about · email me · subscribe
Spurious correlation #3,993 · 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 New Mexico 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 in New Mexico decreased, it led to a surplus of spare time for the residents. This unexpected surplus of time prompted a shift in daily routines, including a decline in midday television viewing. As a result, the viewership count for Days of Our Lives experienced a dip, proving that even the most unexpected factors can influence TV watching habits.

Model: dalle-3
Prompt: Generate an image in the style of a Polaroid photo capturing a cozy living room in New Mexico. The scene shows a peaceful living room with a switched-off TV, a pile of colorful yarn, and a knitting project beside it. In the background, a group of energetic people are doing Zumba dance moves. The atmosphere is serene, with no sign of the previous burglars. 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 New Mexico 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: Cyber folk Surrealism a Polaroid photo Psychedelic Low poly
ChatGPT: a Polaroid photo

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 New Mexico and Viewership count for Days of Our Lives, in the following situation: Because the burglars in New Mexico were actually avid fans of Days of Our Lives, and now that they've found other hobbies, they're too busy knitting and doing Zumba classes to tune in.. Keep the description simple.
ChatGPT: In a cozy living room in New Mexico, the TV that used to be tuned into Days of Our Lives is now switched off. A pile of colorful yarn sits next to a knitting project, and a group of people is energetically doing Zumba dance moves in the background. The room is peaceful now, with no sign of burglars who used to be avid viewers of the show.

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: [ a Polaroid photo ] and depicting this scene: In a cozy living room in New Mexico, the TV that used to be tuned into Days of Our Lives is now switched off. A pile of colorful yarn sits next to a knitting project, and a group of people is energetically doing Zumba dance moves in the background. The room is peaceful now, with no sign of burglars who used to be avid viewers of the show. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image in the style of a Polaroid photo capturing a cozy living room in New Mexico. The scene shows a peaceful living room with a switched-off TV, a pile of colorful yarn, and a knitting project beside it. In the background, a group of energetic people are doing Zumba dance moves. The atmosphere is serene, with no sign of the previous burglars.

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

AI academic paper

(Because p < 0.01)
Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership

Journal of Eccentric 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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 New Mexico and Viewership count for Days of Our Lives. Make lots of jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, just make it sound clever.

Your research team used data from FBI Criminal Justice Information Services and Wikipedia to assess this nagging question. You found a correlation coefficient of 0.9384693 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]]
Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership

[[ABSTRACT]]
In this study, we bring together the seemingly disparate worlds of soap operas and crime statistics to investigate the relationship between burglaries in New Mexico and viewership count for the long-running soap opera, Days of Our Lives. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we scrutinized crime rates and soap opera viewership from 1985 to 2021. Surprisingly, our analysis revealed a remarkably strong correlation, with a correlation coefficient of 0.9384693 and p < 0.01, indicating a highly significant association between the two seemingly unrelated variables. Our findings suggest that further investigation into the influence of soap operas on criminal behavior may be warranted, and we hope this study serves as a compelling foundation for future research in the curious intersection of television viewership and criminal activity.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 New Mexico 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]]
Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership

[[ABSTRACT]]
In this study, we bring together the seemingly disparate worlds of soap operas and crime statistics to investigate the relationship between burglaries in New Mexico and viewership count for the long-running soap opera, Days of Our Lives. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we scrutinized crime rates and soap opera viewership from 1985 to 2021. Surprisingly, our analysis revealed a remarkably strong correlation, with a correlation coefficient of 0.9384693 and p < 0.01, indicating a highly significant association between the two seemingly unrelated variables. Our findings suggest that further investigation into the influence of soap operas on criminal behavior may be warranted, and we hope this study serves as a compelling foundation for future research in the curious intersection of television viewership and criminal activity.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
Introduction

While the sprawling desert vistas of New Mexico may bring to mind images of tumbleweeds and cowboys, our research has delved into a different kind of Wild West drama - the correlation between burglaries in the Land of Enchantment and the viewership count for the venerable soap opera, Days of Our Lives. Cue the dramatic music, because this study aims to unravel the enigmatic link between criminal activity and daytime television dramas.

It may seem like an odd couple - burglaries and soap operas - but our investigation has unearthed an unexpected connection that would make even the most seasoned detective raise an eyebrow. By blending crime statistics with the saucy plots and melodramatic twists of Days of Our Lives, we have embarked on a quest to shed light on this peculiar relationship.

As we embark on this journey, it is essential to recognize that while correlations can be detected, causation remains elusive. We do not, by any means, imply that tuning in to Days of Our Lives would prompt an upstanding citizen to turn to a life of crime or that burglars are simply avid soap opera enthusiasts. However, the statistically robust relationship we have uncovered between these variables demands our attention and further exploration.

So, saddle up and join us as we ride into the sunset of soap opera intrigue and criminal statistics. This may just be the beginning of a tale that is stranger than fiction - a story where the lines between daytime drama and real-life crime blur in unexpected ways.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Burglaries in New Mexico 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership

[[ABSTRACT]]
In this study, we bring together the seemingly disparate worlds of soap operas and crime statistics to investigate the relationship between burglaries in New Mexico and viewership count for the long-running soap opera, Days of Our Lives. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we scrutinized crime rates and soap opera viewership from 1985 to 2021. Surprisingly, our analysis revealed a remarkably strong correlation, with a correlation coefficient of 0.9384693 and p < 0.01, indicating a highly significant association between the two seemingly unrelated variables. Our findings suggest that further investigation into the influence of soap operas on criminal behavior may be warranted, and we hope this study serves as a compelling foundation for future research in the curious intersection of television viewership and criminal activity.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
While the sprawling desert vistas of New Mexico may bring to mind images of tumbleweeds and cowboys, our research has delved into a different kind of Wild West drama - the correlation between burglaries in the Land of Enchantment and the viewership count for the venerable soap opera, Days of Our Lives. Cue the dramatic music, because this study aims to unravel the enigmatic link between criminal activity and daytime television dramas.
It may seem like an odd couple - burglaries and soap operas - but our investigation has unearthed an unexpected connection that would make even the most seasoned detective raise an eyebrow. By blending crime statistics with the saucy plots and melodramatic twists of Days of Our Lives, we have embarked on a quest to shed light on this peculiar relationship.
As we embark on this journey, it is essential to recognize that while correlations can be detected, causation remains elusive. We do not, by any means, imply that tuning in to Days of Our Lives would prompt an upstanding citizen to turn to a life of crime or that burglars are simply avid soap opera enthusiasts. However, the statistically robust relationship we have uncovered between these variables demands our attention and further exploration.
So, saddle up and join us as we ride into the sunset of soap opera intrigue and criminal statistics. This may just be the beginning of a tale that is stranger than fiction - a story where the lines between daytime drama and real-life crime blur in unexpected ways.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The authors find, in "Smith et al. (2010)," a comprehensive analysis of crime rates in New Mexico, providing detailed insights into the spatial and temporal patterns of burglaries in this region. The study elucidates the various socioeconomic and demographic factors that may influence criminal activity, shedding light on the complex tapestry of motivations behind property crimes. Additionally, "Doe and Johnson (2015)" delve into the psychological underpinnings of criminal behavior, offering a nuanced exploration of the cognitive processes that may drive individuals to engage in illicit activities. These seminal works serve as the bedrock upon which our investigation of the links between soap opera viewership and burglary rates in New Mexico is built.

Transitioning to a more unconventional realm of literature, "The Art of the Steal" by Frank W. Abagnale offers a gripping firsthand account of the intricacies of theft and deception, providing a fascinating perspective on the world of crime. On the subject of soap operas, "Days of Passion: A Culinary Journey" by Stephanie King whisks readers away on a savory adventure that tantalizes the senses, though it regrettably fails to provide empirical evidence regarding its impact on criminal proclivities.

Moving into the realm of fiction, "The Burglar on the Prowl" by Lawrence Block and "Days of Deception" by Linda Castillo captivate readers with their tales of intrigue and suspense, albeit in a fictional environment. As we traverse the lines between fact and fiction, it becomes increasingly apparent that our investigation treads upon a veritable minefield of unexpected connections and enthralling narratives.

Further enriching the cultural milieu surrounding our research, cinematic masterpieces such as "Ocean's Eleven" and "Gone in 60 Seconds" offer cinematic portrayals of high-stakes theft and daring heists, tangentially relating to the theme of our inquiry. While not directly tied to soap operas or New Mexico, these films add a dash of Hollywood glamour to our exploration of criminal intrigue.

In the interplay of reality and make-believe, our investigation stands poised at the intersection of statistical analysis, pop culture, and daring escapades. The peculiar dance between daytime drama and criminal activity beckons us into a realm where the improbable becomes enshrined as a statistical reality, evoking a sense of whimsy that is as captivating as it is confounding.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 New Mexico 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]]
Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership

[[ABSTRACT]]
In this study, we bring together the seemingly disparate worlds of soap operas and crime statistics to investigate the relationship between burglaries in New Mexico and viewership count for the long-running soap opera, Days of Our Lives. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we scrutinized crime rates and soap opera viewership from 1985 to 2021. Surprisingly, our analysis revealed a remarkably strong correlation, with a correlation coefficient of 0.9384693 and p < 0.01, indicating a highly significant association between the two seemingly unrelated variables. Our findings suggest that further investigation into the influence of soap operas on criminal behavior may be warranted, and we hope this study serves as a compelling foundation for future research in the curious intersection of television viewership and criminal activity.

[[INTRODUCTION]]
Introduction
While the sprawling desert vistas of New Mexico may bring to mind images of tumbleweeds and cowboys, our research has delved into a different kind of Wild West drama - the correlation between burglaries in the Land of Enchantment and the viewership count for the venerable soap opera, Days of Our Lives. Cue the dramatic music, because this study aims to unravel the enigmatic link between criminal activity and daytime television dramas.
It may seem like an odd couple - burglaries and soap operas - but our investigation has unearthed an unexpected connection that would make even the most seasoned detective raise an eyebrow. By blending crime statistics with the saucy plots and melodramatic twists of Days of Our Lives, we have embarked on a quest to shed light on this peculiar relationship.
As we embark on this journey, it is essential to recognize that while correlations can be detected, causation remains elusive. We do not, by any means, imply that tuning in to Days of Our Lives would prompt an upstanding citizen to turn to a life of crime or that burglars are simply avid soap opera enthusiasts. However, the statistically robust relationship we have uncovered between these variables demands our attention and further exploration.
So, saddle up and join us as we ride into the sunset of soap opera intrigue and criminal statistics. This may just be the beginning of a tale that is stranger than fiction - a story where the lines between daytime drama and real-life crime blur in unexpected ways.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To illuminate the intriguing connection between burglaries in New Mexico and the viewership count for Days of Our Lives, our research team undertook a voyage into the convoluted world of data collection and analysis. We meticulously gathered data from multiple sources, including the FBI Criminal Justice Information Services and the font of all knowledge, Wikipedia.

To extract the relevant crime statistics, we donned our metaphorical detective hats and combed through the FBI Uniform Crime Reporting (UCR) program's database, meticulously sifting through the treasure trove of burglary data from the Land of Enchantment over the span of 1985 to 2021. These crime figures provided us with a comprehensive understanding of the ebb and flow of illicit activities in New Mexico, offering a canvas on which to sketch our investigation.

Simultaneously, we delved into the labyrinthine expanse of soap opera lore, tapping into the vast reserves of Wikipedia to extract the viewership count for the long-running melodrama, Days of Our Lives. With the dexterity of a seasoned archivist, we stitched together a timeline of the soap opera's viewership, spanning from the bygone era of the '80s to the present day, with due attention to the dramatic peaks and valleys of audience engagement.

Once we amassed the bedrock of data, we embarked on a statistical odyssey, employing the venerable spearman correlation analysis to unveil the hidden threads weaving together burglaries and soap opera viewership. With a flourish of statistical wizardry, we determined the correlation coefficient and p-value to ascertain the strength and significance of the relationship between these seemingly incongruous variables.

Our data-crafting journey traversed the virtual plains of internet archives and crime databases, finally converging in a spirited dance of numbers and insights to shed light on the enigmatic bond between daytime television dramas and criminal activities. Bend an ear, dear reader, and join us in the exhilarating quest that peeled back the layers of this bizarre tapestry of correlations.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Burglaries in New Mexico 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 0.9384693, r-squared of 0.8807247, 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]]
Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership

[[ABSTRACT]]
In this study, we bring together the seemingly disparate worlds of soap operas and crime statistics to investigate the relationship between burglaries in New Mexico and viewership count for the long-running soap opera, Days of Our Lives. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we scrutinized crime rates and soap opera viewership from 1985 to 2021. Surprisingly, our analysis revealed a remarkably strong correlation, with a correlation coefficient of 0.9384693 and p < 0.01, indicating a highly significant association between the two seemingly unrelated variables. Our findings suggest that further investigation into the influence of soap operas on criminal behavior may be warranted, and we hope this study serves as a compelling foundation for future research in the curious intersection of television viewership and criminal activity.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
While the sprawling desert vistas of New Mexico may bring to mind images of tumbleweeds and cowboys, our research has delved into a different kind of Wild West drama - the correlation between burglaries in the Land of Enchantment and the viewership count for the venerable soap opera, Days of Our Lives. Cue the dramatic music, because this study aims to unravel the enigmatic link between criminal activity and daytime television dramas.
It may seem like an odd couple - burglaries and soap operas - but our investigation has unearthed an unexpected connection that would make even the most seasoned detective raise an eyebrow. By blending crime statistics with the saucy plots and melodramatic twists of Days of Our Lives, we have embarked on a quest to shed light on this peculiar relationship.
As we embark on this journey, it is essential to recognize that while correlations can be detected, causation remains elusive. We do not, by any means, imply that tuning in to Days of Our Lives would prompt an upstanding citizen to turn to a life of crime or that burglars are simply avid soap opera enthusiasts. However, the statistically robust relationship we have uncovered between these variables demands our attention and further exploration.
So, saddle up and join us as we ride into the sunset of soap opera intrigue and criminal statistics. This may just be the beginning of a tale that is stranger than fiction - a story where the lines between daytime drama and real-life crime blur in unexpected ways.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

**[[RESULTS]]**

The correlation analysis between burglaries in New Mexico and viewership count for Days of Our Lives yielded a surprising and eyebrow-raising result. We found a remarkably strong correlation coefficient of 0.9384693, indicating a nearly perfect positive linear relationship between these two variables. In other words, as the viewership count for Days of Our Lives increased, so did the number of burglaries in New Mexico. It seems that the drama on the small screen was mirrored by real-life criminal activity, creating a plot twist worthy of a daytime soap opera itself.

Furthermore, the coefficient of determination (r-squared) was calculated at 0.8807247, indicating that a substantial 88.07% of the variation in burglaries in New Mexico can be explained by the viewership count for Days of Our Lives. This suggests that there is indeed a strong association between these two seemingly disparate phenomena.

The p-value of less than 0.01 indicates that the observed correlation is statistically significant, providing compelling evidence that the association between New Mexico burglaries and Days of Our Lives viewership count is not just a coincidence but a genuine relationship that defies conventional expectations.

In order to visualize this unexpected correlation, a scatterplot (Fig. 1) was constructed to illustrate the strong positive relationship between burglaries in New Mexico and Days of Our Lives viewership count, providing a graphical representation of this unforeseen connection.

These findings challenge conventional wisdom and prompt further investigation into the influence of television viewership on criminal behavior. The statistical evidence uncovered in this study suggests that the influence of daytime soap operas on real-world activities may be more significant than previously assumed, opening avenues for future research that delve into the curious intersection of popular culture and criminal tendencies. It appears that the Days of Our Lives may be more revealing about our society than we ever imagined.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Burglaries in New Mexico 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]]
Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership

[[ABSTRACT]]
In this study, we bring together the seemingly disparate worlds of soap operas and crime statistics to investigate the relationship between burglaries in New Mexico and viewership count for the long-running soap opera, Days of Our Lives. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we scrutinized crime rates and soap opera viewership from 1985 to 2021. Surprisingly, our analysis revealed a remarkably strong correlation, with a correlation coefficient of 0.9384693 and p < 0.01, indicating a highly significant association between the two seemingly unrelated variables. Our findings suggest that further investigation into the influence of soap operas on criminal behavior may be warranted, and we hope this study serves as a compelling foundation for future research in the curious intersection of television viewership and criminal activity.

[[LITERATURE REVIEW]]
The authors find, in "Smith et al. (2010)," a comprehensive analysis of crime rates in New Mexico, providing detailed insights into the spatial and temporal patterns of burglaries in this region. The study elucidates the various socioeconomic and demographic factors that may influence criminal activity, shedding light on the complex tapestry of motivations behind property crimes. Additionally, "Doe and Johnson (2015)" delve into the psychological underpinnings of criminal behavior, offering a nuanced exploration of the cognitive processes that may drive individuals to engage in illicit activities. These seminal works serve as the bedrock upon which our investigation of the links between soap opera viewership and burglary rates in New Mexico is built.
Transitioning to a more unconventional realm of literature, "The Art of the Steal" by Frank W. Abagnale offers a gripping firsthand account of the intricacies of theft and deception, providing a fascinating perspective on the world of crime. On the subject of soap operas, "Days of Passion: A Culinary Journey" by Stephanie King whisks readers away on a savory adventure that tantalizes the senses, though it regrettably fails to provide empirical evidence regarding its impact on criminal proclivities.
Moving into the realm of fiction, "The Burglar on the Prowl" by Lawrence Block and "Days of Deception" by Linda Castillo captivate readers with their tales of intrigue and suspense, albeit in a fictional environment. As we traverse the lines between fact and fiction, it becomes increasingly apparent that our investigation treads upon a veritable minefield of unexpected connections and enthralling narratives.
Further enriching the cultural milieu surrounding our research, cinematic masterpieces such as "Ocean's Eleven" and "Gone in 60 Seconds" offer cinematic portrayals of high-stakes theft and daring heists, tangentially relating to the theme of our inquiry. While not directly tied to soap operas or New Mexico, these films add a dash of Hollywood glamour to our exploration of criminal intrigue.
In the interplay of reality and make-believe, our investigation stands poised at the intersection of statistical analysis, pop culture, and daring escapades. The peculiar dance between daytime drama and criminal activity beckons us into a realm where the improbable becomes enshrined as a statistical reality, evoking a sense of whimsy that is as captivating as it is confounding.

[[RESULTS]]
The correlation analysis between burglaries in New Mexico and viewership count for Days of Our Lives yielded a surprising and eyebrow-raising result. We found a remarkably strong correlation coefficient of 0.9384693, indicating a nearly perfect positive linear relationship between these two variables. In other words, as the viewership count for Days of Our Lives increased, so did the number of burglaries in New Mexico. It seems that the drama on the small screen was mirrored by real-life criminal activity, creating a plot twist worthy of a daytime soap opera itself.
Furthermore, the coefficient of determination (r-squared) was calculated at 0.8807247, indicating that a substantial 88.07% of the variation in burglaries in New Mexico can be explained by the viewership count for Days of Our Lives. This suggests that there is indeed a strong association between these two seemingly disparate phenomena.
The p-value of less than 0.01 indicates that the observed correlation is statistically significant, providing compelling evidence that the association between New Mexico burglaries and Days of Our Lives viewership count is not just a coincidence but a genuine relationship that defies conventional expectations.
In order to visualize this unexpected correlation, a scatterplot (Fig. 1) was constructed to illustrate the strong positive relationship between burglaries in New Mexico and Days of Our Lives viewership count, providing a graphical representation of this unforeseen connection.
These findings challenge conventional wisdom and prompt further investigation into the influence of television viewership on criminal behavior. The statistical evidence uncovered in this study suggests that the influence of daytime soap operas on real-world activities may be more significant than previously assumed, opening avenues for future research that delve into the curious intersection of popular culture and criminal tendencies. It appears that the Days of Our Lives may be more revealing about our society than we ever imagined.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our study has uncovered an intriguing and unexpected relationship between two seemingly incongruous phenomena: burglaries in New Mexico and the viewership count for Days of Our Lives. It is not just a coincidence but a statistical reality that defies conventional expectations. These findings support and extend prior research, such as the comprehensive analysis of crime rates in New Mexico by Smith et al. (2010), which provided valuable insights into the spatial and temporal patterns of burglaries in the region. Our results suggest that societal and cultural influences, including television viewership, may play a more substantial role in shaping criminal behavior than previously assumed.

The correlation coefficient of 0.9384693, with a p-value of less than 0.01, indicates a highly significant association between Days of Our Lives viewership count and burglaries in New Mexico. This aligns with "Doe and Johnson (2015)," who delved into the psychological underpinnings of criminal behavior, and suggests that cognitive processes may be influenced by external stimuli, including the narratives and dramatic portrayals encapsulated in television soap operas.

While it may seem as improbable as a soap opera plot twist, our findings substantiate the idea that the peculiar dance between daytime drama and criminal activity may indeed be linked. Just as "The Art of the Steal" by Frank W. Abagnale offered a firsthand account of the intricacies of theft and deception, our study offers a statistical account of the curious association between soap opera viewership and criminal proclivities. It appears that the drama on the small screen is mirrored by real-life criminal activity, prompting thoughts of intrigue and suspense akin to the fictional tales offered by Lawrence Block and Linda Castillo.

Our results serve as a compelling foundation for future research, paving the way for further investigations into the influence of popular culture on criminal tendencies. As we traverse the lines between fact and fiction, it becomes increasingly apparent that our investigation treads upon a veritable minefield of unexpected connections and enthralling narratives. The statistical evidence uncovered in this study suggests that the influence of daytime soap operas on real-world activities may be more substantial than previously assumed, hinting at the potential for a scripted reality television crossover that is as captivating as it is confounding.

In conclusion, our study challenges conventional wisdom and propels us into a realm where the improbable becomes enshrined as a statistical reality, evoking a sense of whimsy that is as captivating as it is confounding. The Days of Our Lives may be more revealing about our society than we ever imagined, and the allure of this unexpected correlation begs for further exploration at the intersection of popular culture and criminal tendencies. As we close the chapter on this study, the need for continued research into the influence of television viewership on criminal behavior is glaringly evident, and it is our hope that this investigation sparks further curiosity and inquiry in this intriguing field of study.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Burglaries in New Mexico 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]]
Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership

[[ABSTRACT]]
In this study, we bring together the seemingly disparate worlds of soap operas and crime statistics to investigate the relationship between burglaries in New Mexico and viewership count for the long-running soap opera, Days of Our Lives. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we scrutinized crime rates and soap opera viewership from 1985 to 2021. Surprisingly, our analysis revealed a remarkably strong correlation, with a correlation coefficient of 0.9384693 and p < 0.01, indicating a highly significant association between the two seemingly unrelated variables. Our findings suggest that further investigation into the influence of soap operas on criminal behavior may be warranted, and we hope this study serves as a compelling foundation for future research in the curious intersection of television viewership and criminal activity.

[[INTRDUCTION]]
Introduction
While the sprawling desert vistas of New Mexico may bring to mind images of tumbleweeds and cowboys, our research has delved into a different kind of Wild West drama - the correlation between burglaries in the Land of Enchantment and the viewership count for the venerable soap opera, Days of Our Lives. Cue the dramatic music, because this study aims to unravel the enigmatic link between criminal activity and daytime television dramas.
It may seem like an odd couple - burglaries and soap operas - but our investigation has unearthed an unexpected connection that would make even the most seasoned detective raise an eyebrow. By blending crime statistics with the saucy plots and melodramatic twists of Days of Our Lives, we have embarked on a quest to shed light on this peculiar relationship.
As we embark on this journey, it is essential to recognize that while correlations can be detected, causation remains elusive. We do not, by any means, imply that tuning in to Days of Our Lives would prompt an upstanding citizen to turn to a life of crime or that burglars are simply avid soap opera enthusiasts. However, the statistically robust relationship we have uncovered between these variables demands our attention and further exploration.
So, saddle up and join us as we ride into the sunset of soap opera intrigue and criminal statistics. This may just be the beginning of a tale that is stranger than fiction - a story where the lines between daytime drama and real-life crime blur in unexpected ways.

[[RESULTS]]
The correlation analysis between burglaries in New Mexico and viewership count for Days of Our Lives yielded a surprising and eyebrow-raising result. We found a remarkably strong correlation coefficient of 0.9384693, indicating a nearly perfect positive linear relationship between these two variables. In other words, as the viewership count for Days of Our Lives increased, so did the number of burglaries in New Mexico. It seems that the drama on the small screen was mirrored by real-life criminal activity, creating a plot twist worthy of a daytime soap opera itself.
Furthermore, the coefficient of determination (r-squared) was calculated at 0.8807247, indicating that a substantial 88.07% of the variation in burglaries in New Mexico can be explained by the viewership count for Days of Our Lives. This suggests that there is indeed a strong association between these two seemingly disparate phenomena.
The p-value of less than 0.01 indicates that the observed correlation is statistically significant, providing compelling evidence that the association between New Mexico burglaries and Days of Our Lives viewership count is not just a coincidence but a genuine relationship that defies conventional expectations.
In order to visualize this unexpected correlation, a scatterplot (Fig. 1) was constructed to illustrate the strong positive relationship between burglaries in New Mexico and Days of Our Lives viewership count, providing a graphical representation of this unforeseen connection.
These findings challenge conventional wisdom and prompt further investigation into the influence of television viewership on criminal behavior. The statistical evidence uncovered in this study suggests that the influence of daytime soap operas on real-world activities may be more significant than previously assumed, opening avenues for future research that delve into the curious intersection of popular culture and criminal tendencies. It appears that the Days of Our Lives may be more revealing about our society than we ever imagined.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

The results of this study have unraveled an unexpected and spicier-than-a-telenovela connection between burglaries in New Mexico and the viewership count for Days of Our Lives. The nearly perfect positive linear relationship between these variables leaves us pondering whether the melodramatic plotlines of the daytime soap opera are influencing real-life crime or if criminals are just avid fans of dramatic TV. It seems that the intriguing love triangles and familial feuds on screen may be mirrored by the clandestine activities of burglars, creating a storyline worthy of the soap opera itself.

Our findings, with a correlation coefficient of 0.9384693 and a p-value of less than 0.01, have provided compelling evidence that this correlation is not just a soap opera cliffhanger but a genuine statistical relationship. A substantial 88.07% of the variation in burglaries in New Mexico can be explained by the viewership count for Days of Our Lives, showcasing the significant association between these seemingly disparate phenomena.

The graphical representation in the scatterplot illustrates this unforeseen connection, and one can't help but wonder if the escapades of Salem's residents are playing out in the real-world streets of New Mexico.

In the spirit of daytime dramas, where every cliffhanger seems to lead to a shocking revelation, our study may just be the beginning of a tale that is stranger than fiction. However, in conclusion, we assert that no further research is needed in this area, as the link between these two unrelated variables has been sufficiently established. It's time to close this case and tune in to the next soap opera episode.


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 Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Eccentric 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 Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership. Respond only with the name of a fictional organization.

ChatGPT:

The Consortium for Quirky Behavioral 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 Days of Our Crimes: Unraveling the Link Between New Mexico Burglaries and Days of Our Lives Viewership with an abstract of In this study, we bring together the seemingly disparate worlds of soap operas and crime statistics to investigate the relationship between burglaries in New Mexico and viewership count for the long-running soap opera, Days of Our Lives. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, we scrutinized crime rates and soap opera viewership from 1985 to 2021. Surprisingly, our analysis revealed a remarkably strong correlation, with a correlation coefficient of 0.9384693 and p < 0.01, indicating a highly significant association between the two seemingly unrelated variables. Our findings suggest that further investigation into the influence of soap operas on criminal behavior may be warranted, and we hope this study serves as a compelling foundation for future research in the curious intersection of television viewership and criminal activity.

ChatGPT:

New Mexico burglaries, Days of Our Lives viewership, soap opera influence on criminal behavior, crime statistics, FBI Criminal Justice Information Services, New Mexico crime rates, relationship between soap operas and criminal activity, Days of Our Lives viewership correlation, influence of television viewership on criminal behavior, soap opera viewership and crime statistics correlation

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

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 = 0.9384693 (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 = 0.8807247 (Coefficient of determination)
This means 88.1% 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 New Mexico) over the 37 years from 1985 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 9.8E-18. 0.0000000000000000098275339922
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 0.94 in 9.8E-16% of random cases. Said differently, if you correlated 101,754,926,596,406,416 random variables You don't actually need 101 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.

[ 0.88, 0.97 ] 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 New Mexico (Burglary rate)1753.91844.71787.71836.91711.11738.717231511.41421.21326.81447.11376.91452.413941234.71173.11067.91060.11011.310471087.21069.61057.11043.51092.51017.61030.41026.31046887.3821.2828.6853.7769.4697.3648.8607.2
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([1753.9,1844.7,1787.7,1836.9,1711.1,1738.7,1723,1511.4,1421.2,1326.8,1447.1,1376.9,1452.4,1394,1234.7,1173.1,1067.9,1060.1,1011.3,1047,1087.2,1069.6,1057.1,1043.5,1092.5,1017.6,1030.4,1026.3,1046,887.3,821.2,828.6,853.7,769.4,697.3,648.8,607.2,])
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 New Mexico"
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?

Cheers to you for rating this correlation!


Correlation ID: 3993 · Black Variable ID: 20109 · Red Variable ID: 87
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0