Spurious correlation #1,218 · 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 Oregon and the second variable is Viewership count for Days of Our Lives. The chart goes from 1985 to 2021, 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 Oregon and the second variable is Viewership count for Days of Our Lives. The chart goes from 1985 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As burglaries decreased in Oregon, it meant that there were fewer opportunities for the infamous Salem Stalker to strike. With less crime to contend with, the characters in Days of Our Lives found themselves at a loss for dramatic, suspenseful storylines. After all, what's a soap opera without a good old-fashioned whodunit or a stolen family heirloom? With the decrease in burglaries, the show's writers struggled to keep the plot as gripping, leading to a decline in viewership count.

^{Show image generation prompt} Model: dalle-3
Prompt: The prompt is: [ Cyber folk ] style image depicting a cozy living room where a family sits around the television, engrossed in an episode of "Days of Our Lives." On the coffee table, there are scattered detective novels and crime-solving board games. Outside, a neighborhood watch sign is visible, indicating a decrease in burglaries. As a result, the family seems less animated, and the children are less engaged in the show, as their imaginations have been sparked by the thrill of solving fictional mysteries alongside the characters. Let me know if there are any changes you'd like to make! The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

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

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: Fewer burglaries led to lower Days of Our Lives viewership due to decreased amateur detective inspiration, leaving viewers with less excitement and mystery in their own lives.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: 3D Pixar Style Cubism Cyber folk Futuristic Steampunk
ChatGPT: Cyber folk

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. Fewer burglaries led to lower Days of Our Lives viewership due to decreased amateur detective inspiration, leaving viewers with less excitement and mystery in their own lives.
ChatGPT: In a cozy living room, a family sits around the television, engrossed in an episode of "Days of Our Lives." On the coffee table, there are scattered detective novels and crime-solving board games. Outside, a neighborhood watch sign is visible, indicating a decrease in burglaries. As a result, the family seems less animated, and the children are less engaged in the show, as their imaginations have been sparked by the thrill of solving fictional mysteries alongside the characters.

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: [ Cyber folk ] and depicting this scene: In a cozy living room, a family sits around the television, engrossed in an episode of "Days of Our Lives." On the coffee table, there are scattered detective novels and crime-solving board games. Outside, a neighborhood watch sign is visible, indicating a decrease in burglaries. As a result, the family seems less animated, and the children are less engaged in the show, as their imaginations have been sparked by the thrill of solving fictional mysteries alongside the characters. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: The prompt is: [ Cyber folk ] style image depicting a cozy living room where a family sits around the television, engrossed in an episode of "Days of Our Lives." On the coffee table, there are scattered detective novels and crime-solving board games. Outside, a neighborhood watch sign is visible, indicating a decrease in burglaries. As a result, the family seems less animated, and the children are less engaged in the show, as their imaginations have been sparked by the thrill of solving fictional mysteries alongside the characters. Let me know if there are any changes you'd like to make!

*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 Oregon caused Viewership count for Days of Our Lives to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)

The Days of Our Burglaries: An Examination of the Correlation Between Burglaries in Oregon and Viewership Count for Days of Our Lives

Journal of Strange Correlations and Odd Discoveries

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Burglaries in Oregon and Viewership count for Days of Our Lives. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
The Days of Our Burglaries: An Examination of the Correlation Between Burglaries in Oregon and Viewership Count for Days of Our Lives

[[ABSTRACT]]
In this paper, we present a comprehensive analysis of the intriguing relationship between the frequency of burglaries in Oregon and the viewership count for the long-running soap opera, Days of Our Lives. While this research may sound like a soap opera itself, our data-driven investigation uncovers some unexpected twists and turns.

Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we meticulously examined burglary rates in Oregon and the viewership count for Days of Our Lives from 1985 to 2021. Our findings reveal a remarkably strong correlation coefficient of 0.9335386, with a p-value < 0.01. This statistically significant relationship provides compelling evidence of the connection between these seemingly unrelated phenomena – though we must resist the urge to "break in" any exaggerated claims about causation just yet.

Surprisingly, our analysis suggests that as the viewership count for Days of Our Lives fluctuates, so do the burglary rates in Oregon. These findings prompt both a revisiting of assumptions about the social and psychological factors influencing criminal behavior, as well as a consideration of the potential impact of soap operas on community security. Perhaps these compelling narratives are not only captivating audiences but also affecting crime rates – a true "plot twist" in the realm of societal influences.

In conclusion, our research sheds new light on the interplay between popular culture and criminal activity, opening doors to further investigations into the unexpected connections that may "break in" on our conventional understanding of human behavior. As we continue to unravel the complex web of influences shaping our world, this study underscores the importance of delving into even the most seemingly frivolous correlations – after all, when it comes to research, sometimes truth is stranger than fiction.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the world of academia continues its quest to uncover the underlying factors that shape human behavior, certain correlations may seem to be taken straight out of a soap opera script. In this paper, we present a study that delves into the curious relationship between burglaries in Oregon and the viewership count for the long-running soap opera, Days of Our Lives. While the connection between crime and daytime television may sound like the start of a bad joke, our data-driven analysis leads to some unexpectedly compelling findings.
So, a burglar walks into Oregon and starts watching Days of Our Lives... No, this isn't a setup for a punchline; it's the basis for our research. With a statistically significant correlation coefficient and a p-value that would make any statistician's heart flutter, our investigation isn't merely a "soap opera" of speculation – it's a bona fide examination of an intriguing societal phenomenon.
It's no secret that correlations don't always imply causation, but the strength of the relationship we observed between burglaries and Days of Our Lives viewership raises eyebrows much like a dramatic reveal on the show. We resist the temptation to jump to conclusions, though we can't help but tease out the possibilities with a pun or two along the way.
As we embark on our analysis, it becomes evident that the flux in Days of Our Lives viewership corresponds to fluctuations in burglary rates in Oregon. It's almost as if there's a clandestine subplot at play, with soap operas and crime rates engaging in a dramatic dance of influence. This unexpected connection prompts us to reconsider the role of television narratives in shaping behaviors – surely a storyline worthy of a daytime drama.
In bringing our investigation to a conclusion, we find ourselves faced with the tantalizing prospect of uncovering the ways in which seemingly incongruent cultural phenomena intertwine. Our study invites further exploration into the unforeseen connections that may "break in" on our understanding of human conduct, proving that sometimes, in the realm of research, truth truly is stranger than fiction – all while delivering more plot twists than a daytime soap opera.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Smith, Doe, and Jones have each contributed valuable insights into the field of criminology, examining the multifaceted motivations behind burglary rates. In "Criminal Behavior and Societal Influences," Smith delves into the complex interplay of environmental, economic, and social factors in shaping criminal behavior. Similarly, Doe's work, "The Psychology of Theft," offers a psychological perspective on the underlying mechanisms driving individuals to engage in illegal activities. In a separate study, Jones explores the impact of media consumption on societal attitudes and behaviors, shedding light on the potential influence of popular culture on criminal activity.

But what happens when we throw a daytime soap opera into the mix? As it turns out, the answer isn't just another episode of "Days of Our Lives," but a surprising correlation worthy of a dramatic plot twist.

In "Soap Operas and Societal Dynamics," the authors examine the enduring popularity of daytime dramas and their cultural impact. While the focus of the study is not on criminal behavior per se, it provides a valuable foundation for understanding the broader influence of soap operas on societal norms and behaviors. Who knew that tuning in to the latest dramatic developments in Salem could have implications for the safety of our communities?

Furthermore, "The Influence of Television on Viewership Habits" presents a comprehensive analysis of the ways in which television programming can shape viewers' preferences and habits. While its primary focus is on consumer behavior, it inadvertently offers insight into the potential ripple effects of television content on broader social dynamics. After all, who can resist the allure of turning on the TV and getting engrossed in the lives of fictional characters for hours on end?

As part of our rigorous research methodology, we made sure to watch a healthy dose of related TV shows for context. Our thorough investigative efforts included immersing ourselves in the worlds of "The Young and the Restless," "General Hospital," and "All My Children." It's a tough job, but someone has to do it – all in the name of scientific inquiry, of course. Who knew that binge-watching soap operas could be classified as academic research? It all makes sense when you're meticulously analyzing the societal implications of daytime drama, doesn't it?

In addition to our TV escapades, we turn to the works of fiction that hold the theme of crime and intrigue close to their pages. From mysteries and thrillers to crime dramas, each novel offers a glimpse into the enthralling world of criminality and suspense. Titles like "The Girl with the Dragon Tattoo," "Gone Girl," and "The Da Vinci Code" provide a thrilling backdrop for our exploration of the unexpected correlations lurking beneath the surface of seemingly unrelated phenomena. Because what's research without a bit of mystery and suspense, right?

But let's not overlook the impact of non-fiction works that have delved into the complex web of criminal behavior and societal influences. "Freakonomics" and "Blink" offer thought-provoking perspectives on the hidden forces shaping human decision-making, guiding us through a labyrinth of intriguing insights. Who would have thought that the intricacies of human behavior could be so captivating? It's almost as enthralling as trying to unravel the mysteries of daytime soap opera viewership and burglary rates.

Stay tuned for the next episode, where we delve into the methodology behind our investigation, unraveling the enigmatic connections between seemingly disparate realms of human activity. Get ready for more unexpected twists and turns than a soap opera plot – because when it comes to researching the unexpected, we're always ready to "break in" some unanticipated findings.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Burglaries in Oregon and Viewership count for Days of Our Lives. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
The Days of Our Burglaries: An Examination of the Correlation Between Burglaries in Oregon and Viewership Count for Days of Our Lives

[[ABSTRACT]]
In this paper, we present a comprehensive analysis of the intriguing relationship between the frequency of burglaries in Oregon and the viewership count for the long-running soap opera, Days of Our Lives. While this research may sound like a soap opera itself, our data-driven investigation uncovers some unexpected twists and turns.

Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we meticulously examined burglary rates in Oregon and the viewership count for Days of Our Lives from 1985 to 2021. Our findings reveal a remarkably strong correlation coefficient of 0.9335386, with a p-value < 0.01. This statistically significant relationship provides compelling evidence of the connection between these seemingly unrelated phenomena – though we must resist the urge to "break in" any exaggerated claims about causation just yet.

Surprisingly, our analysis suggests that as the viewership count for Days of Our Lives fluctuates, so do the burglary rates in Oregon. These findings prompt both a revisiting of assumptions about the social and psychological factors influencing criminal behavior, as well as a consideration of the potential impact of soap operas on community security. Perhaps these compelling narratives are not only captivating audiences but also affecting crime rates – a true "plot twist" in the realm of societal influences.

In conclusion, our research sheds new light on the interplay between popular culture and criminal activity, opening doors to further investigations into the unexpected connections that may "break in" on our conventional understanding of human behavior. As we continue to unravel the complex web of influences shaping our world, this study underscores the importance of delving into even the most seemingly frivolous correlations – after all, when it comes to research, sometimes truth is stranger than fiction.

[[LITERATURE REVIEW]]
Smith, Doe, and Jones have each contributed valuable insights into the field of criminology, examining the multifaceted motivations behind burglary rates. In "Criminal Behavior and Societal Influences," Smith delves into the complex interplay of environmental, economic, and social factors in shaping criminal behavior. Similarly, Doe's work, "The Psychology of Theft," offers a psychological perspective on the underlying mechanisms driving individuals to engage in illegal activities. In a separate study, Jones explores the impact of media consumption on societal attitudes and behaviors, shedding light on the potential influence of popular culture on criminal activity.
But what happens when we throw a daytime soap opera into the mix? As it turns out, the answer isn't just another episode of "Days of Our Lives," but a surprising correlation worthy of a dramatic plot twist.
In "Soap Operas and Societal Dynamics," the authors examine the enduring popularity of daytime dramas and their cultural impact. While the focus of the study is not on criminal behavior per se, it provides a valuable foundation for understanding the broader influence of soap operas on societal norms and behaviors. Who knew that tuning in to the latest dramatic developments in Salem could have implications for the safety of our communities?
Furthermore, "The Influence of Television on Viewership Habits" presents a comprehensive analysis of the ways in which television programming can shape viewers' preferences and habits. While its primary focus is on consumer behavior, it inadvertently offers insight into the potential ripple effects of television content on broader social dynamics. After all, who can resist the allure of turning on the TV and getting engrossed in the lives of fictional characters for hours on end?
As part of our rigorous research methodology, we made sure to watch a healthy dose of related TV shows for context. Our thorough investigative efforts included immersing ourselves in the worlds of "The Young and the Restless," "General Hospital," and "All My Children." It's a tough job, but someone has to do it – all in the name of scientific inquiry, of course. Who knew that binge-watching soap operas could be classified as academic research? It all makes sense when you're meticulously analyzing the societal implications of daytime drama, doesn't it?
In addition to our TV escapades, we turn to the works of fiction that hold the theme of crime and intrigue close to their pages. From mysteries and thrillers to crime dramas, each novel offers a glimpse into the enthralling world of criminality and suspense. Titles like "The Girl with the Dragon Tattoo," "Gone Girl," and "The Da Vinci Code" provide a thrilling backdrop for our exploration of the unexpected correlations lurking beneath the surface of seemingly unrelated phenomena. Because what's research without a bit of mystery and suspense, right?
But let's not overlook the impact of non-fiction works that have delved into the complex web of criminal behavior and societal influences. "Freakonomics" and "Blink" offer thought-provoking perspectives on the hidden forces shaping human decision-making, guiding us through a labyrinth of intriguing insights. Who would have thought that the intricacies of human behavior could be so captivating? It's almost as enthralling as trying to unravel the mysteries of daytime soap opera viewership and burglary rates.
Stay tuned for the next episode, where we delve into the methodology behind our investigation, unraveling the enigmatic connections between seemingly disparate realms of human activity. Get ready for more unexpected twists and turns than a soap opera plot – because when it comes to researching the unexpected, we're always ready to "break in" some unanticipated findings.

[[RESULTS]]
The analysis of the data on burglaries in Oregon and the viewership count for Days of Our Lives from 1985 to 2021 revealed a striking correlation coefficient of 0.9335386. This strong positive correlation indicates that as the viewership count for Days of Our Lives fluctuated over the years, burglary rates in Oregon also showed corresponding shifts. It's as if the burglars were waiting with bated breath to see who would be stricken with amnesia or have a secret twin next.
The r-squared value of 0.8714943 further solidifies the robustness of the relationship between these two seemingly unrelated variables. This means that a striking 87.15% of the variation in burglary rates in Oregon can be explained by the viewership count for Days of Our Lives. It's almost as if the dramatic tension in the soap opera is mirrored in the ebb and flow of criminal activity – talk about life imitating art!
The p-value of less than 0.01 indicates that the probability of observing such a strong relationship between burglaries in Oregon and the viewership count for Days of Our Lives by chance alone is exceedingly low. It's safe to say that the likelihood of this correlation being a mere coincidence is about as slim as the chances of a character in a soap opera staying dead.
The evidence from our analysis is so compelling that we can confidently dismiss any suspicions of a fluke in the data. The figure (Fig. 1) presents a scatterplot illustrating the pronounced correlation between the burglary rates in Oregon and the viewership count for Days of Our Lives. It's as clear as day that these two variables are not merely passing acquaintances – they're practically entwined in a dramatic embrace, much like star-crossed lovers on the show.
Overall, the results of our study provide unambiguous support for the existence of a remarkable connection between burglaries in Oregon and the viewership count for Days of Our Lives. This unexpected correlation raises captivating implications about the potential influence of popular culture on criminal behavior, with enough twists and turns to make even the most seasoned soap opera writer envious.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our study has not only confirmed the remarkable correlation between burglaries in Oregon and the viewership count for Days of Our Lives, but it has also opened the door to new perspectives on the intricate web of societal influences. Our findings lend weight to the work of Smith, Doe, and Jones, who have meticulously documented the multifaceted motivations behind criminal behavior - though none of them likely considered the potential influence of daytime drama on criminal activity. It seems that in the grand soap opera of life, reality may indeed be stranger than fiction.

Our results robustly support the notion that as the viewership of Days of Our Lives fluctuates, burglary rates in Oregon also demonstrate corresponding shifts. This striking correlation prompts us to vow to remain ever-vigilant in our analysis, as we resist the urge to succumb to overreaching claims about causation. While we're tempted to "break in" any exaggerated claims, we stand firm in our commitment to rigorous scientific inquiry.

This study's findings have profound implications, not only for criminology but also for the broader understanding of societal dynamics. The strength of the correlation coefficient and the r-squared value underscores the notably intertwined relationship between these seemingly disparate variables. The evidence presented practically beckons us to consider incorporating soap opera storylines into crime prevention strategies - because who needs alarms when you have melodramatic plot twists to keep burglars at bay?

The low p-value further solidifies the legitimacy of the correlation, leaving little room to entertain the notion that this connection might be a mere coincidence. In the realm of probabilities, the likelihood of this correlation being happenstance is about as thin as the chances of a soap opera character staying dead. It's as if our findings are the cliffhanger at the end of a particularly suspenseful episode - leaving us on the edge of our seats, eagerly awaiting the next revelation in this captivating saga of societal influences.

As we continue our research endeavors, we must remain mindful of the limitations inherent in our current study. While our findings present a compelling case for the correlation between burglaries in Oregon and the viewership count for Days of Our Lives, we must not lose sight of the need for further investigations to unravel the underlying mechanisms that may drive this unexpected relationship. It's as if we've reached a commercial break in our exploration, leaving the audience hanging as we prepare for the next act in this thrilling research journey.

In the grand scheme of academic inquiry, our study serves as a vivid reminder that even the most unlikely correlations can yield valuable insights. The unexpected connections we've uncovered remind us that when it comes to research, truth has a knack for being stranger than fiction - much like the convoluted plotlines of the soap opera that has captured our attention. We look forward to unpacking these revelations in future studies, as we seek to shed light on the curious interplay of popular culture and criminal behavior.

After all, when it comes to unearthing the unexpected, there's no shortage of surprising twists and turns - just like a soap opera, but with a bit more statistical analysis and a lot less dramatic pauses.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Burglaries in Oregon and Viewership count for Days of Our Lives. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
The Days of Our Burglaries: An Examination of the Correlation Between Burglaries in Oregon and Viewership Count for Days of Our Lives

[[ABSTRACT]]
In this paper, we present a comprehensive analysis of the intriguing relationship between the frequency of burglaries in Oregon and the viewership count for the long-running soap opera, Days of Our Lives. While this research may sound like a soap opera itself, our data-driven investigation uncovers some unexpected twists and turns.

Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we meticulously examined burglary rates in Oregon and the viewership count for Days of Our Lives from 1985 to 2021. Our findings reveal a remarkably strong correlation coefficient of 0.9335386, with a p-value < 0.01. This statistically significant relationship provides compelling evidence of the connection between these seemingly unrelated phenomena – though we must resist the urge to "break in" any exaggerated claims about causation just yet.

Surprisingly, our analysis suggests that as the viewership count for Days of Our Lives fluctuates, so do the burglary rates in Oregon. These findings prompt both a revisiting of assumptions about the social and psychological factors influencing criminal behavior, as well as a consideration of the potential impact of soap operas on community security. Perhaps these compelling narratives are not only captivating audiences but also affecting crime rates – a true "plot twist" in the realm of societal influences.

In conclusion, our research sheds new light on the interplay between popular culture and criminal activity, opening doors to further investigations into the unexpected connections that may "break in" on our conventional understanding of human behavior. As we continue to unravel the complex web of influences shaping our world, this study underscores the importance of delving into even the most seemingly frivolous correlations – after all, when it comes to research, sometimes truth is stranger than fiction.

[[INTRDUCTION]]
As the world of academia continues its quest to uncover the underlying factors that shape human behavior, certain correlations may seem to be taken straight out of a soap opera script. In this paper, we present a study that delves into the curious relationship between burglaries in Oregon and the viewership count for the long-running soap opera, Days of Our Lives. While the connection between crime and daytime television may sound like the start of a bad joke, our data-driven analysis leads to some unexpectedly compelling findings.
So, a burglar walks into Oregon and starts watching Days of Our Lives... No, this isn't a setup for a punchline; it's the basis for our research. With a statistically significant correlation coefficient and a p-value that would make any statistician's heart flutter, our investigation isn't merely a "soap opera" of speculation – it's a bona fide examination of an intriguing societal phenomenon.
It's no secret that correlations don't always imply causation, but the strength of the relationship we observed between burglaries and Days of Our Lives viewership raises eyebrows much like a dramatic reveal on the show. We resist the temptation to jump to conclusions, though we can't help but tease out the possibilities with a pun or two along the way.
As we embark on our analysis, it becomes evident that the flux in Days of Our Lives viewership corresponds to fluctuations in burglary rates in Oregon. It's almost as if there's a clandestine subplot at play, with soap operas and crime rates engaging in a dramatic dance of influence. This unexpected connection prompts us to reconsider the role of television narratives in shaping behaviors – surely a storyline worthy of a daytime drama.
In bringing our investigation to a conclusion, we find ourselves faced with the tantalizing prospect of uncovering the ways in which seemingly incongruent cultural phenomena intertwine. Our study invites further exploration into the unforeseen connections that may "break in" on our understanding of human conduct, proving that sometimes, in the realm of research, truth truly is stranger than fiction – all while delivering more plot twists than a daytime soap opera.

[[RESULTS]]
The analysis of the data on burglaries in Oregon and the viewership count for Days of Our Lives from 1985 to 2021 revealed a striking correlation coefficient of 0.9335386. This strong positive correlation indicates that as the viewership count for Days of Our Lives fluctuated over the years, burglary rates in Oregon also showed corresponding shifts. It's as if the burglars were waiting with bated breath to see who would be stricken with amnesia or have a secret twin next.
The r-squared value of 0.8714943 further solidifies the robustness of the relationship between these two seemingly unrelated variables. This means that a striking 87.15% of the variation in burglary rates in Oregon can be explained by the viewership count for Days of Our Lives. It's almost as if the dramatic tension in the soap opera is mirrored in the ebb and flow of criminal activity – talk about life imitating art!
The p-value of less than 0.01 indicates that the probability of observing such a strong relationship between burglaries in Oregon and the viewership count for Days of Our Lives by chance alone is exceedingly low. It's safe to say that the likelihood of this correlation being a mere coincidence is about as slim as the chances of a character in a soap opera staying dead.
The evidence from our analysis is so compelling that we can confidently dismiss any suspicions of a fluke in the data. The figure (Fig. 1) presents a scatterplot illustrating the pronounced correlation between the burglary rates in Oregon and the viewership count for Days of Our Lives. It's as clear as day that these two variables are not merely passing acquaintances – they're practically entwined in a dramatic embrace, much like star-crossed lovers on the show.
Overall, the results of our study provide unambiguous support for the existence of a remarkable connection between burglaries in Oregon and the viewership count for Days of Our Lives. This unexpected correlation raises captivating implications about the potential influence of popular culture on criminal behavior, with enough twists and turns to make even the most seasoned soap opera writer envious.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In unraveling the enigmatic relationship between burglaries in Oregon and the viewership count for Days of Our Lives, our research has shed light on a correlation as captivating as a daytime soap opera storyline. The statistically significant correlation coefficient of 0.9335386, with a p-value < 0.01, emphasizes the undeniable connection between these seemingly disparate phenomena. It's almost as if the burglars were setting their heist schedules according to the showtimes – they must've really been invested in the characters' love triangles!

The robust r-squared value of 0.8714943 reinforces the substantial influence of Days of Our Lives viewership on burglary rates in Oregon, suggesting a relationship more compelling than any on-screen romance. It's as if the soap opera's dramatic narrative was influencing not just emotions, but criminal activities as well – who knew a TV show could have such real-world impact? And here we thought soap operas were just about suspenseful plotlines and bad acting!

With such a strong body of evidence, we can confidently assert that the correlation between these variables is no mere coincidence. The likelihood of this connection being happenstance is as slim as the chances of a soap opera character staying deceased – especially if they have an evil twin just waiting to make a dramatic return.

In pursuing this research, we've not only unraveled a compelling correlation but also illuminated the possibility of unexpected societal influences. The implications of our findings go beyond the realm of academic curiosity, delving into the interplay of popular culture and criminal behavior. It's a storyline worthy of a daytime drama – who would've thought that the characters of Days of Our Lives were playing a part in the burglary rates of Oregon?

In the spirit of a satisfying conclusion, we confidently assert that no further research is necessary in this area. After all, once a soap opera has had its dramatic climax, any further attempts at a reboot will most likely just fall flat – and we certainly don't need a revival of this "Days of Our Burglaries" drama.

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 The Days of Our Burglaries: An Examination of the Correlation Between Burglaries in Oregon and Viewership Count for Days of Our Lives. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Strange Correlations and Odd Discoveries

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 The Days of Our Burglaries: An Examination of the Correlation Between Burglaries in Oregon and Viewership Count for Days of Our Lives. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Sociological 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 The Days of Our Burglaries: An Examination of the Correlation Between Burglaries in Oregon and Viewership Count for Days of Our Lives with an abstract of In this paper, we present a comprehensive analysis of the intriguing relationship between the frequency of burglaries in Oregon and the viewership count for the long-running soap opera, Days of Our Lives. While this research may sound like a soap opera itself, our data-driven investigation uncovers some unexpected twists and turns.
Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we meticulously examined burglary rates in Oregon and the viewership count for Days of Our Lives from 1985 to 2021. Our findings reveal a remarkably strong correlation coefficient of 0.9335386, with a p-value < 0.01. This statistically significant relationship provides compelling evidence of the connection between these seemingly unrelated phenomena – though we must resist the urge to "break in" any exaggerated claims about causation just yet.
Surprisingly, our analysis suggests that as the viewership count for Days of Our Lives fluctuates, so do the burglary rates in Oregon. These findings prompt both a revisiting of assumptions about the social and psychological factors influencing criminal behavior, as well as a consideration of the potential impact of soap operas on community security. Perhaps these compelling narratives are not only captivating audiences but also affecting crime rates – a true "plot twist" in the realm of societal influences.
In conclusion, our research sheds new light on the interplay between popular culture and criminal activity, opening doors to further investigations into the unexpected connections that may "break in" on our conventional understanding of human behavior. As we continue to unravel the complex web of influences shaping our world, this study underscores the importance of delving into even the most seemingly frivolous correlations – after all, when it comes to research, sometimes truth is stranger than fiction.

ChatGPT:

The Days of Our Lives, burglaries Oregon, soap opera viewership, crime rate correlation, popular culture influence, social and psychological factors, FBI crime data, Days of Our Lives history, criminal behavior analysis, community security impact, societal influences, unexpected correlations, popular culture 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

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

Viewership count for Days of Our Lives
Detailed data title: Metered viewership count for Days of Our Lives
Source: Wikipedia
See what else correlates with Viewership count for Days of Our Lives

Correlation r = 0.9335386 (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 = 0.8714943 (Coefficient of determination)
This means 87.1% of the change in the one variable (i.e., Viewership count for Days of Our Lives) is predictable based on the change in the other (i.e., Burglaries in Oregon) over the 37 years from 1985 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.6E-17.^Show 0.0000000000000000363997895109
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 3.6E-15% of random cases. Said differently, if you correlated 27,472,686,337,940,160 random variables^Note You don't actually need 27 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 36 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 36 because we have two variables measured over a period of 37 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.87, 0.97 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Burglaries in Oregon (Burglary rate)	1886.5	1966.7	1782.7	1764.1	1425.4	1135.4	1176	1106.7	1024.8	1100.8	1102.8	988.3	1033.2	927.5	806.6	748.8	767.2	729.9	801.3	837.3	759.1	657.3	613.2	557.1	516	522	535.2	565.4	529.7	470.6	460.7	414.1	420	394.9	358.8	339.2	338.2
Viewership count for Days of Our Lives (Nielson share)	7200000	7000000	7100000	6500000	5400000	5200000	5400000	4900000	5600000	5300000	5800000	5800000	5100000	5800000	4200000	3800000	3600000	3100000	3100000	2700000	2600000	2300000	2100000	2200000	2200000	2000000	2000000	2100000	1900000	2050000	1800000	1600000	1600000	1600000	1400000	1200000	1200000

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([1886.5,1966.7,1782.7,1764.1,1425.4,1135.4,1176,1106.7,1024.8,1100.8,1102.8,988.3,1033.2,927.5,806.6,748.8,767.2,729.9,801.3,837.3,759.1,657.3,613.2,557.1,516,522,535.2,565.4,529.7,470.6,460.7,414.1,420,394.9,358.8,339.2,338.2,])
array_2 = np.array([7200000,7000000,7100000,6500000,5400000,5200000,5400000,4900000,5600000,5300000,5800000,5800000,5100000,5800000,4200000,3800000,3600000,3100000,3100000,2700000,2600000,2300000,2100000,2200000,2200000,2000000,2000000,2100000,1900000,2050000,1800000,1600000,1600000,1600000,1400000,1200000,1200000,])
array_1_name = "Burglaries in Oregon"
array_2_name = "Viewership count for Days of Our Lives"

# 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 Oregon
Line chart for only Viewership count for Days of Our Lives
The spurious research paper: The Days of Our Burglaries: An Examination of the Correlation Between Burglaries in Oregon and Viewership Count for Days of Our Lives

View another random correlation

How fun was this correlation?

Your rating skills are top-notch!

Correlation ID: 1218 · Black Variable ID: 20115 · Red Variable ID: 87


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