about · email me · subscribe
Spurious correlation #4,737 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is US Tree Nut Consumption per Person and the second variable is Total comments on SmarterEveryDay YouTube videos.  The chart goes from 2007 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As more people started snacking on tree nuts, they unconsciously developed a nutty sense of humor. This led to an uptick in wittier and punnier comments on SmarterEveryDay videos, ultimately cracking everyone up and boosting the total number of comments. It’s like they say, you are what you eat, and in this case, they were all going completely nuts for science with a shell of a good time!

Model: dalle-3
Prompt: Certainly! The image generation prompt for DALL·E-3 is: [ Data cyber art ] Create an image of a bustling kitchen where people are happily snacking on an assortment of tree nuts. Their laughter and playful banter fill the air, creating a lively atmosphere. On a computer screen, depict the SmarterEveryDay YouTube channel displaying a steady stream of comments rolling in, with each comment showcasing an increasing level of humor and wit. The nutty snacking has unleashed a wave of clever and pun-filled remarks, capturing the infectious joy of the nut enthusiasts. Ensure that the visual depiction is simple and does not include any words or speech bubbles. 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: US Tree Nut Consumption per Person and Total comments on SmarterEveryDay 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: Cubism Data cyber art Scalar art Celtic art Cute cartoon
ChatGPT: Data cyber art

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 US Tree Nut Consumption per Person and Total comments on SmarterEveryDay YouTube videos, in the following situation: As more people started snacking on tree nuts, they unconsciously developed a nutty sense of humor. This led to an uptick in wittier and punnier comments on SmarterEveryDay videos, ultimately cracking everyone up and boosting the total number of comments. It’s like they say, you are what you eat, and in this case, they were all going completely nuts for science with a shell of a good time!. Keep the description simple.
ChatGPT: In a bustling kitchen, people are seen happily snacking on an assortment of tree nuts. As they munch away, their laughter and playful banter fill the air, creating a lively atmosphere. Meanwhile, on a computer screen, the SmarterEveryDay YouTube channel displays a steady stream of comments rolling in, with each comment showcasing an increasing level of humor and wit. It's clear that the nutty snacking has unleashed a wave of clever and pun-filled remarks, capturing the infectious joy of the nut enthusiasts.

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: [ Data cyber art ] and depicting this scene: In a bustling kitchen, people are seen happily snacking on an assortment of tree nuts. As they munch away, their laughter and playful banter fill the air, creating a lively atmosphere. Meanwhile, on a computer screen, the SmarterEveryDay YouTube channel displays a steady stream of comments rolling in, with each comment showcasing an increasing level of humor and wit. It's clear that the nutty snacking has unleashed a wave of clever and pun-filled remarks, capturing the infectious joy of the nut enthusiasts. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Certainly! The image generation prompt for DALL·E-3 is: [ Data cyber art ] Create an image of a bustling kitchen where people are happily snacking on an assortment of tree nuts. Their laughter and playful banter fill the air, creating a lively atmosphere. On a computer screen, depict the SmarterEveryDay YouTube channel displaying a steady stream of comments rolling in, with each comment showcasing an increasing level of humor and wit. The nutty snacking has unleashed a wave of clever and pun-filled remarks, capturing the infectious joy of the nut enthusiasts. Ensure that the visual depiction is simple and does not include any words or speech bubbles.

*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 US Tree Nut Consumption per Person caused Total comments on SmarterEveryDay YouTube videos to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)
Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos

The Journal of Nutty Science

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 US Tree Nut Consumption per Person and Total comments on SmarterEveryDay YouTube videos. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from Statista and YouTube to assess this nagging question. You found a correlation coefficient of 0.9048603 and p < 0.01 for 2007 to 2021.

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]]
Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos

[[ABSTRACT]]
Nuts and comments, oh my! This study delves into the unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. Using data from Statista and YouTube, we discovered a nutty correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021. This research cracks open the shell on an unexpected relationship and offers food for thought as we ponder the possibility that nuts can really get the comments flowing on educational content. So, are tree nuts the secret to wittier comments, or is this all just a nutty coincidence? Let's shell-abrate the power of nuts and YouTube commenters as we nut-urally embrace the unexpected twists of statistical analysis.


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 US Tree Nut Consumption per Person and Total comments on SmarterEveryDay YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos

[[ABSTRACT]]
Nuts and comments, oh my! This study delves into the unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. Using data from Statista and YouTube, we discovered a nutty correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021. This research cracks open the shell on an unexpected relationship and offers food for thought as we ponder the possibility that nuts can really get the comments flowing on educational content. So, are tree nuts the secret to wittier comments, or is this all just a nutty coincidence? Let's shell-abrate the power of nuts and YouTube commenters as we nut-urally embrace the unexpected twists of statistical analysis.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The world of statistical analysis often unearths unexpected connections, much like stumbling upon a hidden almond in a bowl of mixed nuts. In this study, we embark on a peculiar journey, delving into the potentially nutty relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. While the idea may seem as wild as a pistachio tree in the Great Plains, our research aims to shine a light on this unlikely association and its implications.

Statista and YouTube data have been like the trusty nutcrackers in our research toolkit, allowing us to peel back the layers of this seemingly whimsical correlation. We were astonished to uncover a correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021, leading us to ponder if there’s more to this nutty connection than meets the eye. It seems that the old adage “you are what you eat” takes on a whole new meaning when considering its impact on intellectual engagement with online educational content.

As we begin to unwrap this pecan of curiosity, we are confronted with the question: Could there be a deeper, more substantive link between nut consumption and the engagement level of YouTube viewers? Is it possible that the humble walnut has the power to elicit wittier comments, or are we simply cracking jokes in the face of statistical coincidence? The prospect of nuts influencing YouTube commenters might seem like a suggestion gone awry, but as we dive into the sea of data analysis, it becomes increasingly apparent that a kernel of truth may exist in this whimsical realm.

Join us as we endeavor to embrace the unconventional twists and turns while cracking open the shell of this statistically significant relationship. After all, in the world of academia, it’s not every day that one gets to blend nut consumption and YouTube comments in a research study – so let's shell-abrate this unexpected union as we nut-urally embark on our journey to uncover the truth behind the potential synergy of nuts and educational content engagement.


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 US Tree Nut Consumption per Person and Total comments on SmarterEveryDay 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. Then you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos

[[ABSTRACT]]
Nuts and comments, oh my! This study delves into the unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. Using data from Statista and YouTube, we discovered a nutty correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021. This research cracks open the shell on an unexpected relationship and offers food for thought as we ponder the possibility that nuts can really get the comments flowing on educational content. So, are tree nuts the secret to wittier comments, or is this all just a nutty coincidence? Let's shell-abrate the power of nuts and YouTube commenters as we nut-urally embrace the unexpected twists of statistical analysis.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of statistical analysis often unearths unexpected connections, much like stumbling upon a hidden almond in a bowl of mixed nuts. In this study, we embark on a peculiar journey, delving into the potentially nutty relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. While the idea may seem as wild as a pistachio tree in the Great Plains, our research aims to shine a light on this unlikely association and its implications.
Statista and YouTube data have been like the trusty nutcrackers in our research toolkit, allowing us to peel back the layers of this seemingly whimsical correlation. We were astonished to uncover a correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021, leading us to ponder if there’s more to this nutty connection than meets the eye. It seems that the old adage “you are what you eat” takes on a whole new meaning when considering its impact on intellectual engagement with online educational content.
As we begin to unwrap this pecan of curiosity, we are confronted with the question: Could there be a deeper, more substantive link between nut consumption and the engagement level of YouTube viewers? Is it possible that the humble walnut has the power to elicit wittier comments, or are we simply cracking jokes in the face of statistical coincidence? The prospect of nuts influencing YouTube commenters might seem like a suggestion gone awry, but as we dive into the sea of data analysis, it becomes increasingly apparent that a kernel of truth may exist in this whimsical realm.
Join us as we endeavor to embrace the unconventional twists and turns while cracking open the shell of this statistically significant relationship. After all, in the world of academia, it’s not every day that one gets to blend nut consumption and YouTube comments in a research study – so let's shell-abrate this unexpected union as we nut-urally embark on our journey to uncover the truth behind the potential synergy of nuts and educational content engagement.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The unlikeliest of connections often hide in plain sight, much like finding a cashew in a can of mixed nuts. As we delve into the curious correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos, we must acknowledge the novelty of this line of inquiry. While the subject matter may appear as unexpected as finding a macadamia tree in Alaska, it is crucial to explore the existing literature on this nutty association.

In "Nutty by Nature," Smith and Doe present a comprehensive analysis of the nutritional benefits of tree nuts, delving into their impact on human health and well-being. However, what the authors failed to foresee is the potential influence of tree nuts on the eloquence and wit of YouTube commenters. As we crack open the shell of statistical analysis, it becomes evident that there is more than meets the eye in this nutty conundrum.

Moving on to "The Almond Affair" by Jones, the focus shifts to the historical and cultural significance of almonds, highlighting their role in culinary traditions. While the book provides valuable insight into the world of nuts, it leaves us yearning for a deeper understanding of how almonds might inspire a torrent of engaging and thought-provoking comments on educational YouTube content.

Venturing into the realm of fiction, "The Cashew Conundrum" by Rowling centers around a group of young wizards unraveling the mysterious connection between magical cashew consumption and the sudden influx of witty remarks in the enchanted realm of social media. While this may seem fanciful, it prompts us to consider the enigmatic potential of nutty influencers transcending the boundaries of reality and online engagement.

Furthermore, a retrospective analysis inspired by numerous late-night cartoons and children's shows reveals a recurrent theme of anthropomorphic nuts engaging in clever banter and witty wordplay. From animated cashews cracking jokes to charismatic pistachios delivering punchlines, it becomes increasingly clear that the influence of nuts on humor and clever commentary extends beyond the realm of statistical significance.

As we sift through this diverse array of literature, it is apparent that the interplay between nut consumption and engagement with online educational content is a topic ripe for exploration. While the findings may initially appear as absurd as a pecan in a pumpkin patch, our research aims to shed light on this curious correlation and its potential implications. With that in mind, we embark on this nutty journey with unshelled enthusiasm and a kernel of curiosity, ready to crack the code of nuts and YouTube comments in pursuit of academic enlightenment and perhaps a few chuckles along the way.


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 US Tree Nut Consumption per Person and Total comments on SmarterEveryDay YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Statista and YouTube . You used data from 2007 to 2021

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]]
Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos

[[ABSTRACT]]
Nuts and comments, oh my! This study delves into the unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. Using data from Statista and YouTube, we discovered a nutty correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021. This research cracks open the shell on an unexpected relationship and offers food for thought as we ponder the possibility that nuts can really get the comments flowing on educational content. So, are tree nuts the secret to wittier comments, or is this all just a nutty coincidence? Let's shell-abrate the power of nuts and YouTube commenters as we nut-urally embrace the unexpected twists of statistical analysis.

[[INTRODUCTION]]
The world of statistical analysis often unearths unexpected connections, much like stumbling upon a hidden almond in a bowl of mixed nuts. In this study, we embark on a peculiar journey, delving into the potentially nutty relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. While the idea may seem as wild as a pistachio tree in the Great Plains, our research aims to shine a light on this unlikely association and its implications.
Statista and YouTube data have been like the trusty nutcrackers in our research toolkit, allowing us to peel back the layers of this seemingly whimsical correlation. We were astonished to uncover a correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021, leading us to ponder if there’s more to this nutty connection than meets the eye. It seems that the old adage “you are what you eat” takes on a whole new meaning when considering its impact on intellectual engagement with online educational content.
As we begin to unwrap this pecan of curiosity, we are confronted with the question: Could there be a deeper, more substantive link between nut consumption and the engagement level of YouTube viewers? Is it possible that the humble walnut has the power to elicit wittier comments, or are we simply cracking jokes in the face of statistical coincidence? The prospect of nuts influencing YouTube commenters might seem like a suggestion gone awry, but as we dive into the sea of data analysis, it becomes increasingly apparent that a kernel of truth may exist in this whimsical realm.
Join us as we endeavor to embrace the unconventional twists and turns while cracking open the shell of this statistically significant relationship. After all, in the world of academia, it’s not every day that one gets to blend nut consumption and YouTube comments in a research study – so let's shell-abrate this unexpected union as we nut-urally embark on our journey to uncover the truth behind the potential synergy of nuts and educational content engagement.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To peel back the layers of this knotty conundrum, we embarked on a multidimensional approach that involved both quantitative and, dare we say, nutty methods. Our research team scoured the vast expanse of the internet, channeling our inner Sherlock Nuts, to gather data from diverse sources. The primary datasets for this study were sourced from Statista and YouTube, with supplementary information sprinkled in from various academic literature on consumer behavior and online engagement.

We began our expedition by extracting the data on US tree nut consumption per person from the statistical treasure trove of Statista. This data, spanning the years 2007 to 2021, provided us with a delectable buffet of nut consumption trends that we meticulously correlated with the total comments on SmarterEveryDay YouTube videos. The comment count data from these videos served as a quirky but intriguing indicator of viewer engagement and interaction with educational content.

In pursuit of cleanliness and order, we meticulously cleaned and wrangled the dataset to ensure its digestibility for the analytical engines of our statistical modeling. Once we had a robust and squeaky-clean dataset, we summoned the powers of correlation analysis to determine the strength and direction of the relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos.

Utilizing the statistical sorcery of software like R and Python, we conjured up scatter plots, correlation matrices, and regression models to unravel the complexities of this nuttastic affair. The correlation coefficient, armed with its trusty sidekick, the p-value, emerged from the statistical cauldron to reveal the strength and significance of the relationship.

As our data dance reached its crescendo, we found ourselves in the midst of statistical revelry, as the correlation coefficient of 0.9048603 with p < 0.01 dazzled us with its presence. This eccentric find prompted us to further investigate whether the synergistic dance of nut consumption and online engagement was merely a statistical fluke or a truly nut-able phenomenon.
Our research journey, akin to a whimsical scavenger hunt, also involved mining insights from diverse academic sources on consumer behavior, online engagement, and the psychology of dietary influences. These secondary resources lent additional context and theoretical grounding to our exploration, enriching our understanding of potential mechanisms underlying the nut-comment nexus.

It is important to note that while our research methods may invoke chuckles and raised eyebrows, their integrity and rigor were unwavering. As we embraced the quirks and surprises of this inquiry, we remained steadfast in our commitment to sound scientific methodologies whilst savoring the unexpected twists and turns along the way.



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 US Tree Nut Consumption per Person and Total comments on SmarterEveryDay YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Statista and YouTube .

For the time period 2007 to 2021, you found a correlation 0.9048603, r-squared of 0.8187722, 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]]
Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos

[[ABSTRACT]]
Nuts and comments, oh my! This study delves into the unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. Using data from Statista and YouTube, we discovered a nutty correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021. This research cracks open the shell on an unexpected relationship and offers food for thought as we ponder the possibility that nuts can really get the comments flowing on educational content. So, are tree nuts the secret to wittier comments, or is this all just a nutty coincidence? Let's shell-abrate the power of nuts and YouTube commenters as we nut-urally embrace the unexpected twists of statistical analysis.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The world of statistical analysis often unearths unexpected connections, much like stumbling upon a hidden almond in a bowl of mixed nuts. In this study, we embark on a peculiar journey, delving into the potentially nutty relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. While the idea may seem as wild as a pistachio tree in the Great Plains, our research aims to shine a light on this unlikely association and its implications.
Statista and YouTube data have been like the trusty nutcrackers in our research toolkit, allowing us to peel back the layers of this seemingly whimsical correlation. We were astonished to uncover a correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021, leading us to ponder if there’s more to this nutty connection than meets the eye. It seems that the old adage “you are what you eat” takes on a whole new meaning when considering its impact on intellectual engagement with online educational content.
As we begin to unwrap this pecan of curiosity, we are confronted with the question: Could there be a deeper, more substantive link between nut consumption and the engagement level of YouTube viewers? Is it possible that the humble walnut has the power to elicit wittier comments, or are we simply cracking jokes in the face of statistical coincidence? The prospect of nuts influencing YouTube commenters might seem like a suggestion gone awry, but as we dive into the sea of data analysis, it becomes increasingly apparent that a kernel of truth may exist in this whimsical realm.
Join us as we endeavor to embrace the unconventional twists and turns while cracking open the shell of this statistically significant relationship. After all, in the world of academia, it’s not every day that one gets to blend nut consumption and YouTube comments in a research study – so let's shell-abrate this unexpected union as we nut-urally embark on our journey to uncover the truth behind the potential synergy of nuts and educational content engagement.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The unearthing of an unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos has left us feeling nuttier than a fruitcake. Our statistical analysis uncovered a correlation coefficient of 0.9048603 and an r-squared of 0.8187722 for the time period spanning from 2007 to 2021. These findings suggest a strong and statistically significant relationship between these two seemingly unrelated variables, causing us to marvel at the unexpected pecan of correlations we stumbled upon.

Upon plotting the data and gazing upon the scatterplot (Fig. 1), it became quite clear that this correlation is not just a bag of mixed nuts. The plot illustrates a clear, upward trend that brings to mind the exponential growth of a cashew tree reaching for the sky. The strong positive correlation displayed in the figure serves as a visual reminder that the relationship between US tree nut consumption per person and the total comments on SmarterEveryDay YouTube videos is not just a fluke – it's a filbert of reality that demands further exploration.

The r-squared value of 0.8187722 further bolsters the credibility of this statistical peculiarity, indicating that approximately 81.88% of the variation in the total comments on SmarterEveryDay YouTube videos can be explained by the variation in US tree nut consumption. We couldn't help but marvel at this surprising bit of insight, feeling as though we stumbled across the elusive end of a rainbow leading to a pot of statistical gold.

With a p-value of less than 0.01, the results unambiguously point to a significant and unlikely association between these two seemingly incongruous variables. It's as though we've cracked open a walnut only to discover an unexpected message hidden within, much like finding a fortune in a fortune cookie that foretells the ebb and flow of YouTube comments based on nut consumption.

In conclusion, our findings shine a light on the unexpected relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. The statistics don't lie – there is a nutty correlation that demands further investigation. As we delve deeper into this enigmatic linkage, we invite our fellow researchers to join us in contemplating the potential impact of nuts on the engagement level of YouTube viewers. After all, in the world of academic research, it's not every day that one gets to blend nut consumption and YouTube comments, but these statistically significant findings suggest that there may be more to this nutty connection than meets the eye. Let's crack on with further exploration, shell-abrating the unexpected twists and turns that have led us to this statistically significant, and undeniably nutty, correlation. Cheers to the unexpected discoveries that enrich the world of scientific inquiry!


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 US Tree Nut Consumption per Person and Total comments on SmarterEveryDay YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos

[[ABSTRACT]]
Nuts and comments, oh my! This study delves into the unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. Using data from Statista and YouTube, we discovered a nutty correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021. This research cracks open the shell on an unexpected relationship and offers food for thought as we ponder the possibility that nuts can really get the comments flowing on educational content. So, are tree nuts the secret to wittier comments, or is this all just a nutty coincidence? Let's shell-abrate the power of nuts and YouTube commenters as we nut-urally embrace the unexpected twists of statistical analysis.

[[LITERATURE REVIEW]]
The unlikeliest of connections often hide in plain sight, much like finding a cashew in a can of mixed nuts. As we delve into the curious correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos, we must acknowledge the novelty of this line of inquiry. While the subject matter may appear as unexpected as finding a macadamia tree in Alaska, it is crucial to explore the existing literature on this nutty association.
In "Nutty by Nature," Smith and Doe present a comprehensive analysis of the nutritional benefits of tree nuts, delving into their impact on human health and well-being. However, what the authors failed to foresee is the potential influence of tree nuts on the eloquence and wit of YouTube commenters. As we crack open the shell of statistical analysis, it becomes evident that there is more than meets the eye in this nutty conundrum.
Moving on to "The Almond Affair" by Jones, the focus shifts to the historical and cultural significance of almonds, highlighting their role in culinary traditions. While the book provides valuable insight into the world of nuts, it leaves us yearning for a deeper understanding of how almonds might inspire a torrent of engaging and thought-provoking comments on educational YouTube content.
Venturing into the realm of fiction, "The Cashew Conundrum" by Rowling centers around a group of young wizards unraveling the mysterious connection between magical cashew consumption and the sudden influx of witty remarks in the enchanted realm of social media. While this may seem fanciful, it prompts us to consider the enigmatic potential of nutty influencers transcending the boundaries of reality and online engagement.
Furthermore, a retrospective analysis inspired by numerous late-night cartoons and children's shows reveals a recurrent theme of anthropomorphic nuts engaging in clever banter and witty wordplay. From animated cashews cracking jokes to charismatic pistachios delivering punchlines, it becomes increasingly clear that the influence of nuts on humor and clever commentary extends beyond the realm of statistical significance.
As we sift through this diverse array of literature, it is apparent that the interplay between nut consumption and engagement with online educational content is a topic ripe for exploration. While the findings may initially appear as absurd as a pecan in a pumpkin patch, our research aims to shed light on this curious correlation and its potential implications. With that in mind, we embark on this nutty journey with unshelled enthusiasm and a kernel of curiosity, ready to crack the code of nuts and YouTube comments in pursuit of academic enlightenment and perhaps a few chuckles along the way.

[[RESULTS]]
The unearthing of an unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos has left us feeling nuttier than a fruitcake. Our statistical analysis uncovered a correlation coefficient of 0.9048603 and an r-squared of 0.8187722 for the time period spanning from 2007 to 2021. These findings suggest a strong and statistically significant relationship between these two seemingly unrelated variables, causing us to marvel at the unexpected pecan of correlations we stumbled upon.
Upon plotting the data and gazing upon the scatterplot (Fig. 1), it became quite clear that this correlation is not just a bag of mixed nuts. The plot illustrates a clear, upward trend that brings to mind the exponential growth of a cashew tree reaching for the sky. The strong positive correlation displayed in the figure serves as a visual reminder that the relationship between US tree nut consumption per person and the total comments on SmarterEveryDay YouTube videos is not just a fluke – it's a filbert of reality that demands further exploration.
The r-squared value of 0.8187722 further bolsters the credibility of this statistical peculiarity, indicating that approximately 81.88% of the variation in the total comments on SmarterEveryDay YouTube videos can be explained by the variation in US tree nut consumption. We couldn't help but marvel at this surprising bit of insight, feeling as though we stumbled across the elusive end of a rainbow leading to a pot of statistical gold.
With a p-value of less than 0.01, the results unambiguously point to a significant and unlikely association between these two seemingly incongruous variables. It's as though we've cracked open a walnut only to discover an unexpected message hidden within, much like finding a fortune in a fortune cookie that foretells the ebb and flow of YouTube comments based on nut consumption.
In conclusion, our findings shine a light on the unexpected relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. The statistics don't lie – there is a nutty correlation that demands further investigation. As we delve deeper into this enigmatic linkage, we invite our fellow researchers to join us in contemplating the potential impact of nuts on the engagement level of YouTube viewers. After all, in the world of academic research, it's not every day that one gets to blend nut consumption and YouTube comments, but these statistically significant findings suggest that there may be more to this nutty connection than meets the eye. Let's crack on with further exploration, shell-abrating the unexpected twists and turns that have led us to this statistically significant, and undeniably nutty, correlation. Cheers to the unexpected discoveries that enrich the world of scientific inquiry!

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The analysis of the connection between US tree nut consumption per person and the total comments on SmarterEveryDay YouTube videos has unveiled a truly nutty correlation that defies conventional expectations. While the literature review initially probed the unconventional nature of our investigation, our research unequivocally reinforces the unexpected influence of tree nuts on online engagement. The statistically significant correlation coefficient of 0.9048603, coupled with a robust r-squared value of 0.8187722, provides concrete evidence supporting the hypothesis that nut consumption and YouTube comments are not just two nuts passing in the night. These findings align with prior research suggestive of the potential impact of nutty influencers transcending the boundaries of reality and online engagement, as humorously highlighted in the fictional "The Cashew Conundrum" by Rowling. Who knew that fantastical nutty tales held a kernel of truth?

The compelling visual representation depicted in the scatterplot serves as a testament to the strength of the correlation, reminiscent of a cashew tree reaching for the sky with unshelled enthusiasm. The upward trend observed on the plot further solidifies the notion that the rise in US tree nut consumption per person is indeed associated with a surge in the total comments on SmarterEveryDay YouTube videos. This unforeseen linkage, akin to finding a pistachio in a haystack, dispels any doubts about the genuineness of our findings. The r-squared value of 0.8187722, indicating that approximately 81.88% of the variation in YouTube comments can be explained by variations in nut consumption, left us feeling as though we uncovered a statistical pot of gold, or perhaps, a delectable nut-filled piñata.

Moreover, the p-value of less than 0.01 clarifies that our outcomes are not merely a fluke in the statistics. They reflect a tangy twist of fate, almost like finding a surprise almond in every bite of a fruitcake. This statistical peculiarity, with its strong and unlikely association between nut consumption and YouTube engagement, beckons further exploration and sparks curiosity. As researchers, we find ourselves cracking open the walnut of possibility, unveiling an unexpected message hidden within, much like finding an esoteric fortune that foretells the ebb and flow of YouTube comments based on nut consumption. Our statistical findings exude an unmistakable air of credibility, a delightful surprise that challenges us to shell-abrate the unusual twists and turns that have unraveled this nutty correlation. Cheers to the unexpected discoveries that enrich the world of scientific inquiry, and here's to cracking on with further exploration, because the path of discovery is indeed paved with unexpected surprises.


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 US Tree Nut Consumption per Person and Total comments on SmarterEveryDay YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos

[[ABSTRACT]]
Nuts and comments, oh my! This study delves into the unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. Using data from Statista and YouTube, we discovered a nutty correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021. This research cracks open the shell on an unexpected relationship and offers food for thought as we ponder the possibility that nuts can really get the comments flowing on educational content. So, are tree nuts the secret to wittier comments, or is this all just a nutty coincidence? Let's shell-abrate the power of nuts and YouTube commenters as we nut-urally embrace the unexpected twists of statistical analysis.

[[INTRDUCTION]]
The world of statistical analysis often unearths unexpected connections, much like stumbling upon a hidden almond in a bowl of mixed nuts. In this study, we embark on a peculiar journey, delving into the potentially nutty relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. While the idea may seem as wild as a pistachio tree in the Great Plains, our research aims to shine a light on this unlikely association and its implications.
Statista and YouTube data have been like the trusty nutcrackers in our research toolkit, allowing us to peel back the layers of this seemingly whimsical correlation. We were astonished to uncover a correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021, leading us to ponder if there’s more to this nutty connection than meets the eye. It seems that the old adage “you are what you eat” takes on a whole new meaning when considering its impact on intellectual engagement with online educational content.
As we begin to unwrap this pecan of curiosity, we are confronted with the question: Could there be a deeper, more substantive link between nut consumption and the engagement level of YouTube viewers? Is it possible that the humble walnut has the power to elicit wittier comments, or are we simply cracking jokes in the face of statistical coincidence? The prospect of nuts influencing YouTube commenters might seem like a suggestion gone awry, but as we dive into the sea of data analysis, it becomes increasingly apparent that a kernel of truth may exist in this whimsical realm.
Join us as we endeavor to embrace the unconventional twists and turns while cracking open the shell of this statistically significant relationship. After all, in the world of academia, it’s not every day that one gets to blend nut consumption and YouTube comments in a research study – so let's shell-abrate this unexpected union as we nut-urally embark on our journey to uncover the truth behind the potential synergy of nuts and educational content engagement.

[[RESULTS]]
The unearthing of an unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos has left us feeling nuttier than a fruitcake. Our statistical analysis uncovered a correlation coefficient of 0.9048603 and an r-squared of 0.8187722 for the time period spanning from 2007 to 2021. These findings suggest a strong and statistically significant relationship between these two seemingly unrelated variables, causing us to marvel at the unexpected pecan of correlations we stumbled upon.
Upon plotting the data and gazing upon the scatterplot (Fig. 1), it became quite clear that this correlation is not just a bag of mixed nuts. The plot illustrates a clear, upward trend that brings to mind the exponential growth of a cashew tree reaching for the sky. The strong positive correlation displayed in the figure serves as a visual reminder that the relationship between US tree nut consumption per person and the total comments on SmarterEveryDay YouTube videos is not just a fluke – it's a filbert of reality that demands further exploration.
The r-squared value of 0.8187722 further bolsters the credibility of this statistical peculiarity, indicating that approximately 81.88% of the variation in the total comments on SmarterEveryDay YouTube videos can be explained by the variation in US tree nut consumption. We couldn't help but marvel at this surprising bit of insight, feeling as though we stumbled across the elusive end of a rainbow leading to a pot of statistical gold.
With a p-value of less than 0.01, the results unambiguously point to a significant and unlikely association between these two seemingly incongruous variables. It's as though we've cracked open a walnut only to discover an unexpected message hidden within, much like finding a fortune in a fortune cookie that foretells the ebb and flow of YouTube comments based on nut consumption.
In conclusion, our findings shine a light on the unexpected relationship between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. The statistics don't lie – there is a nutty correlation that demands further investigation. As we delve deeper into this enigmatic linkage, we invite our fellow researchers to join us in contemplating the potential impact of nuts on the engagement level of YouTube viewers. After all, in the world of academic research, it's not every day that one gets to blend nut consumption and YouTube comments, but these statistically significant findings suggest that there may be more to this nutty connection than meets the eye. Let's crack on with further exploration, shell-abrating the unexpected twists and turns that have led us to this statistically significant, and undeniably nutty, correlation. Cheers to the unexpected discoveries that enrich the world of scientific inquiry!

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, it seems that we have stumbled upon a cashew of a discovery – the remarkable correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. The statistically significant findings leave us feeling nuttier than a walnut in a squirrels' disco, as we contemplate the potential influence of almonds, pecans, and hazelnuts on the witty banter and intellectual engagement of online viewers.

While some may dismiss this correlation as a mere statistical fluke, the evidence speaks for itself – this unexpected relationship demands further exploration and contemplation. As we peel back the layers of this pecan of curiosity, we can't help but crack a smile at the unexpected twists and turns that have led us to this filbert of statistical enlightenment.

So, what's the walnut matter? It seems that the old adage "you are what you eat" takes on a new dimension when considering the engaging potential of tree nuts. Could the humble walnut, in fact, be the secret ingredient behind wittier comments on educational content? Or perhaps we are simply nutting but a nutty coincidence in the face of statistical analysis.

We encourage our fellow researchers to shell-abrate this unexpected union of nut consumption and YouTube engagement, as we declare that no more research is needed in this area. It's time to nut-urally embrace the quirky, shell-shocking findings and nut-ify our understanding of the unconventional connections that enrich the world of scientific inquiry. After all, in the hallowed halls of academia, it's not every day that one gets to blend nut consumption and YouTube comments in a research study – so here's to the delightful surprises that keep our research as fresh as a newly cracked nut!


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 Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Nutty Science


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 Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Nutty Nutritional Research


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Can Tree Nuts on the Go Trigger SmarterYouTube Flow?: Exploring the Relationship Between US Tree Nut Consumption and Total Comments on SmarterEveryDay Videos with an abstract of Nuts and comments, oh my! This study delves into the unlikely correlation between US tree nut consumption and the total comments on SmarterEveryDay YouTube videos. Using data from Statista and YouTube, we discovered a nutty correlation coefficient of 0.9048603 with p < 0.01 for the years 2007 to 2021. This research cracks open the shell on an unexpected relationship and offers food for thought as we ponder the possibility that nuts can really get the comments flowing on educational content. So, are tree nuts the secret to wittier comments, or is this all just a nutty coincidence? Let's shell-abrate the power of nuts and YouTube commenters as we nut-urally embrace the unexpected twists of statistical analysis.

ChatGPT:

US tree nut consumption, SmarterEveryDay videos, YouTube comments, statistical analysis, correlation coefficient, educational content, nut consumption, YouTube analytics

*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

US Tree Nut Consumption per Person
Source: Statista
See what else correlates with US Tree Nut Consumption per Person

Total comments on SmarterEveryDay YouTube videos
Detailed data title: Total comments on SmarterEveryDay YouTube videos.
Source: SmarterEveryDay on YouTube
See what else correlates with Total comments on SmarterEveryDay YouTube videos

Correlation r = 0.9048603 (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 = 0.8187722 (Coefficient of determination)
This means 81.9% of the change in the one variable (i.e., Total comments on SmarterEveryDay YouTube videos) is predictable based on the change in the other (i.e., US Tree Nut Consumption per Person) over the 15 years from 2007 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.6E-6. 0.0000035668854129892046000000
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 0.9 in 0.00036% of random cases. Said differently, if you correlated 280,357 random variables You don't actually need 280 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 14 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 14 because we have two variables measured over a period of 15 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.73, 0.97 ] 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.
200720082009201020112012201320142015201620172018201920202021
US Tree Nut Consumption per Person (Pounds)3.613.583.773.883.794.1844.074.064.855.045.25.435.735.65
Total comments on SmarterEveryDay YouTube videos (Total comments)1410483555243993320961287101901763471084359135991582130177189788215106179020




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([3.61,3.58,3.77,3.88,3.79,4.18,4,4.07,4.06,4.85,5.04,5.2,5.43,5.73,5.65,])
array_2 = np.array([1410,4835,552,4399,33209,61287,101901,76347,108435,91359,91582,130177,189788,215106,179020,])
array_1_name = "US Tree Nut Consumption per Person"
array_2_name = "Total comments on SmarterEveryDay 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?

Your rating skills are legendary!


Correlation ID: 4737 · Black Variable ID: 453 · Red Variable ID: 25507
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0