about · email me · subscribe
Spurious correlation #2,887 · 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 Connecticut 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. Small Image
Download png
, svg

AI explanation

As burglaries decreased, more people felt safe staying home. This led to a decrease in viewership count for Days of Our Lives, as fewer individuals tuned in while cocooning in the comforting security of their own burglar-free homes.

Model: dalle-3
Prompt: Create an image inspired by pop art that features a scene in downtown Connecticut. In the cozy living room of a house, a wacky group of burglars is caught sitting on a bright, colorful couch, completely enthralled by watching the classic soap opera "Days of Our Lives" on a retro TV set. The pop art style should be evident in bold, vivid colors, with comic book-inspired outlines and exaggerated features. The burglars should be depicted in a playful, exaggerated manner, showcasing their captivation with the show. Outside the window, the street should be depicted in a simplified, graphic style, with a peaceful and quiet atmosphere, devoid of any signs of attempted break-ins. The scene should convey the burglars' intense focus on the TV, with decreased viewership count visualized to show the significant amount of screen time they are consuming. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Burglaries in Connecticut and Viewership count for Days of Our Lives. 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: High-tech Concept art Photorealism Pop art Art nouveau
ChatGPT: Pop art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Burglaries in Connecticut and Viewership count for Days of Our Lives, in the following situation: Because burglars were caught binge-watching Days of Our Lives, leading to decreased time for actual burglaries in Connecticut.. Keep the description simple.
ChatGPT: In downtown Connecticut, a group of burglars is caught sitting on a couch inside a cozy living room, completely engrossed in watching Days of Our Lives on TV. Outside the window, the street is quiet, with no signs of any attempted break-ins. The burglars seem too captivated by the show to focus on anything else, and the decreased viewership count suggests that they are consuming a significant amount of screen time.

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: [ Pop art ] and depicting this scene: In downtown Connecticut, a group of burglars is caught sitting on a couch inside a cozy living room, completely engrossed in watching Days of Our Lives on TV. Outside the window, the street is quiet, with no signs of any attempted break-ins. The burglars seem too captivated by the show to focus on anything else, and the decreased viewership count suggests that they are consuming a significant amount of screen time. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image inspired by pop art that features a scene in downtown Connecticut. In the cozy living room of a house, a wacky group of burglars is caught sitting on a bright, colorful couch, completely enthralled by watching the classic soap opera "Days of Our Lives" on a retro TV set. The pop art style should be evident in bold, vivid colors, with comic book-inspired outlines and exaggerated features. The burglars should be depicted in a playful, exaggerated manner, showcasing their captivation with the show. Outside the window, the street should be depicted in a simplified, graphic style, with a peaceful and quiet atmosphere, devoid of any signs of attempted break-ins. The scene should convey the burglars' intense focus on the TV, with decreased viewership count visualized to show the significant amount of screen time they are consuming.

*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.

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 Connecticut caused Viewership count for Days of Our Lives to decrease.

AI academic paper

(Because p < 0.01)
The Days of Our Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership

The Journal of Whimsical Criminology

Jan 2024

Reminder: This paper is AI-generated. Not real!
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 researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Burglaries in Connecticut and Viewership count for Days of Our Lives. Make lots of jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from FBI Criminal Justice Information Services and Wikipedia to assess this nagging question. You found a correlation coefficient of 0.9286625 and p < 0.01 for 1985 to 2021.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The Days of Our Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership

[[ABSTRACT]]
This research paper investigates the entertaining yet unconventional link between the frequency of burglaries in the state of Connecticut and the viewership count of the long-running soap opera, Days of Our Lives. Upon delving into the data from FBI Criminal Justice Information Services and Wikipedia, our team uncovered a surprising correlation coefficient of 0.9286625 and a statistically significant p-value of < 0.01 for the period spanning from 1985 to 2021. Our findings challenge conventional wisdom and prompt further inquiry into the intricate dynamics between daytime television drama and criminal activities. We aim to amuse and enlighten as we explore this unexpected relationship, introducing a novel twist to the realms of criminology and media studies.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Burglaries in Connecticut and Viewership count for Days of Our Lives. Make lots of jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
The Days of Our Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership

[[ABSTRACT]]
This research paper investigates the entertaining yet unconventional link between the frequency of burglaries in the state of Connecticut and the viewership count of the long-running soap opera, Days of Our Lives. Upon delving into the data from FBI Criminal Justice Information Services and Wikipedia, our team uncovered a surprising correlation coefficient of 0.9286625 and a statistically significant p-value of < 0.01 for the period spanning from 1985 to 2021. Our findings challenge conventional wisdom and prompt further inquiry into the intricate dynamics between daytime television drama and criminal activities. We aim to amuse and enlighten as we explore this unexpected relationship, introducing a novel twist to the realms of criminology and media studies.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
The intricate interplay between criminal activities and daytime soap operas has long been a subject of fascination and speculation. This paper seeks to shed light on the unlikely connection between the frequency of burglaries in Connecticut and the viewership count of the beloved soap opera, Days of Our Lives. As we embark on this journey into the realms of criminology and media studies, we aim to both entertain and enlighten, recognizing the unexpected twist this association brings to the forefront of academic inquiry.

In the annals of unconventional research topics, the correlation between televised melodrama and real-world criminal activities stands out as a captivating enigma. One might say that it's a case of grand theft storyline meeting grand theft auto! The soap opera, Days of Our Lives, has captivated audiences with its gripping tales of love, betrayal, and dramatic plot twists for over five decades. On the flip side, burglaries in the state of Connecticut, while far from entertaining, are a sobering reality that demands attention.

Our initial exploration was imbued with the skepticism that commonly greets seemingly outlandish hypotheses. However, our findings proved to be no mere soap opera plot twist. Delving into the data from the FBI Criminal Justice Information Services and Wikipedia, we discovered a surprising correlation coefficient of 0.9286625, which would make any statistical model swoon, and a jaw-dropping p-value of less than 0.01 for the period from 1985 to 2021. It seems that when it comes to crime and daytime dramas, truth is indeed stranger than fiction!

As we navigate this uncharted territory at the intersection of crime statistics and soap opera viewership, it becomes clear that there is more to this connection than meets the eye. The compelling correlation between burglaries in Connecticut and the captivating storylines on Days of Our Lives challenges preconceived notions and calls for a deeper understanding of the intricate dynamics at play. It raises questions that are as perplexing as they are intriguing. Are the viewers of soap operas prone to criminal mischief? Or could it be that the captivating narratives of love, loss, and intrigue actually serve as a buffer against criminal inclinations?

In delving into this unexpected relationship, our paper aims to inject some humor and levity into the often-serious fields of criminology and media studies. After all, when investigating the correlation between crime and soap operas, one can't help but appreciate the irony and drama of it all. So, grab your popcorn and your crime statistics handbook as we embark on this journey into the delightful and dramatic world of daytime television and criminal undertakings. The findings that await are sure to captivate and surprise, much like a well-woven soap opera storyline.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Burglaries in Connecticut and Viewership count for Days of Our Lives. 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]]
The Days of Our Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership

[[ABSTRACT]]
This research paper investigates the entertaining yet unconventional link between the frequency of burglaries in the state of Connecticut and the viewership count of the long-running soap opera, Days of Our Lives. Upon delving into the data from FBI Criminal Justice Information Services and Wikipedia, our team uncovered a surprising correlation coefficient of 0.9286625 and a statistically significant p-value of < 0.01 for the period spanning from 1985 to 2021. Our findings challenge conventional wisdom and prompt further inquiry into the intricate dynamics between daytime television drama and criminal activities. We aim to amuse and enlighten as we explore this unexpected relationship, introducing a novel twist to the realms of criminology and media studies.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intricate interplay between criminal activities and daytime soap operas has long been a subject of fascination and speculation. This paper seeks to shed light on the unlikely connection between the frequency of burglaries in Connecticut and the viewership count of the beloved soap opera, Days of Our Lives. As we embark on this journey into the realms of criminology and media studies, we aim to both entertain and enlighten, recognizing the unexpected twist this association brings to the forefront of academic inquiry.
In the annals of unconventional research topics, the correlation between televised melodrama and real-world criminal activities stands out as a captivating enigma. One might say that it's a case of grand theft storyline meeting grand theft auto! The soap opera, Days of Our Lives, has captivated audiences with its gripping tales of love, betrayal, and dramatic plot twists for over five decades. On the flip side, burglaries in the state of Connecticut, while far from entertaining, are a sobering reality that demands attention.
Our initial exploration was imbued with the skepticism that commonly greets seemingly outlandish hypotheses. However, our findings proved to be no mere soap opera plot twist. Delving into the data from the FBI Criminal Justice Information Services and Wikipedia, we discovered a surprising correlation coefficient of 0.9286625, which would make any statistical model swoon, and a jaw-dropping p-value of less than 0.01 for the period from 1985 to 2021. It seems that when it comes to crime and daytime dramas, truth is indeed stranger than fiction!
As we navigate this uncharted territory at the intersection of crime statistics and soap opera viewership, it becomes clear that there is more to this connection than meets the eye. The compelling correlation between burglaries in Connecticut and the captivating storylines on Days of Our Lives challenges preconceived notions and calls for a deeper understanding of the intricate dynamics at play. It raises questions that are as perplexing as they are intriguing. Are the viewers of soap operas prone to criminal mischief? Or could it be that the captivating narratives of love, loss, and intrigue actually serve as a buffer against criminal inclinations?
In delving into this unexpected relationship, our paper aims to inject some humor and levity into the often-serious fields of criminology and media studies. After all, when investigating the correlation between crime and soap operas, one can't help but appreciate the irony and drama of it all. So, grab your popcorn and your crime statistics handbook as we embark on this journey into the delightful and dramatic world of daytime television and criminal undertakings. The findings that await are sure to captivate and surprise, much like a well-woven soap opera storyline.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The connection between seemingly disparate phenomena has long been a focal point of academic inquiry, and the relationship between burglaries in Connecticut and Days of Our Lives viewership stands as a testament to the unexpected associations waiting to be uncovered. In "Crime and Television: Insights into the Connection between Media and Criminal Behavior," Smith et al. explored the impact of television consumption on criminal activities, offering thought-provoking insights into the potential influence of media on behavioral patterns. Similarly, Doe's seminal work, "Criminal Minds: Unraveling the Mysteries of Deviant Behavior in Society," delves into the intricate motivations behind criminal acts and the various societal influences that may shape them.

While these scholarly works present valuable perspectives on crime and media, the whimsical nature of our own inquiry unveils a unique dimension to this discourse. Building upon the existing literature, we seek to bridge the seemingly incongruous realms of soap opera viewership and criminal endeavors, prompting a reconsideration of the conventional boundaries within criminological and media studies. As we venture beyond the realm of empirical research, let us not overlook the potential insights that can be gleaned from popular non-fiction works such as "The Power of Television: Understanding the Influence of Media on Society" by Jones, in offering a broader context for understanding the impact of television on societal behaviors.

Transitioning from the empirical and theoretical underpinnings, we turn our attention to fictional narratives, which, while not rooted in empirical evidence, often offer narratives that resonate with the human experience. Works of fiction such as "Soap Opera Mysteries: Unraveling the Enigmatic Allure of Daytime Drama" and "The Burglar and the Beautiful: A Tale of Crime and Intrigue" beckon us to consider the inherent drama and allure that permeate both the world of daytime television and criminal activities.

However, as we delve deeper into the realm of literature, it is essential to acknowledge the unconventional sources that have informed our inquiry. While the backs of shampoo bottles may be an unexpected font of insight, the pithy jargon and enticing scent descriptions offer a lens through which we may perceive the unsuspecting connections that permeate our everyday lives. In "Conditioned for Cleanliness: An Unconventional Approach to Investigative Inquiry," the authors humorously, and perhaps inadvertently, provide glimpses into the transformative power of scent and the potential associations it may hold.

In unraveling the correlation between burglaries in Connecticut and Days of Our Lives viewership, our approach combines rigor with whimsy, recognizing that the pursuit of knowledge need not be devoid of amusement. Indeed, it is within the unexpected associations that we often uncover the most intriguing revelations, shedding light on the idiosyncrasies of human behavior and the fascinating intersections of popular culture and criminal activities. With an appreciation for both the serious and the sublime, we invite our readers to join us in this engaging exploration as we untangle the enigmatic relationship between crime statistics and daytime soap operas.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Burglaries in Connecticut and Viewership count for Days of Our Lives. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Wikipedia . You used data from 1985 to 2021

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The Days of Our Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership

[[ABSTRACT]]
This research paper investigates the entertaining yet unconventional link between the frequency of burglaries in the state of Connecticut and the viewership count of the long-running soap opera, Days of Our Lives. Upon delving into the data from FBI Criminal Justice Information Services and Wikipedia, our team uncovered a surprising correlation coefficient of 0.9286625 and a statistically significant p-value of < 0.01 for the period spanning from 1985 to 2021. Our findings challenge conventional wisdom and prompt further inquiry into the intricate dynamics between daytime television drama and criminal activities. We aim to amuse and enlighten as we explore this unexpected relationship, introducing a novel twist to the realms of criminology and media studies.

[[INTRODUCTION]]
The intricate interplay between criminal activities and daytime soap operas has long been a subject of fascination and speculation. This paper seeks to shed light on the unlikely connection between the frequency of burglaries in Connecticut and the viewership count of the beloved soap opera, Days of Our Lives. As we embark on this journey into the realms of criminology and media studies, we aim to both entertain and enlighten, recognizing the unexpected twist this association brings to the forefront of academic inquiry.
In the annals of unconventional research topics, the correlation between televised melodrama and real-world criminal activities stands out as a captivating enigma. One might say that it's a case of grand theft storyline meeting grand theft auto! The soap opera, Days of Our Lives, has captivated audiences with its gripping tales of love, betrayal, and dramatic plot twists for over five decades. On the flip side, burglaries in the state of Connecticut, while far from entertaining, are a sobering reality that demands attention.
Our initial exploration was imbued with the skepticism that commonly greets seemingly outlandish hypotheses. However, our findings proved to be no mere soap opera plot twist. Delving into the data from the FBI Criminal Justice Information Services and Wikipedia, we discovered a surprising correlation coefficient of 0.9286625, which would make any statistical model swoon, and a jaw-dropping p-value of less than 0.01 for the period from 1985 to 2021. It seems that when it comes to crime and daytime dramas, truth is indeed stranger than fiction!
As we navigate this uncharted territory at the intersection of crime statistics and soap opera viewership, it becomes clear that there is more to this connection than meets the eye. The compelling correlation between burglaries in Connecticut and the captivating storylines on Days of Our Lives challenges preconceived notions and calls for a deeper understanding of the intricate dynamics at play. It raises questions that are as perplexing as they are intriguing. Are the viewers of soap operas prone to criminal mischief? Or could it be that the captivating narratives of love, loss, and intrigue actually serve as a buffer against criminal inclinations?
In delving into this unexpected relationship, our paper aims to inject some humor and levity into the often-serious fields of criminology and media studies. After all, when investigating the correlation between crime and soap operas, one can't help but appreciate the irony and drama of it all. So, grab your popcorn and your crime statistics handbook as we embark on this journey into the delightful and dramatic world of daytime television and criminal undertakings. The findings that await are sure to captivate and surprise, much like a well-woven soap opera storyline.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic connection between burglaries in Connecticut and the viewership count of Days of Our Lives, our research team embarked on a multidimensional approach that combined statistical analysis, data mining, and a touch of dramatic flair. We sought to leave no stone unturned, just like a determined soap opera protagonist on a quest for truth and justice.

Data Collection:
Our intrepid journey into the heart of this peculiar correlation began with the collection of criminal statistics from the FBI Criminal Justice Information Services, widely regarded as the repository of crime data that would make even the most seasoned sleuth envious. We also tapped into the vast expanse of knowledge - and trivia - that is Wikipedia, embracing the spirit of unconventional inquiry to unearth the relevant viewership count data for Days of Our Lives from 1985 to 2021. Our research team scoured the internet, navigating through the virtual labyrinth of sources with the dedication and tenacity of a soap opera character on a quest for hidden truths.

Statistical Analysis:
Armed with an arsenal of statistical tools, we sought to untangle the complex web of data we had amassed. We employed robust correlation analysis techniques, unleashing the power of regression models to scrutinize the intriguing relationship between burglary rates in Connecticut and the viewership count of Days of Our Lives. Our statistical approach aimed to cast a spotlight on any significant connection, much like a dramatic revelation in the midst of a soap opera cliffhanger.

Human Behavior Analysis:
Recognizing the human element that underpins both criminal activities and television viewership, we delved into psychological and sociological literature to understand the underlying motivations and influences at play. Our investigation borrowed from the playbooks of behavioral economists and criminologists, seeking to illuminate the intricacies of human decision-making and the potential role of televised drama in shaping real-world actions. It was a quest to decipher the complexities of human behavior that could rival the plot twists of any daytime soap opera.

Narrative Analysis:
Acknowledging the inherent narrative structure of both crime data and soap opera storylines, we embraced an unconventional lens through which to explore the correlation. We uncovered the themes, motifs, and dramatic arcs that unfolded within the data, weaving a compelling narrative that bore the hallmarks of a well-crafted soap opera script. Much like a seasoned soap opera writer, we endeavored to craft a story that would captivate the imagination and hold the audience in rapt attention.

By blending the rigor of statistical inquiry with the intrigue of narrative analysis and the nuance of human behavior, our research methodology sought to emulate the essence of both crime-solving and soap opera storytelling. Our approach wove together strands of evidence and interpretation in a tapestry of investigation that aimed to entertain and enlighten, proving that unconventional research endeavors can be as enthralling as they are insightful.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Burglaries in Connecticut and Viewership count for Days of Our Lives. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Wikipedia .

For the time period 1985 to 2021, you found a correlation 0.9286625, r-squared of 0.8624140, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The Days of Our Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership

[[ABSTRACT]]
This research paper investigates the entertaining yet unconventional link between the frequency of burglaries in the state of Connecticut and the viewership count of the long-running soap opera, Days of Our Lives. Upon delving into the data from FBI Criminal Justice Information Services and Wikipedia, our team uncovered a surprising correlation coefficient of 0.9286625 and a statistically significant p-value of < 0.01 for the period spanning from 1985 to 2021. Our findings challenge conventional wisdom and prompt further inquiry into the intricate dynamics between daytime television drama and criminal activities. We aim to amuse and enlighten as we explore this unexpected relationship, introducing a novel twist to the realms of criminology and media studies.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intricate interplay between criminal activities and daytime soap operas has long been a subject of fascination and speculation. This paper seeks to shed light on the unlikely connection between the frequency of burglaries in Connecticut and the viewership count of the beloved soap opera, Days of Our Lives. As we embark on this journey into the realms of criminology and media studies, we aim to both entertain and enlighten, recognizing the unexpected twist this association brings to the forefront of academic inquiry.
In the annals of unconventional research topics, the correlation between televised melodrama and real-world criminal activities stands out as a captivating enigma. One might say that it's a case of grand theft storyline meeting grand theft auto! The soap opera, Days of Our Lives, has captivated audiences with its gripping tales of love, betrayal, and dramatic plot twists for over five decades. On the flip side, burglaries in the state of Connecticut, while far from entertaining, are a sobering reality that demands attention.
Our initial exploration was imbued with the skepticism that commonly greets seemingly outlandish hypotheses. However, our findings proved to be no mere soap opera plot twist. Delving into the data from the FBI Criminal Justice Information Services and Wikipedia, we discovered a surprising correlation coefficient of 0.9286625, which would make any statistical model swoon, and a jaw-dropping p-value of less than 0.01 for the period from 1985 to 2021. It seems that when it comes to crime and daytime dramas, truth is indeed stranger than fiction!
As we navigate this uncharted territory at the intersection of crime statistics and soap opera viewership, it becomes clear that there is more to this connection than meets the eye. The compelling correlation between burglaries in Connecticut and the captivating storylines on Days of Our Lives challenges preconceived notions and calls for a deeper understanding of the intricate dynamics at play. It raises questions that are as perplexing as they are intriguing. Are the viewers of soap operas prone to criminal mischief? Or could it be that the captivating narratives of love, loss, and intrigue actually serve as a buffer against criminal inclinations?
In delving into this unexpected relationship, our paper aims to inject some humor and levity into the often-serious fields of criminology and media studies. After all, when investigating the correlation between crime and soap operas, one can't help but appreciate the irony and drama of it all. So, grab your popcorn and your crime statistics handbook as we embark on this journey into the delightful and dramatic world of daytime television and criminal undertakings. The findings that await are sure to captivate and surprise, much like a well-woven soap opera storyline.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our investigation into the correlation between burglaries in Connecticut and the viewership count of Days of Our Lives yielded some truly captivating results. The data told a tale that many would find hard to believe, akin to a plot twist straight out of a daytime soap opera!

Upon analyzing the data from 1985 to 2021, we uncovered a remarkably strong correlation coefficient of 0.9286625. This correlation was so strong, it could be considered the crime drama equivalent of a power couple in the soap opera world - think Victor and Nikki Newman for all our soap fans out there!

We also found an r-squared value of 0.8624140, indicating that a whopping 86.24% of the variability in burglaries in Connecticut could be explained by the viewership count of Days of Our Lives. That's a higher percentage than the probability of a Days of Our Lives character coming back from the dead!

To add to the dramatic flair, our findings were further validated by a statistically significant p-value of less than 0.01. This means that the likelihood of our results occurring by chance is slimmer than the chances of a soap opera wedding not being interrupted by some unforeseen calamity.

To illustrate the compelling relationship we uncovered, we present a scatterplot in Figure 1. This visual representation showcases the undeniable connection between these two seemingly disparate variables, demonstrating a trend so striking it would make even the most cynical of soap opera skeptics raise an eyebrow.

In conclusion, our research has revealed a correlation between burglaries in Connecticut and the viewership count of Days of Our Lives that not only captivates the imagination but also challenges conventional notions about the influences of popular media on real-life behaviors. It's a revelation that's sure to spark intense interest and lively discussions in both criminological and media studies circles, and one that might just leave you pondering the unexpected twists and turns of the human psyche. After all, who knew that the drama on our screens could have such an impact on the drama in our communities?


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Burglaries in Connecticut and Viewership count for Days of Our Lives. 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]]
The Days of Our Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership

[[ABSTRACT]]
This research paper investigates the entertaining yet unconventional link between the frequency of burglaries in the state of Connecticut and the viewership count of the long-running soap opera, Days of Our Lives. Upon delving into the data from FBI Criminal Justice Information Services and Wikipedia, our team uncovered a surprising correlation coefficient of 0.9286625 and a statistically significant p-value of < 0.01 for the period spanning from 1985 to 2021. Our findings challenge conventional wisdom and prompt further inquiry into the intricate dynamics between daytime television drama and criminal activities. We aim to amuse and enlighten as we explore this unexpected relationship, introducing a novel twist to the realms of criminology and media studies.

[[LITERATURE REVIEW]]
The connection between seemingly disparate phenomena has long been a focal point of academic inquiry, and the relationship between burglaries in Connecticut and Days of Our Lives viewership stands as a testament to the unexpected associations waiting to be uncovered. In "Crime and Television: Insights into the Connection between Media and Criminal Behavior," Smith et al. explored the impact of television consumption on criminal activities, offering thought-provoking insights into the potential influence of media on behavioral patterns. Similarly, Doe's seminal work, "Criminal Minds: Unraveling the Mysteries of Deviant Behavior in Society," delves into the intricate motivations behind criminal acts and the various societal influences that may shape them.
While these scholarly works present valuable perspectives on crime and media, the whimsical nature of our own inquiry unveils a unique dimension to this discourse. Building upon the existing literature, we seek to bridge the seemingly incongruous realms of soap opera viewership and criminal endeavors, prompting a reconsideration of the conventional boundaries within criminological and media studies. As we venture beyond the realm of empirical research, let us not overlook the potential insights that can be gleaned from popular non-fiction works such as "The Power of Television: Understanding the Influence of Media on Society" by Jones, in offering a broader context for understanding the impact of television on societal behaviors.
Transitioning from the empirical and theoretical underpinnings, we turn our attention to fictional narratives, which, while not rooted in empirical evidence, often offer narratives that resonate with the human experience. Works of fiction such as "Soap Opera Mysteries: Unraveling the Enigmatic Allure of Daytime Drama" and "The Burglar and the Beautiful: A Tale of Crime and Intrigue" beckon us to consider the inherent drama and allure that permeate both the world of daytime television and criminal activities.
However, as we delve deeper into the realm of literature, it is essential to acknowledge the unconventional sources that have informed our inquiry. While the backs of shampoo bottles may be an unexpected font of insight, the pithy jargon and enticing scent descriptions offer a lens through which we may perceive the unsuspecting connections that permeate our everyday lives. In "Conditioned for Cleanliness: An Unconventional Approach to Investigative Inquiry," the authors humorously, and perhaps inadvertently, provide glimpses into the transformative power of scent and the potential associations it may hold.
In unraveling the correlation between burglaries in Connecticut and Days of Our Lives viewership, our approach combines rigor with whimsy, recognizing that the pursuit of knowledge need not be devoid of amusement. Indeed, it is within the unexpected associations that we often uncover the most intriguing revelations, shedding light on the idiosyncrasies of human behavior and the fascinating intersections of popular culture and criminal activities. With an appreciation for both the serious and the sublime, we invite our readers to join us in this engaging exploration as we untangle the enigmatic relationship between crime statistics and daytime soap operas.

[[RESULTS]]
Our investigation into the correlation between burglaries in Connecticut and the viewership count of Days of Our Lives yielded some truly captivating results. The data told a tale that many would find hard to believe, akin to a plot twist straight out of a daytime soap opera!
Upon analyzing the data from 1985 to 2021, we uncovered a remarkably strong correlation coefficient of 0.9286625. This correlation was so strong, it could be considered the crime drama equivalent of a power couple in the soap opera world - think Victor and Nikki Newman for all our soap fans out there!
We also found an r-squared value of 0.8624140, indicating that a whopping 86.24% of the variability in burglaries in Connecticut could be explained by the viewership count of Days of Our Lives. That's a higher percentage than the probability of a Days of Our Lives character coming back from the dead!
To add to the dramatic flair, our findings were further validated by a statistically significant p-value of less than 0.01. This means that the likelihood of our results occurring by chance is slimmer than the chances of a soap opera wedding not being interrupted by some unforeseen calamity.
To illustrate the compelling relationship we uncovered, we present a scatterplot in Figure 1. This visual representation showcases the undeniable connection between these two seemingly disparate variables, demonstrating a trend so striking it would make even the most cynical of soap opera skeptics raise an eyebrow.
In conclusion, our research has revealed a correlation between burglaries in Connecticut and the viewership count of Days of Our Lives that not only captivates the imagination but also challenges conventional notions about the influences of popular media on real-life behaviors. It's a revelation that's sure to spark intense interest and lively discussions in both criminological and media studies circles, and one that might just leave you pondering the unexpected twists and turns of the human psyche. After all, who knew that the drama on our screens could have such an impact on the drama in our communities?

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The correlation we uncovered between burglaries in Connecticut and the viewership count of Days of Our Lives is nothing short of sensational – or should we say, "crime-sational"? Our findings not only support the existing literature that delves into the influence of television on societal behaviors but also add a tantalizing twist to the discourse.

The whimsical nature of our inquiry has led us down a path that few could have envisaged. As we reflect on the insightful observations presented in "The Power of Television: Understanding the Influence of Media on Society" by Jones, we cannot help but marvel at the unsuspected impact that daytime drama can exert on real-life criminal activities. Our results undeniably align with the extant research, affirming the compelling influence of media on human behaviors. It’s a discovery that could rival the most captivating soap opera plotlines!

Furthermore, our investigation breathes new life into the unorthodox sources that have informed our inquiry. While the connection drawn from the back of shampoo bottles might, at first glance, appear far-fetched, the scent of intrigue lingers as we contemplate the unexpected associations we’ve brought to light.

The strength of the correlation coefficient and the persuasive r-squared value indeed make for a compelling case. Our findings not only align with the existing literature but also exceed expectations, much like an unforeseen twist in a daytime drama that has viewers on the edge of their seats.

This research reverberates with implications for both criminological and media studies, punctuating the discourse with an unexpected and irreverent twist. The captivating nature of our findings is sure to stimulate scholarly discussions and prompt broader contemplations about the symbiotic relationship between popular culture and societal behaviors. As we revel in the peculiar connection we’ve unveiled, one cannot help but ponder the idiosyncrasies of human behavior and the delightful intersections between seemingly disparate domains.

In essence, our findings invite us to reconsider the boundaries of conventional academic inquiry, fostering a newfound appreciation for the whimsical and unanticipated connections that underpin our everyday experiences. After all, just like a gripping daytime soap opera, our research has revealed a captivating and unexpected correlation that challenges preconceived notions and implores us to look at the world through a lens of unbridled curiosity and amusement.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Burglaries in Connecticut and Viewership count for Days of Our Lives. 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]]
The Days of Our Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership

[[ABSTRACT]]
This research paper investigates the entertaining yet unconventional link between the frequency of burglaries in the state of Connecticut and the viewership count of the long-running soap opera, Days of Our Lives. Upon delving into the data from FBI Criminal Justice Information Services and Wikipedia, our team uncovered a surprising correlation coefficient of 0.9286625 and a statistically significant p-value of < 0.01 for the period spanning from 1985 to 2021. Our findings challenge conventional wisdom and prompt further inquiry into the intricate dynamics between daytime television drama and criminal activities. We aim to amuse and enlighten as we explore this unexpected relationship, introducing a novel twist to the realms of criminology and media studies.

[[INTRDUCTION]]
The intricate interplay between criminal activities and daytime soap operas has long been a subject of fascination and speculation. This paper seeks to shed light on the unlikely connection between the frequency of burglaries in Connecticut and the viewership count of the beloved soap opera, Days of Our Lives. As we embark on this journey into the realms of criminology and media studies, we aim to both entertain and enlighten, recognizing the unexpected twist this association brings to the forefront of academic inquiry.
In the annals of unconventional research topics, the correlation between televised melodrama and real-world criminal activities stands out as a captivating enigma. One might say that it's a case of grand theft storyline meeting grand theft auto! The soap opera, Days of Our Lives, has captivated audiences with its gripping tales of love, betrayal, and dramatic plot twists for over five decades. On the flip side, burglaries in the state of Connecticut, while far from entertaining, are a sobering reality that demands attention.
Our initial exploration was imbued with the skepticism that commonly greets seemingly outlandish hypotheses. However, our findings proved to be no mere soap opera plot twist. Delving into the data from the FBI Criminal Justice Information Services and Wikipedia, we discovered a surprising correlation coefficient of 0.9286625, which would make any statistical model swoon, and a jaw-dropping p-value of less than 0.01 for the period from 1985 to 2021. It seems that when it comes to crime and daytime dramas, truth is indeed stranger than fiction!
As we navigate this uncharted territory at the intersection of crime statistics and soap opera viewership, it becomes clear that there is more to this connection than meets the eye. The compelling correlation between burglaries in Connecticut and the captivating storylines on Days of Our Lives challenges preconceived notions and calls for a deeper understanding of the intricate dynamics at play. It raises questions that are as perplexing as they are intriguing. Are the viewers of soap operas prone to criminal mischief? Or could it be that the captivating narratives of love, loss, and intrigue actually serve as a buffer against criminal inclinations?
In delving into this unexpected relationship, our paper aims to inject some humor and levity into the often-serious fields of criminology and media studies. After all, when investigating the correlation between crime and soap operas, one can't help but appreciate the irony and drama of it all. So, grab your popcorn and your crime statistics handbook as we embark on this journey into the delightful and dramatic world of daytime television and criminal undertakings. The findings that await are sure to captivate and surprise, much like a well-woven soap opera storyline.

[[RESULTS]]
Our investigation into the correlation between burglaries in Connecticut and the viewership count of Days of Our Lives yielded some truly captivating results. The data told a tale that many would find hard to believe, akin to a plot twist straight out of a daytime soap opera!
Upon analyzing the data from 1985 to 2021, we uncovered a remarkably strong correlation coefficient of 0.9286625. This correlation was so strong, it could be considered the crime drama equivalent of a power couple in the soap opera world - think Victor and Nikki Newman for all our soap fans out there!
We also found an r-squared value of 0.8624140, indicating that a whopping 86.24% of the variability in burglaries in Connecticut could be explained by the viewership count of Days of Our Lives. That's a higher percentage than the probability of a Days of Our Lives character coming back from the dead!
To add to the dramatic flair, our findings were further validated by a statistically significant p-value of less than 0.01. This means that the likelihood of our results occurring by chance is slimmer than the chances of a soap opera wedding not being interrupted by some unforeseen calamity.
To illustrate the compelling relationship we uncovered, we present a scatterplot in Figure 1. This visual representation showcases the undeniable connection between these two seemingly disparate variables, demonstrating a trend so striking it would make even the most cynical of soap opera skeptics raise an eyebrow.
In conclusion, our research has revealed a correlation between burglaries in Connecticut and the viewership count of Days of Our Lives that not only captivates the imagination but also challenges conventional notions about the influences of popular media on real-life behaviors. It's a revelation that's sure to spark intense interest and lively discussions in both criminological and media studies circles, and one that might just leave you pondering the unexpected twists and turns of the human psyche. After all, who knew that the drama on our screens could have such an impact on the drama in our communities?

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In wrapping up our outlandishly captivating investigation, we can confidently state that the correlation between burglaries in Connecticut and the viewership count of Days of Our Lives is no mere soap opera plot twist - it's a groundbreaking finding that will keep both criminologists and soap opera enthusiasts on the edge of their seats. The data has spoken, and it has delivered a revelation so intriguing that it could rival the most gripping storylines on daytime television! As we close this chapter, we find ourselves marveling at the unexpected interplay between crime statistics and soap opera ratings, a connection that is as bewildering as it is ripe with potential for puns and frivolous wordplay.

Indeed, this study has demonstrated a correlation so strong that it might just steal the spotlight from the most notorious soap opera villains. The relationship between burglaries and Days of Our Lives viewership is a saga that challenges preconceived notions and beckons us to delve deeper into the enigmatic influence of daytime dramas on real-world behaviors. In the grand scheme of research investigations, this unlikely yet compelling correlation stands as a testament to the unpredictable nature of human preferences and tendencies, and is a stark reminder that truth can be stranger than fiction.

While we've had our fun uncovering this enthralling connection, it might be time to bid adieu to this particular avenue of inquiry. As much as we would relish spinning more yarns about the whimsical intertwining of crime stats and soap opera viewership, it appears that our findings have reached a resounding crescendo. Therefore, it is with a tinge of melodramatic flair that we assert: no more research is needed in this area. Thank you, and may the days of our research remain as lively and unexpected as the soap opera narratives that have inspired it.


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 Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Whimsical Criminology


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 Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Investigative Sociocultural Studies


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 Crimes: Unveiling the Intriguing Relationship Between Burglaries in Connecticut and Days of Our Lives Viewership with an abstract of This research paper investigates the entertaining yet unconventional link between the frequency of burglaries in the state of Connecticut and the viewership count of the long-running soap opera, Days of Our Lives. Upon delving into the data from FBI Criminal Justice Information Services and Wikipedia, our team uncovered a surprising correlation coefficient of 0.9286625 and a statistically significant p-value of < 0.01 for the period spanning from 1985 to 2021. Our findings challenge conventional wisdom and prompt further inquiry into the intricate dynamics between daytime television drama and criminal activities. We aim to amuse and enlighten as we explore this unexpected relationship, introducing a novel twist to the realms of criminology and media studies.

ChatGPT:

Days of Our Lives, burglaries, Connecticut, soap opera viewership, FBI crime data, criminal activities, correlation coefficient, p-value, daytime television, media studies, criminology, unconventional relationship

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

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 = 0.9286625 (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 = 0.8624140 (Coefficient of determination)
This means 86.2% 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 Connecticut) over the 37 years from 1985 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.21E-16. 0.0000000000000001208208044996
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.93 in 1.21E-14% of random cases. Said differently, if you correlated 8,276,720,256,429,932 random variables You don't actually need 8 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, 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.

[ 0.86, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
1985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021
Burglaries in Connecticut (Burglary rate)1135.51197.61218.3121812361227.71191.11108.6978.1889.8888.4842.2738.3665.9588512499.6494.7460.1456.1435.5444.6446.6431.5431.2423.6431.3411.7359.3334.3286.9281.7249.2223.5181.4187.1146.2
Viewership count for Days of Our Lives (Nielson share)7200000700000071000006500000540000052000005400000490000056000005300000580000058000005100000580000042000003800000360000031000003100000270000026000002300000210000022000002200000200000020000002100000190000020500001800000160000016000001600000140000012000001200000




Why this works

  1. 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.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([1135.5,1197.6,1218.3,1218,1236,1227.7,1191.1,1108.6,978.1,889.8,888.4,842.2,738.3,665.9,588,512,499.6,494.7,460.1,456.1,435.5,444.6,446.6,431.5,431.2,423.6,431.3,411.7,359.3,334.3,286.9,281.7,249.2,223.5,181.4,187.1,146.2,])
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 Connecticut"
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. 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:


View another random correlation

How fun was this correlation?

You're a rater extraordinaire!


Correlation ID: 2887 · Black Variable ID: 20133 · Red Variable ID: 87
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0