Spurious correlation #3,442 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of actuaries in Georgia and the second variable is Miss America's age. The chart goes from 2003 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 The number of actuaries in Georgia and the second variable is Miss America's age. The chart goes from 2003 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of actuaries in Georgia increased, there was a parallel rise in the planning of Miss America pageant activities. This efficient planning inadvertently led to a reduction in the length of the pageant, prompting contestants to speed up their routines. Essentially, more actuaries equated to a higher pageant calculation speed, crowning younger winners in record time. It's a beauty and the mathlete situation!

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Using the style [ Data cyber art ], generate an image of a charming Georgian town with streets lined with an increasing number of calculators. The calculators are diligently crunching numbers as the scene shows Miss America aging in fast-forward, her radiant beauty transforming as time seems to speed up around her. The image should visually illustrate the unique relationship between the growing crowd of actuaries and the rapidly aging Miss America. 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: The number of actuaries in Georgia and Miss America's age. 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: Pop art Cute cartoon Concept art Data cyber art Celtic art
ChatGPT: Data cyber art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both The number of actuaries in Georgia and Miss America's age, in the following situation: Because as the number of actuaries in Georgia increases, Miss America ages due to the sheer amount of number crunching, causing time to pass at an accelerated rate. It's just a result of all those calculators working overtime and aging the poor Miss America.. Keep the description simple.
ChatGPT: In a charming Georgian town, an increasing number of calculators line the streets, diligently crunching numbers. As the calculators hum with activity, Miss America is seen aging in fast-forward, her radiant beauty transforming as time seems to speed up around her. The growing crowd of actuaries and the rapidly aging Miss America visually illustrate the unique relationship between these two variables.

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: [ Data cyber art ] and depicting this scene: In a charming Georgian town, an increasing number of calculators line the streets, diligently crunching numbers. As the calculators hum with activity, Miss America is seen aging in fast-forward, her radiant beauty transforming as time seems to speed up around her. The growing crowd of actuaries and the rapidly aging Miss America visually illustrate the unique relationship between these two variables. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Using the style [ Data cyber art ], generate an image of a charming Georgian town with streets lined with an increasing number of calculators. The calculators are diligently crunching numbers as the scene shows Miss America aging in fast-forward, her radiant beauty transforming as time seems to speed up around her. The image should visually illustrate the unique relationship between the growing crowd of actuaries and the rapidly aging Miss America.

*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 increases in The number of actuaries in Georgia negatively influenced Miss America's age. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)

The Actuary Equation: A Statistical Analysis of Actuary Numbers in Georgia and Miss America's Age

The Journal of Mathematical Glamour

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of actuaries in Georgia and Miss America's age. 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
"The Actuary Equation: A Statistical Analysis of Actuary Numbers in Georgia and Miss America's Age"

[[ABSTRACT]]
This study examines the curious relationship between the number of actuaries in Georgia and the age of Miss America. Utilizing data from the Bureau of Labor Statistics and Wikipedia, we conducted a rigorous statistical analysis covering the years 2003 to 2022. Surprisingly, our findings reveal a remarkably strong negative correlation, with a correlation coefficient of -0.8557955 and p < 0.01. As the number of actuaries in Georgia fluctuates, Miss America's age follows suit in an almost synchronized manner, prompting questions about causality and teasing the boundaries of mere coincidence. This research sheds light on the whimsical interconnectedness of seemingly disparate phenomena and highlights the need for further investigation into the curious world of actuarial science and beauty pageantry.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of actuarial science and beauty pageantry may seem as odd a pairing as peanut butter and pickles, but the relationship between the number of actuaries in Georgia and the age of Miss America has piqued the curiosity of researchers for years. As renowned economist John Kenneth Galbraith once said, "The only function of economic forecasting is to make astrology look respectable," and one might be forgiven for thinking that delving into the connection between these two seemingly unrelated variables falls squarely into the realm of astrological whimsy. However, our study takes a more empirical approach, aiming to uncover any substantive correlation that might exist between the dynamics of these two distinct domains.
The notion that the statistical happenings within the actuarial field could be entangled with the age of the embodiment of American beauty raises eyebrows and invites a chuckle at first glance. One can't help but wonder, is this the universe's way of demonstrating its own sense of humor, or is there a more profound undercurrent connecting the perceived rigidity of numbers with the fluidity of youth and beauty?
The world of actuarial science, renowned for its meticulous number-crunching and risk assessment, collides with the glitz and glamor of the Miss America pageant, an event steeped in tradition and spectacle, to offer an unexpected avenue for investigation. One might say this study aims to unravel the mystery and reveal if there's more to this interplay than meets the eye, or rather, the "I."
As we embark on this journey of statistical discovery, we invite the reader to keep an open mind and perhaps a wry smile at the thought that numbers and pageantry might dance to the same statistical tune. So, without further ado, let us delve into the enigmatic correlation, or causation, between the number of actuaries in Georgia and the age of Miss America.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Given the rather whimsical nature of our inquiry, it is somewhat challenging to identify scholarly works that directly address the correlation between the number of actuaries in Georgia and the age of Miss America. Nonetheless, a review of the literature on related topics offers some valuable insights into the intersection of seemingly disparate domains.

Smith (2010) discusses the influence of demographic factors on beauty pageants, considering variables such as regional population density, socioeconomic status, and even weather patterns. While Smith's work does not explicitly delve into the specific relationship between actuaries and Miss America, it does lay groundwork for the exploration of unexpected correlations between seemingly unrelated phenomena.

Moving beyond the confines of strictly academic literature, Doe (2015) presents a compelling argument in "The Beauty of Numbers: Uncovering Patterns in Unlikely Places." Doe's work encourages readers to embrace serendipity and explore unconventional connections in the world of data analysis. The author introduces the idea that numbers possess an inherent beauty, a notion that resonates with our investigation into the potential aesthetic harmony between actuarial figures and Miss America's age.

In a similar vein, Jones (2018) contends that statistical anomalies often hide in plain sight, waiting to be excavated by curious minds. In "The Art of Data Juxtaposition," Jones provokes readers to contemplate the unexpected symphony that emerges when seemingly incongruent data sets are brought together. While Jones's focus is not on beauty pageants or actuarial science, the underlying message is pertinent to our pursuit of uncovering a meaningful connection between the number of actuaries in Georgia and Miss America's age.

As we venture into more unconventional sources, it is worth noting the potential for unexpected revelations. Works of fiction often offer profound insights into the human experience, and titles such as "Numbers Never Lie: A Tale of Probability and Beauty" by A. Novel (2012) and "The Actuary's Dilemma: Predicting Love, Loss, and Tiara Tosses" by E. Story (2016) present fictitious narratives that may indirectly inform our understanding of the peculiar association under investigation.

Further expanding our scope, popular culture and children's programming may yield unexpected parallels to our empirical study. The animated series "Number Crunchers: Adventures in Probability" and the educational show "Beauteous Equations: Quantitative Glamor for Juveniles" offer lighthearted introductions to numeric concepts and social phenomena that, while not directly related to our research, may inspire a fresh perspective on the uncanny correlation between Georgia's actuaries and the age of Miss America.

In the pursuit of academic inquiry, it is essential to embrace a multidimensional approach, drawing inspiration from an array of sources that extend beyond the traditional confines of scholarly discourse. While our investigation may provoke more than a few quizzical glances, it is precisely this spirit of unconventional exploration that lays the groundwork for the captivating findings we present in this study.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of actuaries in Georgia and Miss America's age. 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]]
"The Actuary Equation: A Statistical Analysis of Actuary Numbers in Georgia and Miss America's Age"

[[ABSTRACT]]
This study examines the curious relationship between the number of actuaries in Georgia and the age of Miss America. Utilizing data from the Bureau of Labor Statistics and Wikipedia, we conducted a rigorous statistical analysis covering the years 2003 to 2022. Surprisingly, our findings reveal a remarkably strong negative correlation, with a correlation coefficient of -0.8557955 and p < 0.01. As the number of actuaries in Georgia fluctuates, Miss America's age follows suit in an almost synchronized manner, prompting questions about causality and teasing the boundaries of mere coincidence. This research sheds light on the whimsical interconnectedness of seemingly disparate phenomena and highlights the need for further investigation into the curious world of actuarial science and beauty pageantry.

[[LITERATURE REVIEW]]
Given the rather whimsical nature of our inquiry, it is somewhat challenging to identify scholarly works that directly address the correlation between the number of actuaries in Georgia and the age of Miss America. Nonetheless, a review of the literature on related topics offers some valuable insights into the intersection of seemingly disparate domains.
Smith (2010) discusses the influence of demographic factors on beauty pageants, considering variables such as regional population density, socioeconomic status, and even weather patterns. While Smith's work does not explicitly delve into the specific relationship between actuaries and Miss America, it does lay groundwork for the exploration of unexpected correlations between seemingly unrelated phenomena.
Moving beyond the confines of strictly academic literature, Doe (2015) presents a compelling argument in "The Beauty of Numbers: Uncovering Patterns in Unlikely Places." Doe's work encourages readers to embrace serendipity and explore unconventional connections in the world of data analysis. The author introduces the idea that numbers possess an inherent beauty, a notion that resonates with our investigation into the potential aesthetic harmony between actuarial figures and Miss America's age.
In a similar vein, Jones (2018) contends that statistical anomalies often hide in plain sight, waiting to be excavated by curious minds. In "The Art of Data Juxtaposition," Jones provokes readers to contemplate the unexpected symphony that emerges when seemingly incongruent data sets are brought together. While Jones's focus is not on beauty pageants or actuarial science, the underlying message is pertinent to our pursuit of uncovering a meaningful connection between the number of actuaries in Georgia and Miss America's age.
As we venture into more unconventional sources, it is worth noting the potential for unexpected revelations. Works of fiction often offer profound insights into the human experience, and titles such as "Numbers Never Lie: A Tale of Probability and Beauty" by A. Novel (2012) and "The Actuary's Dilemma: Predicting Love, Loss, and Tiara Tosses" by E. Story (2016) present fictitious narratives that may indirectly inform our understanding of the peculiar association under investigation.
Further expanding our scope, popular culture and children's programming may yield unexpected parallels to our empirical study. The animated series "Number Crunchers: Adventures in Probability" and the educational show "Beauteous Equations: Quantitative Glamor for Juveniles" offer lighthearted introductions to numeric concepts and social phenomena that, while not directly related to our research, may inspire a fresh perspective on the uncanny correlation between Georgia's actuaries and the age of Miss America.
In the pursuit of academic inquiry, it is essential to embrace a multidimensional approach, drawing inspiration from an array of sources that extend beyond the traditional confines of scholarly discourse. While our investigation may provoke more than a few quizzical glances, it is precisely this spirit of unconventional exploration that lays the groundwork for the captivating findings we present in this study.

[[RESULTS]]
The analysis of the data collected over the time period from 2003 to 2022 revealed a striking negative correlation between the number of actuaries in Georgia and the age of Miss America. The correlation coefficient was calculated to be -0.8557955, indicating a strong inverse relationship between these two variables. The r-squared value of 0.7323859 further solidifies the assertion that changes in the number of actuaries in Georgia can explain approximately 73% of the variation observed in Miss America's age. The p-value of less than 0.01 indicates that this relationship is statistically significant.
The robustness of this correlation was further validated through a visual representation in the form of a scatterplot (Fig. 1). The figure depicts the clear trend of Miss America's age decreasing as the number of actuaries in Georgia increases, and vice versa. It is a compelling visual testament to the unexpectedly synchronized nature of these seemingly unrelated variables.
These findings prompt a reflection on the implications of such a correlation. While causality cannot be established from this analysis alone, the tantalizing question of whether fluctuations in the field of actuarial science could influence the age of Miss America lingers in the air. It is indeed a thought that could make one "act-uarily" pensive.
The jocular tonality of the findings should not detract from their substantive significance. This research adds a new dimension to the understanding of interconnected phenomena and serves as a reminder that the world of statistics and beauty pageantry may not be as disconnected as one might assume. Further studies are warranted to delve into the mechanisms underlying this correlation and its potential implications for the worlds of actuarial science and beauty pageantry.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of this study provide compelling evidence of a remarkably strong negative correlation between the number of actuaries in Georgia and the age of Miss America, thereby lending support to the prior research that hinted at the existence of curious interconnections within seemingly unrelated phenomena. Our findings align with the whimsical explorations of Smith (2010) into the influence of demographic factors on beauty pageants, as evidenced by the synchronized fluctuations between the demographic presence of actuaries and the age of Miss America. The robustness of the negative correlation underscores the unexpected link that Jones (2018) alluded to, emphasizing the potential for statistical anomalies to reveal meaningful associations, even in domains as seemingly disparate as actuarial science and beauty pageantry.

The data not only validated the existence of this correlation, but also quantified its strength with a correlation coefficient of -0.8557955. The r-squared value of 0.7323859 further reinforced the substantial explanatory power of changes in the number of actuaries in Georgia in predicting variations in Miss America's age. Such statistical support resonates with the arguments made by Doe (2015), who encouraged the exploration of unconventional connections in the world of data analysis. This study exemplifies the unforeseen statistical congruence between actuarial figures and the age of Miss America, embodying the aesthetic harmony of numbers, as provocatively suggested by Doe.

The visual representation in the form of a scatterplot serves as a compelling visual testament to the unexpected synchronization between these variables, adding a layer of empirical tangibility to the otherwise whimsically intriguing correlation. This resonates with the playful narratives offered by A. Novel (2012) and E. Story (2016), which indirectly inform our understanding of the curious association between the two seemingly incongruent phenomena.

While the substantial negative correlation is noteworthy, causality remains elusive within the confines of this study. Nonetheless, the tantalizing question of whether fluctuations in the realm of actuarial science could indeed influence the age of Miss America emerges as a contemplative quandary, akin to an intricate actuarial problem waiting to be solved. Further investigation into the mechanisms underlying this correlation is warranted, in keeping with the multidimensional approach advocated by the literature review.

In conclusion, our findings encourage a re-evaluation of the presumed disconnect between domains such as actuarial science and beauty pageantry. The unexpected synchrony between the number of actuaries in Georgia and the age of Miss America challenges conventional beliefs and underscores the potential for serendipitous discoveries within the realms of statistical analysis and social phenomena. As we stand at the intersection of numbers and tiaras, the correlation uncovered in this study sparks not only further statistical inquiry, but also playful contemplation about the unanticipated harmony of seemingly unrelated domains.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of actuaries in Georgia and Miss America's age. 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]]
"The Actuary Equation: A Statistical Analysis of Actuary Numbers in Georgia and Miss America's Age"

[[ABSTRACT]]
This study examines the curious relationship between the number of actuaries in Georgia and the age of Miss America. Utilizing data from the Bureau of Labor Statistics and Wikipedia, we conducted a rigorous statistical analysis covering the years 2003 to 2022. Surprisingly, our findings reveal a remarkably strong negative correlation, with a correlation coefficient of -0.8557955 and p < 0.01. As the number of actuaries in Georgia fluctuates, Miss America's age follows suit in an almost synchronized manner, prompting questions about causality and teasing the boundaries of mere coincidence. This research sheds light on the whimsical interconnectedness of seemingly disparate phenomena and highlights the need for further investigation into the curious world of actuarial science and beauty pageantry.

[[INTRDUCTION]]
The intersection of actuarial science and beauty pageantry may seem as odd a pairing as peanut butter and pickles, but the relationship between the number of actuaries in Georgia and the age of Miss America has piqued the curiosity of researchers for years. As renowned economist John Kenneth Galbraith once said, "The only function of economic forecasting is to make astrology look respectable," and one might be forgiven for thinking that delving into the connection between these two seemingly unrelated variables falls squarely into the realm of astrological whimsy. However, our study takes a more empirical approach, aiming to uncover any substantive correlation that might exist between the dynamics of these two distinct domains.
The notion that the statistical happenings within the actuarial field could be entangled with the age of the embodiment of American beauty raises eyebrows and invites a chuckle at first glance. One can't help but wonder, is this the universe's way of demonstrating its own sense of humor, or is there a more profound undercurrent connecting the perceived rigidity of numbers with the fluidity of youth and beauty?
The world of actuarial science, renowned for its meticulous number-crunching and risk assessment, collides with the glitz and glamor of the Miss America pageant, an event steeped in tradition and spectacle, to offer an unexpected avenue for investigation. One might say this study aims to unravel the mystery and reveal if there's more to this interplay than meets the eye, or rather, the "I."
As we embark on this journey of statistical discovery, we invite the reader to keep an open mind and perhaps a wry smile at the thought that numbers and pageantry might dance to the same statistical tune. So, without further ado, let us delve into the enigmatic correlation, or causation, between the number of actuaries in Georgia and the age of Miss America.

[[RESULTS]]
The analysis of the data collected over the time period from 2003 to 2022 revealed a striking negative correlation between the number of actuaries in Georgia and the age of Miss America. The correlation coefficient was calculated to be -0.8557955, indicating a strong inverse relationship between these two variables. The r-squared value of 0.7323859 further solidifies the assertion that changes in the number of actuaries in Georgia can explain approximately 73% of the variation observed in Miss America's age. The p-value of less than 0.01 indicates that this relationship is statistically significant.
The robustness of this correlation was further validated through a visual representation in the form of a scatterplot (Fig. 1). The figure depicts the clear trend of Miss America's age decreasing as the number of actuaries in Georgia increases, and vice versa. It is a compelling visual testament to the unexpectedly synchronized nature of these seemingly unrelated variables.
These findings prompt a reflection on the implications of such a correlation. While causality cannot be established from this analysis alone, the tantalizing question of whether fluctuations in the field of actuarial science could influence the age of Miss America lingers in the air. It is indeed a thought that could make one "act-uarily" pensive.
The jocular tonality of the findings should not detract from their substantive significance. This research adds a new dimension to the understanding of interconnected phenomena and serves as a reminder that the world of statistics and beauty pageantry may not be as disconnected as one might assume. Further studies are warranted to delve into the mechanisms underlying this correlation and its potential implications for the worlds of actuarial science and beauty pageantry.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the results of this study corroborate the remarkably strong negative correlation between the number of actuaries in Georgia and the age of Miss America. As we wrap our minds around this curious statistical coupling, one cannot help but marvel at the whimsical tango of numbers and pageantry. The synchronicity between the ebb and flow of actuarial professionals and the youthful exuberance of Miss America raises more than a few eyebrows and elicits the occasional wry smile, serving as a poignant reminder that statistical analyses can often offer unexpected delights.

While the nuance of causality remains elusive, the implications of this correlation are both thought-provoking and smile-inducing. As the number of actuaries in Georgia fluctuates, Miss America's age pirouettes gracefully in response, prompting us to ponder the mystical connections between these distinct domains. It is as if the universe itself is engaging in a playful game of statistical charades, blurring the lines between mundanity and magnificence.

Nevertheless, in the spirit of academic rigor, it must be emphasized that the causal relationship between these variables remains unproven. Yet, one cannot resist a knowing smirk at the prospect of numbers quietly steering the pendulum of time for the belle of beauty pageantry.

In the grand theater of statistical analyses, this study serves as a tantalizing overture, inviting further exploration into the enigmatic interplay of actuarial science and beauty pageantry. Yet, in the spirit of prudent judgment, it is declared that the stage has been set, the actors have played their parts, and no further research is warranted in this particular domain. After all, one can only dissect a statistical jest so far before the humor escapes us.

In summary, the dance between the number of actuaries in Georgia and Miss America's age is an enigma that beckons us to revel in its whimsy, ponder the poetry of numerical serendipity, and, perhaps, indulge in a jest or two at the expense of statistical gravity.

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The Actuary Equation: A Statistical Analysis of Actuary Numbers in Georgia and Miss America's Age. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Mathematical Glamour

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Actuary Equation: A Statistical Analysis of Actuary Numbers in Georgia and Miss America's Age. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Numerical Eccentricities Analysis and Research (SNEAR)

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Actuary Equation: A Statistical Analysis of Actuary Numbers in Georgia and Miss America's Age with an abstract of This study examines the curious relationship between the number of actuaries in Georgia and the age of Miss America. Utilizing data from the Bureau of Labor Statistics and Wikipedia, we conducted a rigorous statistical analysis covering the years 2003 to 2022. Surprisingly, our findings reveal a remarkably strong negative correlation, with a correlation coefficient of -0.8557955 and p < 0.01. As the number of actuaries in Georgia fluctuates, Miss America's age follows suit in an almost synchronized manner, prompting questions about causality and teasing the boundaries of mere coincidence. This research sheds light on the whimsical interconnectedness of seemingly disparate phenomena and highlights the need for further investigation into the curious world of actuarial science and beauty pageantry.

ChatGPT:

"actuary statistics," "Georgia actuary numbers," "Miss America age analysis," "correlation between actuaries and Miss America age," "Bureau of Labor Statistics data," "statistical analysis of Georgia actuaries," "causality between actuaries and Miss America age," "actuarial science and beauty pageantry," "synchronized fluctuations of actuaries and Miss America age"

*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

The number of actuaries in Georgia
Detailed data title: BLS estimate of actuaries in Georgia
Source: Bureau of Larbor Statistics
See what else correlates with The number of actuaries in Georgia

Miss America's age
Source: Wikipedia
See what else correlates with Miss America's age

Correlation r = -0.8557955 (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 = 0.7323859 (Coefficient of determination)
This means 73.2% of the change in the one variable (i.e., Miss America's age) is predictable based on the change in the other (i.e., The number of actuaries in Georgia) over the 20 years from 2003 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.5E-6.^Show 0.0000014991768307066170000000
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 -0.86 in 0.00015% of random cases. Said differently, if you correlated 667,033 random variables^Note You don't actually need 667 thousand 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 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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, -0.67 ] 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.

	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
The number of actuaries in Georgia (Actuaries)	300	450	380	440	320	310	360	420	470	360	360	280	290	260	210	210	250	250	870	330
Miss America's age (Age in years)	22	21	24	22	20	19	22	22	17	23	24	24	23	21	21	23	25	24	0	20

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.
Inverted Y-axis: I inverted the Y-axis on the chart above so that the lines would move together. This is visually pleasing, but not at all intuitive. Below is a line graph that does not invert the Y-axis and starts at zero.

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([300,450,380,440,320,310,360,420,470,360,360,280,290,260,210,210,250,250,870,330,])
array_2 = np.array([22,21,24,22,20,19,22,22,17,23,24,24,23,21,21,23,25,24,0,20,])
array_1_name = "The number of actuaries in Georgia"
array_2_name = "Miss America's age"

# 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 The number of actuaries in Georgia
Line chart for only Miss America's age
AI-generated correlation image
The spurious research paper: The Actuary Equation: A Statistical Analysis of Actuary Numbers in Georgia and Miss America's Age

View another random correlation

How fun was this correlation?

Thanks for being the explorer we needed!

Correlation ID: 3442 · Black Variable ID: 6707 · Red Variable ID: 525


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