Spurious correlation #1,895 · 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 South Dakota and the second variable is Viewership count for Days of Our Lives. The chart goes from 1985 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Burglaries in South Dakota and the second variable is Viewership count for Days of Our Lives. The chart goes from 1985 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As burglaries in South Dakota decreased, there was a corresponding decrease in the need for neighborhood watch groups. With less to keep an eye on, residents found themselves with a lot more free time during the day. Some of them decided to spend that time catching up on Days of Our Lives, leading to a decrease in the overall viewership count for the show.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image inspired by the cover of a Discovery magazine, capturing a cozy living room in South Dakota. In the room, a television is broadcasting "Days of Our Lives," with the fictional drama capturing the attention of the viewers. Suddenly, the scene transitions to a dark alley outside, where a burglar is attempting to break into a nearby house. The atmosphere is intensified by the suspenseful music from the show. The living room should exude a warm and inviting ambiance, while the dark alley outside feels foreboding and dangerous. 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 South Dakota 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: Magic realism Realistic Futuristic Data cyber art A Discovery magazine cover image
ChatGPT: A Discovery magazine cover image

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 South Dakota and Viewership count for Days of Our Lives together. Keep the description simple.
ChatGPT: In a cozy living room in South Dakota, the TV is tuned in to "Days of Our Lives," with the fictional drama captivating the viewers. Suddenly, the scene shifts to a dark alley outside, where a burglar is attempting to break into a nearby house while the show's suspenseful music adds to the atmosphere.

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 Discovery magazine cover image ] and depicting this scene: In a cozy living room in South Dakota, the TV is tuned in to "Days of Our Lives," with the fictional drama captivating the viewers. Suddenly, the scene shifts to a dark alley outside, where a burglar is attempting to break into a nearby house while the show's suspenseful music adds to the atmosphere. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image inspired by the cover of a Discovery magazine, capturing a cozy living room in South Dakota. In the room, a television is broadcasting "Days of Our Lives," with the fictional drama capturing the attention of the viewers. Suddenly, the scene transitions to a dark alley outside, where a burglar is attempting to break into a nearby house. The atmosphere is intensified by the suspenseful music from the show. The living room should exude a warm and inviting ambiance, while the dark alley outside feels foreboding and dangerous.

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

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

AI academic paper

(Because p < 0.01)

Days of Our Crimes: A Burglary of Interest in South Dakota

The Journal of Criminological Shenanigans

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Burglaries in South Dakota 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: A Burglary of Interest in South Dakota

[[ABSTRACT]]
This paper investigates the peculiar relationship between the frequency of burglaries in South Dakota and the viewership count for the soap opera "Days of Our Lives." Despite their seemingly unrelated nature, our findings reveal a surprising correlation between these two variables. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, our analysis covers the period from 1985 to 2021. The correlation coefficient of 0.9183756 and p < 0.01 suggest a strong association between these seemingly distinct phenomena. We delve into possible explanations for this unexpected connection, exploring the potential impact of daytime television drama on criminal behavior. Our research sparks both interest and intrigue, offering a unique lens through which to view the dynamics of popular culture and crime in a seemingly unassuming state.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The correlation between seemingly unrelated phenomena has long been a source of intrigue for researchers across various disciplines. In the realm of criminology and cultural studies, unexpected connections have been the subject of countless investigations. We, too, were drawn to explore the peculiar relationship between the frequency of burglaries in South Dakota and the viewership count for the long-running soap opera "Days of Our Lives."
While it may seem as though these two variables belong to different worlds—one rooted in criminal behavior and the other in daytime television drama—our analysis has unveiled a surprising correlation. The aim of this research is to shed light on this unexpected connection and to offer potential explanations for the observed phenomena. As we unveil the findings of our investigation, we invite readers to bear with us through this rather unconventional journey into the world of crime, drama, and correlation analysis.
The conventional wisdom of academia might point to a skepticism towards such an unlikely connection, citing the need for rigorous analysis, robust methodology, and a commitment to uncovering the truth. However, in the spirit of true scholarly investigation, we have embarked on this journey with an open mind, prepared to embrace the unexpected and challenge preconceived notions.
As we embark on this scientific escapade, we implore readers to open their minds to the possibility of unconventional correlations and the nuanced interplay of seemingly disparate societal factors. Our findings have the potential to offer a fresh perspective on the dynamics of popular culture and its influence on criminal behavior within the state of South Dakota. So, grab your notebook and magnifying glass, because we are about to unravel a mystery that could rival those found in the most engrossing of soap opera storylines, complete with unexpected twists and turns.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith and Doe (2005) conducted a comprehensive analysis of factors contributing to burglaries in rural Midwestern states. They identified demographic, economic, and environmental variables as significant predictors of burglary rates. Similarly, Jones et al. (2010) examined the impact of television viewership on societal behavior, focusing on the influence of daytime soap operas. The authors found that viewership of daytime dramas was associated with heightened emotional responses and social interactions among viewers.

As we venture further into the literature, it is essential to acknowledge the broader context in which our research sits. Works such as "Crime and Punishment" by Fyodor Dostoevsky and "The Great Gatsby" by F. Scott Fitzgerald have long captured the complexities of human behavior and societal influences. While these literary works may not offer direct insights into our specific investigation, they do provide a backdrop against which we can contemplate the intertwining of human desires, societal constructs, and unexpected plot twists.

Turning now to popular fiction, the likes of Agatha Christie's "The Mysterious Affair at Styles" and Arthur Conan Doyle's "The Adventure of the Empty House" invite readers to delve into the world of mysteries, deception, and, of course, unexpected correlations. Perhaps, in the case of our investigation, we are about to uncover a not-so-elementary connection between burglaries and soap opera viewership.

In the realm of cinematic entertainment, film enthusiasts may find themselves wondering whether movies like "Ocean's Eleven" and "The Italian Job" provide any parallels to the peculiar correlation we are scrutinizing. While these films may not directly relate to the television viewership of "Days of Our Lives," they do offer a glimpse into the intriguing world of heists, capers, and the allure of unexpected capers, much like the correlation we seek to unravel.

As we navigate through these varied literary and cinematic references, it becomes evident that the intersection of criminal behavior and cultural influences is far from a straightforward matter. Nonetheless, the whimsical nature of our investigation invites a lighthearted exploration of potential parallels, surprising connections, and, quite possibly, some unforeseen plot twists.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Burglaries in South Dakota and Viewership count for Days of Our Lives. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
Days of Our Crimes: A Burglary of Interest in South Dakota

[[ABSTRACT]]
This paper investigates the peculiar relationship between the frequency of burglaries in South Dakota and the viewership count for the soap opera "Days of Our Lives." Despite their seemingly unrelated nature, our findings reveal a surprising correlation between these two variables. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, our analysis covers the period from 1985 to 2021. The correlation coefficient of 0.9183756 and p < 0.01 suggest a strong association between these seemingly distinct phenomena. We delve into possible explanations for this unexpected connection, exploring the potential impact of daytime television drama on criminal behavior. Our research sparks both interest and intrigue, offering a unique lens through which to view the dynamics of popular culture and crime in a seemingly unassuming state.

[[LITERATURE REVIEW]]
In their seminal work, Smith and Doe (2005) conducted a comprehensive analysis of factors contributing to burglaries in rural Midwestern states. They identified demographic, economic, and environmental variables as significant predictors of burglary rates. Similarly, Jones et al. (2010) examined the impact of television viewership on societal behavior, focusing on the influence of daytime soap operas. The authors found that viewership of daytime dramas was associated with heightened emotional responses and social interactions among viewers.
As we venture further into the literature, it is essential to acknowledge the broader context in which our research sits. Works such as "Crime and Punishment" by Fyodor Dostoevsky and "The Great Gatsby" by F. Scott Fitzgerald have long captured the complexities of human behavior and societal influences. While these literary works may not offer direct insights into our specific investigation, they do provide a backdrop against which we can contemplate the intertwining of human desires, societal constructs, and unexpected plot twists.
Turning now to popular fiction, the likes of Agatha Christie's "The Mysterious Affair at Styles" and Arthur Conan Doyle's "The Adventure of the Empty House" invite readers to delve into the world of mysteries, deception, and, of course, unexpected correlations. Perhaps, in the case of our investigation, we are about to uncover a not-so-elementary connection between burglaries and soap opera viewership.
In the realm of cinematic entertainment, film enthusiasts may find themselves wondering whether movies like "Ocean's Eleven" and "The Italian Job" provide any parallels to the peculiar correlation we are scrutinizing. While these films may not directly relate to the television viewership of "Days of Our Lives," they do offer a glimpse into the intriguing world of heists, capers, and the allure of unexpected capers, much like the correlation we seek to unravel.
As we navigate through these varied literary and cinematic references, it becomes evident that the intersection of criminal behavior and cultural influences is far from a straightforward matter. Nonetheless, the whimsical nature of our investigation invites a lighthearted exploration of potential parallels, surprising connections, and, quite possibly, some unforeseen plot twists.

[[RESULTS]]
The statistical analysis of the data revealed a striking correlation between the frequency of burglaries in South Dakota and the viewership count for the beloved soap opera "Days of Our Lives." With a correlation coefficient of 0.9183756 and an r-squared value of 0.8434137, the strength of the association was both remarkable and, dare I say, soap-worthy. The p-value of less than 0.01 further affirmed the significance of this unexpected relationship, leaving even the most skeptical of researchers raising an eyebrow in curiosity.
Figure 1 depicts the scatterplot illustrating the robust correlation between these seemingly incongruent variables. The data points form a nearly perfect diagonal line, reflecting the eerily synchronized pattern of burglaries and soap opera viewership. It's almost as if the characters in "Days of Our Lives" were masterminding the thefts themselves, weaving a narrative of crime and drama that transcends the television screen and infiltrates the real world.
As much as we would all love to attribute this peculiar correlation to a clandestine plot by soap opera aficionados, it is essential to tread cautiously in drawing definitive conclusions. However, the strength of our findings cannot be denied, and it prompts us to consider the potential mechanisms underlying this unforeseen link. Could it be the suspense and intrigue of the soap opera that lures potential burglars indoors, captivated by the unfolding drama and forgetting their criminal intentions? Or perhaps the cultural phenomenon of soap opera viewing is an unconscious outlet for individuals prone to criminal behavior, serving as a temporary reprieve from their illicit inclinations.
Our results beg the question: are the captivating storylines of "Days of Our Lives" more than just entertainment, permeating into the fabric of societal norms and influencing behaviors in ways we have never anticipated? We are left to contemplate the implications of these findings and the broader implications for understanding the intricate interplay between popular culture and criminal activity. Although our investigation yields no definitive answers, it serves as a thought-provoking entry point into a sphere of inquiry that defies conventional boundaries, much like the soap opera that sparked our curiosity.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The unexpected correlation between burglaries in South Dakota and the viewership count for "Days of Our Lives" has prompted a lively discussion among researchers and soap opera enthusiasts alike. Our findings not only support the existing literature on the influence of popular culture on societal behavior but also highlight the need for further exploration into the nuanced connections between seemingly unrelated phenomena.

As we reflect on the literature review, it is intriguing to note how our results align with prior research on the impact of television viewership on societal behavior. Jones et al. (2010) emphasized the heightened emotional responses and social interactions among viewers of daytime soap operas, providing a theoretical framework through which we can understand the unexpected correlation observed in our study. The strong positive correlation coefficient and the significant p-value strongly supported the notion that there is more than meets the eye in the relationship between burglaries and soap opera viewership. Much like the unexpected plot twists in a daytime drama, our results have added a new layer of complexity to the interaction between popular culture and criminal activity.

Furthermore, our investigation has uncovered potential parallels with classic literary works and cinematic references. While the whimsical nature of these references may initially seem out of place in a discussion of empirical research, the unexpected correlation we have uncovered invites a playful examination of the intricate web of influences that shape human behavior. The whimsical nature of our investigation has indeed led to an interesting plot twist in the realm of empirical research, demonstrating that the real world can be just as surprising and multifaceted as the fictional narratives we enjoy.

The robustness of our findings prompts us to contemplate the underlying mechanisms that may drive the observed correlation. Like a gripping soap opera plot, we are left to ponder whether individuals are subconsciously influenced by the captivating storylines of "Days of Our Lives," leading them to either engage in criminal behaviors or seek solace from them through the narrative drama. This unexpected association challenges traditional notions of causality and calls for a more nuanced understanding of the interplay between popular culture and criminal activity.

In conclusion, our investigation has unveiled a compelling correlation between burglaries in South Dakota and the viewership count for "Days of Our Lives," shedding light on the intricate interplay between daytime television drama and criminal behavior. While the unexpected nature of our findings may rival the most elaborate soap opera plotlines, they provide a thought-provoking entry point into a sphere of inquiry that defies conventional boundaries. The parallels with the literature review and the surprising twists emerging from our empirical analysis demonstrate the value of approaching research with a lighthearted curiosity, even in the most unexpected of contexts.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Burglaries in South Dakota and Viewership count for Days of Our Lives. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Days of Our Crimes: A Burglary of Interest in South Dakota

[[ABSTRACT]]
This paper investigates the peculiar relationship between the frequency of burglaries in South Dakota and the viewership count for the soap opera "Days of Our Lives." Despite their seemingly unrelated nature, our findings reveal a surprising correlation between these two variables. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, our analysis covers the period from 1985 to 2021. The correlation coefficient of 0.9183756 and p < 0.01 suggest a strong association between these seemingly distinct phenomena. We delve into possible explanations for this unexpected connection, exploring the potential impact of daytime television drama on criminal behavior. Our research sparks both interest and intrigue, offering a unique lens through which to view the dynamics of popular culture and crime in a seemingly unassuming state.

[[INTRDUCTION]]
The correlation between seemingly unrelated phenomena has long been a source of intrigue for researchers across various disciplines. In the realm of criminology and cultural studies, unexpected connections have been the subject of countless investigations. We, too, were drawn to explore the peculiar relationship between the frequency of burglaries in South Dakota and the viewership count for the long-running soap opera "Days of Our Lives."
While it may seem as though these two variables belong to different worlds—one rooted in criminal behavior and the other in daytime television drama—our analysis has unveiled a surprising correlation. The aim of this research is to shed light on this unexpected connection and to offer potential explanations for the observed phenomena. As we unveil the findings of our investigation, we invite readers to bear with us through this rather unconventional journey into the world of crime, drama, and correlation analysis.
The conventional wisdom of academia might point to a skepticism towards such an unlikely connection, citing the need for rigorous analysis, robust methodology, and a commitment to uncovering the truth. However, in the spirit of true scholarly investigation, we have embarked on this journey with an open mind, prepared to embrace the unexpected and challenge preconceived notions.
As we embark on this scientific escapade, we implore readers to open their minds to the possibility of unconventional correlations and the nuanced interplay of seemingly disparate societal factors. Our findings have the potential to offer a fresh perspective on the dynamics of popular culture and its influence on criminal behavior within the state of South Dakota. So, grab your notebook and magnifying glass, because we are about to unravel a mystery that could rival those found in the most engrossing of soap opera storylines, complete with unexpected twists and turns.

[[RESULTS]]
The statistical analysis of the data revealed a striking correlation between the frequency of burglaries in South Dakota and the viewership count for the beloved soap opera "Days of Our Lives." With a correlation coefficient of 0.9183756 and an r-squared value of 0.8434137, the strength of the association was both remarkable and, dare I say, soap-worthy. The p-value of less than 0.01 further affirmed the significance of this unexpected relationship, leaving even the most skeptical of researchers raising an eyebrow in curiosity.
Figure 1 depicts the scatterplot illustrating the robust correlation between these seemingly incongruent variables. The data points form a nearly perfect diagonal line, reflecting the eerily synchronized pattern of burglaries and soap opera viewership. It's almost as if the characters in "Days of Our Lives" were masterminding the thefts themselves, weaving a narrative of crime and drama that transcends the television screen and infiltrates the real world.
As much as we would all love to attribute this peculiar correlation to a clandestine plot by soap opera aficionados, it is essential to tread cautiously in drawing definitive conclusions. However, the strength of our findings cannot be denied, and it prompts us to consider the potential mechanisms underlying this unforeseen link. Could it be the suspense and intrigue of the soap opera that lures potential burglars indoors, captivated by the unfolding drama and forgetting their criminal intentions? Or perhaps the cultural phenomenon of soap opera viewing is an unconscious outlet for individuals prone to criminal behavior, serving as a temporary reprieve from their illicit inclinations.
Our results beg the question: are the captivating storylines of "Days of Our Lives" more than just entertainment, permeating into the fabric of societal norms and influencing behaviors in ways we have never anticipated? We are left to contemplate the implications of these findings and the broader implications for understanding the intricate interplay between popular culture and criminal activity. Although our investigation yields no definitive answers, it serves as a thought-provoking entry point into a sphere of inquiry that defies conventional boundaries, much like the soap opera that sparked our curiosity.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the surprising correlation between burglaries in South Dakota and the viewership count for "Days of Our Lives" has uncovered an unexpected intertwining of crime and daytime drama. The statistical strength of the association, with a correlation coefficient that would make even the most melodramatic soap opera character blush, suggests a connection that demands further contemplation.

Our findings not only challenge conventional wisdom but also provoke an amusement akin to witnessing a soap opera plot twist. While we refrain from drawing definitive conclusions, the allure of delving into the potential mechanisms underlying this unforeseen link is undeniable. It's as though the soap opera itself has crafted a storyline that extends beyond the screen, weaving its narrative threads into the fabric of real-world criminal behavior. However, caution must be exercised in leaping to conclusions as we navigate this curious confluence of crime and daytime television.

The implications of our research raise more questions than they answer, much like the suspenseful cliffhangers that drive the viewership of "Days of Our Lives." As we bid adieu to this eccentric exploration, we postulate that further inquiries into the influence of popular culture on criminal behavior may prove just as riveting as a soap opera marathon. However, our scholarly sleuthing has, for now, provided a captivating glimpse into the enigmatic dynamics of entertainment and illicit activities. Therefore, we assert that no more research is needed in this area, as the saga of "Days of Our Crimes" has reached its surprising climax.

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: A Burglary of Interest in South Dakota. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Criminological Shenanigans

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: A Burglary of Interest in South Dakota. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Criminology Research

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Days of Our Crimes: A Burglary of Interest in South Dakota with an abstract of This paper investigates the peculiar relationship between the frequency of burglaries in South Dakota and the viewership count for the soap opera "Days of Our Lives." Despite their seemingly unrelated nature, our findings reveal a surprising correlation between these two variables. Utilizing data from the FBI Criminal Justice Information Services and Wikipedia, our analysis covers the period from 1985 to 2021. The correlation coefficient of 0.9183756 and p < 0.01 suggest a strong association between these seemingly distinct phenomena. We delve into possible explanations for this unexpected connection, exploring the potential impact of daytime television drama on criminal behavior. Our research sparks both interest and intrigue, offering a unique lens through which to view the dynamics of popular culture and crime in a seemingly unassuming state.

ChatGPT:

burglary, South Dakota, Days of Our Lives, soap opera, viewership, FBI Criminal Justice Information Services, Wikipedia, correlation, association, criminal behavior, popular culture, daytime television drama

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

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 = 0.9183756 (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 = 0.8434137 (Coefficient of determination)
This means 84.3% 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 South Dakota) over the 37 years from 1985 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.2E-15.^Show 0.0000000000000011744128143346
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.92 in 1.2E-13% of random cases. Said differently, if you correlated 851,489,346,671,154 random variables^Note You don't actually need 851 trillion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 36 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 36 because we have two variables measured over a period of 37 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.85, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Burglaries in South Dakota (Burglary rate)	546.2	553.5	534.1	517.9	474.7	527.4	589.8	541.4	549.2	546.2	540.7	557	553.9	468.6	444	383.7	407.1	399	376.3	408.5	323.3	386.7	332.4	333.6	322.6	390.9	355.4	393.3	400.1	330.1	346.1	348.4	324.6	284.7	300.1	340.1	269.7
Viewership count for Days of Our Lives (Nielson share)	7200000	7000000	7100000	6500000	5400000	5200000	5400000	4900000	5600000	5300000	5800000	5800000	5100000	5800000	4200000	3800000	3600000	3100000	3100000	2700000	2600000	2300000	2100000	2200000	2200000	2000000	2000000	2100000	1900000	2050000	1800000	1600000	1600000	1600000	1400000	1200000	1200000

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([546.2,553.5,534.1,517.9,474.7,527.4,589.8,541.4,549.2,546.2,540.7,557,553.9,468.6,444,383.7,407.1,399,376.3,408.5,323.3,386.7,332.4,333.6,322.6,390.9,355.4,393.3,400.1,330.1,346.1,348.4,324.6,284.7,300.1,340.1,269.7,])
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 South Dakota"
array_2_name = "Viewership count for Days of Our Lives"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Burglaries in South Dakota
Line chart for only Viewership count for Days of Our Lives
AI-generated correlation image
The spurious research paper: Days of Our Crimes: A Burglary of Interest in South Dakota

View another random correlation

How fun was this correlation?

Kudos for rating!

Correlation ID: 1895 · Black Variable ID: 20120 · Red Variable ID: 87


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