about · email me · subscribe
Spurious correlation #4,829 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air quality in Longview, Texas and the second variable is Total length of 3Blue1Brown YouTube videos.  The chart goes from 2015 to 2023, and the two variables track closely in value over that time. Small Image

AI explanation

As the air quality improved, more oxygen became available, leading to enhanced brain function and creativity in the creator of 3Blue1Brown. This resulted in longer, more detailed explanations and visually stunning content, ultimately elevating the total length of the videos. It's like a breath of fresh air for mathematical explanations!

Model: dalle-3
Prompt: Generate an image of Longview, Texas, on a clear sunny day with a sense of fresh air in the atmosphere. In the background, Grant Sanderson of 3Blue1Brown is deeply engaged in crafting intricate mathematical videos. The serene surroundings and refreshing air inspire his mind, leading to the creation of visually stunning and imaginative content. 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: Air quality in Longview, Texas and Total length of 3Blue1Brown 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: Woodblock painting A scene from Skyrim Cute cartoon Scalar art Cyberpunk
ChatGPT: A scene from Skyrim

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air quality in Longview, Texas and Total length of 3Blue1Brown YouTube videos, in the following situation: As the air quality improved, more oxygen became available, leading to enhanced brain function and creativity in the creator of 3Blue1Brown. This resulted in longer, more detailed explanations and visually stunning content, ultimately elevating the total length of the videos. It's like a breath of fresh air for mathematical explanations!. Keep the description simple.
ChatGPT: You see a picturesque scene of Longview, Texas with clear blue skies and fresh, clean air. In the background, the creator of 3Blue1Brown is immersed in creating captivating mathematical videos. As the clean air fills his lungs, his mind becomes clear and inventive, leading to longer and more intricate video explanations. The videos are filled with visually stunning content, reflecting the enhanced creativity and focus brought on by the improved air quality.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A scene from Skyrim ] and depicting this scene: You see a picturesque scene of Longview, Texas with clear blue skies and fresh, clean air. In the background, the creator of 3Blue1Brown is immersed in creating captivating mathematical videos. As the clean air fills his lungs, his mind becomes clear and inventive, leading to longer and more intricate video explanations. The videos are filled with visually stunning content, reflecting the enhanced creativity and focus brought on by the improved air quality. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of Longview, Texas, on a clear sunny day with a sense of fresh air in the atmosphere. In the background, Grant Sanderson of 3Blue1Brown is deeply engaged in crafting intricate mathematical videos. The serene surroundings and refreshing air inspire his mind, leading to the creation of visually stunning and imaginative content.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Air quality in Longview, Texas positively influenced Total length of 3Blue1Brown YouTube videos.

AI academic paper

(Because p < 0.01)
Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos

Journal of Quirky Cross-Disciplinary Studies

Jan 2024
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Air quality in Longview, Texas and Total length of 3Blue1Brown YouTube videos. Make lots of jokes, goofy observations, and puns.

Make the title seem clever.

Your research team used data from Environmental Protection Agency and YouTube to assess this nagging question. You found a correlation coefficient of 0.9175410 and p < 0.01 for 2015 to 2023.

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]]
"Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos"

[[ABSTRACT]]
The intriguing relationship between air quality and YouTube content length has been the source of much speculation, with skeptics dismissing any possibility of correlation as mere 'hot air.' In this study, we delved into the ambient air quality data of Longview, Texas, and the total length of 3Blue1Brown videos to ascertain if there is any substantive link between these seemingly disparate variables. Using data spanning from 2015 to 2023, our research team discovered a remarkably strong correlation coefficient of 0.9175410 and p < 0.01, indicating a statistically significant association. Our findings suggest that as air quality in Longview improves, the length of 3Blue1Brown YouTube videos increases, providing unexpected insights into how atmospheric conditions may influence online educational content creation. This research not only sheds light on the peculiar interplay between environmental factors and internet content but also highlights the importance of 'airing' out unconventional connections in academia.


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 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 Air quality in Longview, Texas and Total length of 3Blue1Brown YouTube videos. Make lots of 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]]
"Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos"

[[ABSTRACT]]
The intriguing relationship between air quality and YouTube content length has been the source of much speculation, with skeptics dismissing any possibility of correlation as mere 'hot air.' In this study, we delved into the ambient air quality data of Longview, Texas, and the total length of 3Blue1Brown videos to ascertain if there is any substantive link between these seemingly disparate variables. Using data spanning from 2015 to 2023, our research team discovered a remarkably strong correlation coefficient of 0.9175410 and p < 0.01, indicating a statistically significant association. Our findings suggest that as air quality in Longview improves, the length of 3Blue1Brown YouTube videos increases, providing unexpected insights into how atmospheric conditions may influence online educational content creation. This research not only sheds light on the peculiar interplay between environmental factors and internet content but also highlights the importance of 'airing' out unconventional connections in academia.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
**[[INTRODUCTION]]**

The world of academic research often takes us down unforeseen paths, leading to discoveries that are as surprising as they are enlightening. In this study, we turn our attention to the unexpected correlation between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos. As we embark on this unconventional journey, it’s important to remember that in the realm of science, the air may be full of particles, but our data analysis is not up in the air.

The seemingly unrelated variables of air quality and video length have caught the attention of inquisitive minds, prompting us to investigate whether there might be a hidden connection between the two. At first glance, it might seem as though trying to find a link between air quality and YouTube content length is like comparing apples and oranges – an endeavor that some might dismiss as mere "fruitless" pursuit. However, we venture forth undeterred, eager to unravel the mysteries that lie within the data.

As we navigate through the world of statistics, it’s crucial to remember that correlation does not imply causation – a foundational principle in research that often leads to "spurious" associations. However, when we stumbled upon the initial correlation coefficient of 0.9175410 with p < 0.01, we couldn't help but be "stumped" by the unexpected strength of the relationship.

Our investigation not only seeks to uncover the statistical interplay between air quality and video length, but also aims to shed light on the potential implications of our findings. We are aware that, as researchers, we must "vent" our curiosity into uncharted territories to explore the multitude of factors that contribute to content creation, even if they appear to be as ill-matched as "chalk" and "cheese."

The results of our study, as we shall see, not only highlight the captivating nature of unconventional correlations but also emphasize the importance of staying open-minded in scientific inquiry. So, let us embark on this comical quest, delving into the depths of data with the unwavering resolve to "clear the air" surrounding this unexpected relationship.


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 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 Air quality in Longview, Texas and Total length of 3Blue1Brown YouTube videos. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos"

[[ABSTRACT]]
The intriguing relationship between air quality and YouTube content length has been the source of much speculation, with skeptics dismissing any possibility of correlation as mere 'hot air.' In this study, we delved into the ambient air quality data of Longview, Texas, and the total length of 3Blue1Brown videos to ascertain if there is any substantive link between these seemingly disparate variables. Using data spanning from 2015 to 2023, our research team discovered a remarkably strong correlation coefficient of 0.9175410 and p < 0.01, indicating a statistically significant association. Our findings suggest that as air quality in Longview improves, the length of 3Blue1Brown YouTube videos increases, providing unexpected insights into how atmospheric conditions may influence online educational content creation. This research not only sheds light on the peculiar interplay between environmental factors and internet content but also highlights the importance of 'airing' out unconventional connections in academia.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of academic research often takes us down unforeseen paths, leading to discoveries that are as surprising as they are enlightening. In this study, we turn our attention to the unexpected correlation between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos. As we embark on this unconventional journey, it’s important to remember that in the realm of science, the air may be full of particles, but our data analysis is not up in the air.
The seemingly unrelated variables of air quality and video length have caught the attention of inquisitive minds, prompting us to investigate whether there might be a hidden connection between the two. At first glance, it might seem as though trying to find a link between air quality and YouTube content length is like comparing apples and oranges – an endeavor that some might dismiss as mere "fruitless" pursuit. However, we venture forth undeterred, eager to unravel the mysteries that lie within the data.
As we navigate through the world of statistics, it’s crucial to remember that correlation does not imply causation – a foundational principle in research that often leads to "spurious" associations. However, when we stumbled upon the initial correlation coefficient of 0.9175410 with p < 0.01, we couldn't help but be "stumped" by the unexpected strength of the relationship.
Our investigation not only seeks to uncover the statistical interplay between air quality and video length, but also aims to shed light on the potential implications of our findings. We are aware that, as researchers, we must "vent" our curiosity into uncharted territories to explore the multitude of factors that contribute to content creation, even if they appear to be as ill-matched as "chalk" and "cheese."
The results of our study, as we shall see, not only highlight the captivating nature of unconventional correlations but also emphasize the importance of staying open-minded in scientific inquiry. So, let us embark on this comical quest, delving into the depths of data with the unwavering resolve to "clear the air" surrounding this unexpected relationship.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The quest to unveil the enigmatic connection between air quality in Longview, Texas, and the length of 3Blue1Brown YouTube videos has prompted a flurry of scholarly investigations. In "Smith et al.," the authors embark on a rigorous analysis of air quality indices, while simultaneously delving into the captivating world of educational content on digital platforms. Through their systematic examination, they unearth compelling evidence that hints at a potential relationship between atmospheric conditions and the duration of online math tutorials.

Additionally, "Doe and Jones" present a comprehensive exploration of Longview's air quality data, employing advanced statistical methodologies to tease out hidden patterns and anomalies. Their findings challenge conventional wisdom and beckon us to consider the possibility of a nuanced interplay between environmental factors and the production of online video content.

Turning our attention to non-fiction literature, "The Air Quality Index Handbook" by Dr. Lisa Smog provides a thorough overview of the intricacies of environmental monitoring, offering valuable insights into the nuances of air quality measurement. Furthermore, "Data Analysis for Dummies" by John Statistics equips researchers with the essential tools to navigate complex datasets and draw meaningful conclusions, proving to be an invaluable resource in our pursuit of uncovering unconventional correlations.

In the realm of fiction, the works of J.R.R. Tolkien, particularly "The Fellowship of the Ring," albeit seemingly unrelated to our research focus, subtly allude to the importance of atmospheric conditions in shaping the narrative. Moreover, the whimsical adventures chronicled in Lewis Carroll's "Alice's Adventures in Wonderland" playfully remind us that unexpected connections often lurk beneath the surface, waiting to be unveiled.

Drawing inspiration from the world of board games, "Ticket to Ride" provides a fitting analogy for our research journey, as we endeavor to traverse uncharted territory in search of meaningful connections. Similarly, the strategic maneuvering required in "Pandemic" offers a parallel to our systematic approach in unraveling the intricate relationship between air quality and digital content creation.

As we embark on this scholarly excursion, we must tread with the intellectual agility of an acrobat, navigating through the scholarly landscape while remaining open to the unexpected twists and turns that await. The literature surrounding our research topic, in all its seriousness and whimsy, serves as a testament to the boundless nature of academic inquiry and the delightful surprises that accompany the pursuit of knowledge.


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 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 Air quality in Longview, Texas and Total length of 3Blue1Brown YouTube videos. Make lots of 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 Environmental Protection Agency and YouTube . You used data from 2015 to 2023

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]]
"Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos"

[[ABSTRACT]]
The intriguing relationship between air quality and YouTube content length has been the source of much speculation, with skeptics dismissing any possibility of correlation as mere 'hot air.' In this study, we delved into the ambient air quality data of Longview, Texas, and the total length of 3Blue1Brown videos to ascertain if there is any substantive link between these seemingly disparate variables. Using data spanning from 2015 to 2023, our research team discovered a remarkably strong correlation coefficient of 0.9175410 and p < 0.01, indicating a statistically significant association. Our findings suggest that as air quality in Longview improves, the length of 3Blue1Brown YouTube videos increases, providing unexpected insights into how atmospheric conditions may influence online educational content creation. This research not only sheds light on the peculiar interplay between environmental factors and internet content but also highlights the importance of 'airing' out unconventional connections in academia.

[[INTRODUCTION]]
The world of academic research often takes us down unforeseen paths, leading to discoveries that are as surprising as they are enlightening. In this study, we turn our attention to the unexpected correlation between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos. As we embark on this unconventional journey, it’s important to remember that in the realm of science, the air may be full of particles, but our data analysis is not up in the air.
The seemingly unrelated variables of air quality and video length have caught the attention of inquisitive minds, prompting us to investigate whether there might be a hidden connection between the two. At first glance, it might seem as though trying to find a link between air quality and YouTube content length is like comparing apples and oranges – an endeavor that some might dismiss as mere "fruitless" pursuit. However, we venture forth undeterred, eager to unravel the mysteries that lie within the data.
As we navigate through the world of statistics, it’s crucial to remember that correlation does not imply causation – a foundational principle in research that often leads to "spurious" associations. However, when we stumbled upon the initial correlation coefficient of 0.9175410 with p < 0.01, we couldn't help but be "stumped" by the unexpected strength of the relationship.
Our investigation not only seeks to uncover the statistical interplay between air quality and video length, but also aims to shed light on the potential implications of our findings. We are aware that, as researchers, we must "vent" our curiosity into uncharted territories to explore the multitude of factors that contribute to content creation, even if they appear to be as ill-matched as "chalk" and "cheese."
The results of our study, as we shall see, not only highlight the captivating nature of unconventional correlations but also emphasize the importance of staying open-minded in scientific inquiry. So, let us embark on this comical quest, delving into the depths of data with the unwavering resolve to "clear the air" surrounding this unexpected relationship.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

**[[METHODOLOGY]]**

**Data Collection and Sources:**
We began our madcap journey into the world of unexpected correlations by collecting air quality data from the Environmental Protection Agency (EPA) for the city of Longview, Texas, spanning the years 2015 to 2023. The data included measurements of common air pollutants such as particulate matter (PM10 and PM2.5), nitrogen dioxide (NO2), sulfur dioxide (SO2), carbon monoxide (CO), and ground-level ozone (O3). Additionally, we mined the internet for all publicly available 3Blue1Brown YouTube videos released during the same time period, extracting the total length of each video in seconds to yield a comprehensive dataset for our analysis. Our team of intrepid researchers scoured the depths of cyberspace, venturing into the vast expanse of YouTube, armed with nothing but a tireless spirit and an insatiable thirst for unearthing peculiar connections.

**Data Analysis:**
With our curious hands full of data, we gallantly marched towards the realm of statistical analysis, wielding the formidable weapons of correlation coefficients and significance testing. We plotted the air quality data alongside the lengths of 3Blue1Brown videos, creating vibrant visualizations that danced across our computer screens with an exhilarating grace. Upon witnessing the initial glimpse of a potential relationship, we eagerly calculated the correlation coefficient, only to find ourselves agog at the unexpected strength of the association. To verify the robustness of our findings, we also subjected the data to rigorous hypothesis testing, ensuring that our results were not merely a statistical sleight of hand. Armed with the tools of research and an undying dedication to uncover the truth, we probed, poked, and prodded the data until it revealed its mysterious secrets.

**Control Variables and Limitations:**
In the midst of our uproarious investigation, we remained vigilant in accounting for any confounding variables that could have influenced our findings. Our analysis diligently controlled for factors such as seasonality, trending topics in mathematics, and any other external forces that could have surreptitiously influenced the length of 3Blue1Brown videos. Additionally, we recognized the limitations inherent in our study, acknowledging that while correlation was indeed present, we could not definitively establish causation. For as much as we sought to "air-tighten" our methodology, the nature of observational research inevitably leaves room for delightful uncertainty and a sprinkling of scientific whimsy.

**Ethical Considerations:**
In our pursuit of scholarly enlightenment, we upheld the highest standards of academic integrity, ensuring the ethical treatment of data and the dissemination of our findings with absolute transparency. We tip our hats to the noble principles of research ethics, knowing that our zany escapade into the unexplored nexus of air quality and YouTube video length was carried out with the utmost respect for the scientific pursuit of truth.

With our methodological musings complete, we present our quirky findings and whimsical insights, offering a delightful departure from the conventional norms of academic exploration.


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 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 Air quality in Longview, Texas and Total length of 3Blue1Brown YouTube videos. Make lots of 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 Environmental Protection Agency and YouTube .

For the time period 2015 to 2023, you found a correlation 0.9175410, r-squared of 0.8418815, 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]]
"Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos"

[[ABSTRACT]]
The intriguing relationship between air quality and YouTube content length has been the source of much speculation, with skeptics dismissing any possibility of correlation as mere 'hot air.' In this study, we delved into the ambient air quality data of Longview, Texas, and the total length of 3Blue1Brown videos to ascertain if there is any substantive link between these seemingly disparate variables. Using data spanning from 2015 to 2023, our research team discovered a remarkably strong correlation coefficient of 0.9175410 and p < 0.01, indicating a statistically significant association. Our findings suggest that as air quality in Longview improves, the length of 3Blue1Brown YouTube videos increases, providing unexpected insights into how atmospheric conditions may influence online educational content creation. This research not only sheds light on the peculiar interplay between environmental factors and internet content but also highlights the importance of 'airing' out unconventional connections in academia.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The world of academic research often takes us down unforeseen paths, leading to discoveries that are as surprising as they are enlightening. In this study, we turn our attention to the unexpected correlation between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos. As we embark on this unconventional journey, it’s important to remember that in the realm of science, the air may be full of particles, but our data analysis is not up in the air.
The seemingly unrelated variables of air quality and video length have caught the attention of inquisitive minds, prompting us to investigate whether there might be a hidden connection between the two. At first glance, it might seem as though trying to find a link between air quality and YouTube content length is like comparing apples and oranges – an endeavor that some might dismiss as mere "fruitless" pursuit. However, we venture forth undeterred, eager to unravel the mysteries that lie within the data.
As we navigate through the world of statistics, it’s crucial to remember that correlation does not imply causation – a foundational principle in research that often leads to "spurious" associations. However, when we stumbled upon the initial correlation coefficient of 0.9175410 with p < 0.01, we couldn't help but be "stumped" by the unexpected strength of the relationship.
Our investigation not only seeks to uncover the statistical interplay between air quality and video length, but also aims to shed light on the potential implications of our findings. We are aware that, as researchers, we must "vent" our curiosity into uncharted territories to explore the multitude of factors that contribute to content creation, even if they appear to be as ill-matched as "chalk" and "cheese."
The results of our study, as we shall see, not only highlight the captivating nature of unconventional correlations but also emphasize the importance of staying open-minded in scientific inquiry. So, let us embark on this comical quest, delving into the depths of data with the unwavering resolve to "clear the air" surrounding this unexpected relationship.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our investigation into the peculiar connection between air quality in Longview, Texas, and the length of 3Blue1Brown YouTube videos have undoubtedly left us breathless with excitement. We unearthed a substantial correlation coefficient of 0.9175410, indicating a remarkably strong relationship between these seemingly unrelated variables. It seems the air in Longview may carry more than just oxygen and pollutants – it may also hold the secret to the length of captivating educational videos.

We also calculated an r-squared value of 0.8418815, suggesting that a whopping 84.18% of the variability in the length of 3Blue1Brown videos can be explained by changes in air quality. This finding not only astonishes us but also reminds us that sometimes, the most unexpected relationships can have a high coefficient of determination – or as we like to call it, the "coefficient of revelation."

Furthermore, the p-value of less than 0.01 reinforced the statistical significance of our findings. This means that the likelihood of the observed correlation between air quality and video length occurring due to random chance is less than 1%, making it a result that is highly improbable to be a fluke. It seems the probability of this association being a mere "whiff" of luck is about as low as finding fresh air in a city center during rush hour.

To visually represent our fascinating discovery, we present Figure 1, a scatterplot that vividly illustrates the robust relationship between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos. The points in the scatterplot are so tightly clustered around the regression line that it's almost as if the data itself is "sticking" to the relationship, refusing to break free from the statistical bond.

In conclusion, our study not only unravels the unexpected link between air quality and online educational content but also adds a touch of whimsy to the world of statistical research. It is clear that in the realm of data analysis, even the most unconventional connections can breathe new life into our understanding of the world – and in this case, into the very videos that populate the internet.


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 Air quality in Longview, Texas and Total length of 3Blue1Brown YouTube videos. 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]]
"Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos"

[[ABSTRACT]]
The intriguing relationship between air quality and YouTube content length has been the source of much speculation, with skeptics dismissing any possibility of correlation as mere 'hot air.' In this study, we delved into the ambient air quality data of Longview, Texas, and the total length of 3Blue1Brown videos to ascertain if there is any substantive link between these seemingly disparate variables. Using data spanning from 2015 to 2023, our research team discovered a remarkably strong correlation coefficient of 0.9175410 and p < 0.01, indicating a statistically significant association. Our findings suggest that as air quality in Longview improves, the length of 3Blue1Brown YouTube videos increases, providing unexpected insights into how atmospheric conditions may influence online educational content creation. This research not only sheds light on the peculiar interplay between environmental factors and internet content but also highlights the importance of 'airing' out unconventional connections in academia.

[[LITERATURE REVIEW]]
The quest to unveil the enigmatic connection between air quality in Longview, Texas, and the length of 3Blue1Brown YouTube videos has prompted a flurry of scholarly investigations. In "Smith et al.," the authors embark on a rigorous analysis of air quality indices, while simultaneously delving into the captivating world of educational content on digital platforms. Through their systematic examination, they unearth compelling evidence that hints at a potential relationship between atmospheric conditions and the duration of online math tutorials.
Additionally, "Doe and Jones" present a comprehensive exploration of Longview's air quality data, employing advanced statistical methodologies to tease out hidden patterns and anomalies. Their findings challenge conventional wisdom and beckon us to consider the possibility of a nuanced interplay between environmental factors and the production of online video content.
Turning our attention to non-fiction literature, "The Air Quality Index Handbook" by Dr. Lisa Smog provides a thorough overview of the intricacies of environmental monitoring, offering valuable insights into the nuances of air quality measurement. Furthermore, "Data Analysis for Dummies" by John Statistics equips researchers with the essential tools to navigate complex datasets and draw meaningful conclusions, proving to be an invaluable resource in our pursuit of uncovering unconventional correlations.
In the realm of fiction, the works of J.R.R. Tolkien, particularly "The Fellowship of the Ring," albeit seemingly unrelated to our research focus, subtly allude to the importance of atmospheric conditions in shaping the narrative. Moreover, the whimsical adventures chronicled in Lewis Carroll's "Alice's Adventures in Wonderland" playfully remind us that unexpected connections often lurk beneath the surface, waiting to be unveiled.
Drawing inspiration from the world of board games, "Ticket to Ride" provides a fitting analogy for our research journey, as we endeavor to traverse uncharted territory in search of meaningful connections. Similarly, the strategic maneuvering required in "Pandemic" offers a parallel to our systematic approach in unraveling the intricate relationship between air quality and digital content creation.
As we embark on this scholarly excursion, we must tread with the intellectual agility of an acrobat, navigating through the scholarly landscape while remaining open to the unexpected twists and turns that await. The literature surrounding our research topic, in all its seriousness and whimsy, serves as a testament to the boundless nature of academic inquiry and the delightful surprises that accompany the pursuit of knowledge.

[[RESULTS]]
The results of our investigation into the peculiar connection between air quality in Longview, Texas, and the length of 3Blue1Brown YouTube videos have undoubtedly left us breathless with excitement. We unearthed a substantial correlation coefficient of 0.9175410, indicating a remarkably strong relationship between these seemingly unrelated variables. It seems the air in Longview may carry more than just oxygen and pollutants – it may also hold the secret to the length of captivating educational videos.
We also calculated an r-squared value of 0.8418815, suggesting that a whopping 84.18% of the variability in the length of 3Blue1Brown videos can be explained by changes in air quality. This finding not only astonishes us but also reminds us that sometimes, the most unexpected relationships can have a high coefficient of determination – or as we like to call it, the "coefficient of revelation."
Furthermore, the p-value of less than 0.01 reinforced the statistical significance of our findings. This means that the likelihood of the observed correlation between air quality and video length occurring due to random chance is less than 1%, making it a result that is highly improbable to be a fluke. It seems the probability of this association being a mere "whiff" of luck is about as low as finding fresh air in a city center during rush hour.
To visually represent our fascinating discovery, we present Figure 1, a scatterplot that vividly illustrates the robust relationship between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos. The points in the scatterplot are so tightly clustered around the regression line that it's almost as if the data itself is "sticking" to the relationship, refusing to break free from the statistical bond.
In conclusion, our study not only unravels the unexpected link between air quality and online educational content but also adds a touch of whimsy to the world of statistical research. It is clear that in the realm of data analysis, even the most unconventional connections can breathe new life into our understanding of the world – and in this case, into the very videos that populate the internet.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our investigation into the perplexing connection between air quality in Longview, Texas, and the length of 3Blue1Brown YouTube videos has launched us into a whirlwind of scientific exploration, leaving us more astounded than when we stumbled upon a statistical outlier during our caffeine-fueled late-night data analysis sessions. Our findings not only validate prior research but also shed light on the whimsical interplay between environmental variables and digital content creation, reminding us that in the world of statistical analysis, sometimes correlation can be as unpredictable as a lab rat on a caffeine overdose exploring a maze.

First and foremost, our results provide compelling support for the work of "Smith et al.," who, much like intrepid explorers, ventured into the uncharted territory of educational content on digital platforms and its potential connection to atmospheric conditions. In a twist of fate as surprising as stumbling upon a unicorn during a stroll through the research park, our study echoes their discovery of a significant relationship between air quality and the duration of online math tutorials. As we navigate the uncharted waters of unusual correlations, it becomes abundantly clear that the winds of statistical significance are blowing in the same direction as those of prior scholarship.

Similarly, the comprehensive analysis conducted by "Doe and Jones" reverberates through our own findings, resonating like a harmonious symphony of academic insight. Their pioneering work in uncovering hidden patterns in Longview's air quality data emerges as a beacon of mathematical truth, guiding us toward the revelation of a robust correlation with the length of 3Blue1Brown videos. Like two scientific peas in a statistically significant pod, our research and theirs stand hand in hand, affirming the unconventional but tangible link between atmospheric conditions and online video production.

The literature review, albeit a delightful blend of serious inquiry and whimsical allusions, has paved the way for our own scholarly foray into the unexpected connections that dwell in the realm of academic investigation. With the strategic maneuvering of "Ticket to Ride" and the steadfast determination akin to battling a virtual "Pandemic," we have embraced the spirit of adventure in pursuit of illuminating the captivating interplay between air quality and digital content creation.

In closing, our study not only validates previous insights but also injects a sense of mirth and wonder into the often-serious realm of scholarly inquiry. The robust correlation we've uncovered is a testament to the delightful surprises that await those who dare to explore the uncharted territories of statistical research, reminding us that, sometimes, the most unexpected connections can breathe new life into our understanding of the world—just like a breath of fresh air on a particularly smoggy day in Longview.


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 Air quality in Longview, Texas and Total length of 3Blue1Brown YouTube videos. 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]]
"Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos"

[[ABSTRACT]]
The intriguing relationship between air quality and YouTube content length has been the source of much speculation, with skeptics dismissing any possibility of correlation as mere 'hot air.' In this study, we delved into the ambient air quality data of Longview, Texas, and the total length of 3Blue1Brown videos to ascertain if there is any substantive link between these seemingly disparate variables. Using data spanning from 2015 to 2023, our research team discovered a remarkably strong correlation coefficient of 0.9175410 and p < 0.01, indicating a statistically significant association. Our findings suggest that as air quality in Longview improves, the length of 3Blue1Brown YouTube videos increases, providing unexpected insights into how atmospheric conditions may influence online educational content creation. This research not only sheds light on the peculiar interplay between environmental factors and internet content but also highlights the importance of 'airing' out unconventional connections in academia.

[[INTRDUCTION]]
The world of academic research often takes us down unforeseen paths, leading to discoveries that are as surprising as they are enlightening. In this study, we turn our attention to the unexpected correlation between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos. As we embark on this unconventional journey, it’s important to remember that in the realm of science, the air may be full of particles, but our data analysis is not up in the air.
The seemingly unrelated variables of air quality and video length have caught the attention of inquisitive minds, prompting us to investigate whether there might be a hidden connection between the two. At first glance, it might seem as though trying to find a link between air quality and YouTube content length is like comparing apples and oranges – an endeavor that some might dismiss as mere "fruitless" pursuit. However, we venture forth undeterred, eager to unravel the mysteries that lie within the data.
As we navigate through the world of statistics, it’s crucial to remember that correlation does not imply causation – a foundational principle in research that often leads to "spurious" associations. However, when we stumbled upon the initial correlation coefficient of 0.9175410 with p < 0.01, we couldn't help but be "stumped" by the unexpected strength of the relationship.
Our investigation not only seeks to uncover the statistical interplay between air quality and video length, but also aims to shed light on the potential implications of our findings. We are aware that, as researchers, we must "vent" our curiosity into uncharted territories to explore the multitude of factors that contribute to content creation, even if they appear to be as ill-matched as "chalk" and "cheese."
The results of our study, as we shall see, not only highlight the captivating nature of unconventional correlations but also emphasize the importance of staying open-minded in scientific inquiry. So, let us embark on this comical quest, delving into the depths of data with the unwavering resolve to "clear the air" surrounding this unexpected relationship.

[[RESULTS]]
The results of our investigation into the peculiar connection between air quality in Longview, Texas, and the length of 3Blue1Brown YouTube videos have undoubtedly left us breathless with excitement. We unearthed a substantial correlation coefficient of 0.9175410, indicating a remarkably strong relationship between these seemingly unrelated variables. It seems the air in Longview may carry more than just oxygen and pollutants – it may also hold the secret to the length of captivating educational videos.
We also calculated an r-squared value of 0.8418815, suggesting that a whopping 84.18% of the variability in the length of 3Blue1Brown videos can be explained by changes in air quality. This finding not only astonishes us but also reminds us that sometimes, the most unexpected relationships can have a high coefficient of determination – or as we like to call it, the "coefficient of revelation."
Furthermore, the p-value of less than 0.01 reinforced the statistical significance of our findings. This means that the likelihood of the observed correlation between air quality and video length occurring due to random chance is less than 1%, making it a result that is highly improbable to be a fluke. It seems the probability of this association being a mere "whiff" of luck is about as low as finding fresh air in a city center during rush hour.
To visually represent our fascinating discovery, we present Figure 1, a scatterplot that vividly illustrates the robust relationship between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos. The points in the scatterplot are so tightly clustered around the regression line that it's almost as if the data itself is "sticking" to the relationship, refusing to break free from the statistical bond.
In conclusion, our study not only unravels the unexpected link between air quality and online educational content but also adds a touch of whimsy to the world of statistical research. It is clear that in the realm of data analysis, even the most unconventional connections can breathe new life into our understanding of the world – and in this case, into the very videos that populate the internet.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has not only shed light on the surprising association between air quality in Longview, Texas, and the total length of 3Blue1Brown YouTube videos but has also proven that statistical analysis can be an absolute "breath" of fresh air. The substantial correlation coefficient of 0.9175410 and the r-squared value of 0.8418815 emphasize the compelling bond between these seemingly unrelated variables, making us wonder if "airing" out thought-provoking educational content is more closely tied to atmospheric conditions than we ever imagined.

The findings of our study prompt us to consider the whimsical possibility that the very particles floating through the air might hold sway over the duration of captivating mathematical explanations on YouTube. As we wrap up our investigation, we bid farewell to this comical quest by asserting that no further research is necessary in this area. After all, we have truly gotten to the "heart and lungs" of the matter, and there's no need to "ventilate" this connection any further. Instead, let's allow this peculiar correlation to hang in the air, adding a touch of intrigue and amusement to the world 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 Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Cross-Disciplinary 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 Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Mathematical Respiratory Ecology and Optimization (SMREO)


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 Breathing in Math: Exploring the Link between Air Quality in Longview, Texas, and the Length of 3Blue1Brown YouTube Videos with an abstract of The intriguing relationship between air quality and YouTube content length has been the source of much speculation, with skeptics dismissing any possibility of correlation as mere 'hot air.' In this study, we delved into the ambient air quality data of Longview, Texas, and the total length of 3Blue1Brown videos to ascertain if there is any substantive link between these seemingly disparate variables. Using data spanning from 2015 to 2023, our research team discovered a remarkably strong correlation coefficient of 0.9175410 and p < 0.01, indicating a statistically significant association. Our findings suggest that as air quality in Longview improves, the length of 3Blue1Brown YouTube videos increases, providing unexpected insights into how atmospheric conditions may influence online educational content creation. This research not only sheds light on the peculiar interplay between environmental factors and internet content but also highlights the importance of 'airing' out unconventional connections in academia.

ChatGPT:

Longview Texas air quality, YouTube video length correlation, 3Blue1Brown videos, air quality data Longview Texas, correlation between air quality and content length, atmospheric conditions and online content, environmental factors and internet content, unconventional connections in academia

*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

Air quality in Longview, Texas
Detailed data title: Percentage of days with good air quality in Longview, TX
Source: Environmental Protection Agency
See what else correlates with Air quality in Longview, Texas

Total length of 3Blue1Brown YouTube videos
Detailed data title: Total length of 3Blue1Brown YouTube videos.
Source: YouTube
See what else correlates with Total length of 3Blue1Brown YouTube videos

Correlation r = 0.9175410 (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 = 0.8418815 (Coefficient of determination)
This means 84.2% of the change in the one variable (i.e., Total length of 3Blue1Brown YouTube videos) is predictable based on the change in the other (i.e., Air quality in Longview, Texas) over the 9 years from 2015 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00049. 0.0004886859841257072000000000
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 0.92 in 0.049% of random cases. Said differently, if you correlated 2,046 random variables Which I absolutely did.
with the same 8 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 8 because we have two variables measured over a period of 9 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.65, 0.98 ] 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.
201520162017201820192020202120222023
Air quality in Longview, Texas (Good air quality)88.767191.803393.131990.384690.607798.347192.054890.13788.3978
Total length of 3Blue1Brown YouTube videos (Total length in seconds)2849156302844315548134635101110269957814153




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. Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
  5. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
  6. 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([88.7671,91.8033,93.1319,90.3846,90.6077,98.3471,92.0548,90.137,88.3978,])
array_2 = np.array([2849,15630,28443,15548,13463,51011,10269,9578,14153,])
array_1_name = "Air quality in Longview, Texas"
array_2_name = "Total length of 3Blue1Brown 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?

I'm grateful for your review!


Correlation ID: 4829 · Black Variable ID: 20837 · Red Variable ID: 25831
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0