about · email me · subscribe
Spurious correlation #2,321 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Robberies in Nevada and the second variable is Gasoline pumped in Latvia.  The chart goes from 1992 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Fewer robberies in Nevada meant there was less demand for getaway cars. This led to a surplus of gasoline in the US, so they decided to export some to Latvia. As a result, the amount of gasoline pumped in Latvia decreased. It's a case of international traffic jams and heists leading to a fueling funny business!

Model: dalle-3
Prompt: Generated Image Prompt: Create an image in the style of a black-and-white newspaper illustration depicting a chaotic scene outside a gas station in a bustling Nevada city. Two robbers are seen fleeing the scene in a stolen car, with police cars in hot pursuit. Across the scene, contrast the chaotic city with a serene countryside in Latvia, where a family is peacefully pumping gasoline into their car at a picturesque roadside station. The two contrasting scenes should be connected, highlighting the stark difference between the bustling urban environment and the calm countryside. 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: Robberies in Nevada and Gasoline pumped in Latvia. 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: Sci-fi fantacy Realistic Realistic Pop art A black-and-white newspaper illustration
ChatGPT: A black-and-white newspaper 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 Robberies in Nevada and Gasoline pumped in Latvia together. Keep the description simple.
ChatGPT: In a bustling city in Nevada, a gas station is the target of a robbery. As the robbers make their getaway in a stolen car, they pass by a scenic countryside in Latvia, where a family is pumping gasoline into their car at a picturesque roadside station.

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: [ A black-and-white newspaper illustration ] and depicting this scene: In a bustling city in Nevada, a gas station is the target of a robbery. As the robbers make their getaway in a stolen car, they pass by a scenic countryside in Latvia, where a family is pumping gasoline into their car at a picturesque roadside station. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generated Image Prompt: Create an image in the style of a black-and-white newspaper illustration depicting a chaotic scene outside a gas station in a bustling Nevada city. Two robbers are seen fleeing the scene in a stolen car, with police cars in hot pursuit. Across the scene, contrast the chaotic city with a serene countryside in Latvia, where a family is peacefully pumping gasoline into their car at a picturesque roadside station. The two contrasting scenes should be connected, highlighting the stark difference between the bustling urban environment and the calm countryside.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Robberies in Nevada caused Gasoline pumped in Latvia to decrease.

AI academic paper

(Because p < 0.01)
Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia

The Journal of Absurd Connections in Cross-Cultural Criminology

Jan 2024

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




Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Robberies in Nevada and Gasoline pumped in Latvia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title an alliteration.

Your research team used data from FBI Criminal Justice Information Services and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9035745 and p < 0.01 for 1992 to 2022.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia

[[ABSTRACT]]
This study scrutinizes the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022. Utilizing data from the FBI Criminal Justice Information Services and the Energy Information Administration, we employed sophisticated statistical analyses to reveal the surprising link between these seemingly disparate events. Our findings revealed a striking correlation coefficient of 0.9035745 with a statistically significant p-value of less than 0.01. Our analysis prompts a rethinking of the factors influencing crime and energy consumption, and will leave readers both amused and bewildered by the curious connection we have unveiled.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Robberies in Nevada and Gasoline pumped in Latvia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia

[[ABSTRACT]]
This study scrutinizes the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022. Utilizing data from the FBI Criminal Justice Information Services and the Energy Information Administration, we employed sophisticated statistical analyses to reveal the surprising link between these seemingly disparate events. Our findings revealed a striking correlation coefficient of 0.9035745 with a statistically significant p-value of less than 0.01. Our analysis prompts a rethinking of the factors influencing crime and energy consumption, and will leave readers both amused and bewildered by the curious connection we have unveiled.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The curious connection between robberies in Nevada and the volume of gasoline pumped in Latvia has long puzzled researchers and bystanders alike. On the surface, these two phenomena appear as incongruent as a penguin in the Sahara or a snowball in Singapore. However, in the hallowed halls of academic inquiry, we are duty-bound to scrutinize even the most preposterous pairings, for as the saying goes, "truth is stranger than fiction."

The aim of this study is to shed light on the perplexing relationship between rogues in the desert expanse of Nevada and the refueling antics in the Baltic gem of Latvia. Are these simply coincidental quirks of fate, or is there a deeper, more clandestine connection lurking in the shadows?

In the spirit of academic inquiry, we approached this investigation with all due seriousness, armed with an arsenal of statistical tools and a healthy dose of skepticism. Yet, as the data unfurled before our analytical gaze, we found ourselves traversing a labyrinth of intrigue and astonishment. The results were as captivating as a magician's disappearing act, leaving us to ponder the enigmatic forces at play.

As we unveil the findings of our investigation, readers may find themselves oscillating between incredulity and fascination. Prepare to embark on a journey that navigates the terrain of crime and energy consumption, where the unexpected is the norm and the conventional is left reeling in disbelief.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Robberies in Nevada and Gasoline pumped in Latvia. 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia

[[ABSTRACT]]
This study scrutinizes the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022. Utilizing data from the FBI Criminal Justice Information Services and the Energy Information Administration, we employed sophisticated statistical analyses to reveal the surprising link between these seemingly disparate events. Our findings revealed a striking correlation coefficient of 0.9035745 with a statistically significant p-value of less than 0.01. Our analysis prompts a rethinking of the factors influencing crime and energy consumption, and will leave readers both amused and bewildered by the curious connection we have unveiled.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The curious connection between robberies in Nevada and the volume of gasoline pumped in Latvia has long puzzled researchers and bystanders alike. On the surface, these two phenomena appear as incongruent as a penguin in the Sahara or a snowball in Singapore. However, in the hallowed halls of academic inquiry, we are duty-bound to scrutinize even the most preposterous pairings, for as the saying goes, "truth is stranger than fiction."
The aim of this study is to shed light on the perplexing relationship between rogues in the desert expanse of Nevada and the refueling antics in the Baltic gem of Latvia. Are these simply coincidental quirks of fate, or is there a deeper, more clandestine connection lurking in the shadows?
In the spirit of academic inquiry, we approached this investigation with all due seriousness, armed with an arsenal of statistical tools and a healthy dose of skepticism. Yet, as the data unfurled before our analytical gaze, we found ourselves traversing a labyrinth of intrigue and astonishment. The results were as captivating as a magician's disappearing act, leaving us to ponder the enigmatic forces at play.
As we unveil the findings of our investigation, readers may find themselves oscillating between incredulity and fascination. Prepare to embark on a journey that navigates the terrain of crime and energy consumption, where the unexpected is the norm and the conventional is left reeling in disbelief.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Several scholarly works have delved into the enigmatic relationship between seemingly unrelated phenomena, prompting a reevaluation of the forces at play. Smith, in "Patterns of Crime and Energy Consumption," explores the potential intersection of criminal activities and energy usage, shedding light on the intricate entanglement of societal behaviors and resource utilization. Doe and Jones, in "Unlikely Bedfellows: Exploring Bizarre Correlations," offer a comprehensive analysis of seemingly unrelated variables, providing a framework for understanding the unexpected connections that may lurk beneath the surface.

Turning to non-fiction accounts, "The Art of Robbery: A Historical Perspective" by A. Robber and "Fueling the Future: A Comprehensive Guide to Global Energy Trends" by E. Gasolina are particularly relevant to our investigation. The former elucidates the evolutionary trajectories of illicit activities, while the latter provides insights into the global dynamics of energy consumption, both of which contribute to a holistic understanding of our research focus.

In the realm of fiction, "The Gasoline Gambit" by R. Heist and "Crime and Pump: A Novel Exploration" by P. Bandit present imaginative narratives that, while not based in empirical evidence, offer an intriguing departure point for drawing parallels to our empirical findings.

Upon perusing various social media platforms, an intriguing observation from a Reddit user under the pseudonym "GasLarcenyGal" sparked our curiosity: "Could the rise in gasoline prices be fueling a surge in robberies? The correlation seems uncannily robust." Likewise, a tweet from @NevadaNefarious pondered, "Robberies on the rise again in the Silver State – could there be a gasoline connection?" These anecdotal musings, while not authoritative scholarly sources, underscore the pervasiveness of speculation around the intersection of crime and fuel-related matters.

The confluence of these inquiries converges in an intellectual mélange that challenges conventional wisdom and dares to entertain the unpredictable. As we endeavor to unravel the peculiar and improbable association between robberies in Nevada and gasoline pumped in Latvia, our exploration treads the fine line between skepticism and astonishment, offering a kaleidoscopic panorama of peculiar connections and bewildering revelations.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Robberies in Nevada and Gasoline pumped in Latvia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Energy Information Administration . You used data from 1992 to 2022

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia

[[ABSTRACT]]
This study scrutinizes the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022. Utilizing data from the FBI Criminal Justice Information Services and the Energy Information Administration, we employed sophisticated statistical analyses to reveal the surprising link between these seemingly disparate events. Our findings revealed a striking correlation coefficient of 0.9035745 with a statistically significant p-value of less than 0.01. Our analysis prompts a rethinking of the factors influencing crime and energy consumption, and will leave readers both amused and bewildered by the curious connection we have unveiled.

[[INTRODUCTION]]
The curious connection between robberies in Nevada and the volume of gasoline pumped in Latvia has long puzzled researchers and bystanders alike. On the surface, these two phenomena appear as incongruent as a penguin in the Sahara or a snowball in Singapore. However, in the hallowed halls of academic inquiry, we are duty-bound to scrutinize even the most preposterous pairings, for as the saying goes, "truth is stranger than fiction."
The aim of this study is to shed light on the perplexing relationship between rogues in the desert expanse of Nevada and the refueling antics in the Baltic gem of Latvia. Are these simply coincidental quirks of fate, or is there a deeper, more clandestine connection lurking in the shadows?
In the spirit of academic inquiry, we approached this investigation with all due seriousness, armed with an arsenal of statistical tools and a healthy dose of skepticism. Yet, as the data unfurled before our analytical gaze, we found ourselves traversing a labyrinth of intrigue and astonishment. The results were as captivating as a magician's disappearing act, leaving us to ponder the enigmatic forces at play.
As we unveil the findings of our investigation, readers may find themselves oscillating between incredulity and fascination. Prepare to embark on a journey that navigates the terrain of crime and energy consumption, where the unexpected is the norm and the conventional is left reeling in disbelief.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

In order to disentangle the enigma surrounding the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia, a multidimensional approach was undertaken. Data on robberies in Nevada was collected from the FBI Criminal Justice Information Services, while information on gasoline consumption in Latvia was sourced from the Energy Information Administration. This hodgepodge of data, collected from 1992 to 2022, formed the bedrock of our analysis.

To embark on this quixotic quest, a series of statistical analyses were employed. The robustness of the relationship between these incongruous variables was scrutinized through the application of various regression models, including ordinary least squares, autoregressive integrated moving average, and perhaps a touch of alchemy. By tapping into the mystical powers of time series analysis, the fluctuations in robberies and the ebb and flow of gasoline consumption were transmuted into digestible nuggets of insight.

Furthermore, to illuminate potential lurking variables and confounders, supplementary analyses such as Granger causality tests and cointegration analyses were conducted. These analyses, akin to unraveling the strands of a complex riddle, sought to untangle any hidden threads connecting the nefarious deeds in Nevada to the fueling frenzy in Latvia.

In our relentless pursuit of understanding this confounding correlation, sensitivity analyses were also performed to gauge the robustness of our findings. These analyses explored the impact of alternative model specifications and data transformations, lending a touch of audacity to our otherwise sober endeavor.

This perspicacious foray into the murky depths of anomalous associations was lubricated by an unyielding commitment to meticulousness and precision. Through the elaborate orchestration of data acquisition and statistical acrobatics, we endeavored to tease out the inextricable connection between roguish robberies and ridiculous refueling, leaving no statistical stone unturned in our pursuit of enlightenment.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Robberies in Nevada and Gasoline pumped in Latvia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

For the time period 1992 to 2022, you found a correlation 0.9035745, r-squared of 0.8164469, 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]]
Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia

[[ABSTRACT]]
This study scrutinizes the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022. Utilizing data from the FBI Criminal Justice Information Services and the Energy Information Administration, we employed sophisticated statistical analyses to reveal the surprising link between these seemingly disparate events. Our findings revealed a striking correlation coefficient of 0.9035745 with a statistically significant p-value of less than 0.01. Our analysis prompts a rethinking of the factors influencing crime and energy consumption, and will leave readers both amused and bewildered by the curious connection we have unveiled.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The curious connection between robberies in Nevada and the volume of gasoline pumped in Latvia has long puzzled researchers and bystanders alike. On the surface, these two phenomena appear as incongruent as a penguin in the Sahara or a snowball in Singapore. However, in the hallowed halls of academic inquiry, we are duty-bound to scrutinize even the most preposterous pairings, for as the saying goes, "truth is stranger than fiction."
The aim of this study is to shed light on the perplexing relationship between rogues in the desert expanse of Nevada and the refueling antics in the Baltic gem of Latvia. Are these simply coincidental quirks of fate, or is there a deeper, more clandestine connection lurking in the shadows?
In the spirit of academic inquiry, we approached this investigation with all due seriousness, armed with an arsenal of statistical tools and a healthy dose of skepticism. Yet, as the data unfurled before our analytical gaze, we found ourselves traversing a labyrinth of intrigue and astonishment. The results were as captivating as a magician's disappearing act, leaving us to ponder the enigmatic forces at play.
As we unveil the findings of our investigation, readers may find themselves oscillating between incredulity and fascination. Prepare to embark on a journey that navigates the terrain of crime and energy consumption, where the unexpected is the norm and the conventional is left reeling in disbelief.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The examination of the relationship between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022 revealed a remarkably strong correlation coefficient of 0.9035745. This correlation suggests a robust positive association between these two seemingly unrelated variables, akin to finding a treasure map at a crime scene or a gas station attendant moonlighting as a masked bandit.

Furthermore, the coefficient of determination (r-squared) of 0.8164469 indicates that approximately 81.64% of the variability in robberies in Nevada can be explained by the volume of gasoline pumped in Latvia. This finding underscores the substantial influence of gasoline pumping habits in Latvia on the nefarious activities in the deserts of Nevada, a relationship as perplexing as a cat chasing a mouse across international borders.

Importantly, the p-value of less than 0.01 attests to the statistical significance of the observed correlation, indicating that the likelihood of such a strong relationship occurring by chance is lower than the probability of encountering a unicorn in a downtown metropolis.

The scatterplot (Fig. 1) visually portrays the robust positive correlation between robberies in Nevada and gasoline pumped in Latvia, a depiction as compelling as a classic caper film from the golden age of Hollywood. The data points form a highly concentrated cluster, illustrating the captivating co-movement of these enigmatic variables throughout the 30-year period.

These findings challenge conventional wisdom and beckon researchers and readers alike to ponder the clandestine forces intertwining the world of crime and energy. The unexpected connection between these peculiar phenomena serves as a captivating enigma, leaving scholars and laypersons alike immersed in a whirlwind of fascination and amusement.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Robberies in Nevada and Gasoline pumped in Latvia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia

[[ABSTRACT]]
This study scrutinizes the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022. Utilizing data from the FBI Criminal Justice Information Services and the Energy Information Administration, we employed sophisticated statistical analyses to reveal the surprising link between these seemingly disparate events. Our findings revealed a striking correlation coefficient of 0.9035745 with a statistically significant p-value of less than 0.01. Our analysis prompts a rethinking of the factors influencing crime and energy consumption, and will leave readers both amused and bewildered by the curious connection we have unveiled.

[[LITERATURE REVIEW]]
Several scholarly works have delved into the enigmatic relationship between seemingly unrelated phenomena, prompting a reevaluation of the forces at play. Smith, in "Patterns of Crime and Energy Consumption," explores the potential intersection of criminal activities and energy usage, shedding light on the intricate entanglement of societal behaviors and resource utilization. Doe and Jones, in "Unlikely Bedfellows: Exploring Bizarre Correlations," offer a comprehensive analysis of seemingly unrelated variables, providing a framework for understanding the unexpected connections that may lurk beneath the surface.
Turning to non-fiction accounts, "The Art of Robbery: A Historical Perspective" by A. Robber and "Fueling the Future: A Comprehensive Guide to Global Energy Trends" by E. Gasolina are particularly relevant to our investigation. The former elucidates the evolutionary trajectories of illicit activities, while the latter provides insights into the global dynamics of energy consumption, both of which contribute to a holistic understanding of our research focus.
In the realm of fiction, "The Gasoline Gambit" by R. Heist and "Crime and Pump: A Novel Exploration" by P. Bandit present imaginative narratives that, while not based in empirical evidence, offer an intriguing departure point for drawing parallels to our empirical findings.
Upon perusing various social media platforms, an intriguing observation from a Reddit user under the pseudonym "GasLarcenyGal" sparked our curiosity: "Could the rise in gasoline prices be fueling a surge in robberies? The correlation seems uncannily robust." Likewise, a tweet from @NevadaNefarious pondered, "Robberies on the rise again in the Silver State – could there be a gasoline connection?" These anecdotal musings, while not authoritative scholarly sources, underscore the pervasiveness of speculation around the intersection of crime and fuel-related matters.
The confluence of these inquiries converges in an intellectual mélange that challenges conventional wisdom and dares to entertain the unpredictable. As we endeavor to unravel the peculiar and improbable association between robberies in Nevada and gasoline pumped in Latvia, our exploration treads the fine line between skepticism and astonishment, offering a kaleidoscopic panorama of peculiar connections and bewildering revelations.

[[RESULTS]]
The examination of the relationship between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022 revealed a remarkably strong correlation coefficient of 0.9035745. This correlation suggests a robust positive association between these two seemingly unrelated variables, akin to finding a treasure map at a crime scene or a gas station attendant moonlighting as a masked bandit.
Furthermore, the coefficient of determination (r-squared) of 0.8164469 indicates that approximately 81.64% of the variability in robberies in Nevada can be explained by the volume of gasoline pumped in Latvia. This finding underscores the substantial influence of gasoline pumping habits in Latvia on the nefarious activities in the deserts of Nevada, a relationship as perplexing as a cat chasing a mouse across international borders.
Importantly, the p-value of less than 0.01 attests to the statistical significance of the observed correlation, indicating that the likelihood of such a strong relationship occurring by chance is lower than the probability of encountering a unicorn in a downtown metropolis.
The scatterplot (Fig. 1) visually portrays the robust positive correlation between robberies in Nevada and gasoline pumped in Latvia, a depiction as compelling as a classic caper film from the golden age of Hollywood. The data points form a highly concentrated cluster, illustrating the captivating co-movement of these enigmatic variables throughout the 30-year period.
These findings challenge conventional wisdom and beckon researchers and readers alike to ponder the clandestine forces intertwining the world of crime and energy. The unexpected connection between these peculiar phenomena serves as a captivating enigma, leaving scholars and laypersons alike immersed in a whirlwind of fascination and amusement.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study corroborate and extend prior research that has probed the peculiar and unexpected relationships between seemingly unrelated phenomena. In line with Smith's exploration of the potential intersection of criminal activities and energy usage, our results lend empirical support to the notion that the amount of gasoline pumped in Latvia exerts a substantial influence on the frequency of robberies in Nevada. The robust positive correlation coefficient unearthed in our analysis aligns with Smith's conceptual groundwork, underscoring the intricate entanglement of societal behaviors and resource utilization in shaping criminal tendencies. Such a connection between geographically distant occurrences could be likened to a transatlantic game of cat and mouse, where the pursuit of gasoline in one locale appears to drive the audacious exploits in another.

Furthermore, our findings echo the comprehensive analysis by Doe and Jones, who advocate for exploring bizarre correlations, by unearthing an exceptionally strong association between robberies in Nevada and gasoline pumped in Latvia. Our statistical analyses have substantiated the unexpected connection, inviting the academic community to embrace the peculiar and the improbable correlations that lurk beneath the surface of empirical datasets. This discovery serves as a testament to the whimsical nature of statistical relationships and the often surprising interplay between seemingly disparate variables.

While the narrative musings of A. Robber and E. Gasolina were not grounded in empirical evidence, they nonetheless afford an imaginative departure point for drawing parallels to our empirical findings. The historical trajectories of illicit activities expounded by A. Robber could, in a twist of fate, find resonance in our observation of the gasoline-generating ripple effect on criminal behavior across continents. Similarly, E. Gasolina's insights into global dynamics of energy consumption are mirrored in the transnational influence of gasoline pumping habits on the nefarious activities in Nevada.

As we navigate the fine line between skepticism and astonishment, our study serves as a reminder of the pervasive power of speculation in shaping scientific inquiry. The anecdotal musings from "GasLarcenyGal" on Reddit and the contemplation from @NevadaNefarious on Twitter, while not scholarly per se, offer a valuable reflection of the inquisitive spirit that permeates the public consciousness. The convergence of these inquiries has invigorated an intellectual mélange that challenges conventional wisdom and dares to entertain the unpredictable. Our empirical findings, therefore, both affirm and transcend the speculative undertones that have permeated the discourse around the intersection of crime and fuel-related matters.

In conclusion, our investigation into the connection between robberies in Nevada and the volume of gasoline pumped in Latvia has unveiled a curious and captivating association that challenges preconceived notions. The unexpected nexus between these enigmatic phenomena beckons scholars and laypersons alike to ponder the clandestine forces intertwining the world of crime and energy. This revelatory connection leaves researchers and readers immersed in a whirlwind of fascination and amusement, much like stumbling upon an unexpected punchline in a somber academic discourse.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Robberies in Nevada and Gasoline pumped in Latvia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia

[[ABSTRACT]]
This study scrutinizes the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022. Utilizing data from the FBI Criminal Justice Information Services and the Energy Information Administration, we employed sophisticated statistical analyses to reveal the surprising link between these seemingly disparate events. Our findings revealed a striking correlation coefficient of 0.9035745 with a statistically significant p-value of less than 0.01. Our analysis prompts a rethinking of the factors influencing crime and energy consumption, and will leave readers both amused and bewildered by the curious connection we have unveiled.

[[INTRDUCTION]]
The curious connection between robberies in Nevada and the volume of gasoline pumped in Latvia has long puzzled researchers and bystanders alike. On the surface, these two phenomena appear as incongruent as a penguin in the Sahara or a snowball in Singapore. However, in the hallowed halls of academic inquiry, we are duty-bound to scrutinize even the most preposterous pairings, for as the saying goes, "truth is stranger than fiction."
The aim of this study is to shed light on the perplexing relationship between rogues in the desert expanse of Nevada and the refueling antics in the Baltic gem of Latvia. Are these simply coincidental quirks of fate, or is there a deeper, more clandestine connection lurking in the shadows?
In the spirit of academic inquiry, we approached this investigation with all due seriousness, armed with an arsenal of statistical tools and a healthy dose of skepticism. Yet, as the data unfurled before our analytical gaze, we found ourselves traversing a labyrinth of intrigue and astonishment. The results were as captivating as a magician's disappearing act, leaving us to ponder the enigmatic forces at play.
As we unveil the findings of our investigation, readers may find themselves oscillating between incredulity and fascination. Prepare to embark on a journey that navigates the terrain of crime and energy consumption, where the unexpected is the norm and the conventional is left reeling in disbelief.

[[RESULTS]]
The examination of the relationship between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022 revealed a remarkably strong correlation coefficient of 0.9035745. This correlation suggests a robust positive association between these two seemingly unrelated variables, akin to finding a treasure map at a crime scene or a gas station attendant moonlighting as a masked bandit.
Furthermore, the coefficient of determination (r-squared) of 0.8164469 indicates that approximately 81.64% of the variability in robberies in Nevada can be explained by the volume of gasoline pumped in Latvia. This finding underscores the substantial influence of gasoline pumping habits in Latvia on the nefarious activities in the deserts of Nevada, a relationship as perplexing as a cat chasing a mouse across international borders.
Importantly, the p-value of less than 0.01 attests to the statistical significance of the observed correlation, indicating that the likelihood of such a strong relationship occurring by chance is lower than the probability of encountering a unicorn in a downtown metropolis.
The scatterplot (Fig. 1) visually portrays the robust positive correlation between robberies in Nevada and gasoline pumped in Latvia, a depiction as compelling as a classic caper film from the golden age of Hollywood. The data points form a highly concentrated cluster, illustrating the captivating co-movement of these enigmatic variables throughout the 30-year period.
These findings challenge conventional wisdom and beckon researchers and readers alike to ponder the clandestine forces intertwining the world of crime and energy. The unexpected connection between these peculiar phenomena serves as a captivating enigma, leaving scholars and laypersons alike immersed in a whirlwind of fascination and amusement.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia has been definitively established through our rigorous statistical analysis. The robust positive association between these seemingly incongruent variables is as befuddling as a cat wearing a disguise, but the evidence speaks for itself. It appears that as gasoline consumption in Latvia waxes and wanes, so too do the nefarious activities in the arid expanse of Nevada, like a synchronized dance between partners who have never met.

Our findings prompt a reconsideration of the factors influencing crime and energy consumption, challenging established paradigms akin to a mischievous prankster upending the solemnity of a formal affair. As we close the chapter on this perplexing saga, we implore fellow scholars to delve into uncharted territories and unravel the mysteries that continue to elude us. However, in the case of the peculiar relationship between robberies in Nevada and gasoline pumped in Latvia, it seems that no further investigation is warranted. The tale of these unlikely bedfellows has been told, leaving us amused and bewildered, and no further research in this area is needed.


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 Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Absurd Connections in Cross-Cultural Criminology


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 Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Eccentric Cross-Cultural Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Roguish Robberies and Ridiculous Refueling: Revisiting the Relationship between Robberies in Nevada and Gasoline Pumped in Latvia with an abstract of This study scrutinizes the correlation between robberies in Nevada and the volume of gasoline pumped in Latvia from 1992 to 2022. Utilizing data from the FBI Criminal Justice Information Services and the Energy Information Administration, we employed sophisticated statistical analyses to reveal the surprising link between these seemingly disparate events. Our findings revealed a striking correlation coefficient of 0.9035745 with a statistically significant p-value of less than 0.01. Our analysis prompts a rethinking of the factors influencing crime and energy consumption, and will leave readers both amused and bewildered by the curious connection we have unveiled.

ChatGPT:

robberies in Nevada, gasoline consumption in Latvia, correlation analysis, statistical analysis, crime and energy consumption, FBI Criminal Justice Information Services, Energy Information Administration, correlation coefficient, p-value, factors influencing crime and energy consumption

*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

Robberies in Nevada
Detailed data title: The robbery rate per 100,000 residents in Nevada
Source: FBI Criminal Justice Information Services
See what else correlates with Robberies in Nevada

Gasoline pumped in Latvia
Detailed data title: Volume of gasoline pumped consumed in Latvia in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Gasoline pumped in Latvia

Correlation r = 0.9035745 (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 = 0.8164469 (Coefficient of determination)
This means 81.6% of the change in the one variable (i.e., Gasoline pumped in Latvia) is predictable based on the change in the other (i.e., Robberies in Nevada) over the 31 years from 1992 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.41E-12. 0.0000000000034078425587640077
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.9 in 3.41E-10% of random cases. Said differently, if you correlated 293,440,786,291 random variables You don't actually need 293 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 30 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 30 because we have two variables measured over a period of 31 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.

[ 0.81, 0.95 ] 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.
1992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Robberies in Nevada (Robbery rate)331.3340.1352.4324.6307.6302.4254.9232.6227.3235.1236.1233210.3194.9282270.4249.4228.1195.9158.4178.6185.7209.8218215.6162.9127.6106.488.775.186.1
Gasoline pumped in Latvia (Million Barrels/Day)11.385211.065810.57819.534259.396188.660278.104117.82747.784158.175348.010968.010968.057387.964388.868499.632888.75417.42746.967126.553425.571045.115074.975344.975344.896174.682194.531514.279454.297814.22743.63836




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.




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([331.3,340.1,352.4,324.6,307.6,302.4,254.9,232.6,227.3,235.1,236.1,233,210.3,194.9,282,270.4,249.4,228.1,195.9,158.4,178.6,185.7,209.8,218,215.6,162.9,127.6,106.4,88.7,75.1,86.1,])
array_2 = np.array([11.3852,11.0658,10.5781,9.53425,9.39618,8.66027,8.10411,7.8274,7.78415,8.17534,8.01096,8.01096,8.05738,7.96438,8.86849,9.63288,8.7541,7.4274,6.96712,6.55342,5.57104,5.11507,4.97534,4.97534,4.89617,4.68219,4.53151,4.27945,4.29781,4.2274,3.63836,])
array_1_name = "Robberies in Nevada"
array_2_name = "Gasoline pumped in Latvia"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!


Correlation ID: 2321 · Black Variable ID: 20202 · Red Variable ID: 24618
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0