Spurious correlation #4,847 · 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 Alice and the second variable is Votes for the Libertarian Presidential candidate in New York. The chart goes from 1984 to 2020, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the first name Alice and the second variable is Votes for the Libertarian Presidential candidate in New York. The chart goes from 1984 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the name Alice gained more popularity, people couldn't help but wonder, "Who is leading a wonderland-esque political campaign?" This curiosity led them to discover the Libertarian candidate, creating a ripple effect of support. It seems like the idea of casting their political beliefs down the rabbit hole really resonated with the newly-Alice-named supporters. Who would have thought that a shift in popularity could lead to such electoral madness?

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a bustling New York City street with a towering billboard prominently displaying the name "Alice" in bold, elegant letters. The crowd below exudes an air of excitement as they chat eagerly amongst themselves. Amidst the bustling scene, a group of enthusiastic supporters wearing top hats and holding signs with the Libertarian party symbol are seen spreading the word about their candidate. The atmosphere is filled with an unexpected sense of electoral excitement as the popularity of the name "Alice" coincides with a surge in support for the Libertarian candidate, who exudes a whimsical and wonder-filled presence. Capture the unexpected sense of wonder and excitement this scene brings to the political landscape. 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 Alice and Votes for the Libertarian Presidential candidate in New York. 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: A TIME magazine cover image Art nouveau Parallax art Realistic Cyberpunk
ChatGPT: A TIME magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Popularity of the first name Alice and Votes for the Libertarian Presidential candidate in New York, in the following situation: As the name Alice gained more popularity, people couldn't help but wonder, "Who is leading a wonderland-esque political campaign?" This curiosity led them to discover the Libertarian candidate, creating a ripple effect of support. It seems like the idea of casting their political beliefs down the rabbit hole really resonated with the newly-Alice-named supporters. Who would have thought that a shift in popularity could lead to such electoral madness?. Keep the description simple.
ChatGPT: In a bustling New York City street, a large billboard proudly displays the name "Alice" in bold, elegant letters, surrounded by a sea of people chatting excitedly. Meanwhile, a group of enthusiastic supporters wearing top hats and holding signs with the Libertarian party symbol are seen spreading the word about their presidential candidate, who has an unmistakable sense of whimsy and wonder about them. The scene is filled with an unexpected sense of electoral excitement as the popularity of the name Alice coincides with a surge in support for the Libertarian candidate, bringing a splash of unexpectedness to the political landscape.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A TIME magazine cover image ] and depicting this scene: In a bustling New York City street, a large billboard proudly displays the name "Alice" in bold, elegant letters, surrounded by a sea of people chatting excitedly. Meanwhile, a group of enthusiastic supporters wearing top hats and holding signs with the Libertarian party symbol are seen spreading the word about their presidential candidate, who has an unmistakable sense of whimsy and wonder about them. The scene is filled with an unexpected sense of electoral excitement as the popularity of the name Alice coincides with a surge in support for the Libertarian candidate, bringing a splash of unexpectedness to the political landscape. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a bustling New York City street with a towering billboard prominently displaying the name "Alice" in bold, elegant letters. The crowd below exudes an air of excitement as they chat eagerly amongst themselves. Amidst the bustling scene, a group of enthusiastic supporters wearing top hats and holding signs with the Libertarian party symbol are seen spreading the word about their candidate. The atmosphere is filled with an unexpected sense of electoral excitement as the popularity of the name "Alice" coincides with a surge in support for the Libertarian candidate, who exudes a whimsical and wonder-filled presence. Capture the unexpected sense of wonder and excitement this scene brings to the political landscape.

*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 an increase in Popularity of the first name Alice caused Votes for the Libertarian Presidential candidate in New York to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York

The Journal of Irreverent Political Psychology

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Popularity of the first name Alice and Votes for the Libertarian Presidential candidate in New York. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
"Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York"

[[ABSTRACT]]
In this paper, we delve into the amiable antics of the charmingly popular first name "Alice" and its purported link to the voting behavior for the Libertarian Presidential candidate in the state of New York. Our research team, through the sophisticated scrutiny of data from the US Social Security Administration and the MIT Election Data and Science Lab, Harvard Dataverse, delves into this curious correlation, seeking to unravel the enigmatic entanglement between nomenclature and political preference.

Upon meticulous analysis, we unearthed a striking correlation coefficient of 0.9802309 and p < 0.01 for the years spanning from 1984 to 2020, suggesting a remarkably robust relationship between the prevalence of the name "Alice" and the penchant for casting ballots in favor of the Libertarian candidate. It seems that, much like Alice in Wonderland, the allure of libertarian ideals has woven its way into the hearts of those bearing this delightful first name.

As we navigate through the labyrinth of statistical inference and electoral behavior, we cannot help but wonder: is the preference for liberty, akin to Alice's pursuit down the rabbit hole, an inherent trait of those bearing this mellifluous moniker? This peculiar correlation may indeed be a whimsical wonderland of an observation.

In conclusion, our findings shed light on the peculiar populace of "Alices" and their profound proclivity for political alternatives. As we unravel this unexpected association, we must remain vigilant to additional factors that may elucidate this connection further. After all, the name "Alice" seems to have a knack for leading us down intriguing paths, not unlike our findings in this research.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As Lewis Carroll famously wrote, "Why, sometimes I've believed as many as six impossible things before breakfast." In the whimsical world of statistical analysis, we often find ourselves pondering the improbable and the unexpected. The connection between a first name and political preferences may just be one of those delightful impossibilities that warrants further exploration.
The association between names and behavior has long intrigued researchers, dating back to the groundbreaking work of Galton in the 19th century. But few could have predicted the prospect of delving into the voting proclivities of individuals named Alice, and their potential penchant for political liberty. It's almost as if we're chasing after the White Rabbit of electoral enigmas.
Now, before we tumble headlong into our analysis, let us pause for a moment to appreciate the sheer pun-tastic potential of this research. I mean, who wouldn't want to explore the "libert-Alice" tendencies of a demographic subset of the New York voting populace? It's certainly a welcome departure from the usual academic fare, and we fully intend to seize this opportunity to inject some Alice-themed levity into our rigorous examination of electoral trends. After all, a little merriment can go a long way in making academic research more "wonderful."
Our research endeavor aims to not only uncover the empirical connection between the ubiquity of the name "Alice" and support for the Libertarian candidate but also to inject a bit of joy and amusement into a field that can sometimes seem rather dour. So, with eyes wide like saucers and hearts brimming with academic curiosity, let us venture forth into the captivating world of electoral nomenclature and political predilections. After all, as the Cheshire Cat might say, "We're all mad here" – mad about unconventional correlations, that is.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

To contextualize our investigation, it is crucial to first explore the existing literature on the influence of nomenclature on political behavior. The seminal work of Smith (2005) highlighted the psychological impact of names on individual decision-making processes, laying the groundwork for subsequent inquiries into this area. Doe's (2010) study further delved into the sociocultural aspects of name associations, underscoring the potential for names to subconsciously influence attitudes and beliefs.

Now, as we embark on our own exploration of the curious correlation between the prevalence of the name "Alice" and support for the Libertarian Presidential candidate in New York, it's worth taking a detour into some unexpected literary references. After all, who would have thought we could draw parallels between our research and books like "Alice's Adventures in Wonderland" by Lewis Carroll? We can't help but wonder if the White Rabbit was a closet Libertarian!

Furthermore, the fictional works of Philip K. Dick in "Do Androids Dream of Electric Sheep?" and Margaret Atwood's "The Handmaid's Tale" prompt us to consider the dystopian implications of a world where a specific name might indeed shape political attitudes. Perhaps we should be on the lookout for an "Alices Are Always Libertarian" dystopian novel.

On a more contemporary note, social media threads have yielded intriguing musings on the correlation we seek to unveil. One Twitter user succinctly pondered, "If you vote Libertarian, are you falling down the 'Alice' hole of political ideology?" Sometimes, the denizens of social media surprise us with their poignant insights, even if they are limited to 280 characters.

But I digress. The crux of the matter is this: our interdisciplinary approach to this study not only draws from conventional academic sources but also embraces the whimsical and imaginative threads of popular literature and online discourse. Who says academia can't have a sense of humor? After all, any scholarly pursuit that involves the name "Alice" is bound to lead us through a maze of curiosities and surprises. It's like an academic rabbit hole of research – with the promise of dad jokes at every twist and turn.

Speaking of dad jokes, why did the libertarian take a ladder to the election? Because he wanted to get on the ballot! And just like that, we're seamlessly blending data analysis with good ol' pun-tastic humor. It's a wonderland of research indeed.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Popularity of the first name Alice and Votes for the Libertarian Presidential candidate in New York. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Your research team collected data from all across the internet, but mostly just used information from US Social Security Administration and MIT Election Data and Science Lab, Harvard Dataverse . You used data from 1984 to 2020

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]]
"Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York"

[[ABSTRACT]]
In this paper, we delve into the amiable antics of the charmingly popular first name "Alice" and its purported link to the voting behavior for the Libertarian Presidential candidate in the state of New York. Our research team, through the sophisticated scrutiny of data from the US Social Security Administration and the MIT Election Data and Science Lab, Harvard Dataverse, delves into this curious correlation, seeking to unravel the enigmatic entanglement between nomenclature and political preference.

Upon meticulous analysis, we unearthed a striking correlation coefficient of 0.9802309 and p < 0.01 for the years spanning from 1984 to 2020, suggesting a remarkably robust relationship between the prevalence of the name "Alice" and the penchant for casting ballots in favor of the Libertarian candidate. It seems that, much like Alice in Wonderland, the allure of libertarian ideals has woven its way into the hearts of those bearing this delightful first name.

As we navigate through the labyrinth of statistical inference and electoral behavior, we cannot help but wonder: is the preference for liberty, akin to Alice's pursuit down the rabbit hole, an inherent trait of those bearing this mellifluous moniker? This peculiar correlation may indeed be a whimsical wonderland of an observation.

In conclusion, our findings shed light on the peculiar populace of "Alices" and their profound proclivity for political alternatives. As we unravel this unexpected association, we must remain vigilant to additional factors that may elucidate this connection further. After all, the name "Alice" seems to have a knack for leading us down intriguing paths, not unlike our findings in this research.

[[INTRODUCTION]]
As Lewis Carroll famously wrote, "Why, sometimes I've believed as many as six impossible things before breakfast." In the whimsical world of statistical analysis, we often find ourselves pondering the improbable and the unexpected. The connection between a first name and political preferences may just be one of those delightful impossibilities that warrants further exploration.
The association between names and behavior has long intrigued researchers, dating back to the groundbreaking work of Galton in the 19th century. But few could have predicted the prospect of delving into the voting proclivities of individuals named Alice, and their potential penchant for political liberty. It's almost as if we're chasing after the White Rabbit of electoral enigmas.
Now, before we tumble headlong into our analysis, let us pause for a moment to appreciate the sheer pun-tastic potential of this research. I mean, who wouldn't want to explore the "libert-Alice" tendencies of a demographic subset of the New York voting populace? It's certainly a welcome departure from the usual academic fare, and we fully intend to seize this opportunity to inject some Alice-themed levity into our rigorous examination of electoral trends. After all, a little merriment can go a long way in making academic research more "wonderful."
Our research endeavor aims to not only uncover the empirical connection between the ubiquity of the name "Alice" and support for the Libertarian candidate but also to inject a bit of joy and amusement into a field that can sometimes seem rather dour. So, with eyes wide like saucers and hearts brimming with academic curiosity, let us venture forth into the captivating world of electoral nomenclature and political predilections. After all, as the Cheshire Cat might say, "We're all mad here" – mad about unconventional correlations, that is.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To unravel the perplexing relationship between the popularity of the name "Alice" and the voting behavior for the Libertarian Presidential candidate in New York, our research team employed an eclectic mix of data collection and statistical analysis methods. First, we hopped down the rabbit hole of the US Social Security Administration's database to gather information on the frequency of the name "Alice" from 1984 to 2020. We then tumbled into the MIT Election Data and Science Lab's archives to procure election data, and emerged unscathed, albeit slightly disoriented, with a trove of voting records.

In our dogged pursuit of this curious connection, we mashed up traditional statistical techniques with a touch of whimsy. We utilized correlation analysis to measure the strength and direction of the relationship between the frequency of the name "Alice" and the number of votes for the Libertarian candidate in New York. Our determination to uncover this enigmatic association rivaled Alice's quest to find her way through Wonderland.

We also employed time series analysis to ascertain the temporal patterns in the prevalence of the name "Alice" and the fluctuations in support for the Libertarian candidate. Our commitment to unearthing this peculiar correlation was as steadfast as the Red Queen's insistence on "off with their heads."

Furthermore, we engaged in a bit of linguistic analysis to explore the phonetic and semantic potential of the name "Alice" and its subtle influence on libertarian leanings. After all, delving into the complexities of language is no small feat, much like Alice's attempts to navigate the nonsensical dialogues of the Jabberwocky.

We then performed a series of regression models to control for potential confounding variables such as age, gender, and socioeconomic factors, much like Alice attempting to control her destiny in a world of capricious characters. This multivariate approach allowed us to disentangle the effects of the name "Alice" from other factors that could influence voting behavior, all while maintaining a steadfast grin, much like the Cheshire Cat.

Lastly, we conducted a sub-analysis of responses to a survey administered exclusively to individuals named "Alice" to capture their unique perspectives on political ideologies and personal experiences. We giggled at the thought of conducting surveys with our Alice cohort, almost as if we were hosting a tea party with the Mad Hatter himself.

In summary, our methodology wove together a tapestry of data exploration, statistical acrobatics, and a sprinkle of whimsy to elucidate the endearing allure of the name "Alice" and its curious connection to libertarian voting tendencies in New York. Just like the White Rabbit's pocket watch, our methods were complex yet charming, and we hope they lead readers down a delightfully unexpected academic path.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Popularity of the first name Alice and Votes for the Libertarian Presidential candidate in New York. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
"Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York"

[[ABSTRACT]]
In this paper, we delve into the amiable antics of the charmingly popular first name "Alice" and its purported link to the voting behavior for the Libertarian Presidential candidate in the state of New York. Our research team, through the sophisticated scrutiny of data from the US Social Security Administration and the MIT Election Data and Science Lab, Harvard Dataverse, delves into this curious correlation, seeking to unravel the enigmatic entanglement between nomenclature and political preference.

Upon meticulous analysis, we unearthed a striking correlation coefficient of 0.9802309 and p < 0.01 for the years spanning from 1984 to 2020, suggesting a remarkably robust relationship between the prevalence of the name "Alice" and the penchant for casting ballots in favor of the Libertarian candidate. It seems that, much like Alice in Wonderland, the allure of libertarian ideals has woven its way into the hearts of those bearing this delightful first name.

As we navigate through the labyrinth of statistical inference and electoral behavior, we cannot help but wonder: is the preference for liberty, akin to Alice's pursuit down the rabbit hole, an inherent trait of those bearing this mellifluous moniker? This peculiar correlation may indeed be a whimsical wonderland of an observation.

In conclusion, our findings shed light on the peculiar populace of "Alices" and their profound proclivity for political alternatives. As we unravel this unexpected association, we must remain vigilant to additional factors that may elucidate this connection further. After all, the name "Alice" seems to have a knack for leading us down intriguing paths, not unlike our findings in this research.

[[LITERATURE REVIEW]]
To contextualize our investigation, it is crucial to first explore the existing literature on the influence of nomenclature on political behavior. The seminal work of Smith (2005) highlighted the psychological impact of names on individual decision-making processes, laying the groundwork for subsequent inquiries into this area. Doe's (2010) study further delved into the sociocultural aspects of name associations, underscoring the potential for names to subconsciously influence attitudes and beliefs.
Now, as we embark on our own exploration of the curious correlation between the prevalence of the name "Alice" and support for the Libertarian Presidential candidate in New York, it's worth taking a detour into some unexpected literary references. After all, who would have thought we could draw parallels between our research and books like "Alice's Adventures in Wonderland" by Lewis Carroll? We can't help but wonder if the White Rabbit was a closet Libertarian!
Furthermore, the fictional works of Philip K. Dick in "Do Androids Dream of Electric Sheep?" and Margaret Atwood's "The Handmaid's Tale" prompt us to consider the dystopian implications of a world where a specific name might indeed shape political attitudes. Perhaps we should be on the lookout for an "Alices Are Always Libertarian" dystopian novel.
On a more contemporary note, social media threads have yielded intriguing musings on the correlation we seek to unveil. One Twitter user succinctly pondered, "If you vote Libertarian, are you falling down the 'Alice' hole of political ideology?" Sometimes, the denizens of social media surprise us with their poignant insights, even if they are limited to 280 characters.
But I digress. The crux of the matter is this: our interdisciplinary approach to this study not only draws from conventional academic sources but also embraces the whimsical and imaginative threads of popular literature and online discourse. Who says academia can't have a sense of humor? After all, any scholarly pursuit that involves the name "Alice" is bound to lead us through a maze of curiosities and surprises. It's like an academic rabbit hole of research – with the promise of dad jokes at every twist and turn.
Speaking of dad jokes, why did the libertarian take a ladder to the election? Because he wanted to get on the ballot! And just like that, we're seamlessly blending data analysis with good ol' pun-tastic humor. It's a wonderland of research indeed.

[[RESULTS]]
Our analysis of the connection between the popularity of the first name "Alice" and votes for the Libertarian Presidential candidate in New York has revealed a remarkably strong correlation. From 1984 to 2020, we found a correlation coefficient of 0.9802309, indicating a near-perfect positive relationship between the two variables. This correlation was further substantiated by an r-squared value of 0.9608526, suggesting that a whopping 96.08% of the variation in Libertarian votes can be explained by the prevalence of the name "Alice." It's almost as if every "Alice" is in wonderland when it comes to libertarianism!
The p-value of less than 0.01 provides compelling evidence to reject the null hypothesis that there is no relationship between the popularity of the name "Alice" and voting behavior for the Libertarian candidate. In other words, it's highly unlikely that this connection is just a mad hatter's coincidence.
Furthermore, the significance of the correlation demonstrates that the likelihood of observing such a strong relationship by mere chance is exceedingly rare. It's like finding a needle in a data haystack – a rare and surprisingly sharp needle at that!
The scatterplot (Fig. 1) visually represents the findings of our analysis, displaying a clear and tight clustering of data points that align with the near-perfect correlation coefficient. It's as if each data point is dutifully following the White Rabbit of statistical significance, leading us down the rabbit hole of astonishing correlations.
In summary, our research has illuminated a compelling link between the prevalence of the name "Alice" and support for the Libertarian Presidential candidate in New York. This unexpected association, much like the plot twists in Carroll's classic tale, adds an element of curiosity and whimsy to the otherwise predictable landscape of electoral behavior.
Now, if only we could get the name "Alice" on the ballot, we might just see an electoral wonderland unfold!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our investigation into the relationship between the popularity of the first name "Alice" and votes for the Libertarian Presidential candidate in New York has unraveled a tale that even Lewis Carroll would envy. The remarkably strong correlation we have unearthed, with a correlation coefficient of 0.9802309 and p < 0.01, supports and extends prior research in this area. It seems that just like Alice herself, the connection between this endearing name and the allure of libertarian ideals is a captivating enigma that defies simple explanation.

Taking a step back, our findings align with Smith's (2005) pioneering work on the psychological impact of names, as well as Doe's (2010) sociocultural exploration of name associations. It appears that the influence of nomenclature on individual decision-making processes isn't just a whimsical notion; it holds substantial empirical weight. It's like the Cheshire Cat of social science theories – you never know when it's going to pop up and surprise you with its significance!

Moreover, the unexpected parallels we drew with literature, such as "Alice's Adventures in Wonderland" and the musings in Philip K. Dick's and Margaret Atwood's works, have turned out to be surprisingly pertinent. It's as if our academic pursuit has taken us through a surreal academic rabbit hole, where every twist and turn takes us deeper into the wonderland of research. Speaking of which, why did the statistics major go to the party? Because they heard that parties always have great "mean" times!

By delving into the robust correlation between the name "Alice" and support for the Libertarian candidate, we have shed light on the potentially influential nature of nomenclature in shaping political preferences. Our findings not only provide fodder for further interdisciplinary exploration but also underscore the need to consider unconventional factors in understanding electoral behavior. It's like a political puzzle, and the "Alice" piece seems to fit perfectly in the Libertarian section.

In pondering the potential implications of our research, one can't help but wonder if this connection goes beyond mere coincidence. Perhaps there are underlying psychological, sociocultural, or even subliminal factors at play. It's a bit like chasing the White Rabbit of name associations – you never know what you might find at the end of the statistical rabbit hole.

As we navigate these intriguing findings, we must remain cautious not to fall down a statistical rabbit hole of our own. It's essential to consider alternative explanations and further avenues of investigation, always with a lighthearted spirit of curiosity. After all, much like Alice herself, our research into this unexpected correlation has been a journey marked by curiosity, whimsy, and maybe just a touch of madness.

Now, if only we could figure out how to get the name "Alice" on the electoral ballot – we might just witness a wonderland of electoral choices unfold right before our very eyes!

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Popularity of the first name Alice and Votes for the Libertarian Presidential candidate in New York. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
"Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York"

[[ABSTRACT]]
In this paper, we delve into the amiable antics of the charmingly popular first name "Alice" and its purported link to the voting behavior for the Libertarian Presidential candidate in the state of New York. Our research team, through the sophisticated scrutiny of data from the US Social Security Administration and the MIT Election Data and Science Lab, Harvard Dataverse, delves into this curious correlation, seeking to unravel the enigmatic entanglement between nomenclature and political preference.

Upon meticulous analysis, we unearthed a striking correlation coefficient of 0.9802309 and p < 0.01 for the years spanning from 1984 to 2020, suggesting a remarkably robust relationship between the prevalence of the name "Alice" and the penchant for casting ballots in favor of the Libertarian candidate. It seems that, much like Alice in Wonderland, the allure of libertarian ideals has woven its way into the hearts of those bearing this delightful first name.

As we navigate through the labyrinth of statistical inference and electoral behavior, we cannot help but wonder: is the preference for liberty, akin to Alice's pursuit down the rabbit hole, an inherent trait of those bearing this mellifluous moniker? This peculiar correlation may indeed be a whimsical wonderland of an observation.

In conclusion, our findings shed light on the peculiar populace of "Alices" and their profound proclivity for political alternatives. As we unravel this unexpected association, we must remain vigilant to additional factors that may elucidate this connection further. After all, the name "Alice" seems to have a knack for leading us down intriguing paths, not unlike our findings in this research.

[[INTRDUCTION]]
As Lewis Carroll famously wrote, "Why, sometimes I've believed as many as six impossible things before breakfast." In the whimsical world of statistical analysis, we often find ourselves pondering the improbable and the unexpected. The connection between a first name and political preferences may just be one of those delightful impossibilities that warrants further exploration.
The association between names and behavior has long intrigued researchers, dating back to the groundbreaking work of Galton in the 19th century. But few could have predicted the prospect of delving into the voting proclivities of individuals named Alice, and their potential penchant for political liberty. It's almost as if we're chasing after the White Rabbit of electoral enigmas.
Now, before we tumble headlong into our analysis, let us pause for a moment to appreciate the sheer pun-tastic potential of this research. I mean, who wouldn't want to explore the "libert-Alice" tendencies of a demographic subset of the New York voting populace? It's certainly a welcome departure from the usual academic fare, and we fully intend to seize this opportunity to inject some Alice-themed levity into our rigorous examination of electoral trends. After all, a little merriment can go a long way in making academic research more "wonderful."
Our research endeavor aims to not only uncover the empirical connection between the ubiquity of the name "Alice" and support for the Libertarian candidate but also to inject a bit of joy and amusement into a field that can sometimes seem rather dour. So, with eyes wide like saucers and hearts brimming with academic curiosity, let us venture forth into the captivating world of electoral nomenclature and political predilections. After all, as the Cheshire Cat might say, "We're all mad here" – mad about unconventional correlations, that is.

[[RESULTS]]
Our analysis of the connection between the popularity of the first name "Alice" and votes for the Libertarian Presidential candidate in New York has revealed a remarkably strong correlation. From 1984 to 2020, we found a correlation coefficient of 0.9802309, indicating a near-perfect positive relationship between the two variables. This correlation was further substantiated by an r-squared value of 0.9608526, suggesting that a whopping 96.08% of the variation in Libertarian votes can be explained by the prevalence of the name "Alice." It's almost as if every "Alice" is in wonderland when it comes to libertarianism!
The p-value of less than 0.01 provides compelling evidence to reject the null hypothesis that there is no relationship between the popularity of the name "Alice" and voting behavior for the Libertarian candidate. In other words, it's highly unlikely that this connection is just a mad hatter's coincidence.
Furthermore, the significance of the correlation demonstrates that the likelihood of observing such a strong relationship by mere chance is exceedingly rare. It's like finding a needle in a data haystack – a rare and surprisingly sharp needle at that!
The scatterplot (Fig. 1) visually represents the findings of our analysis, displaying a clear and tight clustering of data points that align with the near-perfect correlation coefficient. It's as if each data point is dutifully following the White Rabbit of statistical significance, leading us down the rabbit hole of astonishing correlations.
In summary, our research has illuminated a compelling link between the prevalence of the name "Alice" and support for the Libertarian Presidential candidate in New York. This unexpected association, much like the plot twists in Carroll's classic tale, adds an element of curiosity and whimsy to the otherwise predictable landscape of electoral behavior.
Now, if only we could get the name "Alice" on the ballot, we might just see an electoral wonderland unfold!

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has uncovered a truly curious connection between the delightful moniker "Alice" and a penchant for political libertarianism in New York. It appears that those named Alice are indeed inclined to venture down the proverbial rabbit hole of electoral choices and emerge with a preference for alternative political ideals. It's as if they have a tendency to "alter-name-tive" voting patterns! Okay, okay, one more dad joke for good measure.

The robust correlation coefficient of 0.9802309 and a minuscule p-value of less than 0.01 indicate that this association is no mere "wonderland of coincidences," but rather a substantial and statistically significant finding. It's almost as if these "Alices" are leading a political "mad tea party" of their own!

As we reflect on our findings, one cannot help but appreciate the charm and whimsy that "Alices" bring to the world of electoral behavior. Their predilection for libertarian choices seems to be as consistent as the Cheshire Cat's enigmatic grin.

It's evident that this correlation is no fleeting fantasy but a remarkable observation that invites further exploration. With these compelling results, it's clear that we've stumbled onto something quite remarkable, not unlike Alice stumbling into the curious world beyond the looking glass.

In light of these findings, we assert that further investigation into the impact of nomenclature on political preferences is not required. Our unique journey into the "wonder-land" of Alices and Libertarians has proven to be a delightful and thought-provoking endeavor, providing valuable insight while also adding a touch of whimsical wonder to the often staid field of electoral research. After all, we've already found the "mad hatter" of correlations!

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 Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Irreverent Political Psychology

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 Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Nonsensical Studies

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 Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York with an abstract of In this paper, we delve into the amiable antics of the charmingly popular first name "Alice" and its purported link to the voting behavior for the Libertarian Presidential candidate in the state of New York. Our research team, through the sophisticated scrutiny of data from the US Social Security Administration and the MIT Election Data and Science Lab, Harvard Dataverse, delves into this curious correlation, seeking to unravel the enigmatic entanglement between nomenclature and political preference.
Upon meticulous analysis, we unearthed a striking correlation coefficient of 0.9802309 and p < 0.01 for the years spanning from 1984 to 2020, suggesting a remarkably robust relationship between the prevalence of the name "Alice" and the penchant for casting ballots in favor of the Libertarian candidate. It seems that, much like Alice in Wonderland, the allure of libertarian ideals has woven its way into the hearts of those bearing this delightful first name.
As we navigate through the labyrinth of statistical inference and electoral behavior, we cannot help but wonder: is the preference for liberty, akin to Alice's pursuit down the rabbit hole, an inherent trait of those bearing this mellifluous moniker? This peculiar correlation may indeed be a whimsical wonderland of an observation.
In conclusion, our findings shed light on the peculiar populace of "Alices" and their profound proclivity for political alternatives. As we unravel this unexpected association, we must remain vigilant to additional factors that may elucidate this connection further. After all, the name "Alice" seems to have a knack for leading us down intriguing paths, not unlike our findings in this research.

ChatGPT:

Alice, libertarian, voting behavior, correlation, US Social Security Administration, MIT Election Data and Science Lab, Harvard Dataverse, political preference, statistical analysis, nomenclature, presidential candidate, New York, libertarian ideals, electoral behavior, correlation coefficient, Alice in Wonderland, liberty, political alternatives, first name, association, data analysis

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

Votes for the Libertarian Presidential candidate in New York
Detailed data title: Percentage of all votes cast for the Libertarian Presidential candidate in New York
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Libertarian Presidential candidate in New York

Correlation r = 0.9802309 (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 = 0.9608526 (Coefficient of determination)
This means 96.1% of the change in the one variable (i.e., Votes for the Libertarian Presidential candidate in New York) is predictable based on the change in the other (i.e., Popularity of the first name Alice) over the 10 years from 1984 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.5E-7.^Show 0.0000006525100812901347000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.98 in 6.5E-5% of random cases. Said differently, if you correlated 1,532,543 random variables^Note You don't actually need 1 million 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 9 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 9 because we have two variables measured over a period of 10 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.

[ 0.92, 1 ] 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.

	1984	1988	1992	1996	2000	2004	2008	2012	2016	2020
Popularity of the first name Alice (Babies born)	686	825	688	593	669	756	1025	2508	3690	3284
Votes for the Libertarian Presidential candidate in New York (Percentage of votes)	0.175545	0.186704	0.190001	0.189777	0.109896	0.155835	0.253768	0.661703	0.736239	0.695403

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([686,825,688,593,669,756,1025,2508,3690,3284,])
array_2 = np.array([0.175545,0.186704,0.190001,0.189777,0.109896,0.155835,0.253768,0.661703,0.736239,0.695403,])
array_1_name = "Popularity of the first name Alice"
array_2_name = "Votes for the Libertarian Presidential candidate in New York"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Popularity of the first name Alice
Line chart for only Votes for the Libertarian Presidential candidate in New York
AI-generated correlation image
The spurious research paper: Alices Adore Alternatives: Analyzing the Association Between Alice's Antics and Libertarian Loyalties in New York

View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!

Correlation ID: 4847 · Black Variable ID: 2792 · Red Variable ID: 26143


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