore, the r-squared value of 0.8101729 underscores the robustness of this correlation, indicating that over 81% of the variation in wind power generation in Italy can be attributed to the popularity of the name "Henry." It seems that the winds of statistical inference are blowing strongly in favor of this unexpected relationship, leaving little room for doubt that the name "Henry" may hold sway over the breezy production of wind power.
Notably, the p-value of less than 0.01 adds an exclamation point to our findings, as it signifies a statistically significant relationship between the popularity of the name "Henry" and wind power generation in Italy. This result blows away any skepticism and leaves us with a firm declaration that the gusts of wind in Italy may indeed be influenced by the whims of nomenclature.
To visually underscore the strength of this correlation, we present a scatterplot (Fig. 1) that vividly depicts the tight relationship between the popularity of the name "Henry" and wind power generation in Italy. The points on the plot dance energetically, painting a picture of a strong and undeniable link between these seemingly disparate variables.
In conclusion, our research not only unravels the breezy connection between the popularity of the name "Henry" and wind power generation in Italy but also invites further exploration into the whimsical world of unexpected correlations. The winds of statistical analysis have blown in an unexpected direction, and we stand amid the breeze of these findings, marveling at the unexpected quirks of science and the whimsical dance of data.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our findings have stirred up quite a whirlwind of excitement in the realm of research, uncovering a correlation as robust as a gust of wind between the popularity of the name "Henry" and wind power generation in Italy. As we step into the breezy realm of discussion, we find ourselves confronted with a gale of quirky observations and unexpected twists that not only tickle the imagination but also blow open new avenues for exploration.

Revisiting the literature review, it's remarkable how the literary and scholarly works teasingly dance on the edges of our study, echoing the very breeze that we sought to capture in our analysis. The previously light-hearted allusions to nomenclature and natural phenomena, seemingly whimsical at first glance, now emerge as intriguing undercurrents that fortuitously align with our own findings. It's almost as if the whims of research and the wiles of wind have conspired to bring together the seemingly incongruous realms of monikers and meteorology, giving rise to a pun-tastic whirlwind of discovery.

Our results unmistakably lend support to the whimsical notions flirted with in our literature review, validating the wind-swept musings and airy inferences that once danced playfully on the fringes of our inquiry. The significant correlation coefficient effectively fans the flames of our previous readings, establishing a firm link between the airy influence of the name "Henry" and the atmospheric currents powering Italy's wind turbines.

Moreover, the substantial r-squared value breezily bolsters the theoretical underpinnings playfully hinted at in our literary foray, affirming that a considerable 81% of the variation in wind power generation in Italy can be attributed to the enduring popularity of the name "Henry." The winds of empirical inquiry have elegantly intertwined with the gentle breezes of popular culture, blowing away any lingering doubts about the veracity of this unexpected connection.

The satisfyingly p-value provides a gusty exclamation point to our findings, affirming that the winds of statistical inference have not idly meandered but have breezed forth with captivating evidence of the influence of nomenclature on natural phenomena. In the grand symphony of scientific discovery, this statistical eddy showcases how the whims of nomenclature and the currents of causality can collide, creating a tempest of unexpected correlations that leaves us marveling at the playful caprices of data analysis.

In the wake of this extraordinary convergence of whimsy and statistical robustness, we're left with a turbulent storm of curiosity and wonder, beckoning further exploration into the zephyrs of unexpected correlations. Our findings underscore the enchanting dance of data, where the seemingly improbable waltzes alongside the rigorously empirical, inviting researchers to set sail on new breezy adventures in the realm of unanticipated connections.

As we stand amid the windswept landscape of our findings, we're reminded that science, much like the capricious currents of wind, holds within it the promise of unexpected delights and uncharted marvels. And as we bid adieu to this discussion, we eagerly anticipate the breezy horizons that the gales of further exploration may reveal, as we navigate the whimsical winds of research with good humor and unyielding curiosity.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Popularity of the first name Henry and Wind power generated in Italy. 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]]
"Blowin' in the Henry: Exploring the Breezy Connection Between the Popularity of the Name Henry and Wind Power Generation in Italy"

[[ABSTRACT]]
In this study, we embark on an unusual exploration of the correlation between the popularity of the first name "Henry" and the generation of wind power in Italy. Utilizing data from the US Social Security Administration and the Energy Information Administration, we conducted a comprehensive analysis spanning the years 1989 to 2021. Our findings revealed a surprising correlation coefficient of 0.9000961 and a statistically significant p-value of less than 0.01, providing compelling evidence for the influence of the name "Henry" on wind power generation. This peculiar correlation invites us to consider the whimsical yet intriguing possibility that the gusts and zephyrs of wind may be swayed, at least in part, by the popularity of a name. We hope this research sparks a breeze of curiosity and entertainment while shedding light on this unexpectedly captivating connection.

[[INTRDUCTION]]
Amidst the whirlwind of research topics and the gusts of statistical analysis, one peculiar and breezy correlation has captured our attention—the relationship between the popularity of the first name "Henry" and the generation of wind power in Italy. While most studies opt for more traditional and expected variables, we decided to take a leap into the whimsical world of nomenclature and atmospheric influence.
As the winds of curiosity carried us through the annals of data from the US Social Security Administration and the Energy Information Administration, we found ourselves grappling with the question: Could there be a zephyr of truth in the notion that the name "Henry" exerts an unseen force on the production of wind power? Bravely, we ventured forth, armed with regression analyses, p-values, and a dash of humor, determined to uncover the breezy mystery lurking behind this unlikely correlation.
Now, as we present our findings, we urge our esteemed readers to buckle up for a wild ride through the squalls of statistical analysis and the whirlwinds of witty wordplay. What began as a lighthearted inquiry has blown into a significant and robust analysis, revealing a surprising correlation coefficient of 0.9000961 and a p-value of less than 0.01. This robust statistical evidence invites us to speculate on the possibility that the winds of Italy may indeed be ruffled by the popularity of the name "Henry."
In the pages that follow, we will unfurl the data, dissect the methodology, and blow away any skepticism about the legitimacy of this unusual yet captivating exploration. Join us as we venture into the breezy labyrinth of correlation and causation, where even the most unexpected variables can shape the winds of fortune and science. So, hold onto your hats, dear readers, as we embark on this zephyrous escapade into the unexpected intersection of nomenclature and nature.

[[RESULTS]]
The analysis of the data gleaned from the US Social Security Administration and the Energy Information Administration yielded winds of statistical significance, as we uncovered a remarkable correlation between the popularity of the first name "Henry" and wind power generation in Italy from 1989 to 2021. Our research leaves no gust unturned, as we present the compelling results that flutter at the intersection of nomenclature and nature.
The correlation coefficient of 0.9000961 speaks volumes, gusting with a force that cannot be ignored. This strong correlation suggests that the popularity of the name "Henry" is indeed blowing in the wind alongside the generation of wind power in Italy. It's as if the statistical zephyrs have conspired to reveal this surprising relationship, providing evidence that the winds of change may bear the imprint of a popular moniker.
Furthermore, the r-squared value of 0.8101729 underscores the robustness of this correlation, indicating that over 81% of the variation in wind power generation in Italy can be attributed to the popularity of the name "Henry." It seems that the winds of statistical inference are blowing strongly in favor of this unexpected relationship, leaving little room for doubt that the name "Henry" may hold sway over the breezy production of wind power.
Notably, the p-value of less than 0.01 adds an exclamation point to our findings, as it signifies a statistically significant relationship between the popularity of the name "Henry" and wind power generation in Italy. This result blows away any skepticism and leaves us with a firm declaration that the gusts of wind in Italy may indeed be influenced by the whims of nomenclature.
To visually underscore the strength of this correlation, we present a scatterplot (Fig. 1) that vividly depicts the tight relationship between the popularity of the name "Henry" and wind power generation in Italy. The points on the plot dance energetically, painting a picture of a strong and undeniable link between these seemingly disparate variables.
In conclusion, our research not only unravels the breezy connection between the popularity of the name "Henry" and wind power generation in Italy but also invites further exploration into the whimsical world of unexpected correlations. The winds of statistical analysis have blown in an unexpected direction, and we stand amid the breeze of these findings, marveling at the unexpected quirks of science and the whimsical dance of data.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

As the winds of research have blown us through this zephyrous journey, we find ourselves marveling at the unexpected correlation between the popularity of the name "Henry" and wind power generation in Italy. Our findings, with a correlation coefficient of 0.9000961 and a statistically significant p-value of less than 0.01, add a gust of whimsy to the scientific domain. It seems that the winds in Italy may indeed be singing "Hey, Henry!" as they churn out energy.

This research serves as a breeze of fresh air in the academic world, reminding us that statistical analyses can uncover the most peculiar connections. The robustness of the correlation, with an r-squared value of 0.8101729, emphasizes that over 81% of the wind power variation in Italy can be encapsulated by the popularity of the name "Henry." It's as if the winds are whispering, "Hear, Henry, here's the power!"

Our scatterplot vividly illustrates the harmonious dance between the name "Henry" and wind power generation, painting a picture of a strong correlation that blows away any doubt. Perhaps the winds in Italy are simply partial to a good ol' Henry, and who can blame them? After all, everyone loves a classic name with a breezy charm.

In the end, this study not only fascinates with its quirky findings but also leaves us with the wind at our backs, propelling us toward further exploration of unexpected correlations. After all, when it comes to the breezy bounds of correlation and causation, we've learned that even the wind has a sense of humor.

So, as the zephyrs carry us away from this study, let us bask in the breezy humor of this correlation, for no more research is needed in this whimsically wind-swept arena. It's time to let the name "Henry" and the winds of Italy blow on, carrying our findings to new zephyrous heights.

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 Blowin' in the Henry: Exploring the Breezy Connection Between the Popularity of the Name Henry and Wind Power Generation in Italy. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Whimsical Linguistics

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 Blowin' in the Henry: Exploring the Breezy Connection Between the Popularity of the Name Henry and Wind Power Generation in Italy. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Societal Studies and Eclectic Research

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 Blowin' in the Henry: Exploring the Breezy Connection Between the Popularity of the Name Henry and Wind Power Generation in Italy with an abstract of In this study, we embark on an unusual exploration of the correlation between the popularity of the first name "Henry" and the generation of wind power in Italy. Utilizing data from the US Social Security Administration and the Energy Information Administration, we conducted a comprehensive analysis spanning the years 1989 to 2021. Our findings revealed a surprising correlation coefficient of 0.9000961 and a statistically significant p-value of less than 0.01, providing compelling evidence for the influence of the name "Henry" on wind power generation. This peculiar correlation invites us to consider the whimsical yet intriguing possibility that the gusts and zephyrs of wind may be swayed, at least in part, by the popularity of a name. We hope this research sparks a breeze of curiosity and entertainment while shedding light on this unexpectedly captivating connection.

ChatGPT:

Henry, wind power generation, Italy, correlation, popularity, name, social security administration, Energy Information Administration, correlation coefficient, p-value, wind influence, wind gusts, zephyrs, whimsical, curiosity, entertainment, research, Italy wind power generation

*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 first name Henry
Detailed data title: Babies of all sexes born in the US named Henry
Source: US Social Security Administration
See what else correlates with Popularity of the first name Henry

Wind power generated in Italy
Detailed data title: Total wind power generated in Italy in billion kWh
Source: Energy Information Administration
See what else correlates with Wind power generated in Italy

Correlation r = 0.9000961 (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 = 0.8101729 (Coefficient of determination)
This means 81% of the change in the one variable (i.e., Wind power generated in Italy) is predictable based on the change in the other (i.e., Popularity of the first name Henry) over the 33 years from 1989 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.02E-12.^Show 0.0000000000010232591229808155
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 0.9 in 1.02E-10% of random cases. Said differently, if you correlated 977,269,566,957 random variables^Note You don't actually need 977 billion 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 32 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 32 because we have two variables measured over a period of 33 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.

[ 0.81, 0.95 ] 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.

	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Popularity of the first name Henry (Babies born)	2190	2272	2271	2353	2500	2427	2549	2566	2663	2805	2934	3131	3212	3333	3484	3933	4194	4676	5123	5792	5906	6412	7240	8080	8891	9448	10188	10400	10488	10723	10769	10789	11365
Wind power generated in Italy (Billion kWh)	0.0019	0.002	0.003	0.002	0.004	0.007	0.009	0.033	0.118	0.231	0.403	0.563	1.179	1.404	1.458	1.847	2.344	2.971	4.034	4.861	6.543	9.048	9.775	13.333	14.812	15.089	14.706	17.523	17.5653	17.5568	0	18.6082	20.687

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.
Outlandish outliers: There are "outliers" in this data.^Note In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

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

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

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{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([2190,2272,2271,2353,2500,2427,2549,2566,2663,2805,2934,3131,3212,3333,3484,3933,4194,4676,5123,5792,5906,6412,7240,8080,8891,9448,10188,10400,10488,10723,10769,10789,11365,])
array_2 = np.array([0.0019,0.002,0.003,0.002,0.004,0.007,0.009,0.033,0.118,0.231,0.403,0.563,1.179,1.404,1.458,1.847,2.344,2.971,4.034,4.861,6.543,9.048,9.775,13.333,14.812,15.089,14.706,17.523,17.5653,17.5568,0,18.6082,20.687,])
array_1_name = "Popularity of the first name Henry"
array_2_name = "Wind power generated in Italy"

# 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 first name Henry
Line chart for only Wind power generated in Italy
AI-generated correlation image
The spurious research paper: Blowin' in the Henry: Exploring the Breezy Connection Between the Popularity of the Name Henry and Wind Power Generation in Italy

View another random correlation

How fun was this correlation?

Your rating is much appreciated!

Correlation ID: 4083 · Black Variable ID: 2233 · Red Variable ID: 23750


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