about · email me · subscribe
Spurious correlation #4,732 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air quality in Houghton, Michigan and the second variable is Liquefied petroleum gas used in Central African Republic.  The chart goes from 2008 to 2021, and the two variables track closely in value over that time. Small Image

AI explanation

The cleaner air in Houghton, Michigan somehow sparked a global quest for cleaner energy sources. This led to a spike in demand for Liquefied petroleum gas in the Central African Republic, as people became inspired to cook and heat their homes more efficiently. It's like Houghton became the unofficial ambassador for clean air and LPG, creating a breath of fresh economic and environmental change across the globe! Who knew that Houghton, Michigan's air quality had such far-reaching effects?

Model: dalle-3
Prompt: [ Whimsical illustration ] Generate an image of Houghton, Michigan, with pure, energizing air permeating the scene, and people filled with joyous anticipation for a global transformation. Capture the essence of cleaner energy sources through vibrant colors and a sense of movement in the air. In the background, represent families in the Central African Republic cooking and warming their homes with Liquefied Petroleum Gas (LPG), showcasing gratitude and newfound efficiency. Emphasize the connection between the refreshing breeze from Houghton and the global wave of environmental and economic rejuvenation, as LPG's demand surges and propels change. Highlight the theme of unity and progress without using any words or speech bubbles. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic. 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: 3D Pixar Style Whimsical illustration Psychedelic An image that looks like it is a scene from a Pixar movie Vaporwave
ChatGPT: Whimsical illustration

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic, in the following situation: The cleaner air in Houghton, Michigan somehow sparked a global quest for cleaner energy sources. This led to a spike in demand for Liquefied petroleum gas in the Central African Republic, as people became inspired to cook and heat their homes more efficiently. It's like Houghton became the unofficial ambassador for clean air and LPG, creating a breath of fresh economic and environmental change across the globe! Who knew that Houghton, Michigan's air quality had such far-reaching effects?. Keep the description simple.
ChatGPT: Amidst the crisp and clean air of Houghton, Michigan, people gather in joyous anticipation of a stunning global transformation. The air quality's purity seems to radiate energy, sparking a quest for cleaner energy sources across the world. Meanwhile, in the Central African Republic, families excitedly cook and warm their homes with Liquefied Petroleum Gas (LPG), grateful for the newfound efficiency and cleanliness it brings. The refreshing breeze from Houghton becomes the catalyst for a global wave of environmental and economic rejuvenation, as LPG's demand surges and propels change.

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: [ Whimsical illustration ] and depicting this scene: Amidst the crisp and clean air of Houghton, Michigan, people gather in joyous anticipation of a stunning global transformation. The air quality's purity seems to radiate energy, sparking a quest for cleaner energy sources across the world. Meanwhile, in the Central African Republic, families excitedly cook and warm their homes with Liquefied Petroleum Gas (LPG), grateful for the newfound efficiency and cleanliness it brings. The refreshing breeze from Houghton becomes the catalyst for a global wave of environmental and economic rejuvenation, as LPG's demand surges and propels change. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Whimsical illustration ] Generate an image of Houghton, Michigan, with pure, energizing air permeating the scene, and people filled with joyous anticipation for a global transformation. Capture the essence of cleaner energy sources through vibrant colors and a sense of movement in the air. In the background, represent families in the Central African Republic cooking and warming their homes with Liquefied Petroleum Gas (LPG), showcasing gratitude and newfound efficiency. Emphasize the connection between the refreshing breeze from Houghton and the global wave of environmental and economic rejuvenation, as LPG's demand surges and propels change. Highlight the theme of unity and progress without using any words or speech bubbles.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Air quality in Houghton, Michigan positively influenced Liquefied petroleum gas used in Central African Republic.

AI academic paper

(Because p < 0.01)
Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection

Journal of Eclectic Atmospheric Studies

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




Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9843529 and p < 0.01 for 2008 to 2021.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection"

[[ABSTRACT]]
This study investigates the surprising link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). In a twist of fate, our findings reveal a remarkable correlation between these seemingly unrelated phenomena, highlighting the unexpected interconnectedness of global environmental factors. Utilizing data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), our research team calculated a striking correlation coefficient of 0.9843529 with a p-value of less than 0.01 over the period from 2008 to 2021. The results of this study prompt a reevaluation of our understanding of the interconnected nature of environmental influences and spark intrigue into the potential mechanisms underlying this curious association.


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 Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic. Make lots of jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
"Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection"

[[ABSTRACT]]
This study investigates the surprising link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). In a twist of fate, our findings reveal a remarkable correlation between these seemingly unrelated phenomena, highlighting the unexpected interconnectedness of global environmental factors. Utilizing data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), our research team calculated a striking correlation coefficient of 0.9843529 with a p-value of less than 0.01 over the period from 2008 to 2021. The results of this study prompt a reevaluation of our understanding of the interconnected nature of environmental influences and spark intrigue into the potential mechanisms underlying this curious association.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The quest for understanding the dynamics of air quality has long been an enigma, akin to trying to solve a riddle wrapped in a mystery inside an enigma – with a side of smog. As our world becomes increasingly connected, the intricate web of environmental influences continues to surprise and puzzle researchers. One such perplexing connection that has emerged from the depths of statistical analyses is the unexpected correlation between air quality in Houghton, Michigan, and the utilization of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). Yes, you read that correctly – we're delving into the gas-tly connection between Northern Michigan and Central Africa!

You might think, "What on earth could link the crisp air of Houghton to the LPG usage in the heart of Africa?" Well, dear reader, join us on this expedition as we navigate through the veils of data, statistical analyses, and a pinch of whimsy to unveil the curious association that has left researchers gasping for breath (pun intended).

Before we dive into the depths of this peculiar correlation, it is essential to grasp the significance of air quality and LPG usage in their respective contexts. Houghton, Michigan, nestled in the serene embrace of the Upper Peninsula, is renowned for its picturesque landscapes and the pure, invigorating whiffs of Lake Superior. On the other hand, the Central African Republic grapples with energy disparities and the complexities of delivering clean cooking fuel to its citizens. At first glance, these two locations seem as disparate as a snowstorm and a sandstorm – but as we unravel the data, an intriguing interdependence begins to emerge.

The findings of this study, which we affectionately dub "Burning Bright," are not only intriguing but also raise pressing questions about the interplay of global environmental factors. As we embark on this journey of discovery, prepare to be surprised, amused, and maybe even a little gassy (in the statistical sense, of course) as we unravel the mysteries of this unlikely connection.

Now, sit back, grab a breath of fresh air (avoiding the LPG, if possible), and let's unravel the gas-tly connection between these seemingly distant environmental phenomena.


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 Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
"Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection"

[[ABSTRACT]]
This study investigates the surprising link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). In a twist of fate, our findings reveal a remarkable correlation between these seemingly unrelated phenomena, highlighting the unexpected interconnectedness of global environmental factors. Utilizing data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), our research team calculated a striking correlation coefficient of 0.9843529 with a p-value of less than 0.01 over the period from 2008 to 2021. The results of this study prompt a reevaluation of our understanding of the interconnected nature of environmental influences and spark intrigue into the potential mechanisms underlying this curious association.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The quest for understanding the dynamics of air quality has long been an enigma, akin to trying to solve a riddle wrapped in a mystery inside an enigma – with a side of smog. As our world becomes increasingly connected, the intricate web of environmental influences continues to surprise and puzzle researchers. One such perplexing connection that has emerged from the depths of statistical analyses is the unexpected correlation between air quality in Houghton, Michigan, and the utilization of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). Yes, you read that correctly – we're delving into the gas-tly connection between Northern Michigan and Central Africa!
You might think, "What on earth could link the crisp air of Houghton to the LPG usage in the heart of Africa?" Well, dear reader, join us on this expedition as we navigate through the veils of data, statistical analyses, and a pinch of whimsy to unveil the curious association that has left researchers gasping for breath (pun intended).
Before we dive into the depths of this peculiar correlation, it is essential to grasp the significance of air quality and LPG usage in their respective contexts. Houghton, Michigan, nestled in the serene embrace of the Upper Peninsula, is renowned for its picturesque landscapes and the pure, invigorating whiffs of Lake Superior. On the other hand, the Central African Republic grapples with energy disparities and the complexities of delivering clean cooking fuel to its citizens. At first glance, these two locations seem as disparate as a snowstorm and a sandstorm – but as we unravel the data, an intriguing interdependence begins to emerge.
The findings of this study, which we affectionately dub "Burning Bright," are not only intriguing but also raise pressing questions about the interplay of global environmental factors. As we embark on this journey of discovery, prepare to be surprised, amused, and maybe even a little gassy (in the statistical sense, of course) as we unravel the mysteries of this unlikely connection.
Now, sit back, grab a breath of fresh air (avoiding the LPG, if possible), and let's unravel the gas-tly connection between these seemingly distant environmental phenomena.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The astonishing correlation between air quality in Houghton, Michigan, and the use of Liquefied Petroleum Gas (LPG) in the Central African Republic has puzzled and captivated researchers in equal measure. As we embark on this whimsical journey through the literature, we start with the serious endeavors of Smith and colleagues, who diligently investigated air quality dynamics in the Great Lakes region. In "Air Quality and Its Impacts on Human Health," the authors find a comprehensive overview of air pollution sources, atmospheric chemistry, and the physiological effects of poor air quality. However, what Smith and colleagues may not have anticipated is the unexpected tie between the crystalline air of the Upper Peninsula and the distant aroma of LPG in Central Africa.

Doe's seminal work, "The Energy Landscape of Central Africa," delves into the intricate energy consumption patterns in the CAR. The comprehensive study brings to light the challenges and opportunities in providing clean cooking fuel to the populations of the Central African Republic. While the authors ponder the complexities of energy access, little did they know that their work would play a role in unraveling the peculiar connection between Houghton's fresh breeze and the usage of LPG halfway across the globe.

In a turn of events that could rival the plot twists of a mystery novel, the literature also turns to some unexpected sources. From "The Great Lakes Cookbook: Lake Superior's Finest Cuisine" to "Cooking with Fire: Recipes from Around the World," the astute reader might discern a tangential link to LPG usage, albeit in a more culinary context. The notion of flavors floating across continents brings a new dimension to the gas-tly connection, leaving us to wonder if the aroma of simmering stews and sizzling grills might somehow transcend geographical boundaries.

Stepping further into the realms of fiction, "The Lion King" and "Snow Falling on Cedars" may not seem immediately relevant to our gas-tly investigation. However, a closer inspection unveils underlying themes of environmental symbiosis and the interconnectedness of distant lands. Could these fictional narratives subtly hint at the remarkable correlation between Houghton's air quality and LPG utilization in the CAR? The authors leave such questions to the imagination of the reader, much like a tantalizing cliffhanger in a page-turner.

Finally, in the realm of internet memes, the classic "Distracted Boyfriend" image finds an unlikely connection to our investigation. As the viral meme takes on various cultural contexts, we couldn't help but ponder the whimsical idea of Houghton, Michigan, being the distracted boyfriend, drawn towards the scent of LPG from afar, while its usual companion, pristine air, looks on with a mix of bewilderment and amusement.

In the quest for understanding the intersection of air quality and LPG usage, we find ourselves musing over a varied tapestry of literature, from the serious to the unexpected, weaving a narrative that holds the potential for scholarly discovery and a touch of lighthearted amusement. As we transition from the data-driven to the delightfully absurd, we invite the reader to join us in the exploration of this gas-tly conundrum, where the line between the serious and the whimsical begins to blur like a mirage in the desert – or perhaps a puff of smoke from a distant cooking fire.


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 Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration . You used data from 2008 to 2021

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection"

[[ABSTRACT]]
This study investigates the surprising link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). In a twist of fate, our findings reveal a remarkable correlation between these seemingly unrelated phenomena, highlighting the unexpected interconnectedness of global environmental factors. Utilizing data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), our research team calculated a striking correlation coefficient of 0.9843529 with a p-value of less than 0.01 over the period from 2008 to 2021. The results of this study prompt a reevaluation of our understanding of the interconnected nature of environmental influences and spark intrigue into the potential mechanisms underlying this curious association.

[[INTRODUCTION]]
The quest for understanding the dynamics of air quality has long been an enigma, akin to trying to solve a riddle wrapped in a mystery inside an enigma – with a side of smog. As our world becomes increasingly connected, the intricate web of environmental influences continues to surprise and puzzle researchers. One such perplexing connection that has emerged from the depths of statistical analyses is the unexpected correlation between air quality in Houghton, Michigan, and the utilization of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). Yes, you read that correctly – we're delving into the gas-tly connection between Northern Michigan and Central Africa!
You might think, "What on earth could link the crisp air of Houghton to the LPG usage in the heart of Africa?" Well, dear reader, join us on this expedition as we navigate through the veils of data, statistical analyses, and a pinch of whimsy to unveil the curious association that has left researchers gasping for breath (pun intended).
Before we dive into the depths of this peculiar correlation, it is essential to grasp the significance of air quality and LPG usage in their respective contexts. Houghton, Michigan, nestled in the serene embrace of the Upper Peninsula, is renowned for its picturesque landscapes and the pure, invigorating whiffs of Lake Superior. On the other hand, the Central African Republic grapples with energy disparities and the complexities of delivering clean cooking fuel to its citizens. At first glance, these two locations seem as disparate as a snowstorm and a sandstorm – but as we unravel the data, an intriguing interdependence begins to emerge.
The findings of this study, which we affectionately dub "Burning Bright," are not only intriguing but also raise pressing questions about the interplay of global environmental factors. As we embark on this journey of discovery, prepare to be surprised, amused, and maybe even a little gassy (in the statistical sense, of course) as we unravel the mysteries of this unlikely connection.
Now, sit back, grab a breath of fresh air (avoiding the LPG, if possible), and let's unravel the gas-tly connection between these seemingly distant environmental phenomena.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR), our research team embarked on a whimsical journey, employing a mix of statistical wizardry and a touch of serendipity. Fueled by curiosity and a relentless pursuit of knowledge, we harnessed the power of data collected from a multitude of sources, delicately weaving together a tapestry of information from the Environmental Protection Agency (EPA), the Energy Information Administration (EIA), and various other platforms across the vast expanse of the internet.

We charted a course through the seas of statistical analyses, utilizing a delightful combination of regression models, time series analyses, and a sprinkle of machine learning algorithms to navigate through the labyrinth of data points. Our clever manipulation of these data mining tools was akin to concocting a potion, as we sought to distill the essence of the relationship between air quality in Houghton and the utilization of LPG in the CAR. It was a veritable cauldron of calculations and computations, with a dollop of creativity and a pinch of whimsy thrown into the mix for good measure.

With a mischievous glint in our eyes and a software suite at our disposal, we performed a rigorous examination of the data from 2008 to 2021, uncovering hidden patterns and relationships that even the most astute of statistical sleuths would find impressive. Our methods were as rigorous as they were charming, mirroring the intricate dance of intertwined global environmental influences that we sought to elucidate.

At the heart of our methodology lay a quest for understanding that was as profound as it was lighthearted, weaving a tale of inquiry and exploration that would have made even the most stoic of researchers crack a smile. The tools and techniques we employed were the instruments of our musical symphony, harmonizing disparate data points into a melodious composition of statistical significance that would leave the most discerning of audiences in awe.

In summary, our methodology played host to a delightful array of statistical acrobatics, digital sorcery, and a touch of whimsy, all in service of deciphering the curious connection between air quality in Houghton and LPG usage in the CAR.


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 Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration .

For the time period 2008 to 2021, you found a correlation 0.9843529, r-squared of 0.9689507, 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]]
"Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection"

[[ABSTRACT]]
This study investigates the surprising link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). In a twist of fate, our findings reveal a remarkable correlation between these seemingly unrelated phenomena, highlighting the unexpected interconnectedness of global environmental factors. Utilizing data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), our research team calculated a striking correlation coefficient of 0.9843529 with a p-value of less than 0.01 over the period from 2008 to 2021. The results of this study prompt a reevaluation of our understanding of the interconnected nature of environmental influences and spark intrigue into the potential mechanisms underlying this curious association.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The quest for understanding the dynamics of air quality has long been an enigma, akin to trying to solve a riddle wrapped in a mystery inside an enigma – with a side of smog. As our world becomes increasingly connected, the intricate web of environmental influences continues to surprise and puzzle researchers. One such perplexing connection that has emerged from the depths of statistical analyses is the unexpected correlation between air quality in Houghton, Michigan, and the utilization of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). Yes, you read that correctly – we're delving into the gas-tly connection between Northern Michigan and Central Africa!
You might think, "What on earth could link the crisp air of Houghton to the LPG usage in the heart of Africa?" Well, dear reader, join us on this expedition as we navigate through the veils of data, statistical analyses, and a pinch of whimsy to unveil the curious association that has left researchers gasping for breath (pun intended).
Before we dive into the depths of this peculiar correlation, it is essential to grasp the significance of air quality and LPG usage in their respective contexts. Houghton, Michigan, nestled in the serene embrace of the Upper Peninsula, is renowned for its picturesque landscapes and the pure, invigorating whiffs of Lake Superior. On the other hand, the Central African Republic grapples with energy disparities and the complexities of delivering clean cooking fuel to its citizens. At first glance, these two locations seem as disparate as a snowstorm and a sandstorm – but as we unravel the data, an intriguing interdependence begins to emerge.
The findings of this study, which we affectionately dub "Burning Bright," are not only intriguing but also raise pressing questions about the interplay of global environmental factors. As we embark on this journey of discovery, prepare to be surprised, amused, and maybe even a little gassy (in the statistical sense, of course) as we unravel the mysteries of this unlikely connection.
Now, sit back, grab a breath of fresh air (avoiding the LPG, if possible), and let's unravel the gas-tly connection between these seemingly distant environmental phenomena.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our statistical analysis illuminated a striking correlation between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). We found a robust correlation coefficient of 0.9843529, with an r-squared value of 0.9689507 and a p-value of less than 0.01. This correlation indicates a strong linear relationship between the air quality in Houghton and the consumption of LPG in the Central African Republic. It's as if they are gasping for the same breath of fresh air across continents!

The surprising magnitude of this correlation suggests that there may be an underlying connection between these two seemingly disparate environmental factors. The scatterplot (Fig. 1) vividly illustrates this remarkable association, showcasing a clear and compelling trend between the air quality in Houghton and the utilization of LPG in the Central African Republic. It's like witnessing a cosmic dance between unrelated celestial bodies, but with a touch of statistical flair.

These findings prompt us to contemplate the intricate and unexpected ways in which environmental influences can transcend geographical boundaries. It's a reminder that the world is more interconnected than we often assume, and that even the air we breathe in one corner of the globe can be linked to energy usage in a distant land. Who knew that statistical analyses could lead to such a breath-taking revelation?

These results challenge us to rethink our understanding of environmental interconnectedness and open up new avenues of inquiry into the mechanisms underlying this seemingly whimsical correlation. It's a striking reminder that in the world of statistics, there are no coincidences – only correlations waiting to be discovered, no matter how gas-tly they may seem at first sight!


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 Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic. Make lots of 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]]
"Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection"

[[ABSTRACT]]
This study investigates the surprising link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). In a twist of fate, our findings reveal a remarkable correlation between these seemingly unrelated phenomena, highlighting the unexpected interconnectedness of global environmental factors. Utilizing data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), our research team calculated a striking correlation coefficient of 0.9843529 with a p-value of less than 0.01 over the period from 2008 to 2021. The results of this study prompt a reevaluation of our understanding of the interconnected nature of environmental influences and spark intrigue into the potential mechanisms underlying this curious association.

[[LITERATURE REVIEW]]
The astonishing correlation between air quality in Houghton, Michigan, and the use of Liquefied Petroleum Gas (LPG) in the Central African Republic has puzzled and captivated researchers in equal measure. As we embark on this whimsical journey through the literature, we start with the serious endeavors of Smith and colleagues, who diligently investigated air quality dynamics in the Great Lakes region. In "Air Quality and Its Impacts on Human Health," the authors find a comprehensive overview of air pollution sources, atmospheric chemistry, and the physiological effects of poor air quality. However, what Smith and colleagues may not have anticipated is the unexpected tie between the crystalline air of the Upper Peninsula and the distant aroma of LPG in Central Africa.
Doe's seminal work, "The Energy Landscape of Central Africa," delves into the intricate energy consumption patterns in the CAR. The comprehensive study brings to light the challenges and opportunities in providing clean cooking fuel to the populations of the Central African Republic. While the authors ponder the complexities of energy access, little did they know that their work would play a role in unraveling the peculiar connection between Houghton's fresh breeze and the usage of LPG halfway across the globe.
In a turn of events that could rival the plot twists of a mystery novel, the literature also turns to some unexpected sources. From "The Great Lakes Cookbook: Lake Superior's Finest Cuisine" to "Cooking with Fire: Recipes from Around the World," the astute reader might discern a tangential link to LPG usage, albeit in a more culinary context. The notion of flavors floating across continents brings a new dimension to the gas-tly connection, leaving us to wonder if the aroma of simmering stews and sizzling grills might somehow transcend geographical boundaries.
Stepping further into the realms of fiction, "The Lion King" and "Snow Falling on Cedars" may not seem immediately relevant to our gas-tly investigation. However, a closer inspection unveils underlying themes of environmental symbiosis and the interconnectedness of distant lands. Could these fictional narratives subtly hint at the remarkable correlation between Houghton's air quality and LPG utilization in the CAR? The authors leave such questions to the imagination of the reader, much like a tantalizing cliffhanger in a page-turner.
Finally, in the realm of internet memes, the classic "Distracted Boyfriend" image finds an unlikely connection to our investigation. As the viral meme takes on various cultural contexts, we couldn't help but ponder the whimsical idea of Houghton, Michigan, being the distracted boyfriend, drawn towards the scent of LPG from afar, while its usual companion, pristine air, looks on with a mix of bewilderment and amusement.
In the quest for understanding the intersection of air quality and LPG usage, we find ourselves musing over a varied tapestry of literature, from the serious to the unexpected, weaving a narrative that holds the potential for scholarly discovery and a touch of lighthearted amusement. As we transition from the data-driven to the delightfully absurd, we invite the reader to join us in the exploration of this gas-tly conundrum, where the line between the serious and the whimsical begins to blur like a mirage in the desert – or perhaps a puff of smoke from a distant cooking fire.

[[RESULTS]]
The results of our statistical analysis illuminated a striking correlation between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). We found a robust correlation coefficient of 0.9843529, with an r-squared value of 0.9689507 and a p-value of less than 0.01. This correlation indicates a strong linear relationship between the air quality in Houghton and the consumption of LPG in the Central African Republic. It's as if they are gasping for the same breath of fresh air across continents!
The surprising magnitude of this correlation suggests that there may be an underlying connection between these two seemingly disparate environmental factors. The scatterplot (Fig. 1) vividly illustrates this remarkable association, showcasing a clear and compelling trend between the air quality in Houghton and the utilization of LPG in the Central African Republic. It's like witnessing a cosmic dance between unrelated celestial bodies, but with a touch of statistical flair.
These findings prompt us to contemplate the intricate and unexpected ways in which environmental influences can transcend geographical boundaries. It's a reminder that the world is more interconnected than we often assume, and that even the air we breathe in one corner of the globe can be linked to energy usage in a distant land. Who knew that statistical analyses could lead to such a breath-taking revelation?
These results challenge us to rethink our understanding of environmental interconnectedness and open up new avenues of inquiry into the mechanisms underlying this seemingly whimsical correlation. It's a striking reminder that in the world of statistics, there are no coincidences – only correlations waiting to be discovered, no matter how gas-tly they may seem at first sight!

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of our study have certainly blown us away, validating the whimsical inklings we gleaned from the literature review. The unexpected connection we uncovered between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic has not only left us gasping for air but also gasping in amazement at the strength of this correlation. It's like a gas-tly pairing made in statistical heaven!

Our results echo the sentiments of Smith and colleagues, who diligently examined air quality dynamics in the Great Lakes region. Despite their serious endeavors, little did they know that their work would emerge as a precursor to unraveling the cosmic dance between Houghton's fresh breeze and the distant aroma of LPG in Central Africa. It's like their serious efforts paved the way for our unexpected, yet astonishing, discovery.

Doe's comprehensive study on the energy landscape of Central Africa foreshadowed the uncovering of this peculiar connection. The challenges and opportunities in providing clean cooking fuel to the populations of the Central African Republic set the stage for our statistical revelation, as if the data was whispering the secret of their interconnection all along. It's like the study itself was a plot twist waiting to be revealed!

The seemingly absurd tangential link to LPG usage in culinary literature and fiction may have appeared to be just quirky side notes. However, our findings underscore the unexpected potential for connections where one might least expect them. It's like the aroma of simmering stews and sizzling grills transcended geographical boundaries to weave a mysterious statistical tapestry that binds Houghton and the CAR in a whimsical statistical narrative.

As we journey from the serious to the delightfully absurd, we see that our statistically-driven revelations, much like the distracted boyfriend meme, have captured the essence of Houghton, Michigan, being drawn towards the scent of LPG from afar, despite its usual companion of pristine air looking on with amazement. It's like a mirage in the desert – a statistical mirage that has materialized into a profound and thought-provoking insight.

In this gas-tly conundrum, we find ourselves at the crossroads of scholarly discovery and lighthearted amusement. Our statistical findings have not only confirmed prior inklings of unexpected connections but have also opened up a world of intriguing possibilities for future research. This statistical revelation encourages us to embrace the unforeseen and seek correlations in the unlikeliest of places. After all, in the world of statistics, as we have discovered, there are no coincidences – only correlations waiting to be unveiled, no matter how gas-tly they may seem at first sight!


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 Air quality in Houghton, Michigan and Liquefied petroleum gas used in Central African Republic. Make lots of 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]]
"Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection"

[[ABSTRACT]]
This study investigates the surprising link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). In a twist of fate, our findings reveal a remarkable correlation between these seemingly unrelated phenomena, highlighting the unexpected interconnectedness of global environmental factors. Utilizing data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), our research team calculated a striking correlation coefficient of 0.9843529 with a p-value of less than 0.01 over the period from 2008 to 2021. The results of this study prompt a reevaluation of our understanding of the interconnected nature of environmental influences and spark intrigue into the potential mechanisms underlying this curious association.

[[INTRDUCTION]]
The quest for understanding the dynamics of air quality has long been an enigma, akin to trying to solve a riddle wrapped in a mystery inside an enigma – with a side of smog. As our world becomes increasingly connected, the intricate web of environmental influences continues to surprise and puzzle researchers. One such perplexing connection that has emerged from the depths of statistical analyses is the unexpected correlation between air quality in Houghton, Michigan, and the utilization of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). Yes, you read that correctly – we're delving into the gas-tly connection between Northern Michigan and Central Africa!
You might think, "What on earth could link the crisp air of Houghton to the LPG usage in the heart of Africa?" Well, dear reader, join us on this expedition as we navigate through the veils of data, statistical analyses, and a pinch of whimsy to unveil the curious association that has left researchers gasping for breath (pun intended).
Before we dive into the depths of this peculiar correlation, it is essential to grasp the significance of air quality and LPG usage in their respective contexts. Houghton, Michigan, nestled in the serene embrace of the Upper Peninsula, is renowned for its picturesque landscapes and the pure, invigorating whiffs of Lake Superior. On the other hand, the Central African Republic grapples with energy disparities and the complexities of delivering clean cooking fuel to its citizens. At first glance, these two locations seem as disparate as a snowstorm and a sandstorm – but as we unravel the data, an intriguing interdependence begins to emerge.
The findings of this study, which we affectionately dub "Burning Bright," are not only intriguing but also raise pressing questions about the interplay of global environmental factors. As we embark on this journey of discovery, prepare to be surprised, amused, and maybe even a little gassy (in the statistical sense, of course) as we unravel the mysteries of this unlikely connection.
Now, sit back, grab a breath of fresh air (avoiding the LPG, if possible), and let's unravel the gas-tly connection between these seemingly distant environmental phenomena.

[[RESULTS]]
The results of our statistical analysis illuminated a striking correlation between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). We found a robust correlation coefficient of 0.9843529, with an r-squared value of 0.9689507 and a p-value of less than 0.01. This correlation indicates a strong linear relationship between the air quality in Houghton and the consumption of LPG in the Central African Republic. It's as if they are gasping for the same breath of fresh air across continents!
The surprising magnitude of this correlation suggests that there may be an underlying connection between these two seemingly disparate environmental factors. The scatterplot (Fig. 1) vividly illustrates this remarkable association, showcasing a clear and compelling trend between the air quality in Houghton and the utilization of LPG in the Central African Republic. It's like witnessing a cosmic dance between unrelated celestial bodies, but with a touch of statistical flair.
These findings prompt us to contemplate the intricate and unexpected ways in which environmental influences can transcend geographical boundaries. It's a reminder that the world is more interconnected than we often assume, and that even the air we breathe in one corner of the globe can be linked to energy usage in a distant land. Who knew that statistical analyses could lead to such a breath-taking revelation?
These results challenge us to rethink our understanding of environmental interconnectedness and open up new avenues of inquiry into the mechanisms underlying this seemingly whimsical correlation. It's a striking reminder that in the world of statistics, there are no coincidences – only correlations waiting to be discovered, no matter how gas-tly they may seem at first sight!

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our "Burning Bright" study has shed light on the unexpected correlation between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). Who would have thought that these two seemingly unrelated phenomena could be as connected as peanut butter and jelly, or as we should say in this context, as interconnected as air and gas? Our findings have left us gasping for breath, not just from the statistical significance but also from the unexpected plot twist of global environmental influences.

The robust correlation coefficient of 0.9843529 indicates a relationship stronger than the power of love, or at least statistically speaking! The scatterplot showcased this connection with all the grace of a carefully choreographed dance, making us wonder if the air molecules in Houghton are whispering to the LPG users in the Central African Republic, "Hey, can you gas me up too?"

However, as much as we revel in the whimsy of this peculiar association, we must acknowledge the serious implications of our findings. The interconnectedness of environmental influences transcending geographical boundaries highlights the need for global cooperation in addressing air quality and energy usage. It's a reminder that we are all in this breathing and burning world together, and even statistical analyses can ignite a spark of environmental awareness.

In the end, it is with a mix of delight and disbelief that we assert: No more research is needed in this gas-tly connection! Let these findings be a breath of fresh air in the realm of environmental correlations and pave the way for more astoundingly unexpected discoveries in the future. As for now, let's exhale, celebrate the statistical serendipity, and marvel at the peculiar interdependence of our gaseous fates!


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 Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Eclectic Atmospheric 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 Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Atmospheric Research and International Gas Studies (SARIGS)


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 Burning Bright: Air Quality in Houghton, Michigan and Liquefied Petroleum Gas in Central African Republic - A Gas-tly Connection with an abstract of This study investigates the surprising link between air quality in Houghton, Michigan, and the usage of Liquefied Petroleum Gas (LPG) in the Central African Republic (CAR). In a twist of fate, our findings reveal a remarkable correlation between these seemingly unrelated phenomena, highlighting the unexpected interconnectedness of global environmental factors. Utilizing data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA), our research team calculated a striking correlation coefficient of 0.9843529 with a p-value of less than 0.01 over the period from 2008 to 2021. The results of this study prompt a reevaluation of our understanding of the interconnected nature of environmental influences and spark intrigue into the potential mechanisms underlying this curious association.

ChatGPT:

air quality, Houghton Michigan, Liquefied Petroleum Gas, Central African Republic, environmental factors, correlation coefficient, EPA data, EIA data, global environmental influences, interconnectedness, mechanisms

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

Air quality in Houghton, Michigan
Detailed data title: Percentage of days with good or moderate air quality in Houghton, MI
Source: Environmental Protection Agency
See what else correlates with Air quality in Houghton, Michigan

Liquefied petroleum gas used in Central African Republic
Detailed data title: Volume of liquefied petroleum gas used consumed in Central African Republic in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Liquefied petroleum gas used in Central African Republic

Correlation r = 0.9843529 (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 = 0.9689507 (Coefficient of determination)
This means 96.9% of the change in the one variable (i.e., Liquefied petroleum gas used in Central African Republic) is predictable based on the change in the other (i.e., Air quality in Houghton, Michigan) over the 14 years from 2008 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.05E-10. 0.0000000002048738693361079000
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 0.98 in 2.05E-8% of random cases. Said differently, if you correlated 4,881,051,953 random variables You don't actually need 4 billion 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.

[ 0.95, 1 ] 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.
20082009201020112012201320142015201620172018201920202021
Air quality in Houghton, Michigan (Good air quality)1111111111110.9914531
Liquefied petroleum gas used in Central African Republic (Million Barrels/Day)0.06356160.06356160.06356160.06356160.06356160.06356160.06356160.06356160.06356160.06356160.06356160.06356160.06072730.0640776




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. Outlandish outliers: There are "outliers" in this data. In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

    For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

    (This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
    They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.




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([1,1,1,1,1,1,1,1,1,1,1,1,0.991453,1,])
array_2 = np.array([0.0635616,0.0635616,0.0635616,0.0635616,0.0635616,0.0635616,0.0635616,0.0635616,0.0635616,0.0635616,0.0635616,0.0635616,0.0607273,0.0640776,])
array_1_name = "Air quality in Houghton, Michigan"
array_2_name = "Liquefied petroleum gas used in Central African Republic"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your correlation rating is out of this world!


Correlation ID: 4732 · Black Variable ID: 22088 · Red Variable ID: 24285
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0