Spurious correlation #3,306 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The distance between Neptune and the Sun and the second variable is Burglaries in Vermont. 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 The distance between Neptune and the Sun and the second variable is Burglaries in Vermont. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Neptune cozied up to the Sun, it sent out some chill vibes that reached all the way to Vermont. The burglars, being sensitive to cosmic energies, just didn't feel like working in such a harmonious space. Plus, with Neptune's mystical powers at play, it created a foggy confusion for the burglars, making them forget what they came for in the first place. Just a celestial case of making the universe align for law-abiding citizens!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image that appears to be a scene from 'Star Wars' with Neptune slowly drifting away from the glowing sun in the background, its blue hues shimmering against the dark backdrop of space. In the foreground, depict a peaceful Vermont town with a row of houses bathed in warm sunlight, their front doors shut tight. The residents go about their day with smiles on their faces, and there is no sign of burglary. 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: The distance between Neptune and the Sun and Burglaries in Vermont. 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: Cute 2D animation Oragami Sci-fi fantacy Low poly An image that looks like it is a scene from 'Star Wars'
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 The distance between Neptune and the Sun and Burglaries in Vermont, in the following situation: As Neptune moved closer, its gravitational pull weakened, creating less "neptunatic" energy for mischief, thus reducing the urge for burglary in Vermont. The diminishing distance literally "stole" the motivation for thievery, leading to a "safe" decrease in criminal activity.. Keep the description simple.
ChatGPT: In the distance, Neptune slowly drifts away from the glowing sun, its blue hues shimmering against the dark backdrop of space. Meanwhile, in a peaceful Vermont town, a row of houses stands bathed in warm sunlight. The front doors are shut tight, and there are smiles on the faces of the residents as they go about their day, with no sign of burglary.

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 the distance, Neptune slowly drifts away from the glowing sun, its blue hues shimmering against the dark backdrop of space. Meanwhile, in a peaceful Vermont town, a row of houses stands bathed in warm sunlight. The front doors are shut tight, and there are smiles on the faces of the residents as they go about their day, with no sign of burglary. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that appears to be a scene from 'Star Wars' with Neptune slowly drifting away from the glowing sun in the background, its blue hues shimmering against the dark backdrop of space. In the foreground, depict a peaceful Vermont town with a row of houses bathed in warm sunlight, their front doors shut tight. The residents go about their day with smiles on their faces, and there is no sign of burglary.

*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 The distance between Neptune and the Sun caused Burglaries in Vermont to decrease.

AI academic paper

(Because p < 0.01)

When Neptune's Away, Burglars Will Play: A Stellar Connection to the Rise in Burglaries in Vermont

The Interstellar Journal of Criminal Astronomy

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 The distance between Neptune and the Sun and Burglaries in Vermont. Make lots of 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]]
When Neptune's Away, Burglars Will Play: A Stellar Connection to the Rise in Burglaries in Vermont

[[ABSTRACT]]
This research paper presents the findings of a peculiar correlation between the distance between Neptune and the Sun and the prevalence of burglaries in Vermont. Utilizing data from Astropy for the planetary positions and FBI Criminal Justice Information Services for burglary rates, a correlation coefficient of 0.9261749 and p < 0.01 for the period from 1985 to 2022 was established. The unexpected link between a distant ice giant and earthly criminal activity prompts a reevaluation of the factors influencing criminal behavior. This study humorously explores the potential cosmic impact on the behavior of burglars and highlights the importance of considering astronomical factors in criminological research.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between celestial bodies and human behavior has long been a subject of fascination and speculation. From astrology to lunar phases, there is a rich tradition of connecting the movements of the heavens with the lives of those on Earth. However, in the realm of scientific inquiry, the notion that the distance between Neptune and the Sun could have any bearing on criminal activity may seem, at first glance, as fantastical as a science fiction plot.
But, lo and behold, this study delves into the unexpected and rather peculiar correlation between Neptune's distant orbit and the incidence of burglaries in the state of Vermont. It appears that when Neptune decides to take a prolonged spin around the Sun, the mischievous urges of burglars in Vermont surge. The statistical evidence for this correlation will indeed make you do a double take, possibly followed by a comedic, exaggerated eye-roll.
Given the notorious frosty and enigmatic nature of Neptune, one might be left scratching their head in genuine bewilderment. How could a frigid and distant ice giant, situated some 2.7 billion miles away, possibly influence the criminal inclinations of individuals in the Green Mountain State? It seems that in the vast cosmic dance of planets and stars, Neptune has decided to play a role in the criminal pursuits of certain earthly mischief-makers.
This study aims to unravel this bizarre connection and contemplate the implications of our findings. Is there a cosmic code that influences whether burglars decide to take action, or is it simply a quirk of statistical fate? Strap in for a riveting journey through the cosmos and the criminal underworld, as we endeavor to shed light on this unlikely linkage.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al. (2010)," the authors find a positive correlation between the distance of Neptune from the Sun and an increase in burglaries in Vermont. The study provides a comprehensive analysis of planetary positions and crime data, suggesting a potential association between celestial mechanics and criminal behavior. The authors propose that as Neptune drifts farther away from the Sun, there is a corresponding surge in the audacious exploits of burglars within the boundaries of Vermont.

Doe and Jones (2015) further investigate this intriguing connection, offering a nuanced exploration of the temporal patterns in both Neptune's orbit and burglary rates in Vermont. Their findings corroborate the notion that Neptune's celestial wanderings may indeed exert a curious influence on the criminal proclivities of individuals within the state.

The link between planetary positions and criminal activity prompts a reconsideration of traditional criminological frameworks. Drawing inspiration from non-fiction works such as "The Planets" by Dava Sobel, "Astrophysics for People in a Hurry" by Neil deGrasse Tyson, and "The Secret Influence of the Moon" by Louise McWhirter, we are reminded of the enduring fascination with celestial bodies and their potential impact on human affairs.

Turning to fictional literature, the works of Isaac Asimov, Arthur C. Clarke, and Philip K. Dick offer speculative narratives that blur the boundaries between the cosmic and the terrestrial. Could it be that celestial events, including the position of Neptune, hold a sway over human behavior worthy of exploration in a criminological context?

In a departure from traditional scholarly sources, this investigation extends to unlikely arenas of inquiry. As the authors sought to cast a wide net in the quest for understanding, an exhaustive review of the backs of shampoo bottles was undertaken in pursuit of cosmic insights. Although the veracity of data gleaned from such unconventional sources remains subject to scrutiny, the study remains open to the possibility of unexpected revelations lurking behind the glossy labels of everyday toiletries.

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 The distance between Neptune and the Sun and Burglaries in Vermont. Make lots of 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]]
When Neptune's Away, Burglars Will Play: A Stellar Connection to the Rise in Burglaries in Vermont

[[ABSTRACT]]
This research paper presents the findings of a peculiar correlation between the distance between Neptune and the Sun and the prevalence of burglaries in Vermont. Utilizing data from Astropy for the planetary positions and FBI Criminal Justice Information Services for burglary rates, a correlation coefficient of 0.9261749 and p < 0.01 for the period from 1985 to 2022 was established. The unexpected link between a distant ice giant and earthly criminal activity prompts a reevaluation of the factors influencing criminal behavior. This study humorously explores the potential cosmic impact on the behavior of burglars and highlights the importance of considering astronomical factors in criminological research.

[[LITERATURE REVIEW]]
In "Smith et al. (2010)," the authors find a positive correlation between the distance of Neptune from the Sun and an increase in burglaries in Vermont. The study provides a comprehensive analysis of planetary positions and crime data, suggesting a potential association between celestial mechanics and criminal behavior. The authors propose that as Neptune drifts farther away from the Sun, there is a corresponding surge in the audacious exploits of burglars within the boundaries of Vermont.
Doe and Jones (2015) further investigate this intriguing connection, offering a nuanced exploration of the temporal patterns in both Neptune's orbit and burglary rates in Vermont. Their findings corroborate the notion that Neptune's celestial wanderings may indeed exert a curious influence on the criminal proclivities of individuals within the state.
The link between planetary positions and criminal activity prompts a reconsideration of traditional criminological frameworks. Drawing inspiration from non-fiction works such as "The Planets" by Dava Sobel, "Astrophysics for People in a Hurry" by Neil deGrasse Tyson, and "The Secret Influence of the Moon" by Louise McWhirter, we are reminded of the enduring fascination with celestial bodies and their potential impact on human affairs.
Turning to fictional literature, the works of Isaac Asimov, Arthur C. Clarke, and Philip K. Dick offer speculative narratives that blur the boundaries between the cosmic and the terrestrial. Could it be that celestial events, including the position of Neptune, hold a sway over human behavior worthy of exploration in a criminological context?
In a departure from traditional scholarly sources, this investigation extends to unlikely arenas of inquiry. As the authors sought to cast a wide net in the quest for understanding, an exhaustive review of the backs of shampoo bottles was undertaken in pursuit of cosmic insights. Although the veracity of data gleaned from such unconventional sources remains subject to scrutiny, the study remains open to the possibility of unexpected revelations lurking behind the glossy labels of everyday toiletries.

[[RESULTS]]
The statistical analysis of the data revealed a remarkably strong correlation between the distance of Neptune from the Sun and the incidence of burglaries in Vermont. The correlation coefficient of 0.9261749 indicated a powerful relationship between these seemingly unrelated variables. Furthermore, the r-squared value of 0.8578000 suggested that approximately 85.78% of the variance in burglary rates in Vermont could be explained by the distance of Neptune from the Sun. The p-value of less than 0.01 provided strong evidence against the null hypothesis and supported the robustness of the correlation.
The scatterplot (Fig. 1) visually depicts the striking relationship between the two variables, with Neptune's distance from the Sun consistently corresponding to fluctuations in the burglary rates in Vermont. One might say that the burglars in Vermont were truly "over the moon" whenever Neptune decided to take a extended vacation from the Sun.
Upon pondering these findings, one cannot help but marvel at the absurdity of the cosmic influence on criminal behavior. It seems that when Neptune veers further from the Sun, burglars in Vermont are inclined to "break and enter" into action. This unforeseen resonance between an icy planet and earthly crime rates leaves one to wonder whether celestial bodies might hold the key to unravelling criminal motivations.
The implications of this correlation extend beyond the realm of criminology and evoke a sense of cosmic mystery. Perhaps Neptune's elusive allure stimulates a peculiar alignment of the stars that sparks mischievous intentions among burglars. Such an astronomical twist in the tale of criminal activity reminds us that in the vast expanse of the universe, even the most unfathomable connections may come to light.
In conclusion, this study sheds an intriguing, albeit unconventional, light on the interplay between celestial movements and human behavior. While the causality behind this peculiar correlation remains enigmatic, the statistical evidence for the influence of Neptune's distance from the Sun on burglary rates in Vermont prompts a rethinking of traditional perspectives on criminal behavior. It behooves us to consider the cosmic dance of planets and stars in our understanding of earthly phenomena, reminding us that the universe may hold some out-of-this-world explanations for terrestrial occurrences.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study provide intriguing support for the previous research conducted by Smith et al. (2010) and Doe and Jones (2015) in uncovering the peculiar connection between Neptune's distance from the Sun and the occurrence of burglaries in Vermont. The statistical analysis has solidified the notion that as Neptune ventures farther away from the Sun, an increase in burglary rates within the boundaries of Vermont is discernible, reiterating the potential influence of celestial mechanics on criminal behavior.

The positive correlation coefficient of 0.9261749 aligns with the conclusions drawn by Smith et al. (2010), who originally brought attention to this unfathomable association. This reaffirmation supports the assertion that Neptune's celestial wanderings may indeed exert a curious influence on the audacious exploits of burglars. Furthermore, the robustness of the correlation, as indicated by the low p-value of less than 0.01, underscores the validity of the relationship uncovered in prior research and emphasizes the significance of embracing unconventional perspectives in the realm of criminological inquiry.

The literature review humorously delved into the unlikely juxtaposition of nonfiction works exploring celestial bodies and speculative narratives blurring the boundaries between the cosmic and the terrestrial. Despite the whimsical nature of these explorations, the empirical evidence presented in this study lends credence to the thought-provoking ideas proposed in those scholarly and fictional works. It appears that the unexpected resonance discovered in this investigation reinforces the notion that celestial events, including the position of Neptune, hold a sway over human behavior worthy of serious consideration.

The graphical depiction of the correlation between Neptune's distance from the Sun and burglary rates in Vermont, as illustrated in the scatterplot (Fig. 1), effectively complements the empirical findings, visually encapsulating the surprising relationship between these seemingly disparate variables. The scatterplot serves as a compelling visual testament to the statistical significance of the correlation, transcending the boundaries of traditional criminological analyses by offering a whimsical portrayal of the cosmic dance and its earthly repercussions.

As the discussion turns toward pondering the cosmic influence on criminal behavior, one is reminded of the peculiar alignment of the stars that appears to coincide with mischievous intentions among burglars. The unexpected revelation of this correlation suggests that the universe holds out-of-this-world explanations for terrestrial occurrences, encouraging a broader consideration of celestial phenomena in our understanding of earthly manifestations. This study, while lighthearted and unconventional, prompts a reevaluation of the factors influencing criminal behavior, challenging researchers and scholars to embrace the cosmic mystery and the potential influence it may have on human conduct.

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 The distance between Neptune and the Sun and Burglaries in Vermont. Make lots of 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]]
When Neptune's Away, Burglars Will Play: A Stellar Connection to the Rise in Burglaries in Vermont

[[ABSTRACT]]
This research paper presents the findings of a peculiar correlation between the distance between Neptune and the Sun and the prevalence of burglaries in Vermont. Utilizing data from Astropy for the planetary positions and FBI Criminal Justice Information Services for burglary rates, a correlation coefficient of 0.9261749 and p < 0.01 for the period from 1985 to 2022 was established. The unexpected link between a distant ice giant and earthly criminal activity prompts a reevaluation of the factors influencing criminal behavior. This study humorously explores the potential cosmic impact on the behavior of burglars and highlights the importance of considering astronomical factors in criminological research.

[[INTRDUCTION]]
The relationship between celestial bodies and human behavior has long been a subject of fascination and speculation. From astrology to lunar phases, there is a rich tradition of connecting the movements of the heavens with the lives of those on Earth. However, in the realm of scientific inquiry, the notion that the distance between Neptune and the Sun could have any bearing on criminal activity may seem, at first glance, as fantastical as a science fiction plot.
But, lo and behold, this study delves into the unexpected and rather peculiar correlation between Neptune's distant orbit and the incidence of burglaries in the state of Vermont. It appears that when Neptune decides to take a prolonged spin around the Sun, the mischievous urges of burglars in Vermont surge. The statistical evidence for this correlation will indeed make you do a double take, possibly followed by a comedic, exaggerated eye-roll.
Given the notorious frosty and enigmatic nature of Neptune, one might be left scratching their head in genuine bewilderment. How could a frigid and distant ice giant, situated some 2.7 billion miles away, possibly influence the criminal inclinations of individuals in the Green Mountain State? It seems that in the vast cosmic dance of planets and stars, Neptune has decided to play a role in the criminal pursuits of certain earthly mischief-makers.
This study aims to unravel this bizarre connection and contemplate the implications of our findings. Is there a cosmic code that influences whether burglars decide to take action, or is it simply a quirk of statistical fate? Strap in for a riveting journey through the cosmos and the criminal underworld, as we endeavor to shed light on this unlikely linkage.

[[RESULTS]]
The statistical analysis of the data revealed a remarkably strong correlation between the distance of Neptune from the Sun and the incidence of burglaries in Vermont. The correlation coefficient of 0.9261749 indicated a powerful relationship between these seemingly unrelated variables. Furthermore, the r-squared value of 0.8578000 suggested that approximately 85.78% of the variance in burglary rates in Vermont could be explained by the distance of Neptune from the Sun. The p-value of less than 0.01 provided strong evidence against the null hypothesis and supported the robustness of the correlation.
The scatterplot (Fig. 1) visually depicts the striking relationship between the two variables, with Neptune's distance from the Sun consistently corresponding to fluctuations in the burglary rates in Vermont. One might say that the burglars in Vermont were truly "over the moon" whenever Neptune decided to take a extended vacation from the Sun.
Upon pondering these findings, one cannot help but marvel at the absurdity of the cosmic influence on criminal behavior. It seems that when Neptune veers further from the Sun, burglars in Vermont are inclined to "break and enter" into action. This unforeseen resonance between an icy planet and earthly crime rates leaves one to wonder whether celestial bodies might hold the key to unravelling criminal motivations.
The implications of this correlation extend beyond the realm of criminology and evoke a sense of cosmic mystery. Perhaps Neptune's elusive allure stimulates a peculiar alignment of the stars that sparks mischievous intentions among burglars. Such an astronomical twist in the tale of criminal activity reminds us that in the vast expanse of the universe, even the most unfathomable connections may come to light.
In conclusion, this study sheds an intriguing, albeit unconventional, light on the interplay between celestial movements and human behavior. While the causality behind this peculiar correlation remains enigmatic, the statistical evidence for the influence of Neptune's distance from the Sun on burglary rates in Vermont prompts a rethinking of traditional perspectives on criminal behavior. It behooves us to consider the cosmic dance of planets and stars in our understanding of earthly phenomena, reminding us that the universe may hold some out-of-this-world explanations for terrestrial occurrences.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

The results of this study reveal a stellar connection that is truly out of this world. It appears that when Neptune's distance from the Sun increases, burglars in Vermont experience a surge of criminal activity, as if they were taking cues from a celestial criminal mastermind. This unexpected correlation between a distant ice giant and earthly burglary rates is both mystifying and comical. It seems that even in the vast expanse of the cosmos, the mischievous inclinations of burglars can't help but be influenced by the dance of the planets.

The statistical evidence for this correlation is as clear as a cloudless night sky. The robust correlation coefficient and the p-value of less than 0.01 leave little room for doubt. Indeed, it appears that when Neptune is feeling particularly distant, the burglars in Vermont are feeling particularly bold. It's as if the planet's gravitational pull is tugging at their criminal impulses, leading them to "break and enter" with an otherworldly enthusiasm.

While some may find it hard to believe that a planet situated billions of miles away could have any bearing on earthly criminal behavior, the numbers don't lie. The scatterplot, with its unmistakable trend line, provides a visual representation of this curious connection, leaving no room for skepticism. It's enough to make one contemplate whether Neptune is issuing some kind of cosmic invitation to the burglars of Vermont, beckoning them to partake in their extraterrestrial escapades.

In light of these findings, it is clear that the cosmic dance of planets and stars has a part to play in the earthly antics of burglars. However, this research presents a conclusive evidence and further inquiry in this area is unnecessary. The data speaks for itself, and it's time to let this peculiar cosmic caper take its place in the annals of academic curiosities. After all, there's only so much celestial influence one can "planet" for in the realm of criminology.

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 When Neptune's Away, Burglars Will Play: A Stellar Connection to the Rise in Burglaries in Vermont. Respond only with the name of a fictional academic journal.

ChatGPT:

The Interstellar Journal of Criminal Astronomy

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 When Neptune's Away, Burglars Will Play: A Stellar Connection to the Rise in Burglaries in Vermont. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Celestial Criminology Research

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled When Neptune's Away, Burglars Will Play: A Stellar Connection to the Rise in Burglaries in Vermont with an abstract of This research paper presents the findings of a peculiar correlation between the distance between Neptune and the Sun and the prevalence of burglaries in Vermont. Utilizing data from Astropy for the planetary positions and FBI Criminal Justice Information Services for burglary rates, a correlation coefficient of 0.9261749 and p < 0.01 for the period from 1985 to 2022 was established. The unexpected link between a distant ice giant and earthly criminal activity prompts a reevaluation of the factors influencing criminal behavior. This study humorously explores the potential cosmic impact on the behavior of burglars and highlights the importance of considering astronomical factors in criminological research.

ChatGPT:

Neptune distance, Sun, burglaries, Vermont, correlation, Astropy, planetary positions, FBI Criminal Justice Information Services, burglary rates, correlation coefficient, p-value, 1985-2022, ice giant, criminal behavior, cosmic impact, criminological research

*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

The distance between Neptune and the Sun
Detailed data title: The average distance between Neptune and the Sun as measured on the first day of each month
Source: Caclculated using Astropy
Additional Info: ^{See full details} I wrote a Python script using Astropy to calculate the distance between the named planets on the first day of each month for every year.

See what else correlates with The distance between Neptune and the Sun

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

Correlation r = 0.9261749 (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 = 0.8578000 (Coefficient of determination)
This means 85.8% of the change in the one variable (i.e., Burglaries in Vermont) is predictable based on the change in the other (i.e., The distance between Neptune and the Sun) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.02E-17.^Show 0.0000000000000000802410355539
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 0.93 in 8.02E-15% of random cases. Said differently, if you correlated 12,462,451,326,768,756 random variables^Note You don't actually need 12 quadrillion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 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.

[ 0.86, 0.96 ] 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
The distance between Neptune and the Sun (Planetary distance (AU))	30.2535	30.2445	30.2347	30.2248	30.2152	30.2064	30.1985	30.1912	30.1844	30.1774	30.1698	30.161	30.1509	30.1396	30.1273	30.1147	30.1024	30.0908	30.0803	30.071	30.0627	30.055	30.0473	30.0391	30.0301	30.02	30.0091	29.9976	29.9861	29.9751	29.9652	29.9565	29.9491	29.9427	29.9369	29.931	29.9246	29.9174
Burglaries in Vermont (Burglary rate)	973.8	949.2	1110.4	1096.8	1029.1	1087.3	1020.1	825.6	874.3	736.9	760.9	673	613.1	671.1	595.7	575	513.9	566	487.1	552.9	511.7	551.8	515.1	565.8	558.3	534.9	612.5	667.6	534.7	333.8	324.9	302.2	311.4	239.6	206.1	154.2	181.8	152.1

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.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

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([30.2535,30.2445,30.2347,30.2248,30.2152,30.2064,30.1985,30.1912,30.1844,30.1774,30.1698,30.161,30.1509,30.1396,30.1273,30.1147,30.1024,30.0908,30.0803,30.071,30.0627,30.055,30.0473,30.0391,30.0301,30.02,30.0091,29.9976,29.9861,29.9751,29.9652,29.9565,29.9491,29.9427,29.9369,29.931,29.9246,29.9174,])
array_2 = np.array([973.8,949.2,1110.4,1096.8,1029.1,1087.3,1020.1,825.6,874.3,736.9,760.9,673,613.1,671.1,595.7,575,513.9,566,487.1,552.9,511.7,551.8,515.1,565.8,558.3,534.9,612.5,667.6,534.7,333.8,324.9,302.2,311.4,239.6,206.1,154.2,181.8,152.1,])
array_1_name = "The distance between Neptune and the Sun"
array_2_name = "Burglaries in Vermont"

# 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 The distance between Neptune and the Sun
Line chart for only Burglaries in Vermont
AI-generated correlation image
The spurious research paper: When Neptune's Away, Burglars Will Play: A Stellar Connection to the Rise in Burglaries in Vermont

View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!

Correlation ID: 3306 · Black Variable ID: 1932 · Red Variable ID: 20124


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