Download png, svg
AI explanation
As robberies in Delaware decreased, it led to a surplus in security systems. This surplus was then exported to India where it sparked a flame of interest in better home security, leading to a sharp decrease in kerosene used for lighting. In other words, Delaware's drop in crime truly lit a fire in India to switch to alternative lighting sources, making it a shining example of unexpected global impact!Model: dalle-3
Prompt: [ Cute cartoon ] Create an image of a colorful bustling city street in Delaware, filled with quaint buildings and lively storefronts, with people of all sizes, shapes, and colors moving around and engaging in various activities. Along the street, cheerful police officers are strolling and keeping an eye on the bustling city. In the distance, visualize a group of mischievous-looking criminals happily turning in their illegal activities and choosing to participate in law-abiding behavior under the watchful eye of the vigilant officers. Next, shift the scene to a charming rural area in India, where adorable cartoon characters are seen using renewable energy sources like solar power for lighting and cooking. Showcase their happiness and content as they joyfully adopt this eco-friendly lifestyle, indicating a positive change from their previous dependency on kerosene due to the decrease in smuggling activities, all thanks to the impact of the law-abiding behavior adopted in the bustling city of Delaware. Ensure that the image captures the transition from a lively, bustling city to a peaceful, harmonious rural village, reflecting positive changes and law-abiding behavior in both settings. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:
Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: Decrease in Robberies in Delaware Leads to Decrease in Kerosene Used in India: Criminals Too Busy Being Law-Abiding Citizens to Smuggle Kerosene Overseas. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Cute cartoon inspired by bauhaus Scalar art Cutsy art illustration 3D Pixar Style
ChatGPT: Cute cartoon
Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. Decrease in Robberies in Delaware Leads to Decrease in Kerosene Used in India: Criminals Too Busy Being Law-Abiding Citizens to Smuggle Kerosene Overseas
ChatGPT: Imagine a bustling city street in Delaware with people going about their daily lives, and police officers patrolling the area. In the distance, a group of criminals is seen turning in their illegal activities and opting for law-abiding behavior. Now shift to a rural area in India where people are seen using less kerosene for lighting and cooking. Instead, they are using renewable energy sources like solar power due to the decrease in kerosene smuggling activities, as the criminals are busy following the law in Delaware.
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: [ Cute cartoon ] and depicting this scene: Imagine a bustling city street in Delaware with people going about their daily lives, and police officers patrolling the area. In the distance, a group of criminals is seen turning in their illegal activities and opting for law-abiding behavior. Now shift to a rural area in India where people are seen using less kerosene for lighting and cooking. Instead, they are using renewable energy sources like solar power due to the decrease in kerosene smuggling activities, as the criminals are busy following the law in Delaware. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Cute cartoon ] Create an image of a colorful bustling city street in Delaware, filled with quaint buildings and lively storefronts, with people of all sizes, shapes, and colors moving around and engaging in various activities. Along the street, cheerful police officers are strolling and keeping an eye on the bustling city. In the distance, visualize a group of mischievous-looking criminals happily turning in their illegal activities and choosing to participate in law-abiding behavior under the watchful eye of the vigilant officers. Next, shift the scene to a charming rural area in India, where adorable cartoon characters are seen using renewable energy sources like solar power for lighting and cooking. Showcase their happiness and content as they joyfully adopt this eco-friendly lifestyle, indicating a positive change from their previous dependency on kerosene due to the decrease in smuggling activities, all thanks to the impact of the law-abiding behavior adopted in the bustling city of Delaware. Ensure that the image captures the transition from a lively, bustling city to a peaceful, harmonious rural village, reflecting positive changes and law-abiding behavior in both settings.
*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.
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 Delaware caused Kerosene used in India to decrease. Include one good pun.
AI academic paper
Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India The International Journal of Eccentric Connections Jan 2024 Reminder: This paper is AI-generated. Not real! |
Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.
Please draft the title and abstract of an academic research paper presenting the findings of the connection between Robberies in Delaware and Kerosene used in India. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.
Make the title seem clever.
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 0.8266620 and p < 0.01 for 1985 to 2021.
Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)
[[TITLE]]
Lorem ipsum dolor sit
[[ABSTRACT]]
Lorem ipsum dolor sit
ChatGPT:
[[TITLE]]
"Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India"
[[ABSTRACT]]
This paper investigates the curious correlation between the incidence of robberies in the state of Delaware and kerosene consumption in India. Employing data from the FBI's Criminal Justice Information Services and the Energy Information Administration, we conducted a thorough quantitative analysis spanning the years 1985 to 2021. Our findings revealed a striking correlation coefficient of 0.8266620 and a statistically significant p-value of less than 0.01, indicating a robust association between these seemingly disparate variables. While typically mundane in nature, our exploration uncovered a connection one could say is "illuminating," shedding light on an unexpected relationship that fuels both curiosity and potential avenues for further research.
Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.
Please make up the introduction section of an academic research paper presenting the findings of the connection between Robberies in Delaware and Kerosene used in India. 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]]
"Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India"
[[ABSTRACT]]
This paper investigates the curious correlation between the incidence of robberies in the state of Delaware and kerosene consumption in India. Employing data from the FBI's Criminal Justice Information Services and the Energy Information Administration, we conducted a thorough quantitative analysis spanning the years 1985 to 2021. Our findings revealed a striking correlation coefficient of 0.8266620 and a statistically significant p-value of less than 0.01, indicating a robust association between these seemingly disparate variables. While typically mundane in nature, our exploration uncovered a connection one could say is "illuminating," shedding light on an unexpected relationship that fuels both curiosity and potential avenues for further research.
-------
Your response should start like this:
[[INTRODUCTION]]
ChatGPT:
[[INTRODUCTION]]
The interplay between crime and environmental factors has long been a topic of interest and debate in the field of criminology. From the impact of urban planning on crime rates to the influence of climate change on criminal behavior, researchers continue to explore the intricate and often surprising relationships that exist between seemingly unrelated phenomena. In this paper, we delve into the uncharted territory of the connection between robberies in Delaware and kerosene consumption in India, a topic that, at first glance, may seem about as related as apples and orangutans.
As the saying goes, "Where there's smoke, there's fire," and in our case, the smoke has led us to discover some unexpected flames of correlation between these two seemingly disparate variables. Our investigation aims to shine a light on this peculiar nexus—one that has remained cloaked in mystery until now.
It is not uncommon for researchers to stumble upon unexpected relationships in their data. However, the correlation we uncovered between robbery rates in the First State and the consumption of kerosene in the subcontinent is as surprising as finding a croissant in a crate of crickets. Nonetheless, armed with statistical tools and a keen sense of curiosity, we set out to unravel this intriguing mystery, seeking to bring to light a connection that may seem as improbable as an economist with a sense of humor.
In unraveling this enigmatic linkage, our research also aims to exemplify the potential for unearthing novel perspectives in the most unlikely of places. So, with our data in hand and our skepticism in check, we embarked on a journey to investigate what might be termed a "bright" correlation—one that raises intriguing questions even as it shines a light on an area of research that may have remained dimly lit until now.
Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.
Please make up a literature review section of an academic research paper presenting the findings of the connection between Robberies in Delaware and Kerosene used in India. 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]]
"Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India"
[[ABSTRACT]]
This paper investigates the curious correlation between the incidence of robberies in the state of Delaware and kerosene consumption in India. Employing data from the FBI's Criminal Justice Information Services and the Energy Information Administration, we conducted a thorough quantitative analysis spanning the years 1985 to 2021. Our findings revealed a striking correlation coefficient of 0.8266620 and a statistically significant p-value of less than 0.01, indicating a robust association between these seemingly disparate variables. While typically mundane in nature, our exploration uncovered a connection one could say is "illuminating," shedding light on an unexpected relationship that fuels both curiosity and potential avenues for further research.
-------
And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The interplay between crime and environmental factors has long been a topic of interest and debate in the field of criminology. From the impact of urban planning on crime rates to the influence of climate change on criminal behavior, researchers continue to explore the intricate and often surprising relationships that exist between seemingly unrelated phenomena. In this paper, we delve into the uncharted territory of the connection between robberies in Delaware and kerosene consumption in India, a topic that, at first glance, may seem about as related as apples and orangutans.
As the saying goes, "Where there's smoke, there's fire," and in our case, the smoke has led us to discover some unexpected flames of correlation between these two seemingly disparate variables. Our investigation aims to shine a light on this peculiar nexus—one that has remained cloaked in mystery until now.
It is not uncommon for researchers to stumble upon unexpected relationships in their data. However, the correlation we uncovered between robbery rates in the First State and the consumption of kerosene in the subcontinent is as surprising as finding a croissant in a crate of crickets. Nonetheless, armed with statistical tools and a keen sense of curiosity, we set out to unravel this intriguing mystery, seeking to bring to light a connection that may seem as improbable as an economist with a sense of humor.
In unraveling this enigmatic linkage, our research also aims to exemplify the potential for unearthing novel perspectives in the most unlikely of places. So, with our data in hand and our skepticism in check, we embarked on a journey to investigate what might be termed a "bright" correlation—one that raises intriguing questions even as it shines a light on an area of research that may have remained dimly lit until now.
-------
Your response should start like this:
[[LITERATURE REVIEW]]
ChatGPT:
[[LITERATURE REVIEW]]
In their study "Crime and Energy Consumption: Unveiling the Elusive Link," Smith and Doe (2015) delve into the intriguing relationship between criminal activities and energy usage. While their research primarily focuses on the connection between burglary rates and electricity consumption, their findings open the door to broader explorations of the intersection between crime and energy usage. Meanwhile, Jones and Smith (2018) tackle the subject from a different angle in their publication "Lighting Up Crime: Exploring the Effect of Illumination on Robbery Rates." Their study explores the impact of street lighting on criminal behavior, shedding light on the literal and figurative ways in which illumination can affect crime.
Transitioning from the realm of non-fiction research to literature with potential relevance, it is worth noting the work of Adler in "Oil Lamps and Larceny: A Historical Analysis" (2007). Although not directly related to modern-day kerosene usage, this historical exploration of oil and theft contains intriguing parallels to our own investigation. Similarly, the novel "The Kerosene Caper" by Mystery Author (2014) offers a fictional glimpse into the world of crime and kerosene, suggesting that this connection may have been hiding in plain sight all along.
In addition to these publications, a less formal yet equally enlightening avenue of exploration involves the classic animated series "Inspector Kerosene and the Case of the Dastardly Delinquents." While intended for a younger audience, the detective's unconventional methods of solving crimes involving combustible liquids may offer unexpected insights into our own research topic.
As the investigation unfolds, the unexpected twists and turns in our pursuit of understanding the link between robberies in Delaware and kerosene consumption in India mirror the sometimes baffling nature of human behavior. In the words of Albert Einstein, "Coincidence is God's way of remaining anonymous," and perhaps this unexpected correlation is simply another manifestation of the mysteries that permeate our world.
Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.
Please make up the methodology section of an academic research paper presenting the findings of the connection between Robberies in Delaware and Kerosene used in India. 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 1985 to 2021
Make up the research methods you don't know. Make them a bit goofy and convoluted.
Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India"
[[ABSTRACT]]
This paper investigates the curious correlation between the incidence of robberies in the state of Delaware and kerosene consumption in India. Employing data from the FBI's Criminal Justice Information Services and the Energy Information Administration, we conducted a thorough quantitative analysis spanning the years 1985 to 2021. Our findings revealed a striking correlation coefficient of 0.8266620 and a statistically significant p-value of less than 0.01, indicating a robust association between these seemingly disparate variables. While typically mundane in nature, our exploration uncovered a connection one could say is "illuminating," shedding light on an unexpected relationship that fuels both curiosity and potential avenues for further research.
[[INTRODUCTION]]
The interplay between crime and environmental factors has long been a topic of interest and debate in the field of criminology. From the impact of urban planning on crime rates to the influence of climate change on criminal behavior, researchers continue to explore the intricate and often surprising relationships that exist between seemingly unrelated phenomena. In this paper, we delve into the uncharted territory of the connection between robberies in Delaware and kerosene consumption in India, a topic that, at first glance, may seem about as related as apples and orangutans.
As the saying goes, "Where there's smoke, there's fire," and in our case, the smoke has led us to discover some unexpected flames of correlation between these two seemingly disparate variables. Our investigation aims to shine a light on this peculiar nexus—one that has remained cloaked in mystery until now.
It is not uncommon for researchers to stumble upon unexpected relationships in their data. However, the correlation we uncovered between robbery rates in the First State and the consumption of kerosene in the subcontinent is as surprising as finding a croissant in a crate of crickets. Nonetheless, armed with statistical tools and a keen sense of curiosity, we set out to unravel this intriguing mystery, seeking to bring to light a connection that may seem as improbable as an economist with a sense of humor.
In unraveling this enigmatic linkage, our research also aims to exemplify the potential for unearthing novel perspectives in the most unlikely of places. So, with our data in hand and our skepticism in check, we embarked on a journey to investigate what might be termed a "bright" correlation—one that raises intriguing questions even as it shines a light on an area of research that may have remained dimly lit until now.
-------
Your response should start like this:
[[METHODOLOGY]]
ChatGPT:
[[METHODOLOGY]]
Given the peculiar nature of our research question and the seemingly incongruous nature of our variables, our methodology bore the burden of being as unconventional as the topic itself. With a mix of rigour and whimsy, we sought to navigate the labyrinthine pathways of data analysis in a manner befitting the unexpected connection we aimed to uncover.
First and foremost, our approach hinged on the meticulous curation of data spanning the years 1985 to 2021 from sources as diverse as the digital landscape itself. The FBI's Criminal Justice Information Services and the Energy Information Administration formed the bedrock of our investigation, providing us with a treasure trove of numbers, trends, and surprises – like an academic version of a detective's kit, complete with statistical magnifying glasses and analytical fingerprinting tools.
From there, our analysis took a journey as twisted and convoluted as a mystery novel. We employed an intricate series of statistical techniques, including but not limited to time series analysis, correlation matrices, and regression models, each more formidable than a cryptic crossword puzzle. These tools, while daunting to the uninitiated, paved the way for us to discern patterns, trends, and a correlation coefficient that stood out as prominently as a fluorescent highlighter in a sea of monochrome data.
Our analysis did not stop at mere number-crunching, though; for our endeavor was akin to digging for treasure in a sea of uncertainty. Hence, we plumbed the depths of historical and contemporary literature, seeking to understand the context, implications, and potential explanations for the unforeseen association we unearthed.
At every step, we grappled with the weighty responsibility of balancing statistical rigor with the captivating allure of an enigmatic correlation, akin to walking a tightrope while juggling. It is with this intricate blend of methodological sobriety and whimsical curiosity that we embarked upon our quest to illuminate a nexus that may be as unpredictable as a cat in a room full of rocking chairs.
Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.
Please make up the results section of an academic research paper presenting the findings of the connection between Robberies in Delaware and Kerosene used in India. 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 1985 to 2021, you found a correlation 0.8266620, r-squared of 0.6833701, 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]]
"Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India"
[[ABSTRACT]]
This paper investigates the curious correlation between the incidence of robberies in the state of Delaware and kerosene consumption in India. Employing data from the FBI's Criminal Justice Information Services and the Energy Information Administration, we conducted a thorough quantitative analysis spanning the years 1985 to 2021. Our findings revealed a striking correlation coefficient of 0.8266620 and a statistically significant p-value of less than 0.01, indicating a robust association between these seemingly disparate variables. While typically mundane in nature, our exploration uncovered a connection one could say is "illuminating," shedding light on an unexpected relationship that fuels both curiosity and potential avenues for further research.
-------
And here is the methodology section that led to this result:
[[METHODOLOGY]]
The interplay between crime and environmental factors has long been a topic of interest and debate in the field of criminology. From the impact of urban planning on crime rates to the influence of climate change on criminal behavior, researchers continue to explore the intricate and often surprising relationships that exist between seemingly unrelated phenomena. In this paper, we delve into the uncharted territory of the connection between robberies in Delaware and kerosene consumption in India, a topic that, at first glance, may seem about as related as apples and orangutans.
As the saying goes, "Where there's smoke, there's fire," and in our case, the smoke has led us to discover some unexpected flames of correlation between these two seemingly disparate variables. Our investigation aims to shine a light on this peculiar nexus—one that has remained cloaked in mystery until now.
It is not uncommon for researchers to stumble upon unexpected relationships in their data. However, the correlation we uncovered between robbery rates in the First State and the consumption of kerosene in the subcontinent is as surprising as finding a croissant in a crate of crickets. Nonetheless, armed with statistical tools and a keen sense of curiosity, we set out to unravel this intriguing mystery, seeking to bring to light a connection that may seem as improbable as an economist with a sense of humor.
In unraveling this enigmatic linkage, our research also aims to exemplify the potential for unearthing novel perspectives in the most unlikely of places. So, with our data in hand and our skepticism in check, we embarked on a journey to investigate what might be termed a "bright" correlation—one that raises intriguing questions even as it shines a light on an area of research that may have remained dimly lit until now.
-------
Your response should start like this:
[[RESULTS]]
ChatGPT:
[[RESULTS]]
The analysis of the data collected from the FBI's Criminal Justice Information Services and the Energy Information Administration uncovered a substantial correlation between the incidence of robberies in Delaware and kerosene consumption in India. The correlation coefficient of 0.8266620 suggests a strong positive relationship between these seemingly unrelated variables and is statistically significant with a p-value of less than 0.01. This illuminating discovery challenges conventional wisdom and prompts a reevaluation of the interconnectedness of socioeconomic and environmental factors.
Figure 1 depicts the scatterplot illustrating the remarkable correlation between robberies in Delaware and kerosene consumption in India. The data points form a distinct pattern that mirrors the statistical findings, further emphasizing the unexpected yet compelling relationship between the two variables. One might say that this connection is as surprising as finding a genie in a kerosene lamp!
The results of this investigation not only underscore the need for interdisciplinary collaboration but also highlight the potential for serendipitous discoveries in the vast landscape of empirical research. As we shed light on this unusual association, it becomes evident that there is much more to be learned from seemingly incongruent phenomena. This unexpected correlation between crime in the United States and kerosene usage in India certainly sets the stage for further exploration and invites researchers to approach the study of crime and environmental factors with a "brighter" perspective.
Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.
Please make up the discussion section of an academic research paper presenting the findings of the connection between Robberies in Delaware and Kerosene used in India. 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]]
"Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India"
[[ABSTRACT]]
This paper investigates the curious correlation between the incidence of robberies in the state of Delaware and kerosene consumption in India. Employing data from the FBI's Criminal Justice Information Services and the Energy Information Administration, we conducted a thorough quantitative analysis spanning the years 1985 to 2021. Our findings revealed a striking correlation coefficient of 0.8266620 and a statistically significant p-value of less than 0.01, indicating a robust association between these seemingly disparate variables. While typically mundane in nature, our exploration uncovered a connection one could say is "illuminating," shedding light on an unexpected relationship that fuels both curiosity and potential avenues for further research.
[[LITERATURE REVIEW]]
In their study "Crime and Energy Consumption: Unveiling the Elusive Link," Smith and Doe (2015) delve into the intriguing relationship between criminal activities and energy usage. While their research primarily focuses on the connection between burglary rates and electricity consumption, their findings open the door to broader explorations of the intersection between crime and energy usage. Meanwhile, Jones and Smith (2018) tackle the subject from a different angle in their publication "Lighting Up Crime: Exploring the Effect of Illumination on Robbery Rates." Their study explores the impact of street lighting on criminal behavior, shedding light on the literal and figurative ways in which illumination can affect crime.
Transitioning from the realm of non-fiction research to literature with potential relevance, it is worth noting the work of Adler in "Oil Lamps and Larceny: A Historical Analysis" (2007). Although not directly related to modern-day kerosene usage, this historical exploration of oil and theft contains intriguing parallels to our own investigation. Similarly, the novel "The Kerosene Caper" by Mystery Author (2014) offers a fictional glimpse into the world of crime and kerosene, suggesting that this connection may have been hiding in plain sight all along.
In addition to these publications, a less formal yet equally enlightening avenue of exploration involves the classic animated series "Inspector Kerosene and the Case of the Dastardly Delinquents." While intended for a younger audience, the detective's unconventional methods of solving crimes involving combustible liquids may offer unexpected insights into our own research topic.
As the investigation unfolds, the unexpected twists and turns in our pursuit of understanding the link between robberies in Delaware and kerosene consumption in India mirror the sometimes baffling nature of human behavior. In the words of Albert Einstein, "Coincidence is God's way of remaining anonymous," and perhaps this unexpected correlation is simply another manifestation of the mysteries that permeate our world.
[[RESULTS]]
The analysis of the data collected from the FBI's Criminal Justice Information Services and the Energy Information Administration uncovered a substantial correlation between the incidence of robberies in Delaware and kerosene consumption in India. The correlation coefficient of 0.8266620 suggests a strong positive relationship between these seemingly unrelated variables and is statistically significant with a p-value of less than 0.01. This illuminating discovery challenges conventional wisdom and prompts a reevaluation of the interconnectedness of socioeconomic and environmental factors.
Figure 1 depicts the scatterplot illustrating the remarkable correlation between robberies in Delaware and kerosene consumption in India. The data points form a distinct pattern that mirrors the statistical findings, further emphasizing the unexpected yet compelling relationship between the two variables. One might say that this connection is as surprising as finding a genie in a kerosene lamp!
The results of this investigation not only underscore the need for interdisciplinary collaboration but also highlight the potential for serendipitous discoveries in the vast landscape of empirical research. As we shed light on this unusual association, it becomes evident that there is much more to be learned from seemingly incongruent phenomena. This unexpected correlation between crime in the United States and kerosene usage in India certainly sets the stage for further exploration and invites researchers to approach the study of crime and environmental factors with a "brighter" perspective.
-------
Your response should start like this:
[[DISCUSSION]]
ChatGPT:
[[DISCUSSION]]
The findings of our investigation introduce a compelling and somewhat unexpected dimension to the intersection of crime and environmental factors. Our results not only align with prior research on the relationship between criminal activities and energy consumption but also offer an "illuminating" perspective on the broader landscape of interconnections. The striking correlation coefficient of 0.8266620 and the statistically significant p-value lend strong support to our initial hypothesis and validate the "far-from-dim" nature of the association between robberies in Delaware and kerosene consumption in India.
Reflecting on the literature review, the seemingly outlandish associations found in fictional and non-fictional works may not be as far-fetched as one might assume. The publication "Lighting Up Crime: Exploring the Effect of Illumination on Robbery Rates" by Jones and Smith (2018), in particular, aligns with our own findings, albeit in a more literal sense. Just as the titular Inspector Kerosene in the widely acclaimed animated series may offer unconventional insights into crime-solving, our research has brought to light a connection worthy of further exploration.
The unexpected twists and turns encountered in our pursuit of understanding the connection between robberies in Delaware and kerosene consumption in India offer a parallel to the sometimes confounding nature of human behavior. These findings echo the sentiment of Albert Einstein, suggesting that perhaps this unexpected correlation is indeed another manifestation of the myriad mysteries that encompass our world.
In light of the results, it becomes apparent that there is value in approaching research with a propensity for unexpected discoveries. The discovery of a significant correlation between crime in the United States and kerosene usage in India calls for a reevaluation of traditional disciplinary boundaries and paves the way for synergistic collaborations across diverse fields of study. As we shed light on this unusual association, it is clear that this novel correlation affords the opportunity for further investigation and invites researchers to approach the study of crime and environmental factors with a "brighter" perspective.
Overall, our research highlights the potentially "illuminating" insights that can emerge from seemingly unrelated variables, and underscores the significance of fortuitous discoveries in empirical research. Our unexpected correlation between robberies in Delaware and kerosene usage in India undoubtedly warrants further exploration and may serve as a catalyst for future investigations into the interface between societal trends and environmental dynamics.
Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.
Please make up a short conclusion of an academic research paper presenting the findings of the connection between Robberies in Delaware and Kerosene used in India. 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]]
"Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India"
[[ABSTRACT]]
This paper investigates the curious correlation between the incidence of robberies in the state of Delaware and kerosene consumption in India. Employing data from the FBI's Criminal Justice Information Services and the Energy Information Administration, we conducted a thorough quantitative analysis spanning the years 1985 to 2021. Our findings revealed a striking correlation coefficient of 0.8266620 and a statistically significant p-value of less than 0.01, indicating a robust association between these seemingly disparate variables. While typically mundane in nature, our exploration uncovered a connection one could say is "illuminating," shedding light on an unexpected relationship that fuels both curiosity and potential avenues for further research.
[[INTRDUCTION]]
The interplay between crime and environmental factors has long been a topic of interest and debate in the field of criminology. From the impact of urban planning on crime rates to the influence of climate change on criminal behavior, researchers continue to explore the intricate and often surprising relationships that exist between seemingly unrelated phenomena. In this paper, we delve into the uncharted territory of the connection between robberies in Delaware and kerosene consumption in India, a topic that, at first glance, may seem about as related as apples and orangutans.
As the saying goes, "Where there's smoke, there's fire," and in our case, the smoke has led us to discover some unexpected flames of correlation between these two seemingly disparate variables. Our investigation aims to shine a light on this peculiar nexus—one that has remained cloaked in mystery until now.
It is not uncommon for researchers to stumble upon unexpected relationships in their data. However, the correlation we uncovered between robbery rates in the First State and the consumption of kerosene in the subcontinent is as surprising as finding a croissant in a crate of crickets. Nonetheless, armed with statistical tools and a keen sense of curiosity, we set out to unravel this intriguing mystery, seeking to bring to light a connection that may seem as improbable as an economist with a sense of humor.
In unraveling this enigmatic linkage, our research also aims to exemplify the potential for unearthing novel perspectives in the most unlikely of places. So, with our data in hand and our skepticism in check, we embarked on a journey to investigate what might be termed a "bright" correlation—one that raises intriguing questions even as it shines a light on an area of research that may have remained dimly lit until now.
[[RESULTS]]
The analysis of the data collected from the FBI's Criminal Justice Information Services and the Energy Information Administration uncovered a substantial correlation between the incidence of robberies in Delaware and kerosene consumption in India. The correlation coefficient of 0.8266620 suggests a strong positive relationship between these seemingly unrelated variables and is statistically significant with a p-value of less than 0.01. This illuminating discovery challenges conventional wisdom and prompts a reevaluation of the interconnectedness of socioeconomic and environmental factors.
Figure 1 depicts the scatterplot illustrating the remarkable correlation between robberies in Delaware and kerosene consumption in India. The data points form a distinct pattern that mirrors the statistical findings, further emphasizing the unexpected yet compelling relationship between the two variables. One might say that this connection is as surprising as finding a genie in a kerosene lamp!
The results of this investigation not only underscore the need for interdisciplinary collaboration but also highlight the potential for serendipitous discoveries in the vast landscape of empirical research. As we shed light on this unusual association, it becomes evident that there is much more to be learned from seemingly incongruent phenomena. This unexpected correlation between crime in the United States and kerosene usage in India certainly sets the stage for further exploration and invites researchers to approach the study of crime and environmental factors with a "brighter" perspective.
-------
Your response should start like this:
[[CONCLUSION]]
ChatGPT:
[[CONCLUSION]]
In conclusion, our research has brought to light a fascinating correlation between robberies in Delaware and kerosene consumption in India, a connection that seemed as unlikely as finding a needle in a haystack made of glow sticks. The robust statistical evidence of this unexpected relationship challenges traditional assumptions and sparks curiosity for further exploration. As we wrap up this study, it's clear that this correlation may not just be a statistical anomaly but could truly be a case of "lighting the way" for future research. Researchers, however, need not fuel themselves with endless studies on this particular connection; we believe this avenue of investigation has been sufficiently illuminated.
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 Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India. Respond only with the name of a fictional academic journal.
ChatGPT:
The International Journal of Eccentric Connections
Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India. Respond only with the name of a fictional organization.
ChatGPT:
The International Society for Quirky Scientific Research
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 Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India with an abstract of This paper investigates the curious correlation between the incidence of robberies in the state of Delaware and kerosene consumption in India. Employing data from the FBI's Criminal Justice Information Services and the Energy Information Administration, we conducted a thorough quantitative analysis spanning the years 1985 to 2021. Our findings revealed a striking correlation coefficient of 0.8266620 and a statistically significant p-value of less than 0.01, indicating a robust association between these seemingly disparate variables. While typically mundane in nature, our exploration uncovered a connection one could say is "illuminating," shedding light on an unexpected relationship that fuels both curiosity and potential avenues for further research.
ChatGPT:
robberies in Delaware, kerosene consumption in India, correlation, quantitative analysis, FBI Criminal Justice Information Services, Energy Information Administration, correlation coefficient, p-value, association, unexpected relationship, research opportunities
*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.
Discover a new correlation
View all correlations
View all research papers
Report an error
Data details
Robberies in DelawareDetailed data title: The robbery rate per 100,000 residents in Delaware
Source: FBI Criminal Justice Information Services
See what else correlates with Robberies in Delaware
Kerosene used in India
Detailed data title: Volume of kerosene used consumed in India in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in India
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 = 0.6833701 (Coefficient of determination)
This means 68.3% of the change in the one variable (i.e., Kerosene used in India) is predictable based on the change in the other (i.e., Robberies in Delaware) over the 37 years from 1985 through 2021.
p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.91E-10. 0.0000000002909698554138838000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.
But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.
Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.83 in 2.91E-8% of random cases. Said differently, if you correlated 3,436,782,132 random variables You don't actually need 3 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 36 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 36 because we have two variables measured over a period of 37 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.
[ 0.69, 0.91 ] 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.
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 | 2020 | 2021 | |
Robberies in Delaware (Robbery rate) | 124.3 | 124.2 | 122.5 | 118.8 | 138.8 | 164.8 | 214.7 | 151.2 | 186.7 | 161.6 | 198.7 | 179.9 | 243.6 | 194.2 | 198 | 177.9 | 145.1 | 143.2 | 176.1 | 161.8 | 155.2 | 209.8 | 203.9 | 211.5 | 189.8 | 204.4 | 171.6 | 163.3 | 133.3 | 135.8 | 131.3 | 142.6 | 113.1 | 89.2 | 80.8 | 0 | 56.2 |
Kerosene used in India (Million Barrels/Day) | 134.203 | 142 | 153 | 168 | 173 | 178 | 175 | 198 | 182 | 206 | 198 | 203 | 212 | 250 | 227 | 238.806 | 220.93 | 220.358 | 216.652 | 198.424 | 198.587 | 201.298 | 198.333 | 196.481 | 197.041 | 189.078 | 183 | 166 | 157 | 154 | 149 | 128 | 88 | 76.9508 | 59.2101 | 40.4265 | 34.1946 |
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
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
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. - Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
Try it yourself
You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.Step 2: Open a plaintext editor like Notepad and paste the code below into it.
Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"
Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.
Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.
Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.
Step 7: Run the Python script by typing "python calculate_correlation.py"
If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:
"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."
# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats
# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):
# Calculate Pearson correlation coefficient and p-value
correlation, p_value = stats.pearsonr(array1, array2)
# Calculate R-squared as the square of the correlation coefficient
r_squared = correlation**2
return correlation, r_squared, p_value
# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([124.3,124.2,122.5,118.8,138.8,164.8,214.7,151.2,186.7,161.6,198.7,179.9,243.6,194.2,198,177.9,145.1,143.2,176.1,161.8,155.2,209.8,203.9,211.5,189.8,204.4,171.6,163.3,133.3,135.8,131.3,142.6,113.1,89.2,80.8,0,56.2,])
array_2 = np.array([134.203,142,153,168,173,178,175,198,182,206,198,203,212,250,227,238.806,220.93,220.358,216.652,198.424,198.587,201.298,198.333,196.481,197.041,189.078,183,166,157,154,149,128,88,76.9508,59.2101,40.4265,34.1946,])
array_1_name = "Robberies in Delaware"
array_2_name = "Kerosene used in India"
# 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:
- High resolution line chart
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 Robberies in Delaware
- Line chart for only Kerosene used in India
- The spurious research paper: Fuelling Crime: An Unexpected Link Between Robberies in Delaware and Kerosene Consumption in India
Your correlation inspection deserves a standing ovation!
Correlation ID: 1214 · Black Variable ID: 20231 · Red Variable ID: 24537