Spurious correlation #3,951 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the first name Katherine and the second variable is Burglaries in Hawaii. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the first name Katherine and the second variable is Burglaries in Hawaii. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the saying goes, "Kat's out of the bag," and it seems that also applies to burglars in Hawaii! With fewer Katherines around, there were less Kat burglars trying to pull off heists in the sunny state. It appears that the name Katherine was previously a common alias for cat burglars with a penchant for pilfering pineapples. However, with this name falling out of favor, it seems the purr-petrators have also disappeared, leading to a decrease in burglaries. It's a feline mystery, but it looks like Hawaii can rest easy knowing that the Katherine connection has been pawsitively purr-vented!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image with the style of a Discovery magazine cover, portraying a sunny office in Hawaii during the Hawaiian shirt Friday tradition. The office should appear quieter with fewer Katherines participating. Show the security guard stationed at the front entrance paying closer attention to his duties and the visible effect of a decrease in burglaries across the islands of Hawaii due to the heightened security presence. The image should capture the serene yet vigilant atmosphere of the office and the impact of the security guard's increased focus on preventing theft. 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: Popularity of the first name Katherine and Burglaries in Hawaii. 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: Woodblock painting Concept art A Discovery magazine cover image A Discovery magazine cover image Magic realism
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 Popularity of the first name Katherine and Burglaries in Hawaii, in the following situation: Because as the popularity of the name Katherine decreased, fewer people were named Katherine, which led to a decrease in the number of Katherines participating in Hawaiian shirt Fridays at work. With less Katherine-induced distraction, office security increased, leading to a decrease in burglaries in Hawaii.. Keep the description simple.
ChatGPT: In a sunny office in Hawaii, the Hawaiian shirt Friday tradition seemed a bit quieter as fewer Katherines participated. The once bustling office now had fewer Katherines joining in the fun. With this change, the security guard stationed at the front entrance was able to pay closer attention to his duties. The result was a decrease in burglaries across the islands of Hawaii, as the heightened security presence deterred potential thieves.

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 sunny office in Hawaii, the Hawaiian shirt Friday tradition seemed a bit quieter as fewer Katherines participated. The once bustling office now had fewer Katherines joining in the fun. With this change, the security guard stationed at the front entrance was able to pay closer attention to his duties. The result was a decrease in burglaries across the islands of Hawaii, as the heightened security presence deterred potential thieves. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image with the style of a Discovery magazine cover, portraying a sunny office in Hawaii during the Hawaiian shirt Friday tradition. The office should appear quieter with fewer Katherines participating. Show the security guard stationed at the front entrance paying closer attention to his duties and the visible effect of a decrease in burglaries across the islands of Hawaii due to the heightened security presence. The image should capture the serene yet vigilant atmosphere of the office and the impact of the security guard's increased focus on preventing theft.

*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 Popularity of the first name Katherine caused Burglaries in Hawaii to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii

The Journal of Quirky Social Science Research

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Popularity of the first name Katherine and Burglaries in Hawaii. 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 a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii

[[ABSTRACT]]
The relationship between first names and crime has intrigued researchers for decades. In this study, we investigated the unlikely correlation between the popularity of the first name "Katherine" and incidents of burglary in the sunny state of Hawaii. By utilizing data from the US Social Security Administration for name popularity trends and FBI Criminal Justice Information Services for burglary rates from 1985 to 2022, we set out to uncover whether there exists a significant connection between the two seemingly unrelated phenomena. Our findings revealed a stunningly high correlation coefficient of 0.9753855 and an incredibly low p-value of less than 0.01, indicating a robust statistical association between the frequency of the name "Katherine" and the incidence of burglaries in the palm tree-laden paradise. This unexpected link prompts further investigation into the potential influence of names on criminal behavior and raises the question: are individuals named Katherine more likely to "break in" to certain behaviors, or is this simply a coincidental cat burglary caper?

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
The interplay between individual names and societal trends has long captured the interest of researchers across various disciplines. From the influence of names on career success to their impact on romantic attraction, the association between nomenclature and human behavior continues to fascinate scholars. In the realm of criminology, the investigation of potential correlations between first names and criminal activities has yielded intriguing, if not somewhat peculiar, findings.
Our research delves into the peculiar correlation between the prevalence of the first name "Katherine" and incidents of burglary in the idyllic state of Hawaii. Yes, you read that right—Katherine and burglaries in Hawaii. While the connection may initially seem as far-fetched as a pineapple pizza, the data suggest otherwise.
As we embark on this unconventional academic journey, it is important to clarify our position. Our approach is neither to stigmatize individuals with the name Katherine nor to suggest that the name itself possesses any criminal propensity. Instead, we are motivated by a curiosity akin to stumbling upon a surfing goat—a rare and unexpected phenomenon that demands further examination.
The conventional wisdom in criminology often focuses on socioeconomic factors, demographics, and environmental influences as determinants of criminal behavior. Rarely, if ever, does one expect to encounter a hypothesis centered on the statistical relationship between a name and crime. Nonetheless, it is precisely this unorthodox line of inquiry that enlivens the academic landscape and prompts us to take a closer look at the potential connection between the popularity of the name Katherine and the prevalence of burglaries in the tropical paradise of Hawaii.
Our research, therefore, is not only a testament to the inherently wacky nature of scientific exploration but also a reminder that in the realm of empirical inquiry, one must be prepared for unexpected revelations. So, buckle up and get ready to embark on an academic escapade into the peculiar terrain where Katherine meets crime—whether it's a mere coincidence or the name is truly a "cat burglar" in disguise awaits our investigation.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Smith et al. (2015) examined the potential influence of first names on criminal behavior in their study "Monikers and Misdemeanors: Unveiling the Name-Crime Nexus." Interestingly, their analysis of national crime data revealed no significant correlation between popular first names and criminal activities. However, their research did not specifically investigate the connection between the name Katherine and burglary in Hawaii, leaving the field wide open for our quirky investigation.

Doe and Jones (2018) conducted a comprehensive analysis in their article "The Name Game: Unraveling the Mysteries of Monikers." Their study focused on the influence of first names on various aspects of life, including career success, romantic relationships, and even criminal tendencies. While their findings unveiled some unexpected associations, the specific link between the name Katherine and burglaries in the Hawaiian archipelago remained uncharted territory.

Turning to related books, "The Science of Names" by Linguist L. E. Xicon (2019) provides a detailed exploration of the psychological and sociological implications of naming conventions. Although Xicon's work traverses a wide array of topics related to names, the direct connection to criminal behavior and specific names has yet to be extensively covered.

In the realm of fiction, "The Cat Burglar's Secret" by Mystery Author S. Neaky (2020) presents an intriguing narrative of a cunning thief who operates under the guise of a demure persona. While this work of fiction may not offer empirical evidence, it certainly mirrors the enigmatic nature of our investigation into the unsuspecting name Katherine and its purported association with burglaries in Hawaii.

Another fictitious book, "The Curious Case of the Kooky Katherine" by Novelist A. Musing (2017), delves into the peculiar adventures of individuals possessing the name Katherine. Although the book strays far from academic rigor, its whimsical portrayal of Katherine-related escapades mirrors the idiosyncratic essence of our research inquiry.

Furthermore, the internet meme "Katherine the Great Burglar" has garnered attention on social media platforms, playfully jesting about the alleged stealthy activities of individuals bearing the name Katherine. While memes serve as lighthearted jests, they nonetheless encapsulate the popular fascination with the interplay between names and unexpected associations, mirroring the spirit of our unconventional investigation.

In examining the existing literature, it becomes evident that while the scholarly realm has explored the influence of names on various facets of life, the specific link between the name Katherine and burglaries in Hawaii remains largely untapped. As we venture into this uncharted territory, a treasure trove of quirky revelations awaits our exploration.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Popularity of the first name Katherine and Burglaries in Hawaii. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from US Social Security Administration and FBI Criminal Justice Information Services . You used data from 1985 to 2022

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]]
Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii

[[ABSTRACT]]
The relationship between first names and crime has intrigued researchers for decades. In this study, we investigated the unlikely correlation between the popularity of the first name "Katherine" and incidents of burglary in the sunny state of Hawaii. By utilizing data from the US Social Security Administration for name popularity trends and FBI Criminal Justice Information Services for burglary rates from 1985 to 2022, we set out to uncover whether there exists a significant connection between the two seemingly unrelated phenomena. Our findings revealed a stunningly high correlation coefficient of 0.9753855 and an incredibly low p-value of less than 0.01, indicating a robust statistical association between the frequency of the name "Katherine" and the incidence of burglaries in the palm tree-laden paradise. This unexpected link prompts further investigation into the potential influence of names on criminal behavior and raises the question: are individuals named Katherine more likely to "break in" to certain behaviors, or is this simply a coincidental cat burglary caper?

[[INTRODUCTION]]
Introduction
The interplay between individual names and societal trends has long captured the interest of researchers across various disciplines. From the influence of names on career success to their impact on romantic attraction, the association between nomenclature and human behavior continues to fascinate scholars. In the realm of criminology, the investigation of potential correlations between first names and criminal activities has yielded intriguing, if not somewhat peculiar, findings.
Our research delves into the peculiar correlation between the prevalence of the first name "Katherine" and incidents of burglary in the idyllic state of Hawaii. Yes, you read that right—Katherine and burglaries in Hawaii. While the connection may initially seem as far-fetched as a pineapple pizza, the data suggest otherwise.
As we embark on this unconventional academic journey, it is important to clarify our position. Our approach is neither to stigmatize individuals with the name Katherine nor to suggest that the name itself possesses any criminal propensity. Instead, we are motivated by a curiosity akin to stumbling upon a surfing goat—a rare and unexpected phenomenon that demands further examination.
The conventional wisdom in criminology often focuses on socioeconomic factors, demographics, and environmental influences as determinants of criminal behavior. Rarely, if ever, does one expect to encounter a hypothesis centered on the statistical relationship between a name and crime. Nonetheless, it is precisely this unorthodox line of inquiry that enlivens the academic landscape and prompts us to take a closer look at the potential connection between the popularity of the name Katherine and the prevalence of burglaries in the tropical paradise of Hawaii.
Our research, therefore, is not only a testament to the inherently wacky nature of scientific exploration but also a reminder that in the realm of empirical inquiry, one must be prepared for unexpected revelations. So, buckle up and get ready to embark on an academic escapade into the peculiar terrain where Katherine meets crime—whether it's a mere coincidence or the name is truly a "cat burglar" in disguise awaits our investigation.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

In order to discern the curious connection between the popularity of the first name "Katherine" and incidences of burglary in the captivating state of Hawaii, our research employed a combination of data collection, statistical analysis, and a dash of whimsy. As researchers, we understand the gravity of our endeavor and have endeavored to approach our methodology with the utmost attention to detail, despite the gravity-defying nature of our hypothesis.

Data Collection:
Our quest for data led us to scour the annals of the US Social Security Administration, where we unearthed the treasure trove of name popularity statistics spanning the years 1985 to 2022. This rich bounty afforded us the opportunity to track the ebbs and flows of Katherine's reign in the realm of nomenclature, providing the foundation upon which our analysis would be built. To complement this, we ventured into the realm of crime statistics (virtually, of course) and obtained burglary data from the FBI Criminal Justice Information Services. We navigated through decades of dastardly deeds to extract the pertinent figures related to burglaries in the Hawaiian archipelago.

Data Cleaning:
With a collection of data as eclectic as a luau buffet, the process of data cleaning proved to be as meticulous as untangling a web of leis. We rigorously scrutinized the datasets, ensuring that outliers and erroneous entries were swiftly ushered out, much like an unwelcome guest at a Hawaiian shirt convention. This step was crucial in ensuring the integrity and accuracy of our subsequent analyses, preventing any statistical "monkey business" from skewing our findings.

Statistical Analysis:
Armed with a pristine dataset, we embarked on a statistical odyssey, employing the venerable tools of correlation analysis and regression modeling. Our partnership with statistical software provided the bridge between hypothesis and evidence, allowing us to wrestle with the quantifiable intricacies of our data. The bracing winds of statistical inference carried us through the wilderness of p-values, confidence intervals, and correlation coefficients, as we sought to unravel the enigmatic relationship between Katherine and crime in the land of aloha.

Consideration of Confounding Variables:
In acknowledging the inherent complexity of human behavior and the multifaceted factors that shape criminal activities, we remain cognizant of potential confounders that may exert influence on our observed association. Our team conducted a thorough review of demographic trends, socioeconomic indicators, and environmental variables, striving to discern whether the purported link between Katherine's popularity and burglary rates could withstand the scrutiny of alternative explanations. Like detectives sifting through a potpourri of clues, we scrutinized the landscape for any hidden variables that could cast doubt on our curious findings.

Ethical Considerations:
In our pursuit of knowledge, we held fast to the principles of academic integrity and ethical conduct. At no point did we seek to impugn the reputation of individuals bearing the name Katherine, recognizing that our research is an exploration of statistical patterns rather than an indictment of any particular group. Our focus on the peculiarity of our findings was tempered by a commitment to scholarship guided by curiosity rather than conjecture.

While some may view our methodology as straying into unorthodox territories, we stand by its rigorous and scrupulous nature, well aware of the levity and gravity interwoven in our pursuit of empirical truth. As our expedition ventures forth, let us not lose sight of the fact that in the realm of academia, the unexpected often leads to the most enlightening discoveries.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Popularity of the first name Katherine and Burglaries in Hawaii. 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]]
Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii

[[ABSTRACT]]
The relationship between first names and crime has intrigued researchers for decades. In this study, we investigated the unlikely correlation between the popularity of the first name "Katherine" and incidents of burglary in the sunny state of Hawaii. By utilizing data from the US Social Security Administration for name popularity trends and FBI Criminal Justice Information Services for burglary rates from 1985 to 2022, we set out to uncover whether there exists a significant connection between the two seemingly unrelated phenomena. Our findings revealed a stunningly high correlation coefficient of 0.9753855 and an incredibly low p-value of less than 0.01, indicating a robust statistical association between the frequency of the name "Katherine" and the incidence of burglaries in the palm tree-laden paradise. This unexpected link prompts further investigation into the potential influence of names on criminal behavior and raises the question: are individuals named Katherine more likely to "break in" to certain behaviors, or is this simply a coincidental cat burglary caper?

[[LITERATURE REVIEW]]
Smith et al. (2015) examined the potential influence of first names on criminal behavior in their study "Monikers and Misdemeanors: Unveiling the Name-Crime Nexus." Interestingly, their analysis of national crime data revealed no significant correlation between popular first names and criminal activities. However, their research did not specifically investigate the connection between the name Katherine and burglary in Hawaii, leaving the field wide open for our quirky investigation.
Doe and Jones (2018) conducted a comprehensive analysis in their article "The Name Game: Unraveling the Mysteries of Monikers." Their study focused on the influence of first names on various aspects of life, including career success, romantic relationships, and even criminal tendencies. While their findings unveiled some unexpected associations, the specific link between the name Katherine and burglaries in the Hawaiian archipelago remained uncharted territory.
Turning to related books, "The Science of Names" by Linguist L. E. Xicon (2019) provides a detailed exploration of the psychological and sociological implications of naming conventions. Although Xicon's work traverses a wide array of topics related to names, the direct connection to criminal behavior and specific names has yet to be extensively covered.
In the realm of fiction, "The Cat Burglar's Secret" by Mystery Author S. Neaky (2020) presents an intriguing narrative of a cunning thief who operates under the guise of a demure persona. While this work of fiction may not offer empirical evidence, it certainly mirrors the enigmatic nature of our investigation into the unsuspecting name Katherine and its purported association with burglaries in Hawaii.
Another fictitious book, "The Curious Case of the Kooky Katherine" by Novelist A. Musing (2017), delves into the peculiar adventures of individuals possessing the name Katherine. Although the book strays far from academic rigor, its whimsical portrayal of Katherine-related escapades mirrors the idiosyncratic essence of our research inquiry.
Furthermore, the internet meme "Katherine the Great Burglar" has garnered attention on social media platforms, playfully jesting about the alleged stealthy activities of individuals bearing the name Katherine. While memes serve as lighthearted jests, they nonetheless encapsulate the popular fascination with the interplay between names and unexpected associations, mirroring the spirit of our unconventional investigation.
In examining the existing literature, it becomes evident that while the scholarly realm has explored the influence of names on various facets of life, the specific link between the name Katherine and burglaries in Hawaii remains largely untapped. As we venture into this uncharted territory, a treasure trove of quirky revelations awaits our exploration.

[[RESULTS]]
Upon analyzing the data collected from the US Social Security Administration and the FBI Criminal Justice Information Services, we discovered a staggering correlation between the popularity of the first name "Katherine" and the incidence of burglaries in Hawaii. The correlation coefficient of 0.9753855 indicates a remarkably strong positive relationship, pointing to a potential influence of the name "Katherine" on criminal activities in the Aloha State.
Our r-squared value of 0.9513770 further bolstered the robustness of this association, suggesting that approximately 95% of the variation in burglary rates can be explained by the variation in the popularity of the name Katherine. It's almost as if every time someone named Katherine moves to Hawaii, the burglary rate decides to tag along for the ride, like an unexpected plus one at a luau.
What's more, the p-value of less than 0.01 provided compelling evidence to reject the null hypothesis, affirming that the correlation we observed is highly unlikely to have occurred by chance. This significant p-value reinforces the credibility of our findings and underscores the legitimacy of the unexpected link between the name Katherine and burglaries in the tropical island paradise.
It is important to note that while our study establishes a clear statistical relationship, it does not imply causation. We cannot definitively conclude that the name Katherine directly causes or influences burglaries in Hawaii. However, the strength of the correlation prompts us to ponder the role of individual names in shaping behavioral outcomes and warrants further investigation into the mechanisms underlying this connection.
To visually depict the striking correlation we uncovered, we present Figure 1, a scatterplot that elegantly captures the remarkably strong association between the popularity of the name "Katherine" and burglary rates in Hawaii. This graph serves as a tangible representation of the surprising relationship, reminding us that truth can indeed be stranger than fiction, especially when it comes to the nexus of nomenclature and nefarious deeds.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The hair-raising correlation between the popularity of the first name "Katherine" and the incidence of burglaries in Hawaii has left us teetering on the edge of disbelief. Our results not only reaffirm the earlier findings of Smith et al. (2015) and Doe and Jones (2018) regarding the influence of first names on unexpected outcomes, but they also catapult these quirky associations into the spotlight of empirical scrutiny. Who would have thought that the moniker "Katherine" could harbor such surprising implications for criminal tendencies in the tropical haven of Hawaii?

Smith et al. (2015) may have debunked the notion of popular first names having an impact on criminal activities in a national context, but our investigation has carved out a unique niche by zeroing in on the picturesque archipelago of Hawaii. It seems that where serene beaches and swaying palm trees abound, the enigma of the name Katherine and its covert connection to burglaries thrives. It's as if each Katherine in Hawaii is silently beckoning the burglar alarms to sing their discordant melodies, a symphony of statistical peculiarity that has left us in wonderment.

Adding substance to our findings, Doe and Jones (2018) hinted at the overarching influence of first names on various life facets, which our study elevates to an unexpected crescendo with the Katherine-burglary nexus. The idiosyncrasies explored in the fictitious works of S. Neaky and A. Musing, though far removed from empirical rigor, have eerily resonated with the true-life eccentricity of our research. It's as if fiction has surreptitiously whispered the secrets that empirical inquiry is now daring to elucidate.

The saga of "Katherine the Great Burglar," a playful meme that ambled through the corridors of social media, now takes on a surreal semblance of truth in light of our weighty statistical revelation. What was once dismissed as internet whimsy has unfolded as a fascinating enigma worthy of academic pursuit. This underscores the capacity of unconventional sources to harbor hidden truths, much like a name concealing a deceptively strong statistical association with criminal activities.

In unraveling the conspicuous correlation between the name Katherine and burglaries in Hawaii, we urge caution in interpreting our findings. While the statistical association is robust, we cannot unequivocally claim causation. Instead, we stand at the threshold of a mysterious realm where names and behavior intertwine in ways that defy conventional understanding. As we perceptively navigate this twilight zone, we beckon future research to delve deeper into the mechanisms underlying this unlikely linkage, all while tipping our figurative hats to the whimsy and wonderment of the unexpected Katherine-burglary odyssey.

In the world of scientific inquiry, truth is often stranger than fiction. And in the case of the Katherine-burglary entanglement, this veritable adage holds true, lending an air of enigmatic intrigue to the often staid domains of statistical analysis and name trends. As we set sail into uncharted waters, anchored by the weight of empirical evidence, we extend an invitation to fellow researchers to join us in peeling back the layers of this kooky yet compelling association, where names become more than mere labels and statistical correlations take on an air of inexplicable, humorous mystique.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Popularity of the first name Katherine and Burglaries in Hawaii. 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]]
Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii

[[ABSTRACT]]
The relationship between first names and crime has intrigued researchers for decades. In this study, we investigated the unlikely correlation between the popularity of the first name "Katherine" and incidents of burglary in the sunny state of Hawaii. By utilizing data from the US Social Security Administration for name popularity trends and FBI Criminal Justice Information Services for burglary rates from 1985 to 2022, we set out to uncover whether there exists a significant connection between the two seemingly unrelated phenomena. Our findings revealed a stunningly high correlation coefficient of 0.9753855 and an incredibly low p-value of less than 0.01, indicating a robust statistical association between the frequency of the name "Katherine" and the incidence of burglaries in the palm tree-laden paradise. This unexpected link prompts further investigation into the potential influence of names on criminal behavior and raises the question: are individuals named Katherine more likely to "break in" to certain behaviors, or is this simply a coincidental cat burglary caper?

[[INTRDUCTION]]
Introduction
The interplay between individual names and societal trends has long captured the interest of researchers across various disciplines. From the influence of names on career success to their impact on romantic attraction, the association between nomenclature and human behavior continues to fascinate scholars. In the realm of criminology, the investigation of potential correlations between first names and criminal activities has yielded intriguing, if not somewhat peculiar, findings.
Our research delves into the peculiar correlation between the prevalence of the first name "Katherine" and incidents of burglary in the idyllic state of Hawaii. Yes, you read that right—Katherine and burglaries in Hawaii. While the connection may initially seem as far-fetched as a pineapple pizza, the data suggest otherwise.
As we embark on this unconventional academic journey, it is important to clarify our position. Our approach is neither to stigmatize individuals with the name Katherine nor to suggest that the name itself possesses any criminal propensity. Instead, we are motivated by a curiosity akin to stumbling upon a surfing goat—a rare and unexpected phenomenon that demands further examination.
The conventional wisdom in criminology often focuses on socioeconomic factors, demographics, and environmental influences as determinants of criminal behavior. Rarely, if ever, does one expect to encounter a hypothesis centered on the statistical relationship between a name and crime. Nonetheless, it is precisely this unorthodox line of inquiry that enlivens the academic landscape and prompts us to take a closer look at the potential connection between the popularity of the name Katherine and the prevalence of burglaries in the tropical paradise of Hawaii.
Our research, therefore, is not only a testament to the inherently wacky nature of scientific exploration but also a reminder that in the realm of empirical inquiry, one must be prepared for unexpected revelations. So, buckle up and get ready to embark on an academic escapade into the peculiar terrain where Katherine meets crime—whether it's a mere coincidence or the name is truly a "cat burglar" in disguise awaits our investigation.

[[RESULTS]]
Upon analyzing the data collected from the US Social Security Administration and the FBI Criminal Justice Information Services, we discovered a staggering correlation between the popularity of the first name "Katherine" and the incidence of burglaries in Hawaii. The correlation coefficient of 0.9753855 indicates a remarkably strong positive relationship, pointing to a potential influence of the name "Katherine" on criminal activities in the Aloha State.
Our r-squared value of 0.9513770 further bolstered the robustness of this association, suggesting that approximately 95% of the variation in burglary rates can be explained by the variation in the popularity of the name Katherine. It's almost as if every time someone named Katherine moves to Hawaii, the burglary rate decides to tag along for the ride, like an unexpected plus one at a luau.
What's more, the p-value of less than 0.01 provided compelling evidence to reject the null hypothesis, affirming that the correlation we observed is highly unlikely to have occurred by chance. This significant p-value reinforces the credibility of our findings and underscores the legitimacy of the unexpected link between the name Katherine and burglaries in the tropical island paradise.
It is important to note that while our study establishes a clear statistical relationship, it does not imply causation. We cannot definitively conclude that the name Katherine directly causes or influences burglaries in Hawaii. However, the strength of the correlation prompts us to ponder the role of individual names in shaping behavioral outcomes and warrants further investigation into the mechanisms underlying this connection.
To visually depict the striking correlation we uncovered, we present Figure 1, a scatterplot that elegantly captures the remarkably strong association between the popularity of the name "Katherine" and burglary rates in Hawaii. This graph serves as a tangible representation of the surprising relationship, reminding us that truth can indeed be stranger than fiction, especially when it comes to the nexus of nomenclature and nefarious deeds.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has shed light on the unexpected and, dare I say, "breaking" connection between the popularity of the first name "Katherine" and incidences of burglaries in the tropical haven of Hawaii. That's right, folks, it turns out there's more to the name Katherine than meets the eye. It's not just a moniker; it's a statistical sensation that seems to have a "breaking and entering" charm when it comes to crime rates in the Aloha State.

Our findings, with a correlation coefficient that practically screams "come at me, bro," and an r-squared value that confidently struts around like it owns the place, have left us pondering the curious potential influence of names on the propensity for illicit activities. It's as if every mention of "Katherine" triggers a series of "breaking news" alerts in the realm of burglary rates. Who knew a seemingly innocent name could have such a "cat burglar" effect?

However, it's crucial to maintain a scholarly sobriety and acknowledge that correlation does not imply causation. We're not proposing that individuals named Katherine are any more likely to engage in criminal behavior than others. But hey, the data doesn't lie, and it's certainly given us something to ponder over our next pineapple and ham pizza.

As we wrap up our exploration into the whimsical world where names and crime intertwine, it's clear that there's much more to be uncovered in this field. Perhaps this is just the tip of the iceberg, or should I say, the top of the palm tree? Who knows what other names may be harboring secret influences on societal trends?

In the meantime, we assert with the utmost confidence, no more research is needed in this area. We've uncovered a link that's as clear as a sunny day in Hawaii. It's time to let Katherine and burglaries bask in the academic spotlight for now.

And with that, we'll leave you to ponder the age-old question: If a Katherine moves to Hawaii, do burglaries follow? Until next time, aloha and mahalo for following this quirky journey through the unexpected nexus of nomenclature and mischievous misdeeds.

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 Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Social Science Research

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 Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Social Anomalies Research and Analysis

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 Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii with an abstract of The relationship between first names and crime has intrigued researchers for decades. In this study, we investigated the unlikely correlation between the popularity of the first name "Katherine" and incidents of burglary in the sunny state of Hawaii. By utilizing data from the US Social Security Administration for name popularity trends and FBI Criminal Justice Information Services for burglary rates from 1985 to 2022, we set out to uncover whether there exists a significant connection between the two seemingly unrelated phenomena. Our findings revealed a stunningly high correlation coefficient of 0.9753855 and an incredibly low p-value of less than 0.01, indicating a robust statistical association between the frequency of the name "Katherine" and the incidence of burglaries in the palm tree-laden paradise. This unexpected link prompts further investigation into the potential influence of names on criminal behavior and raises the question: are individuals named Katherine more likely to "break in" to certain behaviors, or is this simply a coincidental cat burglary caper?

ChatGPT:

First names, name popularity, Katherine, burglaries, crime correlation, Hawaii, US Social Security Administration data, FBI Criminal Justice Information Services data, name influence on criminal behavior

*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

Popularity of the first name Katherine
Detailed data title: Babies of all sexes born in the US named Katherine
Source: US Social Security Administration
See what else correlates with Popularity of the first name Katherine

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

Correlation r = 0.9753855 (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 = 0.9513770 (Coefficient of determination)
This means 95.1% of the change in the one variable (i.e., Burglaries in Hawaii) is predictable based on the change in the other (i.e., Popularity of the first name Katherine) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.1E-25.^Show 0.0000000000000000000000003120
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 0.98 in 3.1E-23% of random cases. Said differently, if you correlated 3,205,128,205,128,205,074,432,000 random variables^Note You don't actually need 3 septillion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 37 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 37 because we have two variables measured over a period of 38 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.95, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Popularity of the first name Katherine (Babies born)	10171	10616	10480	11196	11509	11657	11514	11170	10525	9605	9000	8890	8527	8217	7942	8122	7894	7224	7135	6771	6405	6300	5825	5354	4435	3868	4193	3951	3722	3693	3462	3274	2860	2676	2449	1989	1816	1727
Burglaries in Hawaii (Burglary rate)	1154.1	1338.8	1155.6	1255.8	1343.4	1228.2	1234.4	1121.2	1135.7	1189.9	1165.3	1079.5	1073.4	936.2	794.7	880.3	909.7	1025.4	913.6	857.8	769	678.6	708.2	730	713.7	638.6	592.5	550.5	552	526	475.7	418.8	389.6	401.9	390.9	329.1	332.2	260

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([10171,10616,10480,11196,11509,11657,11514,11170,10525,9605,9000,8890,8527,8217,7942,8122,7894,7224,7135,6771,6405,6300,5825,5354,4435,3868,4193,3951,3722,3693,3462,3274,2860,2676,2449,1989,1816,1727,])
array_2 = np.array([1154.1,1338.8,1155.6,1255.8,1343.4,1228.2,1234.4,1121.2,1135.7,1189.9,1165.3,1079.5,1073.4,936.2,794.7,880.3,909.7,1025.4,913.6,857.8,769,678.6,708.2,730,713.7,638.6,592.5,550.5,552,526,475.7,418.8,389.6,401.9,390.9,329.1,332.2,260,])
array_1_name = "Popularity of the first name Katherine"
array_2_name = "Burglaries in Hawaii"

# 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 Popularity of the first name Katherine
Line chart for only Burglaries in Hawaii
AI-generated correlation image
The spurious research paper: Breaking and Entering Katherine: An Unconventional Connection Between Name Popularity and Burglaries in Hawaii

View another random correlation

How fun was this correlation?

Bravo! Your evaluation rocks!

Correlation ID: 3951 · Black Variable ID: 2044 · Red Variable ID: 20087


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