about · email me · subscribe
Spurious correlation #2,429 · 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 Kevin and the second variable is Robberies in Connecticut.  The chart goes from 1985 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Fewer Kevins meant fewer Home Alones. Without the master of booby traps to contend with, burglars found it much easier to pursue alternative career paths.

Model: dalle-3
Prompt: Generate an image of a minimalist, brutalist playground set in a bustling Connecticut town. The playground is teeming with energetic children, with a specific focus on a group of kids engaged in an intense game of tag. One particular boy, named Kevin, stands out as the leader of this mischievous group, known as the "Klepto-Kevs." Over time, the number of Kevins in the neighborhood decreases, resulting in a noticeable decline in the "Klepto-Kevs" and, subsequently, a significant decrease in robberies around town. The once bustling playground now exudes a sense of safety and tranquility. 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 Kevin and Robberies in Connecticut. 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: Concept art Celtic art Cyber folk Brutalism Cubism
ChatGPT: Brutalism

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 Kevin and Robberies in Connecticut, in the following situation: As the popularity of the name Kevin waned, so too did the number of Kevins, or "Klepto-Kevs" as they call themselves, traditionally known for their thievery shenanigans. With fewer Kevins around, there were less "Klepto-Kev" capers to contend with in Connecticut, leading to a surprising dip in robberies. It seems the collective "Kevolution" away from mischief-making may have inadvertently thwarted the criminal activities in the Nutmeg State.. Keep the description simple.
ChatGPT: In a bustling Connecticut town, the playground buzzes with children's laughter. A group of kids engage in a game of tag, with one boy leading the pack. His name is Kevin, the most popular name in the neighborhood. As the years go by, the number of Kevins dwindles, and so does the mischievous group known as the "Klepto-Kevs." With fewer "Klepto-Kevs" around, the town experiences a remarkable decrease in robberies, and the once bustling playground becomes a safer, more peaceful place.

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: [ Brutalism ] and depicting this scene: In a bustling Connecticut town, the playground buzzes with children's laughter. A group of kids engage in a game of tag, with one boy leading the pack. His name is Kevin, the most popular name in the neighborhood. As the years go by, the number of Kevins dwindles, and so does the mischievous group known as the "Klepto-Kevs." With fewer "Klepto-Kevs" around, the town experiences a remarkable decrease in robberies, and the once bustling playground becomes a safer, more peaceful place. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a minimalist, brutalist playground set in a bustling Connecticut town. The playground is teeming with energetic children, with a specific focus on a group of kids engaged in an intense game of tag. One particular boy, named Kevin, stands out as the leader of this mischievous group, known as the "Klepto-Kevs." Over time, the number of Kevins in the neighborhood decreases, resulting in a noticeable decline in the "Klepto-Kevs" and, subsequently, a significant decrease in robberies around town. The once bustling playground now exudes a sense of safety and tranquility.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Popularity of the first name Kevin caused Robberies in Connecticut to decrease.

AI academic paper

(Because p < 0.01)
Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut

Journal of Quirky Sociological Studies

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Popularity of the first name Kevin and Robberies in Connecticut. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title seem clever.

Your research team used data from US Social Security Administration and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.9706924 and p < 0.01 for 1985 to 2022.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut"

[[ABSTRACT]]
This study delves into the intriguing relationship between the prevalence of the first name Kevin and the occurrence of robberies in the state of Connecticut. Leveraging data from the US Social Security Administration and the FBI Criminal Justice Information Services, our research team conducted a comprehensive analysis spanning the years 1985 to 2022. Our findings revealed a remarkably robust correlation coefficient of 0.9706924 and a p-value of less than 0.01, highlighting a statistically significant association between the two variables.

Despite the initial absurdity of the topic, our investigation uncovers startling patterns that beckon further inquiry. The implications of our discoveries arguably extend beyond mere coincidence, prompting us to ponder the idiosyncrasies of nomenclature and their potential impact on societal behavior. This research surely adds a new twist to the classic "Kevin was here" graffiti trope!


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Popularity of the first name Kevin and Robberies in Connecticut. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
"Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut"

[[ABSTRACT]]
This study delves into the intriguing relationship between the prevalence of the first name Kevin and the occurrence of robberies in the state of Connecticut. Leveraging data from the US Social Security Administration and the FBI Criminal Justice Information Services, our research team conducted a comprehensive analysis spanning the years 1985 to 2022. Our findings revealed a remarkably robust correlation coefficient of 0.9706924 and a p-value of less than 0.01, highlighting a statistically significant association between the two variables.

Despite the initial absurdity of the topic, our investigation uncovers startling patterns that beckon further inquiry. The implications of our discoveries arguably extend beyond mere coincidence, prompting us to ponder the idiosyncrasies of nomenclature and their potential impact on societal behavior. This research surely adds a new twist to the classic "Kevin was here" graffiti trope!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The study of human behavior has long been a fascinating and perplexing endeavor, with researchers tirelessly seeking to untangle the intricate web of factors that shape our actions. From the influence of socioeconomic status to the impact of environmental cues, the quest for understanding the drivers of human conduct often leads down unexpected paths. In this vein, our research sets out to explore an unusual but undeniably captivating connection - the relationship between the popularity of the first name Kevin and incidences of robbery in the state of Connecticut.

As we embark on this academic odyssey, we are reminded of the timeless adage, "What's in a name?" Well, as it turns out, quite a bit, it seems. The name Kevin, often associated with affable quirks and perhaps a penchant for questionable fashion choices (note the resurgence of acid-washed jeans in the '80s), now finds itself at the center of a statistical conundrum. With a twinkle in our eyes and a spreadsheet at the ready, we navigated through decades of data - a task akin to finding the proverbial needle in a haystack, or perhaps, in this case, the elusive Kevin in a sea of Johns and Marys.

Venturing into uncharted territory, we combed through records from the US Social Security Administration, unearthing the temporal ebb and flow of Kevin's reign in the realm of given names. Simultaneously, we delved into the FBI Criminal Justice Information Services' repository of crime statistics, where the tales of illicit activities unfolded in meticulous detail. With bated breath and an unwavering commitment to scientific rigor, we commenced our analysis, appreciating the irony of equating crime data with the moniker Kevin - a play on words that surely warrants a chuckle.

However, what the numbers revealed was no mere jest. A correlation coefficient of 0.9706924 loomed large, practically waving a flag emblazoned with the words "Kevin was here" in bold, italicized font. The statistical significance was undeniable, with a p-value so minuscule it prompted a collective audibly raised eyebrow from our team. The sheer magnitude of the association challenged our preconceptions, urging us to grapple with the implications of our findings.

Indeed, our foray into the realm of nomenclature and delinquency offers a tantalizing glimpse into the intersection of whimsy and data-driven inquiry. As we unravel the Kevin-ious mysteries that dance at the periphery of societal norms, we invite fellow scholars to partake in this unlikely voyage. While our initial hypothesis may have been met with skepticism, there is no denying the peculiarity of our discoveries, holding profound implications that extend beyond a mere witticism adorning a bathroom stall. It appears that Kevin may have quietly woven his influence into the fabric of criminal behavior, leaving us to ponder the whims of nomenclature and the eccentricities of human conduct.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Popularity of the first name Kevin and Robberies in Connecticut. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut"

[[ABSTRACT]]
This study delves into the intriguing relationship between the prevalence of the first name Kevin and the occurrence of robberies in the state of Connecticut. Leveraging data from the US Social Security Administration and the FBI Criminal Justice Information Services, our research team conducted a comprehensive analysis spanning the years 1985 to 2022. Our findings revealed a remarkably robust correlation coefficient of 0.9706924 and a p-value of less than 0.01, highlighting a statistically significant association between the two variables.

Despite the initial absurdity of the topic, our investigation uncovers startling patterns that beckon further inquiry. The implications of our discoveries arguably extend beyond mere coincidence, prompting us to ponder the idiosyncrasies of nomenclature and their potential impact on societal behavior. This research surely adds a new twist to the classic "Kevin was here" graffiti trope!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The study of human behavior has long been a fascinating and perplexing endeavor, with researchers tirelessly seeking to untangle the intricate web of factors that shape our actions. From the influence of socioeconomic status to the impact of environmental cues, the quest for understanding the drivers of human conduct often leads down unexpected paths. In this vein, our research sets out to explore an unusual but undeniably captivating connection - the relationship between the popularity of the first name Kevin and incidences of robbery in the state of Connecticut.
As we embark on this academic odyssey, we are reminded of the timeless adage, "What's in a name?" Well, as it turns out, quite a bit, it seems. The name Kevin, often associated with affable quirks and perhaps a penchant for questionable fashion choices (note the resurgence of acid-washed jeans in the '80s), now finds itself at the center of a statistical conundrum. With a twinkle in our eyes and a spreadsheet at the ready, we navigated through decades of data - a task akin to finding the proverbial needle in a haystack, or perhaps, in this case, the elusive Kevin in a sea of Johns and Marys.
Venturing into uncharted territory, we combed through records from the US Social Security Administration, unearthing the temporal ebb and flow of Kevin's reign in the realm of given names. Simultaneously, we delved into the FBI Criminal Justice Information Services' repository of crime statistics, where the tales of illicit activities unfolded in meticulous detail. With bated breath and an unwavering commitment to scientific rigor, we commenced our analysis, appreciating the irony of equating crime data with the moniker Kevin - a play on words that surely warrants a chuckle.
However, what the numbers revealed was no mere jest. A correlation coefficient of 0.9706924 loomed large, practically waving a flag emblazoned with the words "Kevin was here" in bold, italicized font. The statistical significance was undeniable, with a p-value so minuscule it prompted a collective audibly raised eyebrow from our team. The sheer magnitude of the association challenged our preconceptions, urging us to grapple with the implications of our findings.
Indeed, our foray into the realm of nomenclature and delinquency offers a tantalizing glimpse into the intersection of whimsy and data-driven inquiry. As we unravel the Kevin-ious mysteries that dance at the periphery of societal norms, we invite fellow scholars to partake in this unlikely voyage. While our initial hypothesis may have been met with skepticism, there is no denying the peculiarity of our discoveries, holding profound implications that extend beyond a mere witticism adorning a bathroom stall. It appears that Kevin may have quietly woven his influence into the fabric of criminal behavior, leaving us to ponder the whims of nomenclature and the eccentricities of human conduct.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The investigation into the correlation between the predominance of the appellation Kevin and the perpetration of larcenies in the state of Connecticut prompts a thorough review of existing literature on the subject. While seemingly preposterous at first blush, the possibility of a connection between the popularity of a given name and criminal activity calls for a comprehensive exploration of related studies and scholarly works.

Smith, in "Population Dynamics and Name Frequencies in the United States," examines the evolution of naming trends and their societal implications. The author delves into the cyclical nature of name popularities, positing that shifts in naming conventions may mirror broader cultural and behavioral shifts. However, Smith's work does not specifically address the potential influence of specific names on criminal behavior, leaving our inquiry in uncharted waters - or should we say, un-Kevin-ed territories.

In a similar vein, Doe's "The Psychology of Names: Unraveling the Impact of Naming Conventions on Individual Choices" offers insights into the psychological underpinnings of nomenclature. The study delves into the subconscious associations evoked by different names and their implications for decision-making processes. Nonetheless, while illuminating, Doe's work fails to directly address the potential connection between name popularity and criminal proclivities—an omission that our research endeavors to rectify.

Jones, in "Statistical Analysis of Name Correlations and Social Behavior," provides a comprehensive analysis of the statistical relationships between naming patterns and various societal phenomena. However, the author primarily focuses on broader sociological trends and fails to specifically explore the potential link between a singular name and criminal activities, leaving our investigation with little more than a myriad of statistical correlations and a conspicuous absence of Kevin-related insights.

As the literature on the influence of names on human behavior falls short of addressing the peculiar nexus of the name Kevin with criminal activities, our exploration delves into unorthodox sources of inspiration to shed light on this enigmatic correlation.

Drawing from the realms of non-fiction, works such as "Freakonomics" by Steven D. Levitt and Stephen J. Dubner and "Outliers" by Malcolm Gladwell provide thought-provoking discussions on unexpected correlations and unconventional influencers shaping societal phenomena. Although these esteemed authors do not broach the topic of specific names and criminal behavior, their unorthodox analyses encourage a nuanced approach to unraveling the Kevin-ious mysteries that intrigue us.

In the domain of literature and popular culture, fictional works such as "The Name of the Rose" by Umberto Eco and "The Curious Incident of the Dog in the Night-Time" by Mark Haddon challenge conventional perspectives on the significance of names. They provoke contemplation on the potential interplay between nomenclature and the intricacies of human conduct, albeit in a narrative context that differs from our empirical pursuit. These literary works serve as a whimsical reminder that names, like clues in a detective novel, may hold unforeseen significance when piecing together the puzzle of societal phenomena.

Furthermore, childhood cartoons and television shows, including "Scooby-Doo" and "The Powerpuff Girls," albeit seemingly lighthearted in nature, offer unconventional parallels to our undertaking. These animated series often feature characters with distinctive names, and while their adventures are fiction, they compel us to consider the potential influence of nomenclature on behavioral archetypes. The playful escapades of these animated ensembles, though far removed from scholarly inquiry, implore us to maintain a sense of levity in our pursuit of understanding the Kevin-ious conundrum that unfolds before us.

In synthesizing the existing literature with unconventional sources of inspiration, our investigation is poised to navigate the obscure byways of nomenclature and societal behavior, aiming to uncover the profound implications of the Kevin-robbery correlation. This literature review, aptly intertwined with whimsical observations, serves as the prelude to our unorthodox quest for unraveling the undefined nuances of Kevin-ious behavior.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Popularity of the first name Kevin and Robberies in Connecticut. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
"Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut"

[[ABSTRACT]]
This study delves into the intriguing relationship between the prevalence of the first name Kevin and the occurrence of robberies in the state of Connecticut. Leveraging data from the US Social Security Administration and the FBI Criminal Justice Information Services, our research team conducted a comprehensive analysis spanning the years 1985 to 2022. Our findings revealed a remarkably robust correlation coefficient of 0.9706924 and a p-value of less than 0.01, highlighting a statistically significant association between the two variables.

Despite the initial absurdity of the topic, our investigation uncovers startling patterns that beckon further inquiry. The implications of our discoveries arguably extend beyond mere coincidence, prompting us to ponder the idiosyncrasies of nomenclature and their potential impact on societal behavior. This research surely adds a new twist to the classic "Kevin was here" graffiti trope!

[[INTRODUCTION]]
The study of human behavior has long been a fascinating and perplexing endeavor, with researchers tirelessly seeking to untangle the intricate web of factors that shape our actions. From the influence of socioeconomic status to the impact of environmental cues, the quest for understanding the drivers of human conduct often leads down unexpected paths. In this vein, our research sets out to explore an unusual but undeniably captivating connection - the relationship between the popularity of the first name Kevin and incidences of robbery in the state of Connecticut.
As we embark on this academic odyssey, we are reminded of the timeless adage, "What's in a name?" Well, as it turns out, quite a bit, it seems. The name Kevin, often associated with affable quirks and perhaps a penchant for questionable fashion choices (note the resurgence of acid-washed jeans in the '80s), now finds itself at the center of a statistical conundrum. With a twinkle in our eyes and a spreadsheet at the ready, we navigated through decades of data - a task akin to finding the proverbial needle in a haystack, or perhaps, in this case, the elusive Kevin in a sea of Johns and Marys.
Venturing into uncharted territory, we combed through records from the US Social Security Administration, unearthing the temporal ebb and flow of Kevin's reign in the realm of given names. Simultaneously, we delved into the FBI Criminal Justice Information Services' repository of crime statistics, where the tales of illicit activities unfolded in meticulous detail. With bated breath and an unwavering commitment to scientific rigor, we commenced our analysis, appreciating the irony of equating crime data with the moniker Kevin - a play on words that surely warrants a chuckle.
However, what the numbers revealed was no mere jest. A correlation coefficient of 0.9706924 loomed large, practically waving a flag emblazoned with the words "Kevin was here" in bold, italicized font. The statistical significance was undeniable, with a p-value so minuscule it prompted a collective audibly raised eyebrow from our team. The sheer magnitude of the association challenged our preconceptions, urging us to grapple with the implications of our findings.
Indeed, our foray into the realm of nomenclature and delinquency offers a tantalizing glimpse into the intersection of whimsy and data-driven inquiry. As we unravel the Kevin-ious mysteries that dance at the periphery of societal norms, we invite fellow scholars to partake in this unlikely voyage. While our initial hypothesis may have been met with skepticism, there is no denying the peculiarity of our discoveries, holding profound implications that extend beyond a mere witticism adorning a bathroom stall. It appears that Kevin may have quietly woven his influence into the fabric of criminal behavior, leaving us to ponder the whims of nomenclature and the eccentricities of human conduct.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:

The first step in our investigation involved sourcing data from the US Social Security Administration and the FBI Criminal Justice Information Services. We delved into the annals of the Social Security Administration’s records to extract the occurrence of the name Kevin over the years, trawling through the veritable ocean of names to locate our titular character amongst the waves of appellations. The process of isolating Kevin amidst the ever-shifting tides of nomenclature was akin to a whimsical game of hide-and-seek - a fitting metaphor for our scholarly pursuit.

Simultaneously, we navigated through the labyrinthine corridors of crime statistics housed within the FBI Criminal Justice Information Services. Here, our team scoured the datasets, unraveling the intricate tapestry of criminal activities in the state of Connecticut. The dance of digits and the interplay of felonious narratives served as a captivating backdrop to our quest, as we aimed to uncover any semblance of Kevin's clandestine influence on criminal misadventures.

Data Analysis:

With a treasure trove of data at our disposal, we embarked on the arduous yet exhilarating journey of statistical analysis. Our quest for clarity led us to concoct a complex symphony of regression analyses, time-series modeling, and correlation assessments. As we meticulously sifted through the numerical fragments, we breathed life into the numbers, allowing them to tell their own tale - a saga punctuated by the enigmatic presence of Kevin and his potential impact on delinquency.

The statistical rigmarole demanded our undivided attention, as we coaxed patterns and relationships from the labyrinthine depths of our datasets. The meticulous calculus of associations and significance thrust us into a world of numerical intrigue, seemingly a cosmic tango between Kevin's popularity and the ebb and flow of nefarious activities in Connecticut. In the words of a wise sage, our statistical odyssey was tantamount to seeking a needle in a haystack, only to stumble upon a trove of Kevin clones, each beckoning from divergent corners of the numerical expanse.

Eventually, our efforts culminated in the emergence of a correlation coefficient of 0.9706924, casting a resplendent sheen over our analytical travail. The statistical significance thus uncovered, with a p-value tantamount to spotting a unicorn in a field of thoroughbreds, fortified our earnest quest, compelling us to confront the startling implications of our findings.

Limitations:

It is imperative to acknowledge the inherent limitations of our methodology. While our statistical analyses have foregrounded a compelling association between the prevalence of the name Kevin and the incidence of robberies in Connecticut, our study remains confined to the realm of correlation. The complexities of human behavior, steeped in an amalgam of cultural, social, and psychological influences, cannot be wholly encapsulated within the numerical embrace of our analyses.

Despite the jocund mirth that pervaded our scholarly endeavors, we remain attuned to the need for cautious interpretation and further inquiry. Our study, however unlikely its premise, serves as a beacon beckoning forth further investigatory rigor and contemplation. The Kevin-ious mysteries we have unearthed demand the scrutiny of future scholars inclined toward the whimsical and the whimsically analytical.

In summary, our methodological sojourn is a testament to the peculiar juncture of statistical inquiry and playful dedication, underscoring the scholarly merits of unearthing unconventional associations and the inescapable allure of an enigmatic name.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Popularity of the first name Kevin and Robberies in Connecticut. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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 .

For the time period 1985 to 2022, you found a correlation 0.9706924, r-squared of 0.9422437, and p < 0.01.

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

Here is the title and abstract of the paper:
[[TITLE]]
"Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut"

[[ABSTRACT]]
This study delves into the intriguing relationship between the prevalence of the first name Kevin and the occurrence of robberies in the state of Connecticut. Leveraging data from the US Social Security Administration and the FBI Criminal Justice Information Services, our research team conducted a comprehensive analysis spanning the years 1985 to 2022. Our findings revealed a remarkably robust correlation coefficient of 0.9706924 and a p-value of less than 0.01, highlighting a statistically significant association between the two variables.

Despite the initial absurdity of the topic, our investigation uncovers startling patterns that beckon further inquiry. The implications of our discoveries arguably extend beyond mere coincidence, prompting us to ponder the idiosyncrasies of nomenclature and their potential impact on societal behavior. This research surely adds a new twist to the classic "Kevin was here" graffiti trope!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The study of human behavior has long been a fascinating and perplexing endeavor, with researchers tirelessly seeking to untangle the intricate web of factors that shape our actions. From the influence of socioeconomic status to the impact of environmental cues, the quest for understanding the drivers of human conduct often leads down unexpected paths. In this vein, our research sets out to explore an unusual but undeniably captivating connection - the relationship between the popularity of the first name Kevin and incidences of robbery in the state of Connecticut.
As we embark on this academic odyssey, we are reminded of the timeless adage, "What's in a name?" Well, as it turns out, quite a bit, it seems. The name Kevin, often associated with affable quirks and perhaps a penchant for questionable fashion choices (note the resurgence of acid-washed jeans in the '80s), now finds itself at the center of a statistical conundrum. With a twinkle in our eyes and a spreadsheet at the ready, we navigated through decades of data - a task akin to finding the proverbial needle in a haystack, or perhaps, in this case, the elusive Kevin in a sea of Johns and Marys.
Venturing into uncharted territory, we combed through records from the US Social Security Administration, unearthing the temporal ebb and flow of Kevin's reign in the realm of given names. Simultaneously, we delved into the FBI Criminal Justice Information Services' repository of crime statistics, where the tales of illicit activities unfolded in meticulous detail. With bated breath and an unwavering commitment to scientific rigor, we commenced our analysis, appreciating the irony of equating crime data with the moniker Kevin - a play on words that surely warrants a chuckle.
However, what the numbers revealed was no mere jest. A correlation coefficient of 0.9706924 loomed large, practically waving a flag emblazoned with the words "Kevin was here" in bold, italicized font. The statistical significance was undeniable, with a p-value so minuscule it prompted a collective audibly raised eyebrow from our team. The sheer magnitude of the association challenged our preconceptions, urging us to grapple with the implications of our findings.
Indeed, our foray into the realm of nomenclature and delinquency offers a tantalizing glimpse into the intersection of whimsy and data-driven inquiry. As we unravel the Kevin-ious mysteries that dance at the periphery of societal norms, we invite fellow scholars to partake in this unlikely voyage. While our initial hypothesis may have been met with skepticism, there is no denying the peculiarity of our discoveries, holding profound implications that extend beyond a mere witticism adorning a bathroom stall. It appears that Kevin may have quietly woven his influence into the fabric of criminal behavior, leaving us to ponder the whims of nomenclature and the eccentricities of human conduct.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis of the data from the US Social Security Administration and the FBI Criminal Justice Information Services for the years 1985 to 2022 led to some truly intriguing findings. We calculated a strikingly high correlation coefficient of 0.9706924, indicating a strong positive relationship between the prevalence of the name Kevin and the occurrences of robberies in Connecticut. The r-squared value of 0.9422437 further attests to the robustness of this association, explaining approximately 94.2% of the variation in robbery rates solely based on the popularity of the name Kevin. Additionally, the statistical significance was firmly established with a p-value of less than 0.01, underscoring the reliability of our results and dismissing any doubts about the existence of this seemingly improbable link.

Our revelations are encapsulated in Figure 1, a scatterplot displaying the conspicuous correlation between the frequency of the name Kevin and the occurrence of robberies in Connecticut. The data points form a tightly packed, upward-sloping pattern, unequivocally demonstrating the pronounced positive relationship between these seemingly disparate variables. The figure serves as a striking visual representation of the unexpected connections our investigation uncovered, standing testament to the adage that "the truth is stranger than fiction."

Our results beckon further exploration into the mechanisms underlying this unlikely correlation, offering fertile ground for future inquiries into the interplay of nomenclature and societal phenomena. The implications of our discoveries extend beyond mere statistical curiosities, inviting contemplation of the idiosyncrasies of human behavior. While the initial premise of our study may have elicited a few raised eyebrows, the gravity of our findings demands acknowledgment and incites ponderings about the mysterious influence of nomenclature on human behavior. This indeed adds a new twist to the "Kevin was here" graffiti trope, invoking a mixture of amusement and awe at the unexpected ways in which names may shape our world.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Popularity of the first name Kevin and Robberies in Connecticut. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut"

[[ABSTRACT]]
This study delves into the intriguing relationship between the prevalence of the first name Kevin and the occurrence of robberies in the state of Connecticut. Leveraging data from the US Social Security Administration and the FBI Criminal Justice Information Services, our research team conducted a comprehensive analysis spanning the years 1985 to 2022. Our findings revealed a remarkably robust correlation coefficient of 0.9706924 and a p-value of less than 0.01, highlighting a statistically significant association between the two variables.

Despite the initial absurdity of the topic, our investigation uncovers startling patterns that beckon further inquiry. The implications of our discoveries arguably extend beyond mere coincidence, prompting us to ponder the idiosyncrasies of nomenclature and their potential impact on societal behavior. This research surely adds a new twist to the classic "Kevin was here" graffiti trope!

[[LITERATURE REVIEW]]
The investigation into the correlation between the predominance of the appellation Kevin and the perpetration of larcenies in the state of Connecticut prompts a thorough review of existing literature on the subject. While seemingly preposterous at first blush, the possibility of a connection between the popularity of a given name and criminal activity calls for a comprehensive exploration of related studies and scholarly works.
Smith, in "Population Dynamics and Name Frequencies in the United States," examines the evolution of naming trends and their societal implications. The author delves into the cyclical nature of name popularities, positing that shifts in naming conventions may mirror broader cultural and behavioral shifts. However, Smith's work does not specifically address the potential influence of specific names on criminal behavior, leaving our inquiry in uncharted waters - or should we say, un-Kevin-ed territories.
In a similar vein, Doe's "The Psychology of Names: Unraveling the Impact of Naming Conventions on Individual Choices" offers insights into the psychological underpinnings of nomenclature. The study delves into the subconscious associations evoked by different names and their implications for decision-making processes. Nonetheless, while illuminating, Doe's work fails to directly address the potential connection between name popularity and criminal proclivities—an omission that our research endeavors to rectify.
Jones, in "Statistical Analysis of Name Correlations and Social Behavior," provides a comprehensive analysis of the statistical relationships between naming patterns and various societal phenomena. However, the author primarily focuses on broader sociological trends and fails to specifically explore the potential link between a singular name and criminal activities, leaving our investigation with little more than a myriad of statistical correlations and a conspicuous absence of Kevin-related insights.
As the literature on the influence of names on human behavior falls short of addressing the peculiar nexus of the name Kevin with criminal activities, our exploration delves into unorthodox sources of inspiration to shed light on this enigmatic correlation.
Drawing from the realms of non-fiction, works such as "Freakonomics" by Steven D. Levitt and Stephen J. Dubner and "Outliers" by Malcolm Gladwell provide thought-provoking discussions on unexpected correlations and unconventional influencers shaping societal phenomena. Although these esteemed authors do not broach the topic of specific names and criminal behavior, their unorthodox analyses encourage a nuanced approach to unraveling the Kevin-ious mysteries that intrigue us.
In the domain of literature and popular culture, fictional works such as "The Name of the Rose" by Umberto Eco and "The Curious Incident of the Dog in the Night-Time" by Mark Haddon challenge conventional perspectives on the significance of names. They provoke contemplation on the potential interplay between nomenclature and the intricacies of human conduct, albeit in a narrative context that differs from our empirical pursuit. These literary works serve as a whimsical reminder that names, like clues in a detective novel, may hold unforeseen significance when piecing together the puzzle of societal phenomena.
Furthermore, childhood cartoons and television shows, including "Scooby-Doo" and "The Powerpuff Girls," albeit seemingly lighthearted in nature, offer unconventional parallels to our undertaking. These animated series often feature characters with distinctive names, and while their adventures are fiction, they compel us to consider the potential influence of nomenclature on behavioral archetypes. The playful escapades of these animated ensembles, though far removed from scholarly inquiry, implore us to maintain a sense of levity in our pursuit of understanding the Kevin-ious conundrum that unfolds before us.
In synthesizing the existing literature with unconventional sources of inspiration, our investigation is poised to navigate the obscure byways of nomenclature and societal behavior, aiming to uncover the profound implications of the Kevin-robbery correlation. This literature review, aptly intertwined with whimsical observations, serves as the prelude to our unorthodox quest for unraveling the undefined nuances of Kevin-ious behavior.

[[RESULTS]]
Our analysis of the data from the US Social Security Administration and the FBI Criminal Justice Information Services for the years 1985 to 2022 led to some truly intriguing findings. We calculated a strikingly high correlation coefficient of 0.9706924, indicating a strong positive relationship between the prevalence of the name Kevin and the occurrences of robberies in Connecticut. The r-squared value of 0.9422437 further attests to the robustness of this association, explaining approximately 94.2% of the variation in robbery rates solely based on the popularity of the name Kevin. Additionally, the statistical significance was firmly established with a p-value of less than 0.01, underscoring the reliability of our results and dismissing any doubts about the existence of this seemingly improbable link.
Our revelations are encapsulated in Figure 1, a scatterplot displaying the conspicuous correlation between the frequency of the name Kevin and the occurrence of robberies in Connecticut. The data points form a tightly packed, upward-sloping pattern, unequivocally demonstrating the pronounced positive relationship between these seemingly disparate variables. The figure serves as a striking visual representation of the unexpected connections our investigation uncovered, standing testament to the adage that "the truth is stranger than fiction."
Our results beckon further exploration into the mechanisms underlying this unlikely correlation, offering fertile ground for future inquiries into the interplay of nomenclature and societal phenomena. The implications of our discoveries extend beyond mere statistical curiosities, inviting contemplation of the idiosyncrasies of human behavior. While the initial premise of our study may have elicited a few raised eyebrows, the gravity of our findings demands acknowledgment and incites ponderings about the mysterious influence of nomenclature on human behavior. This indeed adds a new twist to the "Kevin was here" graffiti trope, invoking a mixture of amusement and awe at the unexpected ways in which names may shape our world.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our investigation into the correlation between the popularity of the name Kevin and the prevalence of robberies in Connecticut has unearthed remarkably compelling results. Despite the seemingly whimsical nature of our study, our findings stand as a testament to the unanticipated potential of nomenclature to influence societal behavior. The robust correlation coefficient of 0.9706924 and the statistically significant p-value of less than 0.01 lend weight to the existence of a genuine association between the frequency of the name Kevin and the occurrences of robberies.

Our results not only reinforce the pioneering work of Smith, Doe, and Jones in highlighting the socio-behavioral connotations of nomenclature but also extend their premises to a specific name-criminal activity relationship. This resonance with prior literature emphasizes the serious implications of seemingly comical conjectures – or in this case, the "Kevin-ious" hypotheses.

While our exploration delves into unorthodox territories of scholarly pursuits, the gravity of our findings calls for earnest consideration of the potential influences of seemingly innocuous factors on societal dynamics. Indeed, our discoveries evoke a certain irony, akin to the unexpected twists in a detective novel or the whimsy of a cartoon, underscoring the profound and unexpected interplay of nomenclature and human conduct – a correlation that is certainly not to be "cartooned" away.

These results, along with their unequivocal support from prior literature, present a compelling case for further investigations into the underlying mechanisms and implications of name-society associations. Our research dismantles conventional skepticism around the tangential nature of nomenclature studies, advocating for an expanded consideration of the idiosyncrasies that shape our world – the Kevin-ious behavioral quirks that beckon our scholarly attention.

The strangeness of our findings is reminiscent of a childhood mystery, wherein the seemingly mundane pieces come together to form an unexpected tableau. As we unravel this enigmatic correlation, we are reminded of the captivating complexity of human behavior and the potential influences that lie in the often-overlooked details of nomenclature. Our inquiry not only poses a whimsical challenge to conventional thinking but also invites a deeper contemplation of the multifaceted nature of societal phenomena.

In essence, our investigation prompts a reconsideration of the "Kevin-ious" outliers that reside on the entangled web of nomenclature and societal behaviors. As we venture forth into the uncharted territories of name-society correlations, it is our hope that our revelatory findings will inspire continued explorations and perhaps even a touch of levity amidst the serious pursuit of unraveling the captivating mysteries of human behavior.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Popularity of the first name Kevin and Robberies in Connecticut. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut"

[[ABSTRACT]]
This study delves into the intriguing relationship between the prevalence of the first name Kevin and the occurrence of robberies in the state of Connecticut. Leveraging data from the US Social Security Administration and the FBI Criminal Justice Information Services, our research team conducted a comprehensive analysis spanning the years 1985 to 2022. Our findings revealed a remarkably robust correlation coefficient of 0.9706924 and a p-value of less than 0.01, highlighting a statistically significant association between the two variables.

Despite the initial absurdity of the topic, our investigation uncovers startling patterns that beckon further inquiry. The implications of our discoveries arguably extend beyond mere coincidence, prompting us to ponder the idiosyncrasies of nomenclature and their potential impact on societal behavior. This research surely adds a new twist to the classic "Kevin was here" graffiti trope!

[[INTRDUCTION]]
The study of human behavior has long been a fascinating and perplexing endeavor, with researchers tirelessly seeking to untangle the intricate web of factors that shape our actions. From the influence of socioeconomic status to the impact of environmental cues, the quest for understanding the drivers of human conduct often leads down unexpected paths. In this vein, our research sets out to explore an unusual but undeniably captivating connection - the relationship between the popularity of the first name Kevin and incidences of robbery in the state of Connecticut.
As we embark on this academic odyssey, we are reminded of the timeless adage, "What's in a name?" Well, as it turns out, quite a bit, it seems. The name Kevin, often associated with affable quirks and perhaps a penchant for questionable fashion choices (note the resurgence of acid-washed jeans in the '80s), now finds itself at the center of a statistical conundrum. With a twinkle in our eyes and a spreadsheet at the ready, we navigated through decades of data - a task akin to finding the proverbial needle in a haystack, or perhaps, in this case, the elusive Kevin in a sea of Johns and Marys.
Venturing into uncharted territory, we combed through records from the US Social Security Administration, unearthing the temporal ebb and flow of Kevin's reign in the realm of given names. Simultaneously, we delved into the FBI Criminal Justice Information Services' repository of crime statistics, where the tales of illicit activities unfolded in meticulous detail. With bated breath and an unwavering commitment to scientific rigor, we commenced our analysis, appreciating the irony of equating crime data with the moniker Kevin - a play on words that surely warrants a chuckle.
However, what the numbers revealed was no mere jest. A correlation coefficient of 0.9706924 loomed large, practically waving a flag emblazoned with the words "Kevin was here" in bold, italicized font. The statistical significance was undeniable, with a p-value so minuscule it prompted a collective audibly raised eyebrow from our team. The sheer magnitude of the association challenged our preconceptions, urging us to grapple with the implications of our findings.
Indeed, our foray into the realm of nomenclature and delinquency offers a tantalizing glimpse into the intersection of whimsy and data-driven inquiry. As we unravel the Kevin-ious mysteries that dance at the periphery of societal norms, we invite fellow scholars to partake in this unlikely voyage. While our initial hypothesis may have been met with skepticism, there is no denying the peculiarity of our discoveries, holding profound implications that extend beyond a mere witticism adorning a bathroom stall. It appears that Kevin may have quietly woven his influence into the fabric of criminal behavior, leaving us to ponder the whims of nomenclature and the eccentricities of human conduct.

[[RESULTS]]
Our analysis of the data from the US Social Security Administration and the FBI Criminal Justice Information Services for the years 1985 to 2022 led to some truly intriguing findings. We calculated a strikingly high correlation coefficient of 0.9706924, indicating a strong positive relationship between the prevalence of the name Kevin and the occurrences of robberies in Connecticut. The r-squared value of 0.9422437 further attests to the robustness of this association, explaining approximately 94.2% of the variation in robbery rates solely based on the popularity of the name Kevin. Additionally, the statistical significance was firmly established with a p-value of less than 0.01, underscoring the reliability of our results and dismissing any doubts about the existence of this seemingly improbable link.
Our revelations are encapsulated in Figure 1, a scatterplot displaying the conspicuous correlation between the frequency of the name Kevin and the occurrence of robberies in Connecticut. The data points form a tightly packed, upward-sloping pattern, unequivocally demonstrating the pronounced positive relationship between these seemingly disparate variables. The figure serves as a striking visual representation of the unexpected connections our investigation uncovered, standing testament to the adage that "the truth is stranger than fiction."
Our results beckon further exploration into the mechanisms underlying this unlikely correlation, offering fertile ground for future inquiries into the interplay of nomenclature and societal phenomena. The implications of our discoveries extend beyond mere statistical curiosities, inviting contemplation of the idiosyncrasies of human behavior. While the initial premise of our study may have elicited a few raised eyebrows, the gravity of our findings demands acknowledgment and incites ponderings about the mysterious influence of nomenclature on human behavior. This indeed adds a new twist to the "Kevin was here" graffiti trope, invoking a mixture of amusement and awe at the unexpected ways in which names may shape our world.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In scrutinizing the enigmatic association between the prevalence of the name Kevin and the incidence of robberies in Connecticut, our study has unearthed a compelling correlation, provoking contemplation on the idiosyncrasies of nomenclature and their potential implications for societal conduct. The remarkably robust correlation coefficient and the statistical significance of our findings demand acknowledgment, compelling us to ponder the unexpected influence of names on human behavior. While our initial hypothesis may have garnered a few quizzical glances, the evidence speaks volumes, underscoring the perplexing ways in which nomenclature may stealthily intertwine with societal phenomena.

The intersection of the whimsy of nomenclature and the seriousness of criminal behavior has undoubtedly left us with a distinctive conundrum that tickles the intellect. As we conclude this paper, we bid adieu to our exploration, acknowledging the revelatory nature of our findings and the quizzical yet profound implications of the "Kevin-ious" mysteries. However, we assert that no further research in this "Kevin-nected" field is necessary, for sometimes, the most beguiling phenomena are best left to simmer in the quirky annals of academic discovery.


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 Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Sociological Studies


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 Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut. Respond only with the name of a fictional organization.

ChatGPT:

The International Society for the Study of Unlikely Correlations


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 Kevin-ious Behavior: Investigating the Link Between the Popularity of the Name Kevin and Robberies in Connecticut with an abstract of This study delves into the intriguing relationship between the prevalence of the first name Kevin and the occurrence of robberies in the state of Connecticut. Leveraging data from the US Social Security Administration and the FBI Criminal Justice Information Services, our research team conducted a comprehensive analysis spanning the years 1985 to 2022. Our findings revealed a remarkably robust correlation coefficient of 0.9706924 and a p-value of less than 0.01, highlighting a statistically significant association between the two variables.
Despite the initial absurdity of the topic, our investigation uncovers startling patterns that beckon further inquiry. The implications of our discoveries arguably extend beyond mere coincidence, prompting us to ponder the idiosyncrasies of nomenclature and their potential impact on societal behavior. This research surely adds a new twist to the classic "Kevin was here" graffiti trope!

ChatGPT:

Kevin, name prevalence, robberies, Connecticut, correlation, social security administration, FBI Crime Statistics, nomenclature, societal behavior, name popularity, crime rates

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

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

Correlation r = 0.9706924 (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 = 0.9422437 (Coefficient of determination)
This means 94.2% of the change in the one variable (i.e., Robberies in Connecticut) is predictable based on the change in the other (i.e., Popularity of the first name Kevin) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.9E-24. 0.0000000000000000000000069467
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.97 in 6.9E-22% of random cases. Said differently, if you correlated 143,953,243,986,353,247,485,952 random variables You don't actually need 143 sextillion 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, 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.

[ 0.94, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Popularity of the first name Kevin (Babies born)1896020082205572028321308204832034119701191361736715917146211332612525122921270212629120761176111266109461080610559980787997333658262385951591351954555383831422621238321032060
Robberies in Connecticut (Robbery rate)190192.2178.1187.6214.8234.8224.4210.9196.7187.8163.2169.6152.9133.8123.5112.5121.8117.6120.8119.7112.3127.3122.9115.5113.799.4102.9103.398.788.281.675.678.761.754.557.254.344.9




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([18960,20082,20557,20283,21308,20483,20341,19701,19136,17367,15917,14621,13326,12525,12292,12702,12629,12076,11761,11266,10946,10806,10559,9807,8799,7333,6582,6238,5951,5913,5195,4555,3838,3142,2621,2383,2103,2060,])
array_2 = np.array([190,192.2,178.1,187.6,214.8,234.8,224.4,210.9,196.7,187.8,163.2,169.6,152.9,133.8,123.5,112.5,121.8,117.6,120.8,119.7,112.3,127.3,122.9,115.5,113.7,99.4,102.9,103.3,98.7,88.2,81.6,75.6,78.7,61.7,54.5,57.2,54.3,44.9,])
array_1_name = "Popularity of the first name Kevin"
array_2_name = "Robberies in Connecticut"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating skills are top-notch!


Correlation ID: 2429 · Black Variable ID: 2011 · Red Variable ID: 20230
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0