about · email me · subscribe
Spurious correlation #1,180 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is US Tobacco Production and the second variable is Number of Slot Machines in Nevada.  The chart goes from 2000 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As US tobacco production decreased, there was less secondhand smoke to create that authentic smoky casino atmosphere. With fewer people smoking, there was a reduced demand for slot machines as smoking and gambling went hand in hand. The realization dawned that slot machines can't function on secondhand smoke alone, and so the number of slot machines in Nevada stubbed out along with the decline in tobacco production.

Model: dalle-3
Prompt: Generate an image of a cyberpunk world where a vast field of tobacco plants is withering under neon-lit skies, symbolizing the decrease in US tobacco production. Fewer plants stand in the field, their leaves wilted and fading under the city's glow. In the background, a group of figures can be seen, smoking fewer cigarettes than before, shrouded in the hazy glimmer of the city. Nearby, a futuristic casino stands, its slot machines flashing in the darkness, but with fewer people taking smoke breaks, reflecting the declining demand. The scene presents a juxtaposition of nature's decline and the changing habits of a society intertwined with technology and industry. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: As US tobacco production decreased, fewer people were smoking, which meant fewer people were taking smoke breaks at casinos, leading to a decrease in demand for slot machines in Nevada.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Cyberpunk Hyper-realistic Sci-fi fantacy A photo-realistic image Art nouveau
ChatGPT: Cyberpunk

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. As US tobacco production decreased, fewer people were smoking, which meant fewer people were taking smoke breaks at casinos, leading to a decrease in demand for slot machines in Nevada.
ChatGPT: Imagine a field of tobacco plants with fewer plants than before, indicating a decrease in US tobacco production. In the background, you can see a group of people smoking fewer cigarettes than before. Then, picture a casino with fewer people taking smoke breaks, leading to a decrease in demand for slot machines.

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: [ Cyberpunk ] and depicting this scene: Imagine a field of tobacco plants with fewer plants than before, indicating a decrease in US tobacco production. In the background, you can see a group of people smoking fewer cigarettes than before. Then, picture a casino with fewer people taking smoke breaks, leading to a decrease in demand for slot machines. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a cyberpunk world where a vast field of tobacco plants is withering under neon-lit skies, symbolizing the decrease in US tobacco production. Fewer plants stand in the field, their leaves wilted and fading under the city's glow. In the background, a group of figures can be seen, smoking fewer cigarettes than before, shrouded in the hazy glimmer of the city. Nearby, a futuristic casino stands, its slot machines flashing in the darkness, but with fewer people taking smoke breaks, reflecting the declining demand. The scene presents a juxtaposition of nature's decline and the changing habits of a society intertwined with technology and industry.

*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 a decrease in US Tobacco Production caused Number of Slot Machines in Nevada to decrease.

AI academic paper

(Because p < 0.01)
Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada

The Journal of Unlikely Connections

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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Tobacco Production and Number of Slot Machines in Nevada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Include a pun in the title.

Your research team used data from Statista and UNLV to assess this nagging question. You found a correlation coefficient of 0.8274039 and p < 0.01 for 2000 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]]
"Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada"

[[ABSTRACT]]
This study aimed to investigate the curious connection between US tobacco production and the number of slot machines in the illustrious state of Nevada. By utilizing data from Statista and the University of Nevada, Las Vegas, we embarked on a statistical odyssey to uncover potential correlations that may shed light on this peculiar relationship. Our findings revealed a striking correlation coefficient of 0.8274039 with a significance level of p < 0.01 for the years spanning from 2000 to 2022. While our results may seem like a mere smokescreen, they lend credence to the notion that the tobacco industry and the allure of slot machines may indeed share a deeper connection, one that could be more than just a mere "roll of the dice." This research underscores the potential for fruitful exploration at the intersection of agricultural production and the gaming industry, challenging us to examine correlations that may be more than mere statistical happenstance.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Tobacco Production and Number of Slot Machines in Nevada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
"Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada"

[[ABSTRACT]]
This study aimed to investigate the curious connection between US tobacco production and the number of slot machines in the illustrious state of Nevada. By utilizing data from Statista and the University of Nevada, Las Vegas, we embarked on a statistical odyssey to uncover potential correlations that may shed light on this peculiar relationship. Our findings revealed a striking correlation coefficient of 0.8274039 with a significance level of p < 0.01 for the years spanning from 2000 to 2022. While our results may seem like a mere smokescreen, they lend credence to the notion that the tobacco industry and the allure of slot machines may indeed share a deeper connection, one that could be more than just a mere "roll of the dice." This research underscores the potential for fruitful exploration at the intersection of agricultural production and the gaming industry, challenging us to examine correlations that may be more than mere statistical happenstance.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Tobacco and slot machines may seem like an unlikely pair, much like peanut butter and jalapenos – a combination that raises eyebrows and elicits skepticism. However, in the vast tapestry of statistical relationships, sometimes the most unexpected pairings hold hidden truths that beg to be unraveled. In this paper, we delve into the intriguing link between US tobacco production and the number of slot machines in the renowned gambling haven of Nevada.

As much as we'd love to claim that the allure of slot machines simply stems from their flashy lights and occasional payouts, our inquisitive minds couldn't help but wonder if there might be a deeper, more unfiltered connection – much like that distinct aroma of freshly brewed coffee and the prospect of financial risk. To tackle this curious conundrum, we harnessed the power of data from esteemed sources such as Statista and the University of Nevada, Las Vegas, aiming to let the numbers speak for themselves, as they often do, albeit in a rather cryptic and enigmatic language.

While some may dismiss this investigation as a mere flight of fancy, akin to pondering the correlation between the abundance of cacti in Arizona and the popularity of cowboy hats, our initial foray into the realm of data analysis has yielded surprisingly robust findings. Our results revealed a correlation coefficient that raises an eyebrow or two, standing at a rather impressive 0.8274039, signaling a relationship that appears to be more than a mere statistical hiccup. With a significance level of p < 0.01 for the years spanning from 2000 to 2022, the evidence has left us pondering the possibility that there might be more to this association than meets the eye – a reality akin to discovering that an artichoke and an aardvark share a similarly shaped ear.

As we venture further into our analysis, it becomes increasingly evident that the smoke-filled rooms of tobacco production and the glittering halls of slot machines may share a more intricate dance than initially surmised. In uncovering these potential connections, we challenge the notion of happenstance and invite the academic community to engage in this peculiar pas de deux between agriculture and the allure of gambling, daring to explore the possibility of a relationship that is more than just a "roll of the dice." Join us on this statistical odyssey as we aim to shine a light on the intriguing and unexpected connections that may lie beneath the surface of seemingly unrelated industries, where what meets the eye may be but a mere facade, akin to a deck of cards cleverly concealing a royal flush.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Tobacco Production and Number of Slot Machines in Nevada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada"

[[ABSTRACT]]
This study aimed to investigate the curious connection between US tobacco production and the number of slot machines in the illustrious state of Nevada. By utilizing data from Statista and the University of Nevada, Las Vegas, we embarked on a statistical odyssey to uncover potential correlations that may shed light on this peculiar relationship. Our findings revealed a striking correlation coefficient of 0.8274039 with a significance level of p < 0.01 for the years spanning from 2000 to 2022. While our results may seem like a mere smokescreen, they lend credence to the notion that the tobacco industry and the allure of slot machines may indeed share a deeper connection, one that could be more than just a mere "roll of the dice." This research underscores the potential for fruitful exploration at the intersection of agricultural production and the gaming industry, challenging us to examine correlations that may be more than mere statistical happenstance.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Tobacco and slot machines may seem like an unlikely pair, much like peanut butter and jalapenos – a combination that raises eyebrows and elicits skepticism. However, in the vast tapestry of statistical relationships, sometimes the most unexpected pairings hold hidden truths that beg to be unraveled. In this paper, we delve into the intriguing link between US tobacco production and the number of slot machines in the renowned gambling haven of Nevada.
As much as we'd love to claim that the allure of slot machines simply stems from their flashy lights and occasional payouts, our inquisitive minds couldn't help but wonder if there might be a deeper, more unfiltered connection – much like that distinct aroma of freshly brewed coffee and the prospect of financial risk. To tackle this curious conundrum, we harnessed the power of data from esteemed sources such as Statista and the University of Nevada, Las Vegas, aiming to let the numbers speak for themselves, as they often do, albeit in a rather cryptic and enigmatic language.
While some may dismiss this investigation as a mere flight of fancy, akin to pondering the correlation between the abundance of cacti in Arizona and the popularity of cowboy hats, our initial foray into the realm of data analysis has yielded surprisingly robust findings. Our results revealed a correlation coefficient that raises an eyebrow or two, standing at a rather impressive 0.8274039, signaling a relationship that appears to be more than a mere statistical hiccup. With a significance level of p < 0.01 for the years spanning from 2000 to 2022, the evidence has left us pondering the possibility that there might be more to this association than meets the eye – a reality akin to discovering that an artichoke and an aardvark share a similarly shaped ear.
As we venture further into our analysis, it becomes increasingly evident that the smoke-filled rooms of tobacco production and the glittering halls of slot machines may share a more intricate dance than initially surmised. In uncovering these potential connections, we challenge the notion of happenstance and invite the academic community to engage in this peculiar pas de deux between agriculture and the allure of gambling, daring to explore the possibility of a relationship that is more than just a "roll of the dice." Join us on this statistical odyssey as we aim to shine a light on the intriguing and unexpected connections that may lie beneath the surface of seemingly unrelated industries, where what meets the eye may be but a mere facade, akin to a deck of cards cleverly concealing a royal flush.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "The Economical Impact of US Tobacco Production" by Smith, the authors find that the prominence of tobacco production in the United States has remained a significant force in the agricultural landscape. This study highlights the economic implications and the intricate web of relationships that stem from tobacco cultivation, painting a picture of an industry steeped in tradition, controversy, and a faint aftertaste of smoky intrigue. Similarly, Doe’s "Gambling Fever: The Economics of Slot Machines in Nevada" presents a comprehensive analysis of the evolution of gambling in Nevada, from the dingy saloons of yore to the glitzy, high-stakes casinos that beckon to visitors from far and wide. The author delves into the economic nuances of the thriving gambling industry, painting a portrait of an enterprise built on risk, chance, and a whole lot of flashing lights.

In their book “Tobacco and the Wild West,” Jones et al. explore the historical and cultural significance of tobacco in shaping the narrative of the American frontier, weaving a tale of smoke rings, rugged cowboys, and a certain je ne sais quoi that seems to linger in the air. Meanwhile, “The Slot Machine Chronicles” by Brown delves into the hypnotic allure of slot machines, the psychology behind their irresistible charm, and the curious dance between risk and reward that keeps players coming back for more.

Venturing into the realm of fiction, works such as "The Smoke and the Spins" by Wills and "Slot Machine Secrets: Unveiling the Elusive Connection" by Stone present imaginative narratives that evoke the enigmatic connection between tobacco production and the lure of slot machines. While their accounts may be purely fictional, they offer a whimsical interpretation of the potential link between these seemingly disparate domains, sparking intrigue and amusement in equal measure.

As the research progressed, the authors stumbled upon an array of unexpectedly pertinent literature. Surprisingly, the backs of shampoo bottles revealed a plethora of insights into the subtle interplay of bubbles, scents, and marketing strategies, mirroring the complex dynamics at play in the world of tobacco production and slot machines. While not conventional scholarly sources, these unassuming containers provided a refreshing perspective, reminding the authors of the need to approach research with a sense of openness and curiosity akin to stumbling upon a winning combination on a slot machine.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Tobacco Production and Number of Slot Machines in Nevada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Statista and UNLV . You used data from 2000 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]]
"Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada"

[[ABSTRACT]]
This study aimed to investigate the curious connection between US tobacco production and the number of slot machines in the illustrious state of Nevada. By utilizing data from Statista and the University of Nevada, Las Vegas, we embarked on a statistical odyssey to uncover potential correlations that may shed light on this peculiar relationship. Our findings revealed a striking correlation coefficient of 0.8274039 with a significance level of p < 0.01 for the years spanning from 2000 to 2022. While our results may seem like a mere smokescreen, they lend credence to the notion that the tobacco industry and the allure of slot machines may indeed share a deeper connection, one that could be more than just a mere "roll of the dice." This research underscores the potential for fruitful exploration at the intersection of agricultural production and the gaming industry, challenging us to examine correlations that may be more than mere statistical happenstance.

[[INTRODUCTION]]
Tobacco and slot machines may seem like an unlikely pair, much like peanut butter and jalapenos – a combination that raises eyebrows and elicits skepticism. However, in the vast tapestry of statistical relationships, sometimes the most unexpected pairings hold hidden truths that beg to be unraveled. In this paper, we delve into the intriguing link between US tobacco production and the number of slot machines in the renowned gambling haven of Nevada.
As much as we'd love to claim that the allure of slot machines simply stems from their flashy lights and occasional payouts, our inquisitive minds couldn't help but wonder if there might be a deeper, more unfiltered connection – much like that distinct aroma of freshly brewed coffee and the prospect of financial risk. To tackle this curious conundrum, we harnessed the power of data from esteemed sources such as Statista and the University of Nevada, Las Vegas, aiming to let the numbers speak for themselves, as they often do, albeit in a rather cryptic and enigmatic language.
While some may dismiss this investigation as a mere flight of fancy, akin to pondering the correlation between the abundance of cacti in Arizona and the popularity of cowboy hats, our initial foray into the realm of data analysis has yielded surprisingly robust findings. Our results revealed a correlation coefficient that raises an eyebrow or two, standing at a rather impressive 0.8274039, signaling a relationship that appears to be more than a mere statistical hiccup. With a significance level of p < 0.01 for the years spanning from 2000 to 2022, the evidence has left us pondering the possibility that there might be more to this association than meets the eye – a reality akin to discovering that an artichoke and an aardvark share a similarly shaped ear.
As we venture further into our analysis, it becomes increasingly evident that the smoke-filled rooms of tobacco production and the glittering halls of slot machines may share a more intricate dance than initially surmised. In uncovering these potential connections, we challenge the notion of happenstance and invite the academic community to engage in this peculiar pas de deux between agriculture and the allure of gambling, daring to explore the possibility of a relationship that is more than just a "roll of the dice." Join us on this statistical odyssey as we aim to shine a light on the intriguing and unexpected connections that may lie beneath the surface of seemingly unrelated industries, where what meets the eye may be but a mere facade, akin to a deck of cards cleverly concealing a royal flush.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To embark upon the unraveling of this enigmatic connection between US tobacco production and the number of slot machines in Nevada, our research team underwent a meticulous and somewhat unorthodox process that involved a humorous amount of data wrangling. Our data, primarily sourced from the hallowed repositories of Statista and the University of Nevada, Las Vegas, subjected our team to a veritable safari through the technological savannahs of the internet, taming the unruly jungle of information to extract the requisite datasets.

After sifting through what felt like an endless array of uncharted virtual territories, we finally stumbled upon the treasure troves of data covering the years from 2000 to 2022. Our search was akin to hunting for a rare jewel amidst a sea of vast and relatively mundane statistical artifacts. The data underwent rigorous scrutiny to ensure its integrity, a process that was about as entertaining as watching paint dry or observing the gradual growth of a bonsai tree - slow and steady, with a hint of absurdity lingering in the background.

With the acquired data in hand, our team then commenced the ritualistic dance of statistical analysis - an elaborate choreography of hypothesis testing, correlation coefficients, and significance levels. We fitted various models with the finesse of a tailor crafting a bespoke suit, each variable woven strategically into the fabric of our analysis. The process bore semblance to unearthing buried treasure, the thrill of discovery juxtaposed with the occasional frustration akin to solving a Rubik's cube blindfolded.

Our methodology also ventured into the realm of time series analysis, where we sought to unravel the intricate temporal patterns that emerge when juxtaposing the ebb and flow of US tobacco production with the oscillating tapestry of slot machine numbers in Nevada. This venture was akin to deciphering a cryptic message etched into the fabric of time, each data point resembling a pixel in a grand mosaic of statistical intrigue.

The resulting statistical scrutiny was not for the faint of heart, demanding a keen eye for detail and a dash of fortitude as we ventured deep into the labyrinth of numbers. We applied various tests and diagnostic procedures with the finesse of a detective pursuing an elusive culprit, untangling the web of statistical relationships with a persistence akin to attempting to fold a fitted sheet.

Ultimately, our methodology embraced the convoluted yet exhilarating endeavor of exploring the unexpected connections that may lie beneath the seemingly disjointed realms of tobacco production and the world of slot machines. Our chosen approach may have been untraditional, reminiscent of navigating a maze blindfolded, but it paved the way for the unveiling of intriguing statistical insights that are ripe for further exploration and contemplation.

This article was intended for context that's more related to tobacco or a game like poker. If the metaphor doesn't fit, feel free to provide a more suitable context to tie it back to either tobacco or gambling.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Tobacco Production and Number of Slot Machines in Nevada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

For the time period 2000 to 2022, you found a correlation 0.8274039, r-squared of 0.6845973, 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]]
"Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada"

[[ABSTRACT]]
This study aimed to investigate the curious connection between US tobacco production and the number of slot machines in the illustrious state of Nevada. By utilizing data from Statista and the University of Nevada, Las Vegas, we embarked on a statistical odyssey to uncover potential correlations that may shed light on this peculiar relationship. Our findings revealed a striking correlation coefficient of 0.8274039 with a significance level of p < 0.01 for the years spanning from 2000 to 2022. While our results may seem like a mere smokescreen, they lend credence to the notion that the tobacco industry and the allure of slot machines may indeed share a deeper connection, one that could be more than just a mere "roll of the dice." This research underscores the potential for fruitful exploration at the intersection of agricultural production and the gaming industry, challenging us to examine correlations that may be more than mere statistical happenstance.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Tobacco and slot machines may seem like an unlikely pair, much like peanut butter and jalapenos – a combination that raises eyebrows and elicits skepticism. However, in the vast tapestry of statistical relationships, sometimes the most unexpected pairings hold hidden truths that beg to be unraveled. In this paper, we delve into the intriguing link between US tobacco production and the number of slot machines in the renowned gambling haven of Nevada.
As much as we'd love to claim that the allure of slot machines simply stems from their flashy lights and occasional payouts, our inquisitive minds couldn't help but wonder if there might be a deeper, more unfiltered connection – much like that distinct aroma of freshly brewed coffee and the prospect of financial risk. To tackle this curious conundrum, we harnessed the power of data from esteemed sources such as Statista and the University of Nevada, Las Vegas, aiming to let the numbers speak for themselves, as they often do, albeit in a rather cryptic and enigmatic language.
While some may dismiss this investigation as a mere flight of fancy, akin to pondering the correlation between the abundance of cacti in Arizona and the popularity of cowboy hats, our initial foray into the realm of data analysis has yielded surprisingly robust findings. Our results revealed a correlation coefficient that raises an eyebrow or two, standing at a rather impressive 0.8274039, signaling a relationship that appears to be more than a mere statistical hiccup. With a significance level of p < 0.01 for the years spanning from 2000 to 2022, the evidence has left us pondering the possibility that there might be more to this association than meets the eye – a reality akin to discovering that an artichoke and an aardvark share a similarly shaped ear.
As we venture further into our analysis, it becomes increasingly evident that the smoke-filled rooms of tobacco production and the glittering halls of slot machines may share a more intricate dance than initially surmised. In uncovering these potential connections, we challenge the notion of happenstance and invite the academic community to engage in this peculiar pas de deux between agriculture and the allure of gambling, daring to explore the possibility of a relationship that is more than just a "roll of the dice." Join us on this statistical odyssey as we aim to shine a light on the intriguing and unexpected connections that may lie beneath the surface of seemingly unrelated industries, where what meets the eye may be but a mere facade, akin to a deck of cards cleverly concealing a royal flush.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of our data revealed a strong positive correlation between US tobacco production and the number of slot machines in Nevada, with a correlation coefficient of 0.8274039 and an r-squared value of 0.6845973. This indicates that approximately 68.46% of the variation in the number of slot machines in Nevada can be explained by the variation in US tobacco production over the years 2000 to 2022. The obtained p-value of less than 0.01 underscores the statistical significance of this relationship, further supporting the idea that these two seemingly unrelated industries may be intertwined in an unexpected manner.

The scatterplot (Fig. 1) visually illustrates the substantial positive relationship between US tobacco production and the number of slot machines in Nevada. The data points align themselves in such a way that one could almost imagine tobacco leaves turning into stacks of casino chips, although that may just be a whimsical interpretation.

While these findings may appear as baffling as finding a pineapple on a pizza, they open up a realm of intriguing possibilities that challenge conventional expectations. It seems that the allure of tobacco and the enchantment of slot machines may share more than just a passing resemblance, much like discovering that a rubber duck and a Nobel laureate share the same middle name.

This research sets the stage for future exploration of the interplay between agricultural production and the gaming industry. Just as a magician skillfully manipulates cards to create an illusion, our findings prompt us to consider the potential hidden dynamics at play, urging us to peek beyond the smoke and mirrors of apparently unrelated sectors. As we embark on this scholarly journey, let us remember that sometimes, beneath the surface of seemingly distinct phenomena, lies a web of connections waiting to be uncovered, much like finding the unexpected harmony between a tuba and a kazoo.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Tobacco Production and Number of Slot Machines in Nevada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
"Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada"

[[ABSTRACT]]
This study aimed to investigate the curious connection between US tobacco production and the number of slot machines in the illustrious state of Nevada. By utilizing data from Statista and the University of Nevada, Las Vegas, we embarked on a statistical odyssey to uncover potential correlations that may shed light on this peculiar relationship. Our findings revealed a striking correlation coefficient of 0.8274039 with a significance level of p < 0.01 for the years spanning from 2000 to 2022. While our results may seem like a mere smokescreen, they lend credence to the notion that the tobacco industry and the allure of slot machines may indeed share a deeper connection, one that could be more than just a mere "roll of the dice." This research underscores the potential for fruitful exploration at the intersection of agricultural production and the gaming industry, challenging us to examine correlations that may be more than mere statistical happenstance.

[[LITERATURE REVIEW]]
In "The Economical Impact of US Tobacco Production" by Smith, the authors find that the prominence of tobacco production in the United States has remained a significant force in the agricultural landscape. This study highlights the economic implications and the intricate web of relationships that stem from tobacco cultivation, painting a picture of an industry steeped in tradition, controversy, and a faint aftertaste of smoky intrigue. Similarly, Doe’s "Gambling Fever: The Economics of Slot Machines in Nevada" presents a comprehensive analysis of the evolution of gambling in Nevada, from the dingy saloons of yore to the glitzy, high-stakes casinos that beckon to visitors from far and wide. The author delves into the economic nuances of the thriving gambling industry, painting a portrait of an enterprise built on risk, chance, and a whole lot of flashing lights.
In their book “Tobacco and the Wild West,” Jones et al. explore the historical and cultural significance of tobacco in shaping the narrative of the American frontier, weaving a tale of smoke rings, rugged cowboys, and a certain je ne sais quoi that seems to linger in the air. Meanwhile, “The Slot Machine Chronicles” by Brown delves into the hypnotic allure of slot machines, the psychology behind their irresistible charm, and the curious dance between risk and reward that keeps players coming back for more.
Venturing into the realm of fiction, works such as "The Smoke and the Spins" by Wills and "Slot Machine Secrets: Unveiling the Elusive Connection" by Stone present imaginative narratives that evoke the enigmatic connection between tobacco production and the lure of slot machines. While their accounts may be purely fictional, they offer a whimsical interpretation of the potential link between these seemingly disparate domains, sparking intrigue and amusement in equal measure.
As the research progressed, the authors stumbled upon an array of unexpectedly pertinent literature. Surprisingly, the backs of shampoo bottles revealed a plethora of insights into the subtle interplay of bubbles, scents, and marketing strategies, mirroring the complex dynamics at play in the world of tobacco production and slot machines. While not conventional scholarly sources, these unassuming containers provided a refreshing perspective, reminding the authors of the need to approach research with a sense of openness and curiosity akin to stumbling upon a winning combination on a slot machine.

[[RESULTS]]
The analysis of our data revealed a strong positive correlation between US tobacco production and the number of slot machines in Nevada, with a correlation coefficient of 0.8274039 and an r-squared value of 0.6845973. This indicates that approximately 68.46% of the variation in the number of slot machines in Nevada can be explained by the variation in US tobacco production over the years 2000 to 2022. The obtained p-value of less than 0.01 underscores the statistical significance of this relationship, further supporting the idea that these two seemingly unrelated industries may be intertwined in an unexpected manner.
The scatterplot (Fig. 1) visually illustrates the substantial positive relationship between US tobacco production and the number of slot machines in Nevada. The data points align themselves in such a way that one could almost imagine tobacco leaves turning into stacks of casino chips, although that may just be a whimsical interpretation.
While these findings may appear as baffling as finding a pineapple on a pizza, they open up a realm of intriguing possibilities that challenge conventional expectations. It seems that the allure of tobacco and the enchantment of slot machines may share more than just a passing resemblance, much like discovering that a rubber duck and a Nobel laureate share the same middle name.
This research sets the stage for future exploration of the interplay between agricultural production and the gaming industry. Just as a magician skillfully manipulates cards to create an illusion, our findings prompt us to consider the potential hidden dynamics at play, urging us to peek beyond the smoke and mirrors of apparently unrelated sectors. As we embark on this scholarly journey, let us remember that sometimes, beneath the surface of seemingly distinct phenomena, lies a web of connections waiting to be uncovered, much like finding the unexpected harmony between a tuba and a kazoo.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The aroma of our research findings wafts through the hallowed halls of academia, leaving in its wake the lingering scent of curiosity and a subtle hint of disbelief. Our investigation into the relationship between US tobacco production and the number of slot machines in Nevada has led us down an unexpected rabbit hole, much like finding a pair of dice in a tobacco pouch. Our results, which may initially strike one as improbable as a vegan steakhouse, have raised eyebrows and prompted chuckles, challenging us to explore the complex dance between agricultural pursuits and the flashy, jingling world of gaming.

Building upon the hallowed foundations laid by Smith's work on the economic impact of US tobacco production, our findings seem to add a subtle note of "I told you so" to the notion that tobacco cultivation carries a weighty significance, much like a heavyweight boxer with a fondness for fine cigars. The correlation coefficient we unveiled waltzes harmoniously with previous research, echoing Doe's musings on the economic nuances of the gambling industry. It's as if our data is whispering a cheeky "I'm in cahoots with the slots" to the observations made by our scholarly forebears.

In a seemingly serendipitous turn of events, our results appear to have lent a rather unexpected wink of approval to the imaginative works of Wills and Stone, who dared to muse on the enigmatic synergy between tobacco and slot machines. What once may have seemed as improbable as finding a pair of dice in a tobacco pouch has emerged as a tangible reality, much like realizing that a magician's top hat truly does hold more than the rabbit of plausibility.

As we traverse this scholarly terrain, we cannot help but be reminded of the unexpected relevance of unconventional sources, such as the insights gleamed from the backs of shampoo bottles. These unassuming vessels of wisdom have nudged us to approach our research with a sense of openness and curiosity, much akin to stumbling upon a winning combination on a slot machine.

Our findings stand as a testament to the fact that sometimes, beneath the surface of seemingly disparate domains, lies a network of connections waiting to be unearthed, much like realizing that a pumpkin and a pineapple share a similar classification as fruit, despite vastly different external appearances. Our research has invited us to glimpse beyond the smoke and mirrors of ostensibly unrelated sectors and dare to peek at the tantalizing enigma that lies beneath, much like watching a magician reveal the captivating secrets hidden within a seemingly ordinary deck of cards.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Tobacco Production and Number of Slot Machines in Nevada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
"Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada"

[[ABSTRACT]]
This study aimed to investigate the curious connection between US tobacco production and the number of slot machines in the illustrious state of Nevada. By utilizing data from Statista and the University of Nevada, Las Vegas, we embarked on a statistical odyssey to uncover potential correlations that may shed light on this peculiar relationship. Our findings revealed a striking correlation coefficient of 0.8274039 with a significance level of p < 0.01 for the years spanning from 2000 to 2022. While our results may seem like a mere smokescreen, they lend credence to the notion that the tobacco industry and the allure of slot machines may indeed share a deeper connection, one that could be more than just a mere "roll of the dice." This research underscores the potential for fruitful exploration at the intersection of agricultural production and the gaming industry, challenging us to examine correlations that may be more than mere statistical happenstance.

[[INTRDUCTION]]
Tobacco and slot machines may seem like an unlikely pair, much like peanut butter and jalapenos – a combination that raises eyebrows and elicits skepticism. However, in the vast tapestry of statistical relationships, sometimes the most unexpected pairings hold hidden truths that beg to be unraveled. In this paper, we delve into the intriguing link between US tobacco production and the number of slot machines in the renowned gambling haven of Nevada.
As much as we'd love to claim that the allure of slot machines simply stems from their flashy lights and occasional payouts, our inquisitive minds couldn't help but wonder if there might be a deeper, more unfiltered connection – much like that distinct aroma of freshly brewed coffee and the prospect of financial risk. To tackle this curious conundrum, we harnessed the power of data from esteemed sources such as Statista and the University of Nevada, Las Vegas, aiming to let the numbers speak for themselves, as they often do, albeit in a rather cryptic and enigmatic language.
While some may dismiss this investigation as a mere flight of fancy, akin to pondering the correlation between the abundance of cacti in Arizona and the popularity of cowboy hats, our initial foray into the realm of data analysis has yielded surprisingly robust findings. Our results revealed a correlation coefficient that raises an eyebrow or two, standing at a rather impressive 0.8274039, signaling a relationship that appears to be more than a mere statistical hiccup. With a significance level of p < 0.01 for the years spanning from 2000 to 2022, the evidence has left us pondering the possibility that there might be more to this association than meets the eye – a reality akin to discovering that an artichoke and an aardvark share a similarly shaped ear.
As we venture further into our analysis, it becomes increasingly evident that the smoke-filled rooms of tobacco production and the glittering halls of slot machines may share a more intricate dance than initially surmised. In uncovering these potential connections, we challenge the notion of happenstance and invite the academic community to engage in this peculiar pas de deux between agriculture and the allure of gambling, daring to explore the possibility of a relationship that is more than just a "roll of the dice." Join us on this statistical odyssey as we aim to shine a light on the intriguing and unexpected connections that may lie beneath the surface of seemingly unrelated industries, where what meets the eye may be but a mere facade, akin to a deck of cards cleverly concealing a royal flush.

[[RESULTS]]
The analysis of our data revealed a strong positive correlation between US tobacco production and the number of slot machines in Nevada, with a correlation coefficient of 0.8274039 and an r-squared value of 0.6845973. This indicates that approximately 68.46% of the variation in the number of slot machines in Nevada can be explained by the variation in US tobacco production over the years 2000 to 2022. The obtained p-value of less than 0.01 underscores the statistical significance of this relationship, further supporting the idea that these two seemingly unrelated industries may be intertwined in an unexpected manner.
The scatterplot (Fig. 1) visually illustrates the substantial positive relationship between US tobacco production and the number of slot machines in Nevada. The data points align themselves in such a way that one could almost imagine tobacco leaves turning into stacks of casino chips, although that may just be a whimsical interpretation.
While these findings may appear as baffling as finding a pineapple on a pizza, they open up a realm of intriguing possibilities that challenge conventional expectations. It seems that the allure of tobacco and the enchantment of slot machines may share more than just a passing resemblance, much like discovering that a rubber duck and a Nobel laureate share the same middle name.
This research sets the stage for future exploration of the interplay between agricultural production and the gaming industry. Just as a magician skillfully manipulates cards to create an illusion, our findings prompt us to consider the potential hidden dynamics at play, urging us to peek beyond the smoke and mirrors of apparently unrelated sectors. As we embark on this scholarly journey, let us remember that sometimes, beneath the surface of seemingly distinct phenomena, lies a web of connections waiting to be uncovered, much like finding the unexpected harmony between a tuba and a kazoo.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the curious relationship between US tobacco production and the number of slot machines in Nevada has yielded compelling results that beckon further exploration, much like finding a four-leaf clover in a field of statistical haystacks. The robust correlation coefficient of 0.8274039 unsurprisingly raises eyebrows and prompts us to ponder the potential interplay between these seemingly disparate industries. Our findings, akin to stumbling upon a treasure map in a bucket of popcorn, underscore the need to delve deeper into the underlying mechanisms that may drive this unexpected association.

The statistical significance of our results, with a p-value of less than 0.01, reaffirms the potential substantive nature of this connection, challenging us to consider the possibility that there might be more to this relationship than a mere statistical anomaly. This intriguing correlation, much like a compelling plot twist in a mystery novel, invites us to reconsider the boundaries of what we perceive as unrelated industries, signaling the potential for fruitful exploration in uncharted research territories.

However, like finding a needle in a haystack, we assert that this study has shed light on a compelling area of inquiry and urge the academic community to embrace this unconventional pairing with the fervor of a detective hot on the trail of a cryptic clue. Yet, much like the end of a magic show, where the illusion is revealed, we contend that no further research in this domain is needed – let the peculiar partnership between US tobacco production and the number of slot machines in Nevada remain a delightful enigma, akin to the unexpected harmony of a kazoo solo in a symphony orchestra.


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 Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unlikely Connections


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 Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Research Studies


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 Smoke and Mirrors: The Relationship Between US Tobacco Production and Number of Slot Machines in Nevada with an abstract of This study aimed to investigate the curious connection between US tobacco production and the number of slot machines in the illustrious state of Nevada. By utilizing data from Statista and the University of Nevada, Las Vegas, we embarked on a statistical odyssey to uncover potential correlations that may shed light on this peculiar relationship. Our findings revealed a striking correlation coefficient of 0.8274039 with a significance level of p < 0.01 for the years spanning from 2000 to 2022. While our results may seem like a mere smokescreen, they lend credence to the notion that the tobacco industry and the allure of slot machines may indeed share a deeper connection, one that could be more than just a mere "roll of the dice." This research underscores the potential for fruitful exploration at the intersection of agricultural production and the gaming industry, challenging us to examine correlations that may be more than mere statistical happenstance.

ChatGPT:

US tobacco production, Nevada slot machines, tobacco industry correlations, agricultural production gaming industry, correlation coefficient, Statista data, University of Nevada Las Vegas study, tobacco and gambling connection, tobacco production statistical odyssey

*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 Tobacco Production
Source: Statista
See what else correlates with US Tobacco Production

Number of Slot Machines in Nevada
Source: UNLV
See what else correlates with Number of Slot Machines in Nevada

Correlation r = 0.8274039 (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 = 0.6845973 (Coefficient of determination)
This means 68.5% of the change in the one variable (i.e., Number of Slot Machines in Nevada) is predictable based on the change in the other (i.e., US Tobacco Production) over the 23 years from 2000 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.1E-6. 0.0000011160838970031080000000
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 0.83 in 0.00011% of random cases. Said differently, if you correlated 895,990 random variables You don't actually need 895 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 22 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 22 because we have two variables measured over a period of 23 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.

[ 0.63, 0.92 ] 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.
20002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
US Tobacco Production (Pounds)1053260000991293000871122000802560000881875000645015000727897000787653000800504000822581000718190000598252000762709000723579000876415000719171000628720000710161000533241000467953000372877000458126000447363000
Number of Slot Machines in Nevada (Slot machines)193000196000186000184000179000178000177000175000172000170000167000187372182574179837175464171101167692164996163757163100136375144410146702




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
  5. 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([1053260000,991293000,871122000,802560000,881875000,645015000,727897000,787653000,800504000,822581000,718190000,598252000,762709000,723579000,876415000,719171000,628720000,710161000,533241000,467953000,372877000,458126000,447363000,])
array_2 = np.array([193000,196000,186000,184000,179000,178000,177000,175000,172000,170000,167000,187372,182574,179837,175464,171101,167692,164996,163757,163100,136375,144410,146702,])
array_1_name = "US Tobacco Production"
array_2_name = "Number of Slot Machines in Nevada"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

I'm grateful for your review!


Correlation ID: 1180 · Black Variable ID: 429 · Red Variable ID: 2
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0