Spurious correlation #3,994 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Burglaries in Washington and the second variable is Kerosene used in Mexico. The chart goes from 1985 to 2019, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Burglaries in Washington and the second variable is Kerosene used in Mexico. The chart goes from 1985 to 2019, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As burglaries decreased in Washington, there was less need for improvised Molotov cocktails, leading to a reduced demand for kerosene in Mexico. Without the need to break into homes in Washington, the supply of kerosene from there also saw a decrease, causing a chain reaction that ultimately led to less kerosene being used in Mexico.

^{Show image generation prompt} Model: dalle-3
Prompt: An image that looks like it is a scene from a Pixar movie, depicting the once bustling thieves' getaway truck sitting idle on the side of a dusty road in a small Washington town. The truck's fuel tank is visibly empty as the community sees a decrease in burglaries. Meanwhile, in a rural village in Mexico, a group of bandits stands around a campfire, frustration evident on their faces as they struggle to ignite the wet wood with a dwindling supply of kerosene. 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: Burglaries in Washington and Kerosene used in Mexico. 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: Parallax art Voxel art Surrealism Whimsical illustration An image that looks like it is a scene from a Pixar movie
ChatGPT: An image that looks like it is a scene from a Pixar movie

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Burglaries in Washington and Kerosene used in Mexico, in the following situation: As burglaries decreased in Washington, thieves had less fuel for their illegal activities, causing a drop in demand for kerosene in Mexico. With fewer stolen goods to transport, kerosene sales went up in smoke, leaving Mexican bandits feeling lit-erally burned.. Keep the description simple.
ChatGPT: In a small Washington town, the community sees a decrease in burglaries. As a result, the once bustling thieves' getaway truck sits idle on the side of a dusty road, its fuel tank empty. Meanwhile, in a rural village in Mexico, a group of bandits stands around a campfire, frustration evident on their faces as they struggle to ignite the wet wood with a dwindling supply of kerosene.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from a Pixar movie ] and depicting this scene: In a small Washington town, the community sees a decrease in burglaries. As a result, the once bustling thieves' getaway truck sits idle on the side of a dusty road, its fuel tank empty. Meanwhile, in a rural village in Mexico, a group of bandits stands around a campfire, frustration evident on their faces as they struggle to ignite the wet wood with a dwindling supply of kerosene. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from a Pixar movie, depicting the once bustling thieves' getaway truck sitting idle on the side of a dusty road in a small Washington town. The truck's fuel tank is visibly empty as the community sees a decrease in burglaries. Meanwhile, in a rural village in Mexico, a group of bandits stands around a campfire, frustration evident on their faces as they struggle to ignite the wet wood with a dwindling supply of kerosene.

*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.
^{Show prompt for explanation} 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 Burglaries in Washington caused Kerosene used in Mexico to decrease.

AI academic paper

(Because p < 0.01)

Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico

The Journal of Comparative Criminology and Energy Consumption

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You 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 Burglaries in Washington and Kerosene used in Mexico. 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico

[[ABSTRACT]]
This research delves into the connection between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019. By using data from FBI Criminal Justice Information Services and Energy Information Administration, we sought to shed light on the seemingly unlikely relationship between crime in the U.S. and energy consumption in Mexico. Our findings reveal a robust correlation coefficient of 0.9356483 with a p-value of less than 0.01 during the study period, suggesting a strong statistical association. This investigation prompts consideration of potential cross-border influences and economic indicators affecting crime rates and energy usage. Additionally, the implications of kerosene's dual role in providing light and potentially aiding criminal activities offer a unique angle for further exploration.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
The study of crime and its underlying factors has long captivated the attention of researchers and policymakers alike. From classic theories of criminology to modern empirical investigations, the quest to understand the complex interplay of societal, economic, and environmental variables continues unabated. In this vein, this paper seeks to unravel the enigmatic relationship between burglaries in Washington and kerosene usage in Mexico, an investigation that promises to shed light on a most unexpected and, dare I say, illuminating correlation.
As the perennial pursuit of knowledge often demands, we embarked on this endeavor armed with an arsenal of data, statistical tools, and the most unfaltering determination to disentangle the web of seemingly disparate phenomena. Our empirical journey traversed the annals of crime records and energy consumption statistics, emerging with a collection of observations that both astounded and tickled our scholarly sensibilities.
Against all odds, our investigation unfurled a robust correlation coefficient of 0.9356483, dazzling us with its statistical prowess reminiscent of a magician's sleight of hand. With a p-value of less than 0.01, the evidence of relationship between these variables shimmered before us like a beacon of significance, beckoning us further into the labyrinth of academic inquiry. It is with great delight and bemusement that we present our findings, eager to chart the uncharted territories of investigative whimsy.
While the correlation itself may seem as peculiar as a mysterious chemical reaction, we cannot discount the potential influence of cross-border dynamics and economic indicators in shaping crime rates and energy usage. Indeed, the interconnectedness of our global village may harbor unexpected truths lurking beneath the surface of conventional wisdom, waiting to be unearthed through the alchemy of rigorous analysis.
Furthermore, the dual role of kerosene in bestowing light upon the darkness and potentially aiding criminal activities presents an intriguing paradox that beckons further exploration. This intersection of practical utility and untoward possibility implores us to consider the multifaceted nature of seemingly mundane substances, infusing our scholarly pursuits with a touch of daring intrigue.
As we delve deeper into the depths of this scholarly escapade, let us not forget the whimsy of intellectual discovery, the thrill of statistical revelation, and the ever-present possibility of uncovering the unexpected. For in the realm of research, as in life, the most captivating revelations often emerge from the least expected quarters, brightening the path forward with the glimmer of newfound knowledge.
End of Introduction

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The investigation of crime and its multifaceted correlates has been a central focus of scholarly inquiry, prompting the exploration of diverse and at times peculiar connections. Smith et al. (2010) conducted a seminal study on the socioeconomic determinants of burglary rates, unveiling intricate patterns of urban development and demographic shifts that contributed to the spatial distribution of criminal activities. Meanwhile, Doe and Jones (2015) delved into the behavioral manifestations of criminal intent, offering nuanced insights into the psychological underpinnings of unlawful intrusions. These foundational works, along with a multitude of empirical inquiries, have paved the way for a deeper understanding of the complex tapestry of criminal behavior.

Venturing beyond the realm of traditional criminology, a series of non-fiction accounts have probed the sociopolitical dimensions of energy consumption and its ramifications on societal dynamics, potentially shedding light on the unanticipated connection under scrutiny. In "Kerosene and Kriminals: A Sociological Study" by Luminary (2012), the author explores the underlying currents of kerosene usage within the context of criminal subcultures, hinting at subtle yet palpable intersections that beg further examination. Additionally, "The Illuminated Path: Energy Expenditure and Crime" by Scholarly (2017) offers a comprehensive analysis of the interplay between energy usage and criminal activities, presenting a compelling case for the intertwined nature of seemingly disparate phenomena.

Transitioning into the realm of fiction, the works of renowned authors have woven tales of intrigue and mystery, echoing the themes of illumination and clandestine activities that parallel the study's focus. In "The Luminous Heist" by ThrillerWriter (2005), the narrative unfolds against the backdrop of a kerosene-lit cityscape, where the protagonist navigates a web of burglaries with a curious reliance on the enigmatic fuel source. Similarly, "Shadows in the Night: A Kerosene Noir" by MysteryNovelist (2013) conjures an atmospheric portrayal of nocturnal exploits, intertwining the allure of kerosene's glow with the shadowy machinations of criminal endeavors.

Continuing this trail of whimsical investigation, animated caricatures and childhood recollections offer an unexpected lens through which to glean insights into the enigmatic correlation at hand. As the sage musings of a beloved cartoon character once opined, "Crime doesn't pay, but kerosene sure illuminates the path to mischief!" (Cartoon Wisdom, 1987). This jesting reflection, although cloaked in lightheartedness, hints at the underlying dynamics of practical utility and potential misuse that underpin the study's focal points.

The convergence of these diverse sources beckons forthright into the idiosyncratic juncture of academic pursuit and playful musings, propelling the inquiry into the realms of unexpected delight and scholarly intrigue. As the landscape of literature expands to encompass an array of perspectives, from empirical rigor to fictitious realms and animated anecdotes, the journey of investigative inquiry acquires a touch of comedic saturation, infusing the scholarly pursuit with the jovial exuberance of playful interplay.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Burglaries in Washington and Kerosene used in Mexico. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Energy Information Administration . You used data from 1985 to 2019

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]]
Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico

[[ABSTRACT]]
This research delves into the connection between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019. By using data from FBI Criminal Justice Information Services and Energy Information Administration, we sought to shed light on the seemingly unlikely relationship between crime in the U.S. and energy consumption in Mexico. Our findings reveal a robust correlation coefficient of 0.9356483 with a p-value of less than 0.01 during the study period, suggesting a strong statistical association. This investigation prompts consideration of potential cross-border influences and economic indicators affecting crime rates and energy usage. Additionally, the implications of kerosene's dual role in providing light and potentially aiding criminal activities offer a unique angle for further exploration.

[[INTRODUCTION]]
Introduction
The study of crime and its underlying factors has long captivated the attention of researchers and policymakers alike. From classic theories of criminology to modern empirical investigations, the quest to understand the complex interplay of societal, economic, and environmental variables continues unabated. In this vein, this paper seeks to unravel the enigmatic relationship between burglaries in Washington and kerosene usage in Mexico, an investigation that promises to shed light on a most unexpected and, dare I say, illuminating correlation.
As the perennial pursuit of knowledge often demands, we embarked on this endeavor armed with an arsenal of data, statistical tools, and the most unfaltering determination to disentangle the web of seemingly disparate phenomena. Our empirical journey traversed the annals of crime records and energy consumption statistics, emerging with a collection of observations that both astounded and tickled our scholarly sensibilities.
Against all odds, our investigation unfurled a robust correlation coefficient of 0.9356483, dazzling us with its statistical prowess reminiscent of a magician's sleight of hand. With a p-value of less than 0.01, the evidence of relationship between these variables shimmered before us like a beacon of significance, beckoning us further into the labyrinth of academic inquiry. It is with great delight and bemusement that we present our findings, eager to chart the uncharted territories of investigative whimsy.
While the correlation itself may seem as peculiar as a mysterious chemical reaction, we cannot discount the potential influence of cross-border dynamics and economic indicators in shaping crime rates and energy usage. Indeed, the interconnectedness of our global village may harbor unexpected truths lurking beneath the surface of conventional wisdom, waiting to be unearthed through the alchemy of rigorous analysis.
Furthermore, the dual role of kerosene in bestowing light upon the darkness and potentially aiding criminal activities presents an intriguing paradox that beckons further exploration. This intersection of practical utility and untoward possibility implores us to consider the multifaceted nature of seemingly mundane substances, infusing our scholarly pursuits with a touch of daring intrigue.
As we delve deeper into the depths of this scholarly escapade, let us not forget the whimsy of intellectual discovery, the thrill of statistical revelation, and the ever-present possibility of uncovering the unexpected. For in the realm of research, as in life, the most captivating revelations often emerge from the least expected quarters, brightening the path forward with the glimmer of newfound knowledge.
End of Introduction

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The pursuit of unraveling the perplexing connection between burglaries in Washington and kerosene usage in Mexico demanded an approach as nuanced and multifaceted as the variables themselves. Our research team embarked on a whimsical journey through the labyrinth of empirical inquiry, employing an eclectic mix of data collection, statistical analysis, and a touch of scholarly flair.

Data Collection:
The first order of business entailed sourcing comprehensive data on burglaries in Washington and kerosene usage in Mexico from 1985 to 2019. Drawing from the wondrous expanse of the internet, our intrepid researchers scoured the digital landscape, traversing the virtual realms of the FBI Criminal Justice Information Services and the Energy Information Administration. As data wizards in pursuit of statistical troves, we gleaned insights from these repositories to construct a veritable tapestry of numerical treasures woven with the threads of empirical evidence.

Data Preprocessing:
With our data haul in tow, the next piece of the puzzle involved an intricate dance with data preprocessing. Much like a culinary maestro perfecting the art of preparation before the grand feast, we meticulously cleansed, transformed, and delicately seasoned the raw numbers to ensure their palatability to statistical algorithms. Outliers were treated with the cautious skepticism of a detective probing a curious case, while missing values received the tender care of a gardener nurturing a wayward bloom.

Statistical Analysis:
Upon achieving the harmonious state of data readiness, we summoned the formidable powers of statistical analysis to scrutinize the interwoven tapestry of burglary rates and kerosene consumption. With the precision of a mathematician sculpting intricate patterns from the fabric of numbers, we unleashed correlation coefficients, p-values, and regression models upon our data ensemble. The ethereal dance of significance testing and model selection ensued, punctuated by the occasional chuckle at the whims of statistical fate.

Cross-Border Considerations:
As we navigated the labyrinth of statistical inquiry, our scholarly compass remained attuned to the potential influence of cross-border dynamics and economic indicators. Indeed, the transnational interplay of crime rates and energy usage beckoned us to consider the geopolitical pulse throbbing beneath the surface. Like intrepid explorers of societal crossroads, we peered beyond the numerical veil, seeking to illuminate the shadowy contours of international interactions that may whisper subtle truths to the discerning ear.

Multiplicity of Perspectives:
Embracing the spirit of intellectual eclecticism, our methodology sought to incorporate a multiplicity of perspectives akin to a kaleidoscope of scholarly insight. From the prismatic lens of interdisciplinary exploration to the kaleidoscopic hues of theoretical nuance, we endeavored to infuse our investigation with a vibrant array of analytical flavors, enriching the academic palate with a tapestry of contrasting yet harmonious methodologies.

Ethical Considerations:
Adhering to the noble precepts of scholarly conduct, we navigated the ethical currents of research with unwavering integrity. Our commitment to upholding ethical standards paralleled the meticulous care of a conservator preserving an invaluable artifact, ensuring that our scholarly expedition left behind the dignified footprint of ethical probity.

In sum, our methodology arose as a quirky mélange of data sleuthing, statistical acrobatics, cross-border contemplation, multiplicity of perspectives, and ethical stewardship, paving the way for a grand adventure in pursuit of enlightening correlation.

End of Methodology

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Burglaries in Washington and Kerosene used in Mexico. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Energy Information Administration .

For the time period 1985 to 2019, you found a correlation 0.9356483, r-squared of 0.8754377, 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]]
Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico

[[ABSTRACT]]
This research delves into the connection between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019. By using data from FBI Criminal Justice Information Services and Energy Information Administration, we sought to shed light on the seemingly unlikely relationship between crime in the U.S. and energy consumption in Mexico. Our findings reveal a robust correlation coefficient of 0.9356483 with a p-value of less than 0.01 during the study period, suggesting a strong statistical association. This investigation prompts consideration of potential cross-border influences and economic indicators affecting crime rates and energy usage. Additionally, the implications of kerosene's dual role in providing light and potentially aiding criminal activities offer a unique angle for further exploration.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
The study of crime and its underlying factors has long captivated the attention of researchers and policymakers alike. From classic theories of criminology to modern empirical investigations, the quest to understand the complex interplay of societal, economic, and environmental variables continues unabated. In this vein, this paper seeks to unravel the enigmatic relationship between burglaries in Washington and kerosene usage in Mexico, an investigation that promises to shed light on a most unexpected and, dare I say, illuminating correlation.
As the perennial pursuit of knowledge often demands, we embarked on this endeavor armed with an arsenal of data, statistical tools, and the most unfaltering determination to disentangle the web of seemingly disparate phenomena. Our empirical journey traversed the annals of crime records and energy consumption statistics, emerging with a collection of observations that both astounded and tickled our scholarly sensibilities.
Against all odds, our investigation unfurled a robust correlation coefficient of 0.9356483, dazzling us with its statistical prowess reminiscent of a magician's sleight of hand. With a p-value of less than 0.01, the evidence of relationship between these variables shimmered before us like a beacon of significance, beckoning us further into the labyrinth of academic inquiry. It is with great delight and bemusement that we present our findings, eager to chart the uncharted territories of investigative whimsy.
While the correlation itself may seem as peculiar as a mysterious chemical reaction, we cannot discount the potential influence of cross-border dynamics and economic indicators in shaping crime rates and energy usage. Indeed, the interconnectedness of our global village may harbor unexpected truths lurking beneath the surface of conventional wisdom, waiting to be unearthed through the alchemy of rigorous analysis.
Furthermore, the dual role of kerosene in bestowing light upon the darkness and potentially aiding criminal activities presents an intriguing paradox that beckons further exploration. This intersection of practical utility and untoward possibility implores us to consider the multifaceted nature of seemingly mundane substances, infusing our scholarly pursuits with a touch of daring intrigue.
As we delve deeper into the depths of this scholarly escapade, let us not forget the whimsy of intellectual discovery, the thrill of statistical revelation, and the ever-present possibility of uncovering the unexpected. For in the realm of research, as in life, the most captivating revelations often emerge from the least expected quarters, brightening the path forward with the glimmer of newfound knowledge.
End of Introduction

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The empirical analysis of the relationship between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019 yielded results that were both statistically significant and, if we may say so ourselves, rather captivating. Our endeavors bore fruit in the form of a robust correlation coefficient of 0.9356483, evoking an air of scientific marvel akin to discovering a hidden talent in an unexpected acquaintance.

With an r-squared value of 0.8754377, our findings painted a picture of strong association, reminiscent of a pair of crime-fighting detectives unraveling the mysteries of statistical intrigue. The p-value of less than 0.01 stood as a testament to the undeniable significance of the relationship, casting a spotlight on the clandestine connection between crime in one locale and the utilization of kerosene in another.

Fig. 1 showcases the scatterplot, a visual testament to the compelling correlation between these seemingly disparate variables. The data points weave a narrative of coalescence, akin to a thrilling plot twist in a suspenseful novel, revealing the intertwined nature of criminal activity and energy consumption.

The strength of the statistical relationship evinced in our results not only piques scholarly curiosity but also beckons consideration of the potential influences at play. In the grand tapestry of global dynamics and economic indicators, the ripple effects of energy usage and crime resonate across borders, much like an unexpected echo in the halls of academic inquiry.

Furthermore, the dual role of kerosene in offering illumination and, intriguingly, potentially abetting criminal endeavors offers a layer of complexity that titillates the senses of intellectual inquiry. This paradoxical duality serves as a reminder of the multifaceted nature of the variables under scrutiny, infusing our scholarly pursuit with a sense of intrigue befitting a captivating mystery novel.

In summation, our findings bring to the fore a captivating correlation, teasing the boundaries of predictability and stoking the flames of scholarly inquisitiveness. As we draw back the curtains on the enigmatic relationship between burglaries in Washington and kerosene usage in Mexico, we can't help but revel in the delightful whimsy of uncovering unexpected connections amidst the annals of statistical exploration.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Burglaries in Washington and Kerosene used in Mexico. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico

[[ABSTRACT]]
This research delves into the connection between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019. By using data from FBI Criminal Justice Information Services and Energy Information Administration, we sought to shed light on the seemingly unlikely relationship between crime in the U.S. and energy consumption in Mexico. Our findings reveal a robust correlation coefficient of 0.9356483 with a p-value of less than 0.01 during the study period, suggesting a strong statistical association. This investigation prompts consideration of potential cross-border influences and economic indicators affecting crime rates and energy usage. Additionally, the implications of kerosene's dual role in providing light and potentially aiding criminal activities offer a unique angle for further exploration.

[[LITERATURE REVIEW]]
The investigation of crime and its multifaceted correlates has been a central focus of scholarly inquiry, prompting the exploration of diverse and at times peculiar connections. Smith et al. (2010) conducted a seminal study on the socioeconomic determinants of burglary rates, unveiling intricate patterns of urban development and demographic shifts that contributed to the spatial distribution of criminal activities. Meanwhile, Doe and Jones (2015) delved into the behavioral manifestations of criminal intent, offering nuanced insights into the psychological underpinnings of unlawful intrusions. These foundational works, along with a multitude of empirical inquiries, have paved the way for a deeper understanding of the complex tapestry of criminal behavior.
Venturing beyond the realm of traditional criminology, a series of non-fiction accounts have probed the sociopolitical dimensions of energy consumption and its ramifications on societal dynamics, potentially shedding light on the unanticipated connection under scrutiny. In "Kerosene and Kriminals: A Sociological Study" by Luminary (2012), the author explores the underlying currents of kerosene usage within the context of criminal subcultures, hinting at subtle yet palpable intersections that beg further examination. Additionally, "The Illuminated Path: Energy Expenditure and Crime" by Scholarly (2017) offers a comprehensive analysis of the interplay between energy usage and criminal activities, presenting a compelling case for the intertwined nature of seemingly disparate phenomena.
Transitioning into the realm of fiction, the works of renowned authors have woven tales of intrigue and mystery, echoing the themes of illumination and clandestine activities that parallel the study's focus. In "The Luminous Heist" by ThrillerWriter (2005), the narrative unfolds against the backdrop of a kerosene-lit cityscape, where the protagonist navigates a web of burglaries with a curious reliance on the enigmatic fuel source. Similarly, "Shadows in the Night: A Kerosene Noir" by MysteryNovelist (2013) conjures an atmospheric portrayal of nocturnal exploits, intertwining the allure of kerosene's glow with the shadowy machinations of criminal endeavors.
Continuing this trail of whimsical investigation, animated caricatures and childhood recollections offer an unexpected lens through which to glean insights into the enigmatic correlation at hand. As the sage musings of a beloved cartoon character once opined, "Crime doesn't pay, but kerosene sure illuminates the path to mischief!" (Cartoon Wisdom, 1987). This jesting reflection, although cloaked in lightheartedness, hints at the underlying dynamics of practical utility and potential misuse that underpin the study's focal points.
The convergence of these diverse sources beckons forthright into the idiosyncratic juncture of academic pursuit and playful musings, propelling the inquiry into the realms of unexpected delight and scholarly intrigue. As the landscape of literature expands to encompass an array of perspectives, from empirical rigor to fictitious realms and animated anecdotes, the journey of investigative inquiry acquires a touch of comedic saturation, infusing the scholarly pursuit with the jovial exuberance of playful interplay.

[[RESULTS]]
The empirical analysis of the relationship between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019 yielded results that were both statistically significant and, if we may say so ourselves, rather captivating. Our endeavors bore fruit in the form of a robust correlation coefficient of 0.9356483, evoking an air of scientific marvel akin to discovering a hidden talent in an unexpected acquaintance.
With an r-squared value of 0.8754377, our findings painted a picture of strong association, reminiscent of a pair of crime-fighting detectives unraveling the mysteries of statistical intrigue. The p-value of less than 0.01 stood as a testament to the undeniable significance of the relationship, casting a spotlight on the clandestine connection between crime in one locale and the utilization of kerosene in another.
Fig. 1 showcases the scatterplot, a visual testament to the compelling correlation between these seemingly disparate variables. The data points weave a narrative of coalescence, akin to a thrilling plot twist in a suspenseful novel, revealing the intertwined nature of criminal activity and energy consumption.
The strength of the statistical relationship evinced in our results not only piques scholarly curiosity but also beckons consideration of the potential influences at play. In the grand tapestry of global dynamics and economic indicators, the ripple effects of energy usage and crime resonate across borders, much like an unexpected echo in the halls of academic inquiry.
Furthermore, the dual role of kerosene in offering illumination and, intriguingly, potentially abetting criminal endeavors offers a layer of complexity that titillates the senses of intellectual inquiry. This paradoxical duality serves as a reminder of the multifaceted nature of the variables under scrutiny, infusing our scholarly pursuit with a sense of intrigue befitting a captivating mystery novel.
In summation, our findings bring to the fore a captivating correlation, teasing the boundaries of predictability and stoking the flames of scholarly inquisitiveness. As we draw back the curtains on the enigmatic relationship between burglaries in Washington and kerosene usage in Mexico, we can't help but revel in the delightful whimsy of uncovering unexpected connections amidst the annals of statistical exploration.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our investigation have lent credence to the hitherto whimsical musings and seemingly lighthearted whispers of interconnectedness embedded within the literature review. Our findings not only supported, but practically high-fived the previous research, showcasing a statistical association so strong it could lift weights at statistical gyms. The robust correlation coefficient of 0.9356483 essentially winked at all the prior studies, exclaiming, "I see your connections and raise you a nearly perfect relationship between burglaries in Washington and kerosene usage in Mexico!"

Venturing back into the curious realm of literature review, the unexpected whispers of societal dynamics and energy consumption found tangible expression in our empirical analysis. In a delightful twist akin to finding a piece of dark chocolate hidden in a salad, the statistical association served as an irrefutable testament to the intricate interplay between crime rates and energy usage. While the jovial juxtaposition of whimsy and scholarly pursuit danced merrily amidst the literature review, the results have proven that investigations into unanticipated correlations can yield captivating insights, akin to stumbling upon a hidden treasure trove of statistical intrigue.

The r-squared value of 0.8754377 mirrored a detective novel's climax, as the relationship unfolded with an intensity matching the rare passion fruit's flavor. The p-value, much like an eagle-eyed sleuth, provided unequivocal evidence of the undeniable significance of the relationship, akin to a smoking gun in the court of statistical inquiry.

The scatterplot, akin to a work of art in a criminally avant-garde exposition, visually portrayed the captivating correlation between burglaries in Washington and kerosene usage in Mexico. The data points formed an enthralling narrative, much like a gripping mystery novel, leaving scholars and casual onlookers alike on the edge of their seats, captivated by the entwined nature of criminal activity and energy consumption.

The paradoxical duality of kerosene, serving as both an illuminating force and a potentially shadowy accomplice to criminal endeavors, posed a puzzling conundrum that titillated the intellect. This duel of purposes acted as a compelling reminder of the multifaceted nature of the variables under scrutiny, akin to a twist in an elaborate plot that leaves the audience stunned and thoroughly amused.

In essence, our endeavor has not only contributed to the academic discourse on crime and energy consumption but has also woven a narrative of unexpected delight and scholarly intrigue. The jovial exuberance of playful interplay, which permeated the literature review, breathes life into the scholarly pursuit, infusing the tapestry of investigative inquiry with a touch of comedic saturation and the boundless energy of delightful whimsy.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Burglaries in Washington and Kerosene used in Mexico. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico

[[ABSTRACT]]
This research delves into the connection between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019. By using data from FBI Criminal Justice Information Services and Energy Information Administration, we sought to shed light on the seemingly unlikely relationship between crime in the U.S. and energy consumption in Mexico. Our findings reveal a robust correlation coefficient of 0.9356483 with a p-value of less than 0.01 during the study period, suggesting a strong statistical association. This investigation prompts consideration of potential cross-border influences and economic indicators affecting crime rates and energy usage. Additionally, the implications of kerosene's dual role in providing light and potentially aiding criminal activities offer a unique angle for further exploration.

[[INTRDUCTION]]
Introduction
The study of crime and its underlying factors has long captivated the attention of researchers and policymakers alike. From classic theories of criminology to modern empirical investigations, the quest to understand the complex interplay of societal, economic, and environmental variables continues unabated. In this vein, this paper seeks to unravel the enigmatic relationship between burglaries in Washington and kerosene usage in Mexico, an investigation that promises to shed light on a most unexpected and, dare I say, illuminating correlation.
As the perennial pursuit of knowledge often demands, we embarked on this endeavor armed with an arsenal of data, statistical tools, and the most unfaltering determination to disentangle the web of seemingly disparate phenomena. Our empirical journey traversed the annals of crime records and energy consumption statistics, emerging with a collection of observations that both astounded and tickled our scholarly sensibilities.
Against all odds, our investigation unfurled a robust correlation coefficient of 0.9356483, dazzling us with its statistical prowess reminiscent of a magician's sleight of hand. With a p-value of less than 0.01, the evidence of relationship between these variables shimmered before us like a beacon of significance, beckoning us further into the labyrinth of academic inquiry. It is with great delight and bemusement that we present our findings, eager to chart the uncharted territories of investigative whimsy.
While the correlation itself may seem as peculiar as a mysterious chemical reaction, we cannot discount the potential influence of cross-border dynamics and economic indicators in shaping crime rates and energy usage. Indeed, the interconnectedness of our global village may harbor unexpected truths lurking beneath the surface of conventional wisdom, waiting to be unearthed through the alchemy of rigorous analysis.
Furthermore, the dual role of kerosene in bestowing light upon the darkness and potentially aiding criminal activities presents an intriguing paradox that beckons further exploration. This intersection of practical utility and untoward possibility implores us to consider the multifaceted nature of seemingly mundane substances, infusing our scholarly pursuits with a touch of daring intrigue.
As we delve deeper into the depths of this scholarly escapade, let us not forget the whimsy of intellectual discovery, the thrill of statistical revelation, and the ever-present possibility of uncovering the unexpected. For in the realm of research, as in life, the most captivating revelations often emerge from the least expected quarters, brightening the path forward with the glimmer of newfound knowledge.
End of Introduction

[[RESULTS]]
The empirical analysis of the relationship between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019 yielded results that were both statistically significant and, if we may say so ourselves, rather captivating. Our endeavors bore fruit in the form of a robust correlation coefficient of 0.9356483, evoking an air of scientific marvel akin to discovering a hidden talent in an unexpected acquaintance.
With an r-squared value of 0.8754377, our findings painted a picture of strong association, reminiscent of a pair of crime-fighting detectives unraveling the mysteries of statistical intrigue. The p-value of less than 0.01 stood as a testament to the undeniable significance of the relationship, casting a spotlight on the clandestine connection between crime in one locale and the utilization of kerosene in another.
Fig. 1 showcases the scatterplot, a visual testament to the compelling correlation between these seemingly disparate variables. The data points weave a narrative of coalescence, akin to a thrilling plot twist in a suspenseful novel, revealing the intertwined nature of criminal activity and energy consumption.
The strength of the statistical relationship evinced in our results not only piques scholarly curiosity but also beckons consideration of the potential influences at play. In the grand tapestry of global dynamics and economic indicators, the ripple effects of energy usage and crime resonate across borders, much like an unexpected echo in the halls of academic inquiry.
Furthermore, the dual role of kerosene in offering illumination and, intriguingly, potentially abetting criminal endeavors offers a layer of complexity that titillates the senses of intellectual inquiry. This paradoxical duality serves as a reminder of the multifaceted nature of the variables under scrutiny, infusing our scholarly pursuit with a sense of intrigue befitting a captivating mystery novel.
In summation, our findings bring to the fore a captivating correlation, teasing the boundaries of predictability and stoking the flames of scholarly inquisitiveness. As we draw back the curtains on the enigmatic relationship between burglaries in Washington and kerosene usage in Mexico, we can't help but revel in the delightful whimsy of uncovering unexpected connections amidst the annals of statistical exploration.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the correlation between burglaries in Washington and kerosene usage in Mexico has illuminated a most unexpected relationship, akin to stumbling upon a clandestine tryst between two variables in the corridors of statistical significance. With a robust correlation coefficient of 0.9356483 and a p-value of less than 0.01, our findings stand as a beacon of scholarly revelry, inviting further exploration into the intersection of crime and energy consumption.

While the statistical association between these seemingly disparate phenomena may appear as curious as a fusion of quantum mechanics and culinary arts, the potential cross-border influences and economic indicators at play beckon further scrutiny. The interconnectedness of our global village serves as a reminder that the web of causation in crime and energy usage may span oceans and traverse borders, much like a globe-trotting detective in pursuit of elusive truths.

The paradoxical dual role of kerosene as a source of light and, intriguingly, potential accomplice in criminal activities, adds a layer of complexity that infuses our scholarly pursuit with the allure of enigmatic possibility. This unusual juxtaposition of practical utility and unforeseen implications evokes the thrill of uncovering unexpected plot twists in the annals of empirical inquiry.

As we bid adieu to this captivating correlation, we stand on the threshold of scholarly exploration, acknowledging the delightful whimsy of uncovering unexpected connections amidst the tapestry of statistical revelation. With the evidence at hand, we assert that the relationship between burglaries in Washington and kerosene usage in Mexico has been sufficiently illuminated, much like a well-lit room in a mystery novel, and no further research is needed in this particular area.

And so, we conclude our scholarly escapade with a twinkle in our academic eyes, reveling in the thrill of unraveling the unexpected amidst the realms of investigation. As we journey forth into the uncharted territories of knowledge, let us not forget the whimsy of intellectual discovery, the thrill of statistical revelation, and the ever-present possibility of uncovering the unexpected.

No further research is needed in this area.

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 Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Comparative Criminology and Energy Consumption

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 Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico. Respond only with the name of a fictional organization.

ChatGPT:

The International Society for Cross-Cultural Criminology and Energy Consumption Analysis

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 Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico with an abstract of This research delves into the connection between burglaries in Washington and kerosene usage in Mexico from 1985 to 2019. By using data from FBI Criminal Justice Information Services and Energy Information Administration, we sought to shed light on the seemingly unlikely relationship between crime in the U.S. and energy consumption in Mexico. Our findings reveal a robust correlation coefficient of 0.9356483 with a p-value of less than 0.01 during the study period, suggesting a strong statistical association. This investigation prompts consideration of potential cross-border influences and economic indicators affecting crime rates and energy usage. Additionally, the implications of kerosene's dual role in providing light and potentially aiding criminal activities offer a unique angle for further exploration.

ChatGPT:

burglaries, Washington, kerosene usage, Mexico, 1985-2019, FBI Criminal Justice Information Services, Energy Information Administration, correlation coefficient, p-value, cross-border influences, economic indicators, crime rates, energy usage, kerosene, light, criminal activities

*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

Burglaries in Washington
Detailed data title: The burglary rate per 100,000 residents in Washington
Source: FBI Criminal Justice Information Services
See what else correlates with Burglaries in Washington

Kerosene used in Mexico
Detailed data title: Volume of kerosene used consumed in Mexico in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Mexico

Correlation r = 0.9356483 (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 = 0.8754377 (Coefficient of determination)
This means 87.5% of the change in the one variable (i.e., Kerosene used in Mexico) is predictable based on the change in the other (i.e., Burglaries in Washington) over the 35 years from 1985 through 2019.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.7E-16.^Show 0.0000000000000001739435868716
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.94 in 1.7E-14% of random cases. Said differently, if you correlated 5,748,990,336,379,405 random variables^Note You don't actually need 5 quadrillion 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 34 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 34 because we have two variables measured over a period of 35 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.

[ 0.88, 0.97 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019
Burglaries in Washington (Burglary rate)	1811.3	1861.5	1904.5	1855.6	1545.1	1262.9	1235.5	1121.7	1067.2	1044.2	1091.2	1057.5	1106.3	1062.5	949.4	907.3	884.7	905.7	950.4	976.8	959.1	920	817.4	811.3	796	818.5	828.9	890.1	838.7	784.1	713.9	676.4	588.3	537.4	459.4
Kerosene used in Mexico (Million Barrels/Day)	31.7589	29.7863	31.4959	29.2459	25.5781	16.8329	10.4219	12.0984	12.611	10.4658	7.69041	7.24044	3.64384	2.47671	1.05206	1.39344	1.8137	1.62192	0.657534	0.765027	0.789041	0.986301	0.920548	0.42623	0.427397	0.591781	0.624658	0.590164	0.657534	0.953425	1.21644	0.918033	0.920548	0.920548	0.933333

Why this works

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.
Lack of causal connection: There is probably^Note 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.
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^Note 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.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} 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([1811.3,1861.5,1904.5,1855.6,1545.1,1262.9,1235.5,1121.7,1067.2,1044.2,1091.2,1057.5,1106.3,1062.5,949.4,907.3,884.7,905.7,950.4,976.8,959.1,920,817.4,811.3,796,818.5,828.9,890.1,838.7,784.1,713.9,676.4,588.3,537.4,459.4,])
array_2 = np.array([31.7589,29.7863,31.4959,29.2459,25.5781,16.8329,10.4219,12.0984,12.611,10.4658,7.69041,7.24044,3.64384,2.47671,1.05206,1.39344,1.8137,1.62192,0.657534,0.765027,0.789041,0.986301,0.920548,0.42623,0.427397,0.591781,0.624658,0.590164,0.657534,0.953425,1.21644,0.918033,0.920548,0.920548,0.933333,])
array_1_name = "Burglaries in Washington"
array_2_name = "Kerosene used in Mexico"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Burglaries in Washington
Line chart for only Kerosene used in Mexico
AI-generated correlation image
The spurious research paper: Fueling Crime: Exploring the Correlation Between Burglaries in Washington and Kerosene Usage in Mexico

View another random correlation

How fun was this correlation?

Your rating is stellar!

Correlation ID: 3994 · Black Variable ID: 20126 · Red Variable ID: 24692


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: