about · email me · subscribe
Spurious correlation #5,064 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and the second variable is Total comments on Tom Scott's YouTube videos.  The chart goes from 2009 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As more operators and tenders fired up their machines in New Jersey, the air became infused with the irresistible aroma of smoky goodness. Viewers couldn't help but snack while watching Tom Scott's videos, leading to a surge in comments as their sticky fingers struggled to type out their thoughts. Who knew that the path to engaging content was through the savory smoke clouds of food and tobacco roasting facilities in the Garden State! Remember, the comments section is a-jar of flavorful discussions.

Model: dalle-3
Prompt: An image that looks like it is a scene from a Pixar movie: In New Jersey, the setting sun bathes the city in a warm golden light, casting long shadows as food and tobacco roasting machines hum with activity. The air is filled with the rich aroma of smoked meat and tobacco. In the foreground, viewers in a cozy living room are captivated by Tom Scott's video on a large screen, their mesmerized eyes reflecting the colorful display. Meanwhile, outside the window, plumes of savory smoke rise against the vibrant sky, symbolizing both the thriving food and tobacco industry and the intense engagement in the online community. 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: The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott 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: An image that looks like it is a scene from a Pixar movie Cubism Minimalism Hyper-realistic Macabre
ChatGPT: An image that looks like it is a scene from a Pixar movie

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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott YouTube videos, in the following situation: As more operators and tenders fired up their machines in New Jersey, the air became infused with the irresistible aroma of smoky goodness. Viewers couldn't help but snack while watching Tom Scott's videos, leading to a surge in comments as their sticky fingers struggled to type out their thoughts. Who knew that the path to engaging content was through the savory smoke clouds of food and tobacco roasting facilities in the Garden State! Remember, the comments section is a-jar of flavorful discussions.. Keep the description simple.
ChatGPT: In New Jersey, the aroma of smoky goodness wafts through the air as food and tobacco roasting machines come to life. Meanwhile, on screens across the state, viewers indulge in snacks and watch Tom Scott's videos, their sticky fingers tapping out a surge of comments. The savory smoke clouds fuel both the food and tobacco industry and the engagement in the comments section.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from a Pixar movie ] and depicting this scene: In New Jersey, the aroma of smoky goodness wafts through the air as food and tobacco roasting machines come to life. Meanwhile, on screens across the state, viewers indulge in snacks and watch Tom Scott's videos, their sticky fingers tapping out a surge of comments. The savory smoke clouds fuel both the food and tobacco industry and the engagement in the comments section. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from a Pixar movie: In New Jersey, the setting sun bathes the city in a warm golden light, casting long shadows as food and tobacco roasting machines hum with activity. The air is filled with the rich aroma of smoked meat and tobacco. In the foreground, viewers in a cozy living room are captivated by Tom Scott's video on a large screen, their mesmerized eyes reflecting the colorful display. Meanwhile, outside the window, plumes of savory smoke rise against the vibrant sky, symbolizing both the thriving food and tobacco industry and the intense engagement in the online community.

*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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey positively influenced Total comments on Tom Scott YouTube videos. Make it feel plausible.

AI academic paper

(Because p < 0.01)
The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos

The Journal of Culinary Nicotine Studies

Jan 2024

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




Model: gpt-3.5-turbo-1106
System prompt: You are a 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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title punny if you can come up with clever pun. If not, just make it sound clever.

Your research team used data from Bureau of Larbor Statistics and YouTube to assess this nagging question. You found a correlation coefficient of 0.9435917 and p < 0.01 for 2009 to 2022.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos

[[ABSTRACT]]
In this study, we set out to explore the unexpectedly spicy correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. This seemingly unrelated duo sparked our curiosity and ignited our research efforts as we sought to determine whether there's a sizzling connection between these two seemingly unrelated phenomena.

Using data from the Bureau of Labor Statistics and YouTube analytics from 2009 to 2022, we employed rigorous statistical methods and, to our surprise, uncovered a correlational coefficient of 0.9435917 (p < 0.01). It appears that the more heat generated by food and tobacco roasting, the more fiery the discussion becomes on Tom Scott's thought-provoking videos.

As we delved deeper into this unexpected linkage, one cannot help but marvel at the toasty relationship brewing between these otherwise unrelated spheres. This study not only sheds light on this quirky association but also offers a light-hearted reminder that sometimes, even the most surprising connections can be sizzling with significance.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos

[[ABSTRACT]]
In this study, we set out to explore the unexpectedly spicy correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. This seemingly unrelated duo sparked our curiosity and ignited our research efforts as we sought to determine whether there's a sizzling connection between these two seemingly unrelated phenomena.

Using data from the Bureau of Labor Statistics and YouTube analytics from 2009 to 2022, we employed rigorous statistical methods and, to our surprise, uncovered a correlational coefficient of 0.9435917 (p < 0.01). It appears that the more heat generated by food and tobacco roasting, the more fiery the discussion becomes on Tom Scott's thought-provoking videos.

As we delved deeper into this unexpected linkage, one cannot help but marvel at the toasty relationship brewing between these otherwise unrelated spheres. This study not only sheds light on this quirky association but also offers a light-hearted reminder that sometimes, even the most surprising connections can be sizzling with significance.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The investigation into seemingly unrelated phenomena often leads to the discovery of surprising and unexpected connections. Such was the case when we stumbled upon an intriguing correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. It was a revelation that left us feeling toasted and intrigued, to say the yeast! (See what I did there?)

Within the confines of this study, we aim to unravel this thermal tie and understand the potential underlying mechanisms that link these contrasting domains. To begin, one must ponder the peculiarity of this association: what could possibly bring together the fiery world of machine operators and the scorching realm of online video comments? It seems we are about to embark on a journey through the unexpected, where every twist and turn may lead to a *roast* revelation.

The Bureau of Labor Statistics provided us with data on the employment of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey, while YouTube analytics served up a plateful of observations on the total comments amassed on Tom Scott's channel.

As we waded through the statistical cauldron, we discovered a surprisingly strong correlation coefficient of 0.9435917 (p < 0.01) between these two seemingly disparate variables. It is a sizzling revelation that calls for further examination and verification. Could it be that the heat from the roasting machines is somehow igniting fervent debating and discussion on YouTube? It's like these data points are shouting, "We're on fire!"

In the following sections of this paper, we will kindle the flames of curiosity and take a *heat*-ful plunge into the heart of this puzzling connection. So, let's leave our *roast* skepticism behind and dig into this *sizzling* mystery, knowing that the potential for groundbreaking discoveries is hotter than ever. After all, in the world of research, it's essential to keep a watchful eye on every potential correlation, even the *pun*expected ones!


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos

[[ABSTRACT]]
In this study, we set out to explore the unexpectedly spicy correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. This seemingly unrelated duo sparked our curiosity and ignited our research efforts as we sought to determine whether there's a sizzling connection between these two seemingly unrelated phenomena.

Using data from the Bureau of Labor Statistics and YouTube analytics from 2009 to 2022, we employed rigorous statistical methods and, to our surprise, uncovered a correlational coefficient of 0.9435917 (p < 0.01). It appears that the more heat generated by food and tobacco roasting, the more fiery the discussion becomes on Tom Scott's thought-provoking videos.

As we delved deeper into this unexpected linkage, one cannot help but marvel at the toasty relationship brewing between these otherwise unrelated spheres. This study not only sheds light on this quirky association but also offers a light-hearted reminder that sometimes, even the most surprising connections can be sizzling with significance.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The investigation into seemingly unrelated phenomena often leads to the discovery of surprising and unexpected connections. Such was the case when we stumbled upon an intriguing correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. It was a revelation that left us feeling toasted and intrigued, to say the yeast! (See what I did there?)
Within the confines of this study, we aim to unravel this thermal tie and understand the potential underlying mechanisms that link these contrasting domains. To begin, one must ponder the peculiarity of this association: what could possibly bring together the fiery world of machine operators and the scorching realm of online video comments? It seems we are about to embark on a journey through the unexpected, where every twist and turn may lead to a *roast* revelation.
The Bureau of Labor Statistics provided us with data on the employment of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey, while YouTube analytics served up a plateful of observations on the total comments amassed on Tom Scott's channel.
As we waded through the statistical cauldron, we discovered a surprisingly strong correlation coefficient of 0.9435917 (p < 0.01) between these two seemingly disparate variables. It is a sizzling revelation that calls for further examination and verification. Could it be that the heat from the roasting machines is somehow igniting fervent debating and discussion on YouTube? It's like these data points are shouting, "We're on fire!"
In the following sections of this paper, we will kindle the flames of curiosity and take a *heat*-ful plunge into the heart of this puzzling connection. So, let's leave our *roast* skepticism behind and dig into this *sizzling* mystery, knowing that the potential for groundbreaking discoveries is hotter than ever. After all, in the world of research, it's essential to keep a watchful eye on every potential correlation, even the *pun*expected ones!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The study of seemingly unrelated yet intriguing connections has long piqued the curiosity of researchers. Smith et al. (2015) delved into the world of unexpected correlations, exploring the intricate links between divergent variables. On the heels of such scholarly endeavors, we embark on a journey through the literature to uncover existing knowledge regarding the association between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and the total comments on Tom Scott's YouTube videos.

In "The Art of Unusual Pairings" by Doe and Jones (2017), the authors ventured into the realm of unorthodox relationships between distinct domains. Their work epitomizes the spirit of our investigation, as we too seek to unravel the seemingly peculiar connection between the sizzling activities of machine operators and the heated discussions on a popular YouTube channel.

But let's not forget the lighthearted side of things amidst this scholarly pursuit. As we set sail into the sea of literature, it's important to remember that a little humor can go a long way. As Mark Twain once said, "The only way to keep your health is to eat what you don't want, drink what you don't like, and do what you'd rather not." Perhaps, one could argue, a *roast* or two might add to the flavor of this academic feast!

Turning our attention to works of fiction that, albeit not academically rigorous, offer insights into unexpected connections, we mustn't disregard the potential wisdom hidden within the pages of "Kafka on the Shore" by Haruki Murakami or "Like Water for Chocolate" by Laura Esquivel. Although not directly related to our subject matter, these novels remind us of the power of fortuitous encounters and unforeseen ties. Who knows, perhaps the characters in these books have unwittingly stumbled upon the secret to unraveling our *sizzling* mystery!

With a tinge of amusement, let's not overlook the seemingly unconventional sources of knowledge in our pursuit of understanding. Research is an adventure, after all, and one must be open to unearthing treasure in unexpected places. As such, it would be remiss of us not to mention the profound insights gleaned from perusing grocery store receipts, laboratory equipment manuals, and even the cryptic writings found on the backs of napkins in dimly lit cafes.

In "The Quest for the Quirky," the authors extolled the virtue of curious and sometimes eccentric sources of inspiration, reminding us that knowledge can be found in the most unlikely of locales. As we venture through the twists and turns of this peculiar research journey, it's essential to keep our eyes peeled for unexpected pockets of wisdom, even if they appear as surprising as stumbling upon a pun in an academic paper!


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 Bureau of Larbor Statistics and YouTube . You used data from 2009 to 2022

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos

[[ABSTRACT]]
In this study, we set out to explore the unexpectedly spicy correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. This seemingly unrelated duo sparked our curiosity and ignited our research efforts as we sought to determine whether there's a sizzling connection between these two seemingly unrelated phenomena.

Using data from the Bureau of Labor Statistics and YouTube analytics from 2009 to 2022, we employed rigorous statistical methods and, to our surprise, uncovered a correlational coefficient of 0.9435917 (p < 0.01). It appears that the more heat generated by food and tobacco roasting, the more fiery the discussion becomes on Tom Scott's thought-provoking videos.

As we delved deeper into this unexpected linkage, one cannot help but marvel at the toasty relationship brewing between these otherwise unrelated spheres. This study not only sheds light on this quirky association but also offers a light-hearted reminder that sometimes, even the most surprising connections can be sizzling with significance.

[[INTRODUCTION]]
The investigation into seemingly unrelated phenomena often leads to the discovery of surprising and unexpected connections. Such was the case when we stumbled upon an intriguing correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. It was a revelation that left us feeling toasted and intrigued, to say the yeast! (See what I did there?)
Within the confines of this study, we aim to unravel this thermal tie and understand the potential underlying mechanisms that link these contrasting domains. To begin, one must ponder the peculiarity of this association: what could possibly bring together the fiery world of machine operators and the scorching realm of online video comments? It seems we are about to embark on a journey through the unexpected, where every twist and turn may lead to a *roast* revelation.
The Bureau of Labor Statistics provided us with data on the employment of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey, while YouTube analytics served up a plateful of observations on the total comments amassed on Tom Scott's channel.
As we waded through the statistical cauldron, we discovered a surprisingly strong correlation coefficient of 0.9435917 (p < 0.01) between these two seemingly disparate variables. It is a sizzling revelation that calls for further examination and verification. Could it be that the heat from the roasting machines is somehow igniting fervent debating and discussion on YouTube? It's like these data points are shouting, "We're on fire!"
In the following sections of this paper, we will kindle the flames of curiosity and take a *heat*-ful plunge into the heart of this puzzling connection. So, let's leave our *roast* skepticism behind and dig into this *sizzling* mystery, knowing that the potential for groundbreaking discoveries is hotter than ever. After all, in the world of research, it's essential to keep a watchful eye on every potential correlation, even the *pun*expected ones!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the scorching connection between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and the total comments on Tom Scott's YouTube videos, our research team delved into a concoction of data collection methods that would make even the most seasoned data wrangler break a sweat.

First, we obtained employment data for food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey from the Bureau of Labor Statistics. This involved sifting through an impressive pile of labor data, which left us feeling as if we were navigating a veritable maze of statistical spices – a true *roast* to behold!

Once we had our paws on this fiery employment data, we scrutinized the trends across the span of 2009 to 2022. We tracked the rising heat signatures of the food and tobacco roasting industry and observed the potential *flame-broiling* effect it might have on other domains.

Simultaneously, we delved into the fiery world of YouTube analytics, tapping into the data treasure trove that lay behind the screen of Tom Scott's thought-provoking videos. The goal was to quantify the total comments on these videos, counting up each nugget of wisdom or word of criticism left by passionate viewers. It was an endeavor that had us feeling as if we were sifting through a *comment*al wave of data – a true amalgamation of digital discourse and a testament to the heat generated by online engagement.

With these datasets in hand, we brought out our statistical spatulas and whipped up a rigorous analysis, mixing in correlation coefficients, hypothesis testing, and other zesty methods. The goal? To distill any potential relationships into a potent elixir of statistical significance.

As we stirred the statistical cauldron, the numbers spoke volumes, revealing a surprisingly robust correlation coefficient of 0.9435917 (p < 0.01) between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and the total comments on Tom Scott's YouTube videos. It was a moment that *heated* up our excitement and left us wondering if we had stumbled upon a *roasted*ly surprising connection.

In the following sections of this paper, we will unveil the specifics of this sizzling correlation, probing the potential mechanisms that underpin this unlikely fusion. The methodology may have been as spicy as a pepper, but the results promise to *heat* up the discourse on potentially unforeseen connections in the world of employment and online engagement. So, let's not extinguish the flames of curiosity just yet – after all, there's a chance that even the most unexpected correlations can be brighter than the hottest fires!


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 Bureau of Larbor Statistics and YouTube .

For the time period 2009 to 2022, you found a correlation 0.9435917, r-squared of 0.8903652, 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]]
The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos

[[ABSTRACT]]
In this study, we set out to explore the unexpectedly spicy correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. This seemingly unrelated duo sparked our curiosity and ignited our research efforts as we sought to determine whether there's a sizzling connection between these two seemingly unrelated phenomena.

Using data from the Bureau of Labor Statistics and YouTube analytics from 2009 to 2022, we employed rigorous statistical methods and, to our surprise, uncovered a correlational coefficient of 0.9435917 (p < 0.01). It appears that the more heat generated by food and tobacco roasting, the more fiery the discussion becomes on Tom Scott's thought-provoking videos.

As we delved deeper into this unexpected linkage, one cannot help but marvel at the toasty relationship brewing between these otherwise unrelated spheres. This study not only sheds light on this quirky association but also offers a light-hearted reminder that sometimes, even the most surprising connections can be sizzling with significance.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The investigation into seemingly unrelated phenomena often leads to the discovery of surprising and unexpected connections. Such was the case when we stumbled upon an intriguing correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. It was a revelation that left us feeling toasted and intrigued, to say the yeast! (See what I did there?)
Within the confines of this study, we aim to unravel this thermal tie and understand the potential underlying mechanisms that link these contrasting domains. To begin, one must ponder the peculiarity of this association: what could possibly bring together the fiery world of machine operators and the scorching realm of online video comments? It seems we are about to embark on a journey through the unexpected, where every twist and turn may lead to a *roast* revelation.
The Bureau of Labor Statistics provided us with data on the employment of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey, while YouTube analytics served up a plateful of observations on the total comments amassed on Tom Scott's channel.
As we waded through the statistical cauldron, we discovered a surprisingly strong correlation coefficient of 0.9435917 (p < 0.01) between these two seemingly disparate variables. It is a sizzling revelation that calls for further examination and verification. Could it be that the heat from the roasting machines is somehow igniting fervent debating and discussion on YouTube? It's like these data points are shouting, "We're on fire!"
In the following sections of this paper, we will kindle the flames of curiosity and take a *heat*-ful plunge into the heart of this puzzling connection. So, let's leave our *roast* skepticism behind and dig into this *sizzling* mystery, knowing that the potential for groundbreaking discoveries is hotter than ever. After all, in the world of research, it's essential to keep a watchful eye on every potential correlation, even the *pun*expected ones!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and total comments on Tom Scott's YouTube videos produced remarkably intriguing results. With a correlational coefficient of 0.9435917, an r-squared of 0.8903652, and a p-value below 0.01, it seems that this connection is as hot as a freshly baked loaf of bread straight out of the oven.

The scatterplot displayed in Figure 1 vividly illustrates the strong positive correlation between the variables, as each data point sizzles with the significance of the association. It's a veritable feast for the eyes, with each point representing a toasty revelation in this unexpected convergence of industrial employment and online engagement.

One cannot help but marvel at the unexpected heat generated by this seemingly unrelated pairing. It's as though the employment landscape of New Jersey is fanning the flames of discussion and comments on the internet, turning the virtual domain into a virtual fire pit of discourse and debate. This finding is certainly no small potatoes, and it provides food for thought for future research endeavors.

This study not only invites a deeper exploration into the underlying mechanisms that drive this remarkable linkage but also serves as a reminder that even the most unexpected connections can hold significant implications. It’s a reminder that in the world of statistics, just like in the kitchen, sometimes the most surprising combinations result in the most delectable outcomes.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos

[[ABSTRACT]]
In this study, we set out to explore the unexpectedly spicy correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. This seemingly unrelated duo sparked our curiosity and ignited our research efforts as we sought to determine whether there's a sizzling connection between these two seemingly unrelated phenomena.

Using data from the Bureau of Labor Statistics and YouTube analytics from 2009 to 2022, we employed rigorous statistical methods and, to our surprise, uncovered a correlational coefficient of 0.9435917 (p < 0.01). It appears that the more heat generated by food and tobacco roasting, the more fiery the discussion becomes on Tom Scott's thought-provoking videos.

As we delved deeper into this unexpected linkage, one cannot help but marvel at the toasty relationship brewing between these otherwise unrelated spheres. This study not only sheds light on this quirky association but also offers a light-hearted reminder that sometimes, even the most surprising connections can be sizzling with significance.

[[LITERATURE REVIEW]]
The study of seemingly unrelated yet intriguing connections has long piqued the curiosity of researchers. Smith et al. (2015) delved into the world of unexpected correlations, exploring the intricate links between divergent variables. On the heels of such scholarly endeavors, we embark on a journey through the literature to uncover existing knowledge regarding the association between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and the total comments on Tom Scott's YouTube videos.
In "The Art of Unusual Pairings" by Doe and Jones (2017), the authors ventured into the realm of unorthodox relationships between distinct domains. Their work epitomizes the spirit of our investigation, as we too seek to unravel the seemingly peculiar connection between the sizzling activities of machine operators and the heated discussions on a popular YouTube channel.
But let's not forget the lighthearted side of things amidst this scholarly pursuit. As we set sail into the sea of literature, it's important to remember that a little humor can go a long way. As Mark Twain once said, "The only way to keep your health is to eat what you don't want, drink what you don't like, and do what you'd rather not." Perhaps, one could argue, a *roast* or two might add to the flavor of this academic feast!
Turning our attention to works of fiction that, albeit not academically rigorous, offer insights into unexpected connections, we mustn't disregard the potential wisdom hidden within the pages of "Kafka on the Shore" by Haruki Murakami or "Like Water for Chocolate" by Laura Esquivel. Although not directly related to our subject matter, these novels remind us of the power of fortuitous encounters and unforeseen ties. Who knows, perhaps the characters in these books have unwittingly stumbled upon the secret to unraveling our *sizzling* mystery!
With a tinge of amusement, let's not overlook the seemingly unconventional sources of knowledge in our pursuit of understanding. Research is an adventure, after all, and one must be open to unearthing treasure in unexpected places. As such, it would be remiss of us not to mention the profound insights gleaned from perusing grocery store receipts, laboratory equipment manuals, and even the cryptic writings found on the backs of napkins in dimly lit cafes.
In "The Quest for the Quirky," the authors extolled the virtue of curious and sometimes eccentric sources of inspiration, reminding us that knowledge can be found in the most unlikely of locales. As we venture through the twists and turns of this peculiar research journey, it's essential to keep our eyes peeled for unexpected pockets of wisdom, even if they appear as surprising as stumbling upon a pun in an academic paper!

[[RESULTS]]
The analysis of the relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and total comments on Tom Scott's YouTube videos produced remarkably intriguing results. With a correlational coefficient of 0.9435917, an r-squared of 0.8903652, and a p-value below 0.01, it seems that this connection is as hot as a freshly baked loaf of bread straight out of the oven.
The scatterplot displayed in Figure 1 vividly illustrates the strong positive correlation between the variables, as each data point sizzles with the significance of the association. It's a veritable feast for the eyes, with each point representing a toasty revelation in this unexpected convergence of industrial employment and online engagement.
One cannot help but marvel at the unexpected heat generated by this seemingly unrelated pairing. It's as though the employment landscape of New Jersey is fanning the flames of discussion and comments on the internet, turning the virtual domain into a virtual fire pit of discourse and debate. This finding is certainly no small potatoes, and it provides food for thought for future research endeavors.
This study not only invites a deeper exploration into the underlying mechanisms that drive this remarkable linkage but also serves as a reminder that even the most unexpected connections can hold significant implications. It’s a reminder that in the world of statistics, just like in the kitchen, sometimes the most surprising combinations result in the most delectable outcomes.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The unexpectedly robust relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and total comments on Tom Scott's YouTube videos is truly a hot topic. Our findings align with previous research on unusual pairings and fortuitous connections, demonstrating that even the most unexpected correlations can hold significant implications.

The robust correlation coefficient of 0.9435917 (p < 0.01) observed in our study harkens back to the work of Smith et al. (2015), who delved into the world of unexpected correlations. Our results supported their contention that seemingly unrelated variables can indeed exhibit strong associations. This unexpected linkage serves as a reminder that just as a toaster can heat bread, it appears that the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey may be fueling the fiery discussions on Tom Scott's YouTube videos.

In the spirit of unconventional wisdom, we cannot overlook the humor and serendipity that permeates our investigation. The lighthearted musings from the literature review, exemplified by a pun here and a jest there, underscore the notion that a little levity can enhance even the most serious academic pursuits. As Mark Twain humorously quipped, "The only way to keep your health is to eat what you don't want, drink what you don't like, and do what you'd rather not." In a similar vein, perhaps the unexpected connection between roasting activities and online engagement serves as a reminder that even in the realm of statistics, the most surprising combinations can yield the most delectable outcomes, much like a perfectly roasted marshmallow over a campfire.

Our study not only offers a thought-provoking insight into this intriguing association but also underscores the profound wisdom that can be unearthed from seemingly unconventional sources. Just as characters in fictional works stumble upon unforeseen ties, the unexpected connection between machine operators and YouTube engagement serves as a reminder that knowledge can be found in the most unsuspecting places. As we navigate this sizzling research landscape, one cannot help but marvel at the seemingly unconventional sources of inspiration that have enriched our understanding of this surprising correlation. After all, as the saying goes, sometimes a well-placed pun in an academic paper can lead to an unexpectedly humorous revelation!

This study presents food for thought for future research endeavors, inviting a deeper exploration into the underlying mechanisms driving this remarkable linkage. Just as unexpected pairings can lead to delectable outcomes in the culinary world, our findings underscore that in the realm of statistics, surprising connections can yield unexpectedly significant implications. As we step back from this peculiar research journey, it's essential to remember that in the academic kitchen, much like the culinary one, the most surprising combinations often result in the most savory outcomes.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and Total comments on Tom Scott YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos

[[ABSTRACT]]
In this study, we set out to explore the unexpectedly spicy correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. This seemingly unrelated duo sparked our curiosity and ignited our research efforts as we sought to determine whether there's a sizzling connection between these two seemingly unrelated phenomena.

Using data from the Bureau of Labor Statistics and YouTube analytics from 2009 to 2022, we employed rigorous statistical methods and, to our surprise, uncovered a correlational coefficient of 0.9435917 (p < 0.01). It appears that the more heat generated by food and tobacco roasting, the more fiery the discussion becomes on Tom Scott's thought-provoking videos.

As we delved deeper into this unexpected linkage, one cannot help but marvel at the toasty relationship brewing between these otherwise unrelated spheres. This study not only sheds light on this quirky association but also offers a light-hearted reminder that sometimes, even the most surprising connections can be sizzling with significance.

[[INTRDUCTION]]
The investigation into seemingly unrelated phenomena often leads to the discovery of surprising and unexpected connections. Such was the case when we stumbled upon an intriguing correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. It was a revelation that left us feeling toasted and intrigued, to say the yeast! (See what I did there?)
Within the confines of this study, we aim to unravel this thermal tie and understand the potential underlying mechanisms that link these contrasting domains. To begin, one must ponder the peculiarity of this association: what could possibly bring together the fiery world of machine operators and the scorching realm of online video comments? It seems we are about to embark on a journey through the unexpected, where every twist and turn may lead to a *roast* revelation.
The Bureau of Labor Statistics provided us with data on the employment of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey, while YouTube analytics served up a plateful of observations on the total comments amassed on Tom Scott's channel.
As we waded through the statistical cauldron, we discovered a surprisingly strong correlation coefficient of 0.9435917 (p < 0.01) between these two seemingly disparate variables. It is a sizzling revelation that calls for further examination and verification. Could it be that the heat from the roasting machines is somehow igniting fervent debating and discussion on YouTube? It's like these data points are shouting, "We're on fire!"
In the following sections of this paper, we will kindle the flames of curiosity and take a *heat*-ful plunge into the heart of this puzzling connection. So, let's leave our *roast* skepticism behind and dig into this *sizzling* mystery, knowing that the potential for groundbreaking discoveries is hotter than ever. After all, in the world of research, it's essential to keep a watchful eye on every potential correlation, even the *pun*expected ones!

[[RESULTS]]
The analysis of the relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and total comments on Tom Scott's YouTube videos produced remarkably intriguing results. With a correlational coefficient of 0.9435917, an r-squared of 0.8903652, and a p-value below 0.01, it seems that this connection is as hot as a freshly baked loaf of bread straight out of the oven.
The scatterplot displayed in Figure 1 vividly illustrates the strong positive correlation between the variables, as each data point sizzles with the significance of the association. It's a veritable feast for the eyes, with each point representing a toasty revelation in this unexpected convergence of industrial employment and online engagement.
One cannot help but marvel at the unexpected heat generated by this seemingly unrelated pairing. It's as though the employment landscape of New Jersey is fanning the flames of discussion and comments on the internet, turning the virtual domain into a virtual fire pit of discourse and debate. This finding is certainly no small potatoes, and it provides food for thought for future research endeavors.
This study not only invites a deeper exploration into the underlying mechanisms that drive this remarkable linkage but also serves as a reminder that even the most unexpected connections can hold significant implications. It’s a reminder that in the world of statistics, just like in the kitchen, sometimes the most surprising combinations result in the most delectable outcomes.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has uncovered a sizzling correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey and total comments on Tom Scott's YouTube videos. The toasty R-squared of 0.8903652, along with the scorching correlational coefficient of 0.9435917, leave little doubt about the fiery relationship between these seemingly unrelated variables. It seems that when it comes to the employment landscape and online engagement, sparks were bound to fly – and fly they did, hotter than a barbecue grill on a summer day.

This unexpected association not only adds some spice to our understanding of industrial employment and virtual discourse but also serves as a *roast*-y reminder that even the most surprising connections can yield substantial insights. It's as if the employment of machine operators has become the *kindling* for a veritable bonfire of online discussions on Tom Scott's YouTube channel.

So, the next time you're enjoying a piping-hot loaf of bread fresh from the oven, remember that the employment landscape of New Jersey might just be igniting a *firestorm* of comments and debates on the internet. It’s a reminder that in the world of statistical analysis, one must always be on the lookout for unexpected correlations – they can truly be the *bread and butter* of groundbreaking discoveries!

Given the robustness of our findings, it is our firm belief that no further research in this area is needed. It's safe to say that the connection between these variables is as well-done as a thoroughly roasted marshmallow – no further probing necessary. This study has truly grilled the matter, and we can confidently bid adieu to this spicy investigation.


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 The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Culinary Nicotine 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 The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos. Respond only with the name of a fictional organization.

ChatGPT:

National Institute for Culinary and Tobacco Studies (NICOTS)


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 The Roasting Hot Topic: Unveiling the Sizzling Link Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in New Jersey and Total Comments on Tom Scott YouTube Videos with an abstract of In this study, we set out to explore the unexpectedly spicy correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in the state of New Jersey and the total comments on Tom Scott's YouTube videos. This seemingly unrelated duo sparked our curiosity and ignited our research efforts as we sought to determine whether there's a sizzling connection between these two seemingly unrelated phenomena.
Using data from the Bureau of Labor Statistics and YouTube analytics from 2009 to 2022, we employed rigorous statistical methods and, to our surprise, uncovered a correlational coefficient of 0.9435917 (p < 0.01). It appears that the more heat generated by food and tobacco roasting, the more fiery the discussion becomes on Tom Scott's thought-provoking videos.
As we delved deeper into this unexpected linkage, one cannot help but marvel at the toasty relationship brewing between these otherwise unrelated spheres. This study not only sheds light on this quirky association but also offers a light-hearted reminder that sometimes, even the most surprising connections can be sizzling with significance.

ChatGPT:

food roasting, tobacco roasting, baking, drying machine operators, tenders, New Jersey, Tom Scott YouTube videos, correlation, statistical analysis, Bureau of Labor Statistics, YouTube analytics, correlational coefficient, heat, discussion, quirky association, significance

*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

The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey
Detailed data title: BLS estimate of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey
Source: Bureau of Larbor Statistics
See what else correlates with The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey

Total comments on Tom Scott's YouTube videos
Detailed data title: Total comments on Tom Scott YouTube videos.
Source: Tom Scott's YouTube
See what else correlates with Total comments on Tom Scott's YouTube videos

Correlation r = 0.9435917 (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 = 0.8903652 (Coefficient of determination)
This means 89% of the change in the one variable (i.e., Total comments on Tom Scott's YouTube videos) is predictable based on the change in the other (i.e., The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey) over the 14 years from 2009 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.1E-7. 0.0000004115925736457067000000
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 0.94 in 4.1E-5% of random cases. Said differently, if you correlated 2,429,587 random variables You don't actually need 2 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 13 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 13 because we have two variables measured over a period of 14 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.

[ 0.83, 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.
20092010201120122013201420152016201720182019202020212022
The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey (Laborers)2902903004204805604804504305506801130600430
Total comments on Tom Scott's YouTube videos (Total comments)27514165331849566930127158113951135242143419267248208799663348274282174207




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.




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([290,290,300,420,480,560,480,450,430,550,680,1130,600,430,])
array_2 = np.array([27514,165,331,8495,66930,127158,113951,135242,143419,267248,208799,663348,274282,174207,])
array_1_name = "The number of food and tobacco roasting, baking, and drying machine operators and tenders in New Jersey"
array_2_name = "Total comments on Tom Scott's 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?

You're a rater extraordinaire!


Correlation ID: 5064 · Black Variable ID: 11729 · Red Variable ID: 25469
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0