about · email me · subscribe
Spurious correlation #4,677 · 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 Frankie and the second variable is Average length of LEMMiNO YouTube videos.  The chart goes from 2012 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Well, as the name Frankie gained popularity, more and more parents started naming their kids after the cool, laid-back vibe often associated with the name. This led to a surge in chill, easygoing individuals who just so happened to have a knack for creating in-depth, lengthy YouTube videos. The Frankies of the world inadvertently became the driving force behind an unusual but undeniable uptick in the average length of LEMMiNO's content. It's as if there's a secret connection between the name Frankie and an innate ability to spin captivating, longer-than-expected tales, turning the YouTube landscape into a playground for extended narratives and intriguing explorations. So, if you ever wondered about the mysterious link between a popular name and the length of online videos, it seems that the Frankies might hold the key to unlocking this quirky phenomenon!

Model: dalle-3
Prompt: Prompt: Generate an image that looks like a scene from 'Star Wars,' capturing a bustling YouTube studio filled with laid-back and distinctive creators named Frankie. The studio is abuzz with laughter and the sound of keyboards clicking as the Frankies chat and brainstorm, naturally lending themselves to creating immersive, extended narratives. The walls are adorned with posters of captivating, longer-than-average videos, showcasing intriguing explorations that captivate viewers. The scene captures the unexpected connection between the rising popularity of the name Frankie and the surge in the average length of LEMMiNO's content, bringing forth a quirky phenomenon in the world of YouTube. 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 Frankie and Average length of LEMMiNO YouTube videos. 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: a meme Woodblock painting Whimsical illustration An image that looks like it is a scene from 'Star Wars' An image that looks like it is a scene from 'Star Wars'
ChatGPT: An image that looks like it is a scene from 'Star Wars'

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 Frankie and Average length of LEMMiNO YouTube videos, in the following situation: Well, as the name Frankie gained popularity, more and more parents started naming their kids after the cool, laid-back vibe often associated with the name. This led to a surge in chill, easygoing individuals who just so happened to have a knack for creating in-depth, lengthy YouTube videos. The Frankies of the world inadvertently became the driving force behind an unusual but undeniable uptick in the average length of LEMMiNO's content. It's as if there's a secret connection between the name Frankie and an innate ability to spin captivating, longer-than-expected tales, turning the YouTube landscape into a playground for extended narratives and intriguing explorations. So, if you ever wondered about the mysterious link between a popular name and the length of online videos, it seems that the Frankies might hold the key to unlocking this quirky phenomenon!. Keep the description simple.
ChatGPT: Imagine a bustling YouTube studio filled with laid-back, easygoing creators named Frankie, each with a distinctive style. The room is abuzz with laughter and the sound of keyboards clicking as the Frankies chat and brainstorm. Their personalities seem to naturally lend themselves to creating immersive, extended narratives. The walls are adorned with posters of their captivating videos, each one longer than the last, showcasing intriguing explorations that captivate viewers. The scene captures the unexpected connection between the rising popularity of the name Frankie and the surge in the average length of LEMMiNO's content, bringing forth a quirky phenomenon in the world of YouTube.

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: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: Imagine a bustling YouTube studio filled with laid-back, easygoing creators named Frankie, each with a distinctive style. The room is abuzz with laughter and the sound of keyboards clicking as the Frankies chat and brainstorm. Their personalities seem to naturally lend themselves to creating immersive, extended narratives. The walls are adorned with posters of their captivating videos, each one longer than the last, showcasing intriguing explorations that captivate viewers. The scene captures the unexpected connection between the rising popularity of the name Frankie and the surge in the average length of LEMMiNO's content, bringing forth a quirky phenomenon in the world of YouTube. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image that looks like a scene from 'Star Wars,' capturing a bustling YouTube studio filled with laid-back and distinctive creators named Frankie. The studio is abuzz with laughter and the sound of keyboards clicking as the Frankies chat and brainstorm, naturally lending themselves to creating immersive, extended narratives. The walls are adorned with posters of captivating, longer-than-average videos, showcasing intriguing explorations that captivate viewers. The scene captures the unexpected connection between the rising popularity of the name Frankie and the surge in the average length of LEMMiNO's content, bringing forth a quirky phenomenon in the world of YouTube.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Popularity of the first name Frankie caused Average length of LEMMiNO YouTube videos to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)
A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos

The Journal of Quirky Name Studies

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Popularity of the first name Frankie and Average length of LEMMiNO YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from US Social Security Administration and YouTube to assess this nagging question. You found a correlation coefficient of 0.9738433 and p < 0.01 for 2012 to 2022.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos

[[ABSTRACT]]
This study delves into the intriguing and often overlooked connection between the frequency of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. Leveraging data from the US Social Security Administration and YouTube, our research team meticulously examined the potential correlation between these seemingly disparate factors. Our findings reveal a remarkably high correlation coefficient of 0.9738433, with a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022.

The implications of this research are both profound and, one might even say, "frankly" surprising. While conventional wisdom might suggest that a name's popularity would have little to do with the length of YouTube videos, our data suggests otherwise. We invite our fellow researchers to join us in this punerrific pursuit of uncovering the obscure correlations that permeate our world.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Popularity of the first name Frankie and Average length of LEMMiNO YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos

[[ABSTRACT]]
This study delves into the intriguing and often overlooked connection between the frequency of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. Leveraging data from the US Social Security Administration and YouTube, our research team meticulously examined the potential correlation between these seemingly disparate factors. Our findings reveal a remarkably high correlation coefficient of 0.9738433, with a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022.

The implications of this research are both profound and, one might even say, "frankly" surprising. While conventional wisdom might suggest that a name's popularity would have little to do with the length of YouTube videos, our data suggests otherwise. We invite our fellow researchers to join us in this punerrific pursuit of uncovering the obscure correlations that permeate our world.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the world of research, one often finds that the most unexpected pairings can yield the most intriguing insights. Our study takes a playful yet methodical approach to investigating the tangled web of connections between the popularity of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. With a twinkle of curiosity in our eyes and a pinch of statistical rigor, we aim to shed light on this enigmatic association.

The intersection of nomenclature and digital content duration may initially appear as a whimsical pursuit, akin to attempting to measure the length of a proverbial piece of string. However, as the adage goes, "All that glitters is not gold," and our research seeks to discern whether the popularity of the name "Frankie" truly glistens with a lustrous statistical relationship to the temporal aspect of LEMMiNO's video oeuvre.

Our investigation was prompted by an observation that, like a haiku composed in invisible ink, had been hiding in plain sight. As we delved into the depths of data from the US Social Security Administration and the labyrinthine archives of YouTube, we dared to wonder whether the eponymous name could wield influence on the artistic endeavors of digital content creators.

As we embarked on our mission, we encountered the classic research conundrum: correlation does not imply causation. Yet, armed with an arsenal of statistical tools and a bounty of good-natured humor, we embarked on our quest to sift through the sea of data and discern the secret patterns that lay beneath. As we traversed the landscape of scatter plots, regression analyses, and error bars, we couldn't help but "Frankly" marvel at the unexpected connections that bloomed like daisies in a field of variables.

We invite our esteemed colleagues to join us on this comical yet compelling voyage of discovery. With a touch of whimsy and a hint of mirth, we set out to uncover the statistical wizardry that links the nomenclature of "Frankie" to the chronology of LEMMiNO's creations. So, dear reader, fasten your seatbelts and prepare to embark on a journey that promises to be as entertaining as it is enlightening.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Popularity of the first name Frankie and Average length of LEMMiNO YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos

[[ABSTRACT]]
This study delves into the intriguing and often overlooked connection between the frequency of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. Leveraging data from the US Social Security Administration and YouTube, our research team meticulously examined the potential correlation between these seemingly disparate factors. Our findings reveal a remarkably high correlation coefficient of 0.9738433, with a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022.

The implications of this research are both profound and, one might even say, "frankly" surprising. While conventional wisdom might suggest that a name's popularity would have little to do with the length of YouTube videos, our data suggests otherwise. We invite our fellow researchers to join us in this punerrific pursuit of uncovering the obscure correlations that permeate our world.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the world of research, one often finds that the most unexpected pairings can yield the most intriguing insights. Our study takes a playful yet methodical approach to investigating the tangled web of connections between the popularity of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. With a twinkle of curiosity in our eyes and a pinch of statistical rigor, we aim to shed light on this enigmatic association.
The intersection of nomenclature and digital content duration may initially appear as a whimsical pursuit, akin to attempting to measure the length of a proverbial piece of string. However, as the adage goes, "All that glitters is not gold," and our research seeks to discern whether the popularity of the name "Frankie" truly glistens with a lustrous statistical relationship to the temporal aspect of LEMMiNO's video oeuvre.
Our investigation was prompted by an observation that, like a haiku composed in invisible ink, had been hiding in plain sight. As we delved into the depths of data from the US Social Security Administration and the labyrinthine archives of YouTube, we dared to wonder whether the eponymous name could wield influence on the artistic endeavors of digital content creators.
As we embarked on our mission, we encountered the classic research conundrum: correlation does not imply causation. Yet, armed with an arsenal of statistical tools and a bounty of good-natured humor, we embarked on our quest to sift through the sea of data and discern the secret patterns that lay beneath. As we traversed the landscape of scatter plots, regression analyses, and error bars, we couldn't help but "Frankly" marvel at the unexpected connections that bloomed like daisies in a field of variables.
We invite our esteemed colleagues to join us on this comical yet compelling voyage of discovery. With a touch of whimsy and a hint of mirth, we set out to uncover the statistical wizardry that links the nomenclature of "Frankie" to the chronology of LEMMiNO's creations. So, dear reader, fasten your seatbelts and prepare to embark on a journey that promises to be as entertaining as it is enlightening.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The relationship between seemingly unrelated factors has long intrigued researchers seeking to uncover hidden connections in the fabric of society. In their study "Names as Insignia: The Influence of Popular Nomenclature on Modern Culture," Smith and Doe (2010) explore the impact of individual names on social phenomena. Their work offers compelling insights into the potential influence of names on various aspects of modern life, laying the groundwork for our investigation into the correlation between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos.

Similarly, Jones (2015) delves into the realm of digital content creation in "The Art and Science of YouTube: Exploring the Aesthetics and Metrics of Online Video." The author examines the multifaceted dynamics that contribute to the duration of YouTube videos, providing a comprehensive overview of factors that may subtly shape content length. While Jones does not specifically address the influence of names on video duration, his exploration adds depth to the context of our research.

Turning our attention to literary works, "The Name Game: A Cultural Analysis of Monikers and Their Impact" by Johnson (2018) offers a comprehensive survey of the significance of names in society. The book delves into the subtleties of how names can shape perceptions and behaviors, weaving a narrative that expands our understanding of the potential influence of nomenclature on various domains, including digital media.

In the fictitious world, the novel "Names and Numbers" by A. Writer (2020) presents a whimsical tale of a protagonist named Frankie whose adventures seem to unfold in parallel with the average length of enigmatic YouTube videos. Although a work of fiction, the novel's thematic portrayal of the interconnectedness of names and digital content providentially echoes the focus of our research.

Moreover, in a recent social media post, the user @DataDive123 shared an intriguing anecdote linking the frequency of the name "Frankie" to the duration of captivating YouTube videos by LEMMiNO. While the post may not constitute a rigorous academic source, it serves as a reminder of the ongoing public dialogue regarding the potential connections between names and digital content characteristics.

As we navigate the labyrinthine landscape of literary and digital discourse, these diverse sources illuminate the multifaceted dimensions of our investigation, lending a nuanced perspective to the enthralling relationship between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Popularity of the first name Frankie and Average length of LEMMiNO YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from US Social Security Administration and YouTube . You used data from 2012 to 2022

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos

[[ABSTRACT]]
This study delves into the intriguing and often overlooked connection between the frequency of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. Leveraging data from the US Social Security Administration and YouTube, our research team meticulously examined the potential correlation between these seemingly disparate factors. Our findings reveal a remarkably high correlation coefficient of 0.9738433, with a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022.

The implications of this research are both profound and, one might even say, "frankly" surprising. While conventional wisdom might suggest that a name's popularity would have little to do with the length of YouTube videos, our data suggests otherwise. We invite our fellow researchers to join us in this punerrific pursuit of uncovering the obscure correlations that permeate our world.

[[INTRODUCTION]]
In the world of research, one often finds that the most unexpected pairings can yield the most intriguing insights. Our study takes a playful yet methodical approach to investigating the tangled web of connections between the popularity of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. With a twinkle of curiosity in our eyes and a pinch of statistical rigor, we aim to shed light on this enigmatic association.
The intersection of nomenclature and digital content duration may initially appear as a whimsical pursuit, akin to attempting to measure the length of a proverbial piece of string. However, as the adage goes, "All that glitters is not gold," and our research seeks to discern whether the popularity of the name "Frankie" truly glistens with a lustrous statistical relationship to the temporal aspect of LEMMiNO's video oeuvre.
Our investigation was prompted by an observation that, like a haiku composed in invisible ink, had been hiding in plain sight. As we delved into the depths of data from the US Social Security Administration and the labyrinthine archives of YouTube, we dared to wonder whether the eponymous name could wield influence on the artistic endeavors of digital content creators.
As we embarked on our mission, we encountered the classic research conundrum: correlation does not imply causation. Yet, armed with an arsenal of statistical tools and a bounty of good-natured humor, we embarked on our quest to sift through the sea of data and discern the secret patterns that lay beneath. As we traversed the landscape of scatter plots, regression analyses, and error bars, we couldn't help but "Frankly" marvel at the unexpected connections that bloomed like daisies in a field of variables.
We invite our esteemed colleagues to join us on this comical yet compelling voyage of discovery. With a touch of whimsy and a hint of mirth, we set out to uncover the statistical wizardry that links the nomenclature of "Frankie" to the chronology of LEMMiNO's creations. So, dear reader, fasten your seatbelts and prepare to embark on a journey that promises to be as entertaining as it is enlightening.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

In order to untangle the enigmatic relationship between the popularity of the first name "Frankie" and the average duration of LEMMiNO YouTube videos, our research team employed a unique and eclectic array of research methods. We harnessed the power of statistical analyses, linguistic insights, and a good dose of humor to shed light on this unconventional correlation.

To quantify the popularity of the name "Frankie," we delved into the extensive archives of the US Social Security Administration's baby name database. With the precision of a seasoned detective and the enthusiasm of a giddy schoolchild, we combed through the voluminous records spanning from 2012 to 2022, capturing the fluctuating fortunes of the moniker "Frankie." Just when one might have thought that the pursuit of data was a monotonous endeavor, the quirks and idiosyncrasies of name popularity kept us on our toes, much like a suspenseful plot twist in a gripping thriller.

Simultaneously, the task of gauging the average length of LEMMiNO YouTube videos involved a unique blend of automation and human judgment. We employed advanced web scraping techniques to harvest the temporal details of the channel's video catalog, and every click of the mouse felt like a step further into the unknown realms of digital content creation. As we navigated the labyrinthine landscape of video metrics, we couldn't help but marvel at the sheer diversity of content, each duration a testament to the creative tapestry woven by LEMMiNO.

Once armed with the raw data, we donned our metaphorical laboratory coats and dived headfirst into a series of rigorous statistical analyses. We employed Pearson's correlation coefficient to measure the strength and direction of the association between the frequency of the name "Frankie" and the temporal aspects of LEMMiNO's oeuvre. The numerical dance of correlation coefficients and p-values unfolded like a thrilling performance, with each statistical test revealing subtle nuances and unexpected patterns. Essentially, we were like detectives deciphering cryptic clues, except our clues were scatter plots and our investigations took place in the intriguing world of quantitative analysis.

Moreover, our research endeavor wasn't merely a quest for numbers; we also sought to uncover the underlying linguistic and cultural resonances that underscored the connection between the name "Frankie" and digital content duration. Our foray into the world of linguistic analysis involved a playful exploration of the semiotic underpinnings of nomenclature and artistic expression, with a nod to the amusing idiosyncrasies of human behavior and nomenclatural predilections. In essence, we were delving into the unique blend of science and linguistics that underpins the quirky correlations of human naming practices and digital content creation.

As we embarked on our methodological escapade, our journey was punctuated with moments of laughter, bemusement, and the occasional exclamation of "Eureka!" The concoction of statistical analysis, linguistic inquiry, and a dash of humor made for a heady brew of scientific exploration that transcended the ordinary.

In essence, our research methodology can be likened to a whimsical dance of data, science, and linguistic musings, converging in a harmonious symphony of statistical discovery. We invite our esteemed colleagues to join us in embracing this offbeat yet intellectually stimulating pursuit, and to share in the delight of uncovering the unexpected connections that lie beneath the veneer of everyday phenomena.

And as we bask in the afterglow of statistical revelations, let us remember that even in the serious pursuit of scientific inquiry, a touch of whimsy can be the secret ingredient that transforms a mundane analysis into a delightful escapade.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Popularity of the first name Frankie and Average length of LEMMiNO YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from US Social Security Administration and YouTube .

For the time period 2012 to 2022, you found a correlation 0.9738433, r-squared of 0.9483708, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos

[[ABSTRACT]]
This study delves into the intriguing and often overlooked connection between the frequency of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. Leveraging data from the US Social Security Administration and YouTube, our research team meticulously examined the potential correlation between these seemingly disparate factors. Our findings reveal a remarkably high correlation coefficient of 0.9738433, with a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022.

The implications of this research are both profound and, one might even say, "frankly" surprising. While conventional wisdom might suggest that a name's popularity would have little to do with the length of YouTube videos, our data suggests otherwise. We invite our fellow researchers to join us in this punerrific pursuit of uncovering the obscure correlations that permeate our world.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the world of research, one often finds that the most unexpected pairings can yield the most intriguing insights. Our study takes a playful yet methodical approach to investigating the tangled web of connections between the popularity of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. With a twinkle of curiosity in our eyes and a pinch of statistical rigor, we aim to shed light on this enigmatic association.
The intersection of nomenclature and digital content duration may initially appear as a whimsical pursuit, akin to attempting to measure the length of a proverbial piece of string. However, as the adage goes, "All that glitters is not gold," and our research seeks to discern whether the popularity of the name "Frankie" truly glistens with a lustrous statistical relationship to the temporal aspect of LEMMiNO's video oeuvre.
Our investigation was prompted by an observation that, like a haiku composed in invisible ink, had been hiding in plain sight. As we delved into the depths of data from the US Social Security Administration and the labyrinthine archives of YouTube, we dared to wonder whether the eponymous name could wield influence on the artistic endeavors of digital content creators.
As we embarked on our mission, we encountered the classic research conundrum: correlation does not imply causation. Yet, armed with an arsenal of statistical tools and a bounty of good-natured humor, we embarked on our quest to sift through the sea of data and discern the secret patterns that lay beneath. As we traversed the landscape of scatter plots, regression analyses, and error bars, we couldn't help but "Frankly" marvel at the unexpected connections that bloomed like daisies in a field of variables.
We invite our esteemed colleagues to join us on this comical yet compelling voyage of discovery. With a touch of whimsy and a hint of mirth, we set out to uncover the statistical wizardry that links the nomenclature of "Frankie" to the chronology of LEMMiNO's creations. So, dear reader, fasten your seatbelts and prepare to embark on a journey that promises to be as entertaining as it is enlightening.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our investigation into the correlation between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos yielded intriguing results. We found a notably high correlation coefficient of 0.9738433, indicating a strong positive relationship between these two variables. The coefficient of determination (r-squared) further bolstered this finding, standing at 0.9483708. Moreover, the p-value of less than 0.01 underscores the statistical significance of our results, affirming the robustness of the observed relationship.

Figure 1 visually portrays the compelling correlation between the frequency of the name "Frankie" and the average duration of LEMMiNO YouTube videos. The scatterplot graphically encapsulates the striking association that emerged from our meticulous analysis, paving the way for a deeper understanding of this unexpected nexus.

The data speaks for itself, illuminating a connection that may have eluded conventional scientific inquiry. The implications of our findings extend beyond the realm of mere statistical indices, shedding light on the intriguing interplay between nomenclature and digital content duration. This serendipitous revelation beckons us to embrace the whimsical and the unexpected in our pursuit of knowledge, reminding us that behind every number and scatterplot lies a story waiting to be told.

In conclusion, our research unearths a "Frank-ly" fascinating relationship between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos. We advocate for continued exploration of seemingly disparate phenomena, as it is often in these unconventional avenues that remarkable discoveries await.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Popularity of the first name Frankie and Average length of LEMMiNO YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos

[[ABSTRACT]]
This study delves into the intriguing and often overlooked connection between the frequency of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. Leveraging data from the US Social Security Administration and YouTube, our research team meticulously examined the potential correlation between these seemingly disparate factors. Our findings reveal a remarkably high correlation coefficient of 0.9738433, with a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022.

The implications of this research are both profound and, one might even say, "frankly" surprising. While conventional wisdom might suggest that a name's popularity would have little to do with the length of YouTube videos, our data suggests otherwise. We invite our fellow researchers to join us in this punerrific pursuit of uncovering the obscure correlations that permeate our world.

[[LITERATURE REVIEW]]
The relationship between seemingly unrelated factors has long intrigued researchers seeking to uncover hidden connections in the fabric of society. In their study "Names as Insignia: The Influence of Popular Nomenclature on Modern Culture," Smith and Doe (2010) explore the impact of individual names on social phenomena. Their work offers compelling insights into the potential influence of names on various aspects of modern life, laying the groundwork for our investigation into the correlation between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos.
Similarly, Jones (2015) delves into the realm of digital content creation in "The Art and Science of YouTube: Exploring the Aesthetics and Metrics of Online Video." The author examines the multifaceted dynamics that contribute to the duration of YouTube videos, providing a comprehensive overview of factors that may subtly shape content length. While Jones does not specifically address the influence of names on video duration, his exploration adds depth to the context of our research.
Turning our attention to literary works, "The Name Game: A Cultural Analysis of Monikers and Their Impact" by Johnson (2018) offers a comprehensive survey of the significance of names in society. The book delves into the subtleties of how names can shape perceptions and behaviors, weaving a narrative that expands our understanding of the potential influence of nomenclature on various domains, including digital media.
In the fictitious world, the novel "Names and Numbers" by A. Writer (2020) presents a whimsical tale of a protagonist named Frankie whose adventures seem to unfold in parallel with the average length of enigmatic YouTube videos. Although a work of fiction, the novel's thematic portrayal of the interconnectedness of names and digital content providentially echoes the focus of our research.
Moreover, in a recent social media post, the user @DataDive123 shared an intriguing anecdote linking the frequency of the name "Frankie" to the duration of captivating YouTube videos by LEMMiNO. While the post may not constitute a rigorous academic source, it serves as a reminder of the ongoing public dialogue regarding the potential connections between names and digital content characteristics.
As we navigate the labyrinthine landscape of literary and digital discourse, these diverse sources illuminate the multifaceted dimensions of our investigation, lending a nuanced perspective to the enthralling relationship between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos.

[[RESULTS]]
Our investigation into the correlation between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos yielded intriguing results. We found a notably high correlation coefficient of 0.9738433, indicating a strong positive relationship between these two variables. The coefficient of determination (r-squared) further bolstered this finding, standing at 0.9483708. Moreover, the p-value of less than 0.01 underscores the statistical significance of our results, affirming the robustness of the observed relationship.
Figure 1 visually portrays the compelling correlation between the frequency of the name "Frankie" and the average duration of LEMMiNO YouTube videos. The scatterplot graphically encapsulates the striking association that emerged from our meticulous analysis, paving the way for a deeper understanding of this unexpected nexus.
The data speaks for itself, illuminating a connection that may have eluded conventional scientific inquiry. The implications of our findings extend beyond the realm of mere statistical indices, shedding light on the intriguing interplay between nomenclature and digital content duration. This serendipitous revelation beckons us to embrace the whimsical and the unexpected in our pursuit of knowledge, reminding us that behind every number and scatterplot lies a story waiting to be told.
In conclusion, our research unearths a "Frank-ly" fascinating relationship between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos. We advocate for continued exploration of seemingly disparate phenomena, as it is often in these unconventional avenues that remarkable discoveries await.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study provide compelling evidence supporting the existence of a remarkably strong correlation between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos. Our results align with prior scholarly works, offering confirmation of the unexpected and, dare we say, amusing relationship between nomenclature and digital content characteristics.

Upon revisiting the literature, the work of Smith and Doe (2010) takes on a newfound significance, as their examination of the influence of individual names on societal phenomena appears remarkably prescient in light of our current findings. While Jones (2015) may not have delved into the influence of names on video duration specifically, their comprehensive overview of factors shaping content length hints at the intricate interplay we have unearthed. Furthermore, the ostensible fictional portrayal in "Names and Numbers" by A. Writer (2020) exaggerates the connections between a protagonist named Frankie and enigmatic YouTube videos, inadvertently inverting fiction into fact.

Our study not only replicates but also extends prior anecdotal sources, as exemplified by the intriguing social media post from @DataDive123, which now assumes an air of academic credibility in light of our statistically significant results. Despite its informal nature, this post foreshadowed the surprising nexus we have brought to light, reinforcing the importance of considering unconventional sources in scholarly inquiry.

In light of our statistical findings, it is paramount to acknowledge the nonpareil nature of the correlation coefficient, which far surpasses what one might reasonably expect in the realms of nomenclature and digital media. The robust r-squared value further solidifies the strength of the relationship, defying conventional expectations and arming us with a compelling scientific oddity. One might even say it's a "Frank-ly astonishing revelation" that beckons further investigation into the whimsical world of name-driven content creation.

As we ponder the broader implications of our findings, it becomes evident that the seemingly random chaos of our complex world conceals unanticipated connections that warrant systematic exploration. Ultimately, our "frank" examination of the overlooked relationship between the first name "Frankie" and LEMMiNO video duration enriches the scientific tapestry by weaving unexpected threads of correlation among seemingly unrelated variables. This punerrific pursuit of uncovering the obscure correlations that permeate our world is a testament to the endless marvels awaiting discovery in the often unexplored realms of scholarly inquiry.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Popularity of the first name Frankie and Average length of LEMMiNO YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos

[[ABSTRACT]]
This study delves into the intriguing and often overlooked connection between the frequency of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. Leveraging data from the US Social Security Administration and YouTube, our research team meticulously examined the potential correlation between these seemingly disparate factors. Our findings reveal a remarkably high correlation coefficient of 0.9738433, with a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022.

The implications of this research are both profound and, one might even say, "frankly" surprising. While conventional wisdom might suggest that a name's popularity would have little to do with the length of YouTube videos, our data suggests otherwise. We invite our fellow researchers to join us in this punerrific pursuit of uncovering the obscure correlations that permeate our world.

[[INTRDUCTION]]
In the world of research, one often finds that the most unexpected pairings can yield the most intriguing insights. Our study takes a playful yet methodical approach to investigating the tangled web of connections between the popularity of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. With a twinkle of curiosity in our eyes and a pinch of statistical rigor, we aim to shed light on this enigmatic association.
The intersection of nomenclature and digital content duration may initially appear as a whimsical pursuit, akin to attempting to measure the length of a proverbial piece of string. However, as the adage goes, "All that glitters is not gold," and our research seeks to discern whether the popularity of the name "Frankie" truly glistens with a lustrous statistical relationship to the temporal aspect of LEMMiNO's video oeuvre.
Our investigation was prompted by an observation that, like a haiku composed in invisible ink, had been hiding in plain sight. As we delved into the depths of data from the US Social Security Administration and the labyrinthine archives of YouTube, we dared to wonder whether the eponymous name could wield influence on the artistic endeavors of digital content creators.
As we embarked on our mission, we encountered the classic research conundrum: correlation does not imply causation. Yet, armed with an arsenal of statistical tools and a bounty of good-natured humor, we embarked on our quest to sift through the sea of data and discern the secret patterns that lay beneath. As we traversed the landscape of scatter plots, regression analyses, and error bars, we couldn't help but "Frankly" marvel at the unexpected connections that bloomed like daisies in a field of variables.
We invite our esteemed colleagues to join us on this comical yet compelling voyage of discovery. With a touch of whimsy and a hint of mirth, we set out to uncover the statistical wizardry that links the nomenclature of "Frankie" to the chronology of LEMMiNO's creations. So, dear reader, fasten your seatbelts and prepare to embark on a journey that promises to be as entertaining as it is enlightening.

[[RESULTS]]
Our investigation into the correlation between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos yielded intriguing results. We found a notably high correlation coefficient of 0.9738433, indicating a strong positive relationship between these two variables. The coefficient of determination (r-squared) further bolstered this finding, standing at 0.9483708. Moreover, the p-value of less than 0.01 underscores the statistical significance of our results, affirming the robustness of the observed relationship.
Figure 1 visually portrays the compelling correlation between the frequency of the name "Frankie" and the average duration of LEMMiNO YouTube videos. The scatterplot graphically encapsulates the striking association that emerged from our meticulous analysis, paving the way for a deeper understanding of this unexpected nexus.
The data speaks for itself, illuminating a connection that may have eluded conventional scientific inquiry. The implications of our findings extend beyond the realm of mere statistical indices, shedding light on the intriguing interplay between nomenclature and digital content duration. This serendipitous revelation beckons us to embrace the whimsical and the unexpected in our pursuit of knowledge, reminding us that behind every number and scatterplot lies a story waiting to be told.
In conclusion, our research unearths a "Frank-ly" fascinating relationship between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos. We advocate for continued exploration of seemingly disparate phenomena, as it is often in these unconventional avenues that remarkable discoveries await.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In this study, our exploration of the correlation between the popularity of the first name "Frankie" and the average duration of LEMMiNO YouTube videos has unveiled an unexpectedly robust relationship. The remarkably high correlation coefficient and statistically significant p-value have, shall we say, "Frankly" left us in awe of the influence wielded by this auspicious name on digital content creation.

Our findings not only affirm the strength of the association but also underscore the whimsical yet profound nature of statistical investigations. We must "Frank-ly" acknowledge that while correlations can amuse and surprise us, they do not imply causation. Nonetheless, we cannot ignore the tantalizing prospect of a world where the length of YouTube videos is not just a matter of artistic choice, but also a nod to the prevalence of certain names in society.

As we bid adieu to this curious foray into the nexus of nomenclature and digital content duration, we implore our esteemed colleagues to retain a sense of humor and curiosity in their scholarly pursuits. For it is in these lighthearted moments of statistical revelation that we may stumble upon the most remarkable insights – the kind that make us nod in appreciation of the delightful oddities inherent in our world.

In summary, we dare to declare that further research in this area may only serve to confirm the delightful and "Frank-ly" entertaining relationship between the popularity of the first name "Frankie" and the average length of LEMMiNO YouTube videos. With that said, we believe it's time to "Frank-ly" lay this particular investigation to rest, as we can all agree that there are only so many "Frankie" puns one can handle in the realm of scientific inquiry.


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 A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Name Studies


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 A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Name Associations


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 A Frank-ly Lengthy Exploration: The Relationship between the Popularity of the First Name Frankie and the Average Length of LEMMiNO YouTube Videos with an abstract of This study delves into the intriguing and often overlooked connection between the frequency of the first name "Frankie" and the average duration of LEMMiNO YouTube videos. Leveraging data from the US Social Security Administration and YouTube, our research team meticulously examined the potential correlation between these seemingly disparate factors. Our findings reveal a remarkably high correlation coefficient of 0.9738433, with a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022.
The implications of this research are both profound and, one might even say, "frankly" surprising. While conventional wisdom might suggest that a name's popularity would have little to do with the length of YouTube videos, our data suggests otherwise. We invite our fellow researchers to join us in this punerrific pursuit of uncovering the obscure correlations that permeate our world.

ChatGPT:

Frankie popularity, first name Frankie, LEMMiNO YouTube videos, correlation, US Social Security Administration, YouTube video duration, correlation coefficient, p-value, statistical significance, name popularity, YouTube video length, YouTube data analysis

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

Average length of LEMMiNO YouTube videos
Detailed data title: Average length of LEMMiNO YouTube videos.
Source: YouTube
See what else correlates with Average length of LEMMiNO YouTube videos

Correlation r = 0.9738433 (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 = 0.9483708 (Coefficient of determination)
This means 94.8% of the change in the one variable (i.e., Average length of LEMMiNO YouTube videos) is predictable based on the change in the other (i.e., Popularity of the first name Frankie) over the 11 years from 2012 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.3E-7. 0.0000004267668556345894400000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.97 in 4.3E-5% of random cases. Said differently, if you correlated 2,343,200 random variables You don't actually need 2 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 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.

[ 0.9, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
20122013201420152016201720182019202020212022
Popularity of the first name Frankie (Babies born)415413443479488560531584716704767
Average length of LEMMiNO YouTube videos (Length in seconds)370.933450.583466.976613.312953.0671030.561077.8902.83317161629.752051




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([415,413,443,479,488,560,531,584,716,704,767,])
array_2 = np.array([370.933,450.583,466.976,613.312,953.067,1030.56,1077.8,902.833,1716,1629.75,2051,])
array_1_name = "Popularity of the first name Frankie"
array_2_name = "Average length of LEMMiNO YouTube videos"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Big thanks for reviewing!


Correlation ID: 4677 · Black Variable ID: 3066 · Red Variable ID: 25588
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0