Spurious correlation #4,170 · 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 Oregon and the second variable is Kerosene used in Australia. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Robberies in Oregon and the second variable is Kerosene used in Australia. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The decrease in robberies in Oregon led to a decrease in the demand for getaway cars, causing a surplus of kerosene in Australia, which in turn led to a decrease in the price of kerosene, thereby reducing overall kerosene usage in the land down under. It's a crime-fighting, fuel-saving domino effect!

^{Show image generation prompt} Model: dalle-3
Prompt: [Robberies in Oregon: An image that looks like it is a scene from a Pixar movie] Create an image of a quaint rural town set in Oregon. The setting should exude a charming and picturesque vibe, with vibrant greenery and cozy houses. In the foreground, depict a group of friendly anthropomorphic cars engaging in conversation, showing a noticeable decrease in tension and apprehension. Meanwhile, an adjacent area represents Australia, where visually appealing containers of kerosene are newly priced and conspicuously abundant. The overall image should have a warm, whimsical quality that reflects the optimistic interconnectedness of these distant but related events. 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 Oregon and Kerosene used in Australia. 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: Woodblock painting An image that looks like it is a scene from a Pixar movie Glitch art Cyberpunk Data cyber art
ChatGPT: Robberies in Oregon: An image that looks like it is a scene from a Pixar movie

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Robberies in Oregon and Kerosene used in Australia, in the following situation: The decrease in robberies in Oregon led to a decrease in the demand for getaway cars, causing a surplus of kerosene in Australia, which in turn led to a decrease in the price of kerosene, thereby reducing overall kerosene usage in the land down under. It's a crime-fighting, fuel-saving domino effect!. Keep the description simple.
ChatGPT: In Oregon, the theft of getaway cars has decreased, resulting in fewer robberies. Meanwhile, in Australia, there is a surplus of kerosene due to reduced demand. This surplus has led to a decrease in the price of kerosene. In the land down under, fewer people are using kerosene, all because of the decrease in robberies in Oregon.

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: [ Robberies in Oregon: An image that looks like it is a scene from a Pixar movie ] and depicting this scene: In Oregon, the theft of getaway cars has decreased, resulting in fewer robberies. Meanwhile, in Australia, there is a surplus of kerosene due to reduced demand. This surplus has led to a decrease in the price of kerosene. In the land down under, fewer people are using kerosene, all because of the decrease in robberies in Oregon. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [Robberies in Oregon: An image that looks like it is a scene from a Pixar movie] Create an image of a quaint rural town set in Oregon. The setting should exude a charming and picturesque vibe, with vibrant greenery and cozy houses. In the foreground, depict a group of friendly anthropomorphic cars engaging in conversation, showing a noticeable decrease in tension and apprehension. Meanwhile, an adjacent area represents Australia, where visually appealing containers of kerosene are newly priced and conspicuously abundant. The overall image should have a warm, whimsical quality that reflects the optimistic interconnectedness of these distant but related events.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Robberies in Oregon caused Kerosene used in Australia to decrease.

AI academic paper

(Because p < 0.01)

Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon

International Journal of Eclectic Quirkiness

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Robberies in Oregon and Kerosene used in Australia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon"

[[ABSTRACT]]
The nexus between seemingly disparate phenomena can often reveal intriguing insights. In this study, we delve into the unexpected relationship between kerosene usage in Australia and robbery occurrences in Oregon. Employing data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research uncovers a statistically significant correlation between these two variables, with a correlation coefficient of 0.9452162 and p < 0.01 from 1985 to 2022. The implications of this connection, though initially puzzling, provide a beacon of illumination for understanding societal behaviors and resource allocation. As we shed light on this curious correlation, we recognize the potential for surprising intersections in seemingly unrelated domains.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
The world is full of interconnected phenomena, some of which are immediately apparent, while others require a closer inspection to reveal their hidden ties. This paper sets out to explore one such unexpected link: the relationship between kerosene consumption in Australia and the rates of robberies in Oregon. At first glance, one might assume these two factors to be as unrelated as a kangaroo and a koala in a game of Scrabble, but our analysis reveals a surprisingly strong correlation between the two.
As researchers, we often find ourselves venturing into uncharted territory, much like intrepid explorers seeking out new frontiers—albeit with significantly fewer dangers than navigating uncharted waters. Our curiosity is piqued by the prospect of uncovering unforeseen connections, akin to stumbling upon a hidden treasure trove of knowledge. In this case, the treasure takes the form of statistical insights that challenge conventional wisdom and leave us grappling with curious revelations.
While kerosene may seem like an unlikely protagonist in the narrative of criminal activity, our findings suggest otherwise. The allure of shedding light on this enigmatic correlation propels us forward, much like moths drawn to a flame—or in this case, perhaps, drawn to a kerosene lamp. Through meticulous data analysis and rigorous statistical methods, we aim to illuminate this unanticipated relationship, unraveling the threads that bind together the seemingly disparate realms of household energy consumption and criminal behavior.
With a firm statistical foundation and a healthy dose of skepticism, we embark on our journey to explore the unexpected convergence of kerosene consumption in Australia and robbery rates in Oregon. As we navigate this unexplored terrain, we invite our readers to join us in this intellectual adventure, where even the most unlikely pairings can offer valuable insights and, dare we say, a few chuckles along the way. After all, who would have thought that kerosene and crime could be entwined in such an illuminating manner?

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The study of seemingly disparate phenomena and their unexpected correlations has long captivated the intellectual curiosity of researchers across various disciplines. As we delve into the intriguing relationship between kerosene consumption in Australia and robbery occurrences in Oregon, we are reminded of the words of renowned scholar John Smith: "The unlikeliest pairings often yield the most illuminating revelations" (Smith, 2005).

In a seminal work on societal behaviors and resource allocation, Doe and Jones (2010) highlighted the complex interplay between environmental factors and criminal activities, shedding light on the nuanced connections that underpin seemingly unrelated domains. This notion resonates deeply with our exploration of the unexpected nexus between kerosene usage and robbery rates, encouraging us to peel back the layers of conventional wisdom and delve into uncharted territories of inquiry.

Drawing from non-fiction literature, the work of environmental economist Mary Brown in "Energy and Society" presents a comprehensive analysis of household energy consumption patterns and their implications for societal dynamics (Brown, 2015). Brown's insights offer valuable groundwork for understanding the broader context of energy use and its potential ramifications on social phenomena.

Additionally, the fiction novel "The Kerosene Conspiracy" by Amy Green weaves a captivating tale of intrigue and clandestine operations, intricately entwining the enigmatic world of kerosene trade with the shadowy realm of criminal enterprises (Green, 2018). While purely fictional, Green's narrative serves as a whimsical reminder of the curious ways in which human imagination can construct elaborate connections between seemingly disparate elements.

As we progress into the realm of unconventional sources, it is worth noting the peculiar but surprisingly informative musings found on the backs of shampoo bottles, offering unexpected insights into the intersecting domains of cleanliness and criminal impulses. While not a traditional academic source, these perceptive observations serve as a lighthearted reminder of the inquisitive nature of scholarly inquiry and the potential for unexpected sources to yield meaningful revelations.

In our pursuit of understanding the intricate link between kerosene consumption in Australia and robbery rates in Oregon, we aim to embrace the unexpected, bridging the realms of serious scholarly inquiry and lighthearted contemplation. Through this eclectic array of literature and offbeat contemplations, we embark on a journey that promises not only profound insights but also a healthy dose of intellectual amusement along the way. After all, who would have thought that a study on kerosene and crime could lead us down such delightfully unexpected avenues?

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Robberies in Oregon and Kerosene used in Australia. 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 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]]
"Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon"

[[ABSTRACT]]
The nexus between seemingly disparate phenomena can often reveal intriguing insights. In this study, we delve into the unexpected relationship between kerosene usage in Australia and robbery occurrences in Oregon. Employing data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research uncovers a statistically significant correlation between these two variables, with a correlation coefficient of 0.9452162 and p < 0.01 from 1985 to 2022. The implications of this connection, though initially puzzling, provide a beacon of illumination for understanding societal behaviors and resource allocation. As we shed light on this curious correlation, we recognize the potential for surprising intersections in seemingly unrelated domains.

[[INTRODUCTION]]
Introduction
The world is full of interconnected phenomena, some of which are immediately apparent, while others require a closer inspection to reveal their hidden ties. This paper sets out to explore one such unexpected link: the relationship between kerosene consumption in Australia and the rates of robberies in Oregon. At first glance, one might assume these two factors to be as unrelated as a kangaroo and a koala in a game of Scrabble, but our analysis reveals a surprisingly strong correlation between the two.
As researchers, we often find ourselves venturing into uncharted territory, much like intrepid explorers seeking out new frontiers—albeit with significantly fewer dangers than navigating uncharted waters. Our curiosity is piqued by the prospect of uncovering unforeseen connections, akin to stumbling upon a hidden treasure trove of knowledge. In this case, the treasure takes the form of statistical insights that challenge conventional wisdom and leave us grappling with curious revelations.
While kerosene may seem like an unlikely protagonist in the narrative of criminal activity, our findings suggest otherwise. The allure of shedding light on this enigmatic correlation propels us forward, much like moths drawn to a flame—or in this case, perhaps, drawn to a kerosene lamp. Through meticulous data analysis and rigorous statistical methods, we aim to illuminate this unanticipated relationship, unraveling the threads that bind together the seemingly disparate realms of household energy consumption and criminal behavior.
With a firm statistical foundation and a healthy dose of skepticism, we embark on our journey to explore the unexpected convergence of kerosene consumption in Australia and robbery rates in Oregon. As we navigate this unexplored terrain, we invite our readers to join us in this intellectual adventure, where even the most unlikely pairings can offer valuable insights and, dare we say, a few chuckles along the way. After all, who would have thought that kerosene and crime could be entwined in such an illuminating manner?

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To illuminate the unexpected correlation between kerosene usage in Australia and robbery rates in Oregon, our research team employed a blend of data collection, statistical analysis, and a touch of whimsy. Our data sources primarily comprised information gleaned from the FBI Criminal Justice Information Services and the Energy Information Administration, emulating the diligent detective work of Sherlock Holmes—though our magnifying glass was, regrettably, merely a metaphorical one.

Data Collection:
Our data collection process resembled a scavenger hunt of epic proportions, traversing the vast expanse of the internet to gather relevant statistics. We meticulously combed through decades' worth of data from 1985 to 2022, akin to intrepid treasure hunters unearthing nuggets of information from the digital soil. The crux of our data rested on the sturdy shoulders of the FBI Criminal Justice Information Services and the Energy Information Administration, serving as our trusty navigational stars in the vast sea of online information. We engaged in data wrangling and cleaning with a fervor akin to a seasoned chef meticulously preparing a dish, ensuring that our datasets were as pristine as a freshly laundered lab coat.

Statistical Analysis:
Applying statistical methods that would make even the most ardent math enthusiast do a celebratory jig, we delved into the heart of our data with great gusto. Armed with regression analyses, correlation coefficients, and p-values, our team donned our statistical thinking caps and waded into the realm of empirical inquiry. We suspended our disbelief and statistical skepticism just long enough to uncover a correlation coefficient of 0.9452162 with a p-value of less than 0.01, confirming the robustness of the relationship between kerosene consumption in Australia and robbery occurrences in Oregon.

Control Variables:
To account for potential confounding factors and avoid stumbling into statistical potholes, we incorporated a variety of control variables into our analyses. Factors such as population demographics, economic indicators, and environmental conditions were akin to the supporting characters in a gripping mystery novel, each playing a crucial role in untangling the web of correlations. In doing so, we endeavored to ensure that our findings would stand up to scrutiny, much like a Jenga tower built with unwavering precision.

Limitations:
While our study illuminates a compelling connection between kerosene usage in Australia and robbery rates in Oregon, it is not without its limitations. The observational nature of the data precludes us from establishing causation, leaving us with a correlation that is as tantalizingly enigmatic as a cliffhanger in a gripping television series. Additionally, the potential presence of unobserved variables lurks in the shadows, much like an elusive figure in a detective novel, reminding us of the inherent complexities of unraveling societal phenomena.

In summary, our research methodology, with its blend of data sleuthing, statistical wizardry, and a sprinkle of humor, provided the foundation for shedding light on the surprising nexus between kerosene consumption in Australia and robbery rates in Oregon. With these analytical tools in hand, we journeyed into the uncharted territory of unexpected correlations, guided by the spirit of discovery and the hope of unearthing compelling insights. After all, what is academic research without a touch of intrigue and amusement?

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Robberies in Oregon and Kerosene used in Australia. 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]]
"Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon"

[[ABSTRACT]]
The nexus between seemingly disparate phenomena can often reveal intriguing insights. In this study, we delve into the unexpected relationship between kerosene usage in Australia and robbery occurrences in Oregon. Employing data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research uncovers a statistically significant correlation between these two variables, with a correlation coefficient of 0.9452162 and p < 0.01 from 1985 to 2022. The implications of this connection, though initially puzzling, provide a beacon of illumination for understanding societal behaviors and resource allocation. As we shed light on this curious correlation, we recognize the potential for surprising intersections in seemingly unrelated domains.

[[LITERATURE REVIEW]]
The study of seemingly disparate phenomena and their unexpected correlations has long captivated the intellectual curiosity of researchers across various disciplines. As we delve into the intriguing relationship between kerosene consumption in Australia and robbery occurrences in Oregon, we are reminded of the words of renowned scholar John Smith: "The unlikeliest pairings often yield the most illuminating revelations" (Smith, 2005).
In a seminal work on societal behaviors and resource allocation, Doe and Jones (2010) highlighted the complex interplay between environmental factors and criminal activities, shedding light on the nuanced connections that underpin seemingly unrelated domains. This notion resonates deeply with our exploration of the unexpected nexus between kerosene usage and robbery rates, encouraging us to peel back the layers of conventional wisdom and delve into uncharted territories of inquiry.
Drawing from non-fiction literature, the work of environmental economist Mary Brown in "Energy and Society" presents a comprehensive analysis of household energy consumption patterns and their implications for societal dynamics (Brown, 2015). Brown's insights offer valuable groundwork for understanding the broader context of energy use and its potential ramifications on social phenomena.
Additionally, the fiction novel "The Kerosene Conspiracy" by Amy Green weaves a captivating tale of intrigue and clandestine operations, intricately entwining the enigmatic world of kerosene trade with the shadowy realm of criminal enterprises (Green, 2018). While purely fictional, Green's narrative serves as a whimsical reminder of the curious ways in which human imagination can construct elaborate connections between seemingly disparate elements.
As we progress into the realm of unconventional sources, it is worth noting the peculiar but surprisingly informative musings found on the backs of shampoo bottles, offering unexpected insights into the intersecting domains of cleanliness and criminal impulses. While not a traditional academic source, these perceptive observations serve as a lighthearted reminder of the inquisitive nature of scholarly inquiry and the potential for unexpected sources to yield meaningful revelations.
In our pursuit of understanding the intricate link between kerosene consumption in Australia and robbery rates in Oregon, we aim to embrace the unexpected, bridging the realms of serious scholarly inquiry and lighthearted contemplation. Through this eclectic array of literature and offbeat contemplations, we embark on a journey that promises not only profound insights but also a healthy dose of intellectual amusement along the way. After all, who would have thought that a study on kerosene and crime could lead us down such delightfully unexpected avenues?

[[RESULTS]]
The analysis of the data collected revealed a strong positive correlation between kerosene consumption in Australia and robbery rates in Oregon. The correlation coefficient of 0.9452162 indicates a robust relationship between these seemingly unrelated variables. This finding suggests that as kerosene consumption in Australia increased, the number of robberies in Oregon also exhibited a corresponding upward trend. The r-squared value of 0.8934337 further confirmed the substantial proportion of the variance in robbery rates that can be explained by changes in kerosene usage.
Fig. 1 displays a scatterplot illustrating the striking correlation between kerosene consumption in Australia and robbery rates in Oregon. The data points form a tightly clustered pattern that unmistakably denotes the significant association between the two variables. It's almost as if the scatterplot itself is exclaiming, "Look at this glaring connection – it's as clear as day!"
The statistical significance of the correlation, with a p-value of less than 0.01, underscores the robustness of the link between kerosene consumption in Australia and robbery rates in Oregon. The probability of observing such a strong correlation by sheer chance is exceedingly low, akin to stumbling upon a needle in a haystack the size of the Australian Outback. This result further strengthens the assertion that the relationship is not a mere fluke, but rather a genuine association worthy of further exploration.
Overall, the results of this investigation highlight the unexpected yet undeniable connection between kerosene consumption in Australia and robbery occurrences in Oregon. While initially as incongruous as a kangaroo in a kilt, these findings shed light on the intricate interplay between seemingly unrelated societal factors. The implications of this correlation stretch beyond the boundaries of our initial expectations, prompting contemplation on the multifaceted influences that shape human behaviors and interactions. As we navigate through the maze of statistical analysis, we find ourselves continually surprised by the unexpected intersections that lie beneath the surface – a reminder that sometimes, the most compelling discoveries emerge from the most unlikely pairings.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have unearthed a startling association between kerosene consumption in Australia and robbery occurrences in Oregon. As we sift through the implications of this unexpected correlation, we are prompted to reflect on the whimsical reminders scattered throughout our literature review. From the peculiar musings found on the backs of shampoo bottles to the thought-provoking fiction of "The Kerosene Conspiracy," the scholarly journey we have embarked upon has woven threads of lighthearted contemplation into the fabric of serious inquiry.

Our findings not only shed light on the robust relationship between kerosene usage and robbery rates but also underscore the depth of unexpected connections that permeate the societal tapestry. Drawing from the wisdom of John Smith, who aptly noted that "the unlikeliest pairings often yield the most illuminating revelations," we recognize the profound implications of this unanticipated nexus.

While initially as incongruous as a kangaroo in a kilt, our results corroborate the prior research that hinted at the hidden influences shaping human behaviors. Doe and Jones' insight into the complex interplay between environmental factors and criminal activities resonates deeply with our findings, affirming the nuanced connections that underpin seemingly unrelated phenomena. As we delve further, it becomes evident that the unexpected correlations we uncover are not mere curiosities but tangible reflections of the intricate interdependencies woven into the fabric of our society.

The statistical significance of the relationship, with a p-value akin to stumbling upon a needle in a haystack the size of the Australian Outback, attests to the substantive nature of the association. This robustness, as highlighted by the virtually yelling scatterplot exclaiming, "Look at this glaring connection – it's as clear as day!", speaks to the undeniable link between kerosene consumption in Australia and robbery rates in Oregon.

In navigating through this unexpected terrain of inquiry, we are reminded that the most compelling discoveries often emerge from the most unlikely pairings. As we bask in the glow of this intriguing revelation, our study beckons us to embrace the serendipitous nature of scholarly pursuit and relish the delightfully unexpected avenues it unveils.

This goofy journey of academia sometimes feels like unlocking secret connections between kerosene and crime, and hey, that's more unexpected than finding a platypus at a penguin party.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Robberies in Oregon and Kerosene used in Australia. 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]]
"Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon"

[[ABSTRACT]]
The nexus between seemingly disparate phenomena can often reveal intriguing insights. In this study, we delve into the unexpected relationship between kerosene usage in Australia and robbery occurrences in Oregon. Employing data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research uncovers a statistically significant correlation between these two variables, with a correlation coefficient of 0.9452162 and p < 0.01 from 1985 to 2022. The implications of this connection, though initially puzzling, provide a beacon of illumination for understanding societal behaviors and resource allocation. As we shed light on this curious correlation, we recognize the potential for surprising intersections in seemingly unrelated domains.

[[INTRDUCTION]]
Introduction
The world is full of interconnected phenomena, some of which are immediately apparent, while others require a closer inspection to reveal their hidden ties. This paper sets out to explore one such unexpected link: the relationship between kerosene consumption in Australia and the rates of robberies in Oregon. At first glance, one might assume these two factors to be as unrelated as a kangaroo and a koala in a game of Scrabble, but our analysis reveals a surprisingly strong correlation between the two.
As researchers, we often find ourselves venturing into uncharted territory, much like intrepid explorers seeking out new frontiers—albeit with significantly fewer dangers than navigating uncharted waters. Our curiosity is piqued by the prospect of uncovering unforeseen connections, akin to stumbling upon a hidden treasure trove of knowledge. In this case, the treasure takes the form of statistical insights that challenge conventional wisdom and leave us grappling with curious revelations.
While kerosene may seem like an unlikely protagonist in the narrative of criminal activity, our findings suggest otherwise. The allure of shedding light on this enigmatic correlation propels us forward, much like moths drawn to a flame—or in this case, perhaps, drawn to a kerosene lamp. Through meticulous data analysis and rigorous statistical methods, we aim to illuminate this unanticipated relationship, unraveling the threads that bind together the seemingly disparate realms of household energy consumption and criminal behavior.
With a firm statistical foundation and a healthy dose of skepticism, we embark on our journey to explore the unexpected convergence of kerosene consumption in Australia and robbery rates in Oregon. As we navigate this unexplored terrain, we invite our readers to join us in this intellectual adventure, where even the most unlikely pairings can offer valuable insights and, dare we say, a few chuckles along the way. After all, who would have thought that kerosene and crime could be entwined in such an illuminating manner?

[[RESULTS]]
The analysis of the data collected revealed a strong positive correlation between kerosene consumption in Australia and robbery rates in Oregon. The correlation coefficient of 0.9452162 indicates a robust relationship between these seemingly unrelated variables. This finding suggests that as kerosene consumption in Australia increased, the number of robberies in Oregon also exhibited a corresponding upward trend. The r-squared value of 0.8934337 further confirmed the substantial proportion of the variance in robbery rates that can be explained by changes in kerosene usage.
Fig. 1 displays a scatterplot illustrating the striking correlation between kerosene consumption in Australia and robbery rates in Oregon. The data points form a tightly clustered pattern that unmistakably denotes the significant association between the two variables. It's almost as if the scatterplot itself is exclaiming, "Look at this glaring connection – it's as clear as day!"
The statistical significance of the correlation, with a p-value of less than 0.01, underscores the robustness of the link between kerosene consumption in Australia and robbery rates in Oregon. The probability of observing such a strong correlation by sheer chance is exceedingly low, akin to stumbling upon a needle in a haystack the size of the Australian Outback. This result further strengthens the assertion that the relationship is not a mere fluke, but rather a genuine association worthy of further exploration.
Overall, the results of this investigation highlight the unexpected yet undeniable connection between kerosene consumption in Australia and robbery occurrences in Oregon. While initially as incongruous as a kangaroo in a kilt, these findings shed light on the intricate interplay between seemingly unrelated societal factors. The implications of this correlation stretch beyond the boundaries of our initial expectations, prompting contemplation on the multifaceted influences that shape human behaviors and interactions. As we navigate through the maze of statistical analysis, we find ourselves continually surprised by the unexpected intersections that lie beneath the surface – a reminder that sometimes, the most compelling discoveries emerge from the most unlikely pairings.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unraveled an unexpected and substantial correlation between kerosene consumption in Australia and robbery rates in Oregon. The statistically significant relationship, akin to a pair of synchronized swimmers in a sea of incongruity, challenges conventional wisdom and prompts a reconsideration of the interconnected fabric of societal dynamics. The robustness of the correlation, with a correlation coefficient akin to a beacon of statistical significance, urges further exploration and contemplation.

The implications of this discovery are as profound and bewildering as discovering a platypus in the pantry. The allure of shedding light on this novel finding is not unlike the enchanting glow of a kerosene lamp, drawing our intellectual curiosity to explore the unforeseen nexus between energy consumption and criminal activity. As our results continue to astound, there is a temptation to exclaim, "Well, I'll be a bilby's uncle!"

It is worth noting that our findings do not imply causation, as tempting as it may be to envision a scenario where burglars are swayed by the flickering kerosene light. Nevertheless, the correlation begs further inquiry and consideration, much like pondering the perplexing riddle of why kangaroos don't tell jokes—because they fear they might "jump out" instead.

In light of these revelatory findings, we assert with confidence that no further research on the bizarre connection between kerosene consumption in Australia and robbery rates in Oregon is necessary. Our work stands as a beacon of statistical intrigue, shedding light on this unexpected pairing and inviting further exploration at the intersection of disparate domains. It's as clear as the Southern Cross in the Australian night sky—the enigmatic link between kerosene and crime is a puzzle worth pondering, albeit one that may leave us scratching our heads in bemusement for years to come.

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 Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon. Respond only with the name of a fictional academic journal.

ChatGPT:

International Journal of Eclectic Quirkiness

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 Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon. Respond only with the name of a fictional organization.

ChatGPT:

The Luminary Council for Energy and Crime Analysis

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon with an abstract of The nexus between seemingly disparate phenomena can often reveal intriguing insights. In this study, we delve into the unexpected relationship between kerosene usage in Australia and robbery occurrences in Oregon. Employing data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research uncovers a statistically significant correlation between these two variables, with a correlation coefficient of 0.9452162 and p < 0.01 from 1985 to 2022. The implications of this connection, though initially puzzling, provide a beacon of illumination for understanding societal behaviors and resource allocation. As we shed light on this curious correlation, we recognize the potential for surprising intersections in seemingly unrelated domains.

ChatGPT:

kerosene consumption, robbery rates, Australia, Oregon, correlation, statistical analysis, societal behaviors, resource allocation, nexus, data analysis, unexpected relationship

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

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

Correlation r = 0.9452162 (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 = 0.8934337 (Coefficient of determination)
This means 89.3% of the change in the one variable (i.e., Kerosene used in Australia) is predictable based on the change in the other (i.e., Robberies in Oregon) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.4E-19.^Show 0.0000000000000000004375665085
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.95 in 4.4E-17% of random cases. Said differently, if you correlated 2,285,366,865,549,308,672 random variables^Note You don't actually need 2 quintillion 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 37 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 37 because we have two variables measured over a period of 38 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.

[ 0.9, 0.97 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!

All values for the years included above: ^Note If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Robberies in Oregon (Robbery rate)	185.6	205.9	196	193	151.8	144.3	150.1	151.4	129.6	138.2	137.9	122.2	117.5	105.2	86.2	84.4	79.1	77.9	79.9	76.6	68.1	73.3	76.4	70.1	65.3	63.1	57.8	62	60.9	57.2	53.7	56.5	59.7	60.1	55.2	51.4	60.6	68.6
Kerosene used in Australia (Million Barrels/Day)	4.88219	4.51233	3.78356	3.27049	3.55068	3.28767	3.0137	3.64754	3.27671	2.47945	2.44657	2.36885	2.52055	2.03562	1.53425	1.90437	1.51507	1.98356	1.5863	0.871585	0.306849	0.254795	0.460274	0.431694	0.627397	0.238356	0.50411	0.565574	0.706849	0.553425	0.665753	0.846995	0.805479	0.452055	0.153425	0.273224	0.213699	0.230137

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([185.6,205.9,196,193,151.8,144.3,150.1,151.4,129.6,138.2,137.9,122.2,117.5,105.2,86.2,84.4,79.1,77.9,79.9,76.6,68.1,73.3,76.4,70.1,65.3,63.1,57.8,62,60.9,57.2,53.7,56.5,59.7,60.1,55.2,51.4,60.6,68.6,])
array_2 = np.array([4.88219,4.51233,3.78356,3.27049,3.55068,3.28767,3.0137,3.64754,3.27671,2.47945,2.44657,2.36885,2.52055,2.03562,1.53425,1.90437,1.51507,1.98356,1.5863,0.871585,0.306849,0.254795,0.460274,0.431694,0.627397,0.238356,0.50411,0.565574,0.706849,0.553425,0.665753,0.846995,0.805479,0.452055,0.153425,0.273224,0.213699,0.230137,])
array_1_name = "Robberies in Oregon"
array_2_name = "Kerosene used in Australia"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Robberies in Oregon
Line chart for only Kerosene used in Australia
AI-generated correlation image
The spurious research paper: Shining a Light on Robberies: The Illuminating Link Between Kerosene Consumption in Australia and Robbery Rates in Oregon

View another random correlation

How fun was this correlation?

Hats off to you for rating!

Correlation ID: 4170 · Black Variable ID: 20212 · Red Variable ID: 24159


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