Spurious correlation #1,987 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Burglaries in North Dakota and the second variable is Liquefied petroleum gas used in Netherlands. 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 Burglaries in North Dakota and the second variable is Liquefied petroleum gas used in Netherlands. 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 burglaries in North Dakota meant there were fewer thieves trying to steal propane, leading to a lower demand for Liquefied Petroleum Gas in the Netherlands. You could say the crime rate and the gas rate are both on the decline!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image that looks like a scene from 'Star Wars' and captures a rural area in North Dakota with a small convenience store surrounded by fields of golden wheat. Meanwhile, include a peaceful village in the Netherlands with windmills in the background, using liquefied petroleum gas for cooking and heating in their homes. The visual should evoke a sense of a unique and mysterious cosmic landscape within a real-world setting. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Burglaries in North Dakota and Liquefied petroleum gas used in Netherlands. 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: An image that looks like it is a scene from 'Star Wars' Realistic Psychedelic An image that looks like it is a scene from A Disney Movie Sci-fi fantacy
ChatGPT: An image that looks like it is a scene from 'Star Wars'

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Burglaries in North Dakota and Liquefied petroleum gas used in Netherlands together. Keep the description simple.
ChatGPT: In a rural area in North Dakota, a small convenience store with a "Burglary Alert" sign on the front is surrounded by fields of golden wheat. Meanwhile, in the Netherlands, a peaceful village with windmills in the background uses Liquefied petroleum gas for cooking and heating in their homes.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: In a rural area in North Dakota, a small convenience store with a "Burglary Alert" sign on the front is surrounded by fields of golden wheat. Meanwhile, in the Netherlands, a peaceful village with windmills in the background uses Liquefied petroleum gas for cooking and heating in their homes. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that looks like a scene from 'Star Wars' and captures a rural area in North Dakota with a small convenience store surrounded by fields of golden wheat. Meanwhile, include a peaceful village in the Netherlands with windmills in the background, using liquefied petroleum gas for cooking and heating in their homes. The visual should evoke a sense of a unique and mysterious cosmic landscape within a real-world setting.

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

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

AI academic paper

(Because p < 0.01)

Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands

Journal of Quirky Crime and Cross-Cultural Conundrums

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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Burglaries in North Dakota and Liquefied petroleum gas used in Netherlands. 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 name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands

[[ABSTRACT]]
This research seeks to unravel the peculiar relationship between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands. Utilizing data from FBI Criminal Justice Information Services and Energy Information Administration, our analysis reveals a surprising correlation coefficient of 0.6915982 and p < 0.01 for the period spanning from 1985 to 2022. The findings not only astound but also amuse, as one cannot help but marvel at the intertwining web of seemingly unrelated phenomena. Our study sheds light on the quirky connections that often elude traditional scholarly inquiry.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of crime and energy consumption has long been a subject of interest within both the academic and law enforcement communities. However, the exploration of the connection between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands represents a rather curious foray into uncharted territory. The juxtaposition of these two seemingly disparate phenomena has raised eyebrows, piqued curiosity, and left many a researcher scratching their heads in puzzlement.
As the saying goes, "Truth is stranger than fiction," and indeed, the correlation uncovered in this study may just prove to be stranger than a work of fiction. The correlation coefficient of 0.6915982 and the statistically significant p-value of less than 0.01 have left us in a state of both bemusement and fascination. The robustness of this relationship between bumbling burglaries and boisterous butanes is truly nothing short of remarkable.
The primary aim of this investigation is to disentangle the enigmatic web of associations that underpin this unlikely pairing, and to shed light on the underlying mechanisms that give rise to such a peculiar correlation. While some may be tempted to dismiss these findings as mere statistical oddities, we believe that they merit closer examination. After all, as researchers, it is our duty to delve into the realms of the unexpected and the inexplicable.
The following sections will delve into the data sources, methodology, and findings, all the while maintaining a sense of academic rigor and scholarly inquiry. But do prepare yourself for the occasional surprise twist or ironic revelation, for this journey through the intricacies of bumbling burglaries and boisterous butanes promises to be anything but mundane.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Several prior studies have examined the relationship between crime and energy consumption, albeit with a focus on more conventional pairings. Smith and Doe (2015) explored the association between vehicle theft and gasoline usage, while Jones (2018) investigated the link between larceny and electricity consumption. However, the peculiar connection between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands has received scant attention in the academic literature.

Turning to broader studies related to crime, energy, and societal dynamics, "Crime and Public Policy" by Wilson and Petersilia (2011) and "The Sociology of Crime" by Mclaughlin and Muncie (2017) provide foundational insights into the multifaceted nature of criminal behavior. While these seminal works do not directly address the specific juxtaposition at hand, they offer a comprehensive understanding of the complex factors that shape criminal activities.

Moving away from the realm of non-fiction, the fictional narratives presented in Dan Brown's "The Da Vinci Code" and Agatha Christie's "The Secret Adversary" offer tantalizing tales of intrigue, deception, and clandestine activities—themes that may offer a sense of kinship with the curious correlation under examination. Additionally, popular television shows such as "Breaking Bad" and "Fargo" capture the essence of criminality and societal idiosyncrasies, offering a lens through which one can marvel at the baffling tapestry of human behavior. As we venture further into the annals of this review, we must be prepared for unexpected twists and perhaps a touch of dark humor.

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

Please make up the results section of an academic research paper presenting the findings of the connection between Burglaries in North Dakota and Liquefied petroleum gas used in Netherlands. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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 2022, you found a correlation 0.6915982, r-squared of 0.4783081, 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]]
Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands

[[ABSTRACT]]
This research seeks to unravel the peculiar relationship between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands. Utilizing data from FBI Criminal Justice Information Services and Energy Information Administration, our analysis reveals a surprising correlation coefficient of 0.6915982 and p < 0.01 for the period spanning from 1985 to 2022. The findings not only astound but also amuse, as one cannot help but marvel at the intertwining web of seemingly unrelated phenomena. Our study sheds light on the quirky connections that often elude traditional scholarly inquiry.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of crime and energy consumption has long been a subject of interest within both the academic and law enforcement communities. However, the exploration of the connection between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands represents a rather curious foray into uncharted territory. The juxtaposition of these two seemingly disparate phenomena has raised eyebrows, piqued curiosity, and left many a researcher scratching their heads in puzzlement.
As the saying goes, "Truth is stranger than fiction," and indeed, the correlation uncovered in this study may just prove to be stranger than a work of fiction. The correlation coefficient of 0.6915982 and the statistically significant p-value of less than 0.01 have left us in a state of both bemusement and fascination. The robustness of this relationship between bumbling burglaries and boisterous butanes is truly nothing short of remarkable.
The primary aim of this investigation is to disentangle the enigmatic web of associations that underpin this unlikely pairing, and to shed light on the underlying mechanisms that give rise to such a peculiar correlation. While some may be tempted to dismiss these findings as mere statistical oddities, we believe that they merit closer examination. After all, as researchers, it is our duty to delve into the realms of the unexpected and the inexplicable.
The following sections will delve into the data sources, methodology, and findings, all the while maintaining a sense of academic rigor and scholarly inquiry. But do prepare yourself for the occasional surprise twist or ironic revelation, for this journey through the intricacies of bumbling burglaries and boisterous butanes promises to be anything but mundane.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The examination of the relationship between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands yielded some rather intriguing results. The correlation coefficient of 0.6915982 suggests a moderately strong positive association between these seemingly unrelated variables. This statistical connection between bumbling burglaries and boisterous butanes has captivated our attention, leaving us both flabbergasted and delighted by the unexpected nature of our findings.

The r-squared value of 0.4783081 indicates that approximately 47.83% of the variation in burglaries in North Dakota can be explained by the usage of liquefied petroleum gas in Netherlands. While this may not account for the entirety of the relationship, it certainly provides substantial insight into the dynamics at play. It seems that these variables, in their own peculiar way, dance a coordinated tango across time and space, defying conventional expectations and confounding conventional wisdom.

Furthermore, the p-value of less than 0.01 underscores the statistical significance of this correlation, reinforcing the notion that this connection between seemingly incongruous phenomena is not merely a figment of statistical noise. It appears that the gravitational pull between the fumbling furtive intruders of North Dakota and the spirited butanes of Netherlands is not to be taken lightly.

Finally, the scatterplot (Fig. 1) visually depicts the compelling relationship between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands. The points on the plot align themselves in a manner that would make even the most avowed skeptic raise an eyebrow. The striking pattern revealed in this visual representation is not only noteworthy but also serves as a testament to the undeniable entwinement of these disparate elements.

In conclusion, our exploration of the curious correlation between burglaries in North Dakota and the utilization of liquefied petroleum gas in Netherlands has uncovered a tapestry of interconnectedness that is as confounding as it is captivating. The evidence presented in this study challenges conventional notions of causality and beckons researchers to embrace the serendipitous discoveries that often lie hidden in the labyrinth of data.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Burglaries in North Dakota and Liquefied petroleum gas used in Netherlands. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands

[[ABSTRACT]]
This research seeks to unravel the peculiar relationship between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands. Utilizing data from FBI Criminal Justice Information Services and Energy Information Administration, our analysis reveals a surprising correlation coefficient of 0.6915982 and p < 0.01 for the period spanning from 1985 to 2022. The findings not only astound but also amuse, as one cannot help but marvel at the intertwining web of seemingly unrelated phenomena. Our study sheds light on the quirky connections that often elude traditional scholarly inquiry.

[[LITERATURE REVIEW]]
Several prior studies have examined the relationship between crime and energy consumption, albeit with a focus on more conventional pairings. Smith and Doe (2015) explored the association between vehicle theft and gasoline usage, while Jones (2018) investigated the link between larceny and electricity consumption. However, the peculiar connection between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands has received scant attention in the academic literature.
Turning to broader studies related to crime, energy, and societal dynamics, "Crime and Public Policy" by Wilson and Petersilia (2011) and "The Sociology of Crime" by Mclaughlin and Muncie (2017) provide foundational insights into the multifaceted nature of criminal behavior. While these seminal works do not directly address the specific juxtaposition at hand, they offer a comprehensive understanding of the complex factors that shape criminal activities.
Moving away from the realm of non-fiction, the fictional narratives presented in Dan Brown's "The Da Vinci Code" and Agatha Christie's "The Secret Adversary" offer tantalizing tales of intrigue, deception, and clandestine activities—themes that may offer a sense of kinship with the curious correlation under examination. Additionally, popular television shows such as "Breaking Bad" and "Fargo" capture the essence of criminality and societal idiosyncrasies, offering a lens through which one can marvel at the baffling tapestry of human behavior. As we venture further into the annals of this review, we must be prepared for unexpected twists and perhaps a touch of dark humor.

[[RESULTS]]
The examination of the relationship between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands yielded some rather intriguing results. The correlation coefficient of 0.6915982 suggests a moderately strong positive association between these seemingly unrelated variables. This statistical connection between bumbling burglaries and boisterous butanes has captivated our attention, leaving us both flabbergasted and delighted by the unexpected nature of our findings.
The r-squared value of 0.4783081 indicates that approximately 47.83% of the variation in burglaries in North Dakota can be explained by the usage of liquefied petroleum gas in Netherlands. While this may not account for the entirety of the relationship, it certainly provides substantial insight into the dynamics at play. It seems that these variables, in their own peculiar way, dance a coordinated tango across time and space, defying conventional expectations and confounding conventional wisdom.
Furthermore, the p-value of less than 0.01 underscores the statistical significance of this correlation, reinforcing the notion that this connection between seemingly incongruous phenomena is not merely a figment of statistical noise. It appears that the gravitational pull between the fumbling furtive intruders of North Dakota and the spirited butanes of Netherlands is not to be taken lightly.
Finally, the scatterplot (Fig. 1) visually depicts the compelling relationship between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands. The points on the plot align themselves in a manner that would make even the most avowed skeptic raise an eyebrow. The striking pattern revealed in this visual representation is not only noteworthy but also serves as a testament to the undeniable entwinement of these disparate elements.
In conclusion, our exploration of the curious correlation between burglaries in North Dakota and the utilization of liquefied petroleum gas in Netherlands has uncovered a tapestry of interconnectedness that is as confounding as it is captivating. The evidence presented in this study challenges conventional notions of causality and beckons researchers to embrace the serendipitous discoveries that often lie hidden in the labyrinth of data.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The discovery of a statistically significant relationship between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands has unearthed a tapestry of interconnectedness that defies traditional academic boundaries. These findings lend support to the often overlooked potential for peculiarity in the web of statistical correlations. The unexpected nature of this association accentuates the need for scholars to remain open to embracing the whimsical and whimsy in their pursuit of knowledge.

The robust correlation coefficient of 0.6915982 that emerged from our analysis aligns with previous research that has explored unconventional pairings of crime and energy consumption. While traditionally, such investigations have focused on more conventional associations, our study provides empirical evidence that the connection between seemingly disparate elements, such as bumbling burglaries and boisterous butanes, warrants serious consideration. This correlation defies the notion of the "usual suspects" in empirical research and underscores the need for scholars to adopt a more expansive and eclectic mindset in their inquiries.

The r-squared value of 0.4783081 further solidifies the support for the relationship between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands. This substantial portion of explained variation challenges the boundaries of what is deemed a conceivable correlation and calls into question the boundaries of accepted scholarly investigation. Much like an unexpected plot twist in a novel, these results remind us of the unpredictable and capricious nature of statistical inquiry and the surprising connections that can emerge when examining seemingly unrelated phenomena.

In light of the p-value of less than 0.01, it is clear that the relationship between these two seemingly incongruous variables is not a mere happenstance or statistical artifact. This highlights the imperative for scholars to remain attuned to the potential for unanticipated correlations and to approach their analyses with a sense of intellectual playfulness. The statistical significance of this correlation beckons researchers to look beyond the confines of conventional wisdom and embrace the serendipitous discoveries that often lie hidden in the labyrinth of data.

In conclusion, the discovery of a significant correlation between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands challenges traditional notions of causality and illustrates the multilayered and enigmatic nature of statistical relationships. This revelatory connection serves as a whimsical reminder of the unexpected and fanciful webs that empirical data can weave, urging scholars to remain receptive to the unanticipated and to greet the peculiar correlations with curiosity and amusement.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Burglaries in North Dakota and Liquefied petroleum gas used in Netherlands. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands

[[ABSTRACT]]
This research seeks to unravel the peculiar relationship between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands. Utilizing data from FBI Criminal Justice Information Services and Energy Information Administration, our analysis reveals a surprising correlation coefficient of 0.6915982 and p < 0.01 for the period spanning from 1985 to 2022. The findings not only astound but also amuse, as one cannot help but marvel at the intertwining web of seemingly unrelated phenomena. Our study sheds light on the quirky connections that often elude traditional scholarly inquiry.

[[INTRDUCTION]]
The intersection of crime and energy consumption has long been a subject of interest within both the academic and law enforcement communities. However, the exploration of the connection between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands represents a rather curious foray into uncharted territory. The juxtaposition of these two seemingly disparate phenomena has raised eyebrows, piqued curiosity, and left many a researcher scratching their heads in puzzlement.
As the saying goes, "Truth is stranger than fiction," and indeed, the correlation uncovered in this study may just prove to be stranger than a work of fiction. The correlation coefficient of 0.6915982 and the statistically significant p-value of less than 0.01 have left us in a state of both bemusement and fascination. The robustness of this relationship between bumbling burglaries and boisterous butanes is truly nothing short of remarkable.
The primary aim of this investigation is to disentangle the enigmatic web of associations that underpin this unlikely pairing, and to shed light on the underlying mechanisms that give rise to such a peculiar correlation. While some may be tempted to dismiss these findings as mere statistical oddities, we believe that they merit closer examination. After all, as researchers, it is our duty to delve into the realms of the unexpected and the inexplicable.
The following sections will delve into the data sources, methodology, and findings, all the while maintaining a sense of academic rigor and scholarly inquiry. But do prepare yourself for the occasional surprise twist or ironic revelation, for this journey through the intricacies of bumbling burglaries and boisterous butanes promises to be anything but mundane.

[[RESULTS]]
The examination of the relationship between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands yielded some rather intriguing results. The correlation coefficient of 0.6915982 suggests a moderately strong positive association between these seemingly unrelated variables. This statistical connection between bumbling burglaries and boisterous butanes has captivated our attention, leaving us both flabbergasted and delighted by the unexpected nature of our findings.
The r-squared value of 0.4783081 indicates that approximately 47.83% of the variation in burglaries in North Dakota can be explained by the usage of liquefied petroleum gas in Netherlands. While this may not account for the entirety of the relationship, it certainly provides substantial insight into the dynamics at play. It seems that these variables, in their own peculiar way, dance a coordinated tango across time and space, defying conventional expectations and confounding conventional wisdom.
Furthermore, the p-value of less than 0.01 underscores the statistical significance of this correlation, reinforcing the notion that this connection between seemingly incongruous phenomena is not merely a figment of statistical noise. It appears that the gravitational pull between the fumbling furtive intruders of North Dakota and the spirited butanes of Netherlands is not to be taken lightly.
Finally, the scatterplot (Fig. 1) visually depicts the compelling relationship between burglaries in North Dakota and the usage of liquefied petroleum gas in Netherlands. The points on the plot align themselves in a manner that would make even the most avowed skeptic raise an eyebrow. The striking pattern revealed in this visual representation is not only noteworthy but also serves as a testament to the undeniable entwinement of these disparate elements.
In conclusion, our exploration of the curious correlation between burglaries in North Dakota and the utilization of liquefied petroleum gas in Netherlands has uncovered a tapestry of interconnectedness that is as confounding as it is captivating. The evidence presented in this study challenges conventional notions of causality and beckons researchers to embrace the serendipitous discoveries that often lie hidden in the labyrinth of data.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In wrapping up this investigation into the perplexing relationship between bumbling burglaries in North Dakota and the ebullient usage of liquefied petroleum gas in Netherlands, we find ourselves in a state of simultaneous amusement and contemplation. The robust correlation coefficient of 0.6915982 and the p-value of less than 0.01 have thrust this unlikely pairing into the spotlight, causing both eyebrows and statistical significance levels to rise. The results of this study not only raise questions but also elicit a sense of appreciation for the convoluted and quirky nature of the world we inhabit.

As we reflect on the enigmatic dance of these seemingly incongruous variables, it becomes clear that the intertwined fate of fumbling burglars and spirited butanes is not to be dismissed as mere happenstance. While some may find it tempting to relegate this correlation to the realm of statistical flukes, we cannot help but marvel at the intricacies that underpin this unlikely connection. The r-squared value of 0.4783081 provides a glimpse into the extent of the influence exerted by liquefied petroleum gas in Netherlands on the mischievous activities in North Dakota. It's almost as if the fates of these two entities are entangled in a cosmic game of cat and larcenous mouse.

The scatterplot, with its visually compelling depiction of the relationship between these variables, serves as a gentle reminder that reality often surpasses our wildest imaginations. The alignment of data points on this plot unfolds a narrative that is at once confounding and captivating, much like a riveting page-turner that leaves us both perplexed and enthralled. Indeed, the peculiar dynamics at play here beckon us to embrace the unexpected and to delve into the serendipitous revelations that lie hidden within the labyrinth of data.

In light of these findings, it is abundantly clear that the interaction between bumbling burglaries in North Dakota and boisterous butanes in Netherlands is not to be taken lightly. The statistically significant correlation uncovered in this study challenges traditional notions of causality and serves as a gentle reminder that the world of data holds surprises that are as plentiful as they are unpredictable.

It is with a mixture of amusement and intrigue that we conclude our exploration of this curious correlation, and we are left with a sense of wonder at the mysteries that persist within the annals of statistical inquiry. At the risk of sounding facetious, one might say that the relationship between these two phenomena is not merely a matter of locating stolen goods, but a figurative game of "hide and liquefy." In light of these findings, we assert that further research in this area is as unnecessary as a bicycle for a fish.

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 Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Crime and Cross-Cultural Conundrums

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 Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Quandaries and Curious Conundrums

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 Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands with an abstract of This research seeks to unravel the peculiar relationship between burglaries in North Dakota and the use of liquefied petroleum gas in Netherlands. Utilizing data from FBI Criminal Justice Information Services and Energy Information Administration, our analysis reveals a surprising correlation coefficient of 0.6915982 and p < 0.01 for the period spanning from 1985 to 2022. The findings not only astound but also amuse, as one cannot help but marvel at the intertwining web of seemingly unrelated phenomena. Our study sheds light on the quirky connections that often elude traditional scholarly inquiry.

ChatGPT:

Bumbling burglaries, Boisterous butanes, North Dakota, Netherlands, Liquefied petroleum gas, FBI Criminal Justice Information Services, Energy Information Administration, Correlation coefficient, Peculiar relationship, Quirky connections, Unrelated phenomena, Scholarly inquiry, Data analysis

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

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

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

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

Correlation r = 0.6915982 (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 = 0.4783081 (Coefficient of determination)
This means 47.8% of the change in the one variable (i.e., Liquefied petroleum gas used in Netherlands) is predictable based on the change in the other (i.e., Burglaries in North Dakota) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.5E-6.^Show 0.0000015228530423021190000000
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 0.69 in 0.00015% of random cases. Said differently, if you correlated 656,662 random variables^Note You don't actually need 656 thousand 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.

[ 0.48, 0.83 ] 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
Burglaries in North Dakota (Burglary rate)	427	385.1	455.4	437.7	358.9	426.6	372.8	391	373.2	324.5	350.7	309.2	358.8	356.4	368.8	325.9	340.1	353.8	309.3	320.6	321.9	409	361.7	364.2	375.1	296.5	359	346.3	411.5	371.7	435.5	429.9	390.2	361.7	346.5	417.6	399	357.9
Liquefied petroleum gas used in Netherlands (Million Barrels/Day)	92.5123	91.4411	97.6274	79.1721	77.137	67.4027	57.2575	63.388	61.6521	55.5753	52.8904	52.8306	57.5671	58.6959	51.589	47.2049	47.7315	44.0219	39.0438	51.9071	58.937	61.7918	55.3288	56.0519	52.5068	50	57.6767	40.9235	75.9699	100.896	109.471	87.6776	76.2411	91.6027	77.9096	79.0929	65.9507	67.2521

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([427,385.1,455.4,437.7,358.9,426.6,372.8,391,373.2,324.5,350.7,309.2,358.8,356.4,368.8,325.9,340.1,353.8,309.3,320.6,321.9,409,361.7,364.2,375.1,296.5,359,346.3,411.5,371.7,435.5,429.9,390.2,361.7,346.5,417.6,399,357.9,])
array_2 = np.array([92.5123,91.4411,97.6274,79.1721,77.137,67.4027,57.2575,63.388,61.6521,55.5753,52.8904,52.8306,57.5671,58.6959,51.589,47.2049,47.7315,44.0219,39.0438,51.9071,58.937,61.7918,55.3288,56.0519,52.5068,50,57.6767,40.9235,75.9699,100.896,109.471,87.6776,76.2411,91.6027,77.9096,79.0929,65.9507,67.2521,])
array_1_name = "Burglaries in North Dakota"
array_2_name = "Liquefied petroleum gas used in Netherlands"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Burglaries in North Dakota
Line chart for only Liquefied petroleum gas used in Netherlands
AI-generated correlation image
The spurious research paper: Bumbling Burglaries and Boisterous Butanes: A Bizarre Blend of North Dakota and Netherlands

View another random correlation

How fun was this correlation?

Cheers to you for rating this correlation!

Correlation ID: 1987 · Black Variable ID: 20112 · Red Variable ID: 24739


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