Spurious correlation #5,157 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Libertarian Senators in New Hampshire and the second variable is Customer satisfaction with The U.S. Postal Service. The chart goes from 1994 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 Votes for Libertarian Senators in New Hampshire and the second variable is Customer satisfaction with The U.S. Postal Service. The chart goes from 1994 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Libertarian votes for Senators in New Hampshire decrease, there's a corresponding decrease in individuals advocating for a free market postal system. With less pressure for competition and efficiency, the U.S. Postal Service becomes complacent, leading to a decline in customer satisfaction. After all, who knew that the path to postal perfection was paved with political preferences in the Live Free or Die state?

^{Show image generation prompt} Model: dalle-3
Prompt: Create a low poly visual of a U.S. Postal Service office in New Hampshire. In the foreground, show a group of disheartened individuals representing the advocates for a free market postal system, their vibrant energy fading. In the background, depict customers waiting in long lines with frustrated expressions, observing delayed deliveries and disengaged, tired postal workers. The scene should reflect the complacency and lack of efficiency within the postal service, capturing the impact of reduced pressure for competition and innovation. 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: Libertarian votes for Senators in New Hampshire and Customer satisfaction with The U.S. Postal Service. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Magic realism High-tech Futuristic Oragami Low poly
ChatGPT: Low poly

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 Libertarian votes for Senators in New Hampshire and Customer satisfaction with The U.S. Postal Service, in the following situation: As Libertarian votes for Senators in New Hampshire decrease, there's a corresponding decrease in individuals advocating for a free market postal system. With less pressure for competition and efficiency, the U.S. Postal Service becomes complacent, leading to a decline in customer satisfaction. After all, who knew that the path to postal perfection was paved with political preferences in the Live Free or Die state?. Keep the description simple.
ChatGPT: In New Hampshire, as Libertarian votes for Senators decrease, a group of people who were advocating for a free market postal system are seen losing their momentum. Meanwhile, at a nearby U.S. Postal Service office, customers are visibly dissatisfied as they wait in long lines, and see delayed deliveries. The workers appear unengaged and tired. The overall atmosphere reflects the growing complacency within the postal service due to reduced pressure for competition and efficiency.

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: [ Low poly ] and depicting this scene: In New Hampshire, as Libertarian votes for Senators decrease, a group of people who were advocating for a free market postal system are seen losing their momentum. Meanwhile, at a nearby U.S. Postal Service office, customers are visibly dissatisfied as they wait in long lines, and see delayed deliveries. The workers appear unengaged and tired. The overall atmosphere reflects the growing complacency within the postal service due to reduced pressure for competition and efficiency. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create a low poly visual of a U.S. Postal Service office in New Hampshire. In the foreground, show a group of disheartened individuals representing the advocates for a free market postal system, their vibrant energy fading. In the background, depict customers waiting in long lines with frustrated expressions, observing delayed deliveries and disengaged, tired postal workers. The scene should reflect the complacency and lack of efficiency within the postal service, capturing the impact of reduced pressure for competition and innovation.

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

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

AI academic paper

(Because p < 0.01)

Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction

The Journal of Postal Politics and Public Opinion

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 Libertarian votes for Senators in New Hampshire and Customer satisfaction with The U.S. Postal Service. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then 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]]
Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction

[[ABSTRACT]]
This study investigates the perplexing relationship between the votes for Libertarian candidates for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Customer Satisfaction Index, we conducted a thorough analysis spanning from 1994 to 2020. Our findings reveal a surprisingly robust correlation coefficient of 0.8947189 with a p-value less than 0.01, sparking intrigue and amusement in the scholarly community. The study raises the question: do citizens with a penchant for political independence also exhibit greater enjoyment in the delivery of their mail? This post-ulatory examination provides a peculiar yet intriguing insight into the forces at play in the intersection of civic engagement and daily correspondence satisfaction.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The U.S. Postal Service, a stalwart institution in the daily lives of Americans, has long been a subject of public scrutiny and occasional comic relief. Despite the advent of email, text messaging, and carrier pigeons (well, maybe not the last one), the Postal Service remains a crucial component of the nation’s communication infrastructure. As for the political scene in New Hampshire, the state is known for its “Live Free or Die” spirit and its occasional love affair with third-party candidates, including those affiliated with the Libertarian party. The intersection of these two seemingly disparate domains – postal satisfaction and libertarian voting patterns – has brought forth a curious and somewhat unexpected avenue of investigation.
In this post-allytical review, we delve into the intriguing question of whether there exists a substantive relationship between citizens' political leanings and their experiences with mail delivery. Can the act of casting a vote for a Libertarian senatorial candidate be seen as an indicator of a predisposition toward greater contentment with the postal services? Such an inquiry may initially appear as whimsical as choosing to send a letter via carrier pigeon in the digital age, but as we dig into the data, an unexpected pattern begins to emerge.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

We commence our exploration of the peculiar nexus of postal satisfaction and political affiliation by examining relevant literature. In "Politics and Mailboxes: A Survey of Libertarian Voters' Attitudes toward Postal Services," Jones et al. uncovered a noteworthy association between libertarian voting patterns and sentiments towards mail delivery. Their survey of Libertarian voters in New Hampshire revealed a statistically significant preference for the U.S. Postal Service in comparison to other delivery methods. Furthermore, Doe and Smith, in their seminal work "The Free Market and Postal Pleasure: An Exploratory Study," conducted in-depth interviews with self-identified Libertarians, noting a propensity for robust enthusiasm regarding the delivery of their packages and mail.
Expanding beyond the narrow confines of academic research, "Stamped from the Beginning: The Definitive History of Racist Ideas in America" by Ibram X. Kendi provides a historical perspective on the role of the Postal Service in shaping civic life, albeit lacking a direct focus on Libertarian voting. In a similar vein, "Neither Snow nor Rain: A History of the United States Postal Service" by Devin Leonard presents a comprehensive account of the challenges and triumphs of the nation’s mail delivery system, offering a backdrop against which to situate our investigation.
Turning to fiction literature, the novel "The Postman" by David Brin explores the concept of postal service in a post-apocalyptic world, shedding light on the significance of communication and correspondence in societal reconstruction. Additionally, "You've Got Mail: A Romantic Comedy Analysis" by Nora Ephron uniquely captures the charm and intrigue of interpersonal communication, albeit through electronic means rather than traditional mail.
Lastly, drawing from the wide spectrum of children's programming, the characters of SpongeBob SquarePants and Patrick Star in "SpongeBob SquarePants" exhibit various modes of mail delivery, offering a lighthearted yet thought-provoking portrayal of the postal system's multifaceted nature. Moreover, the Pony Express segment in "Wild West C.O.W.-Boys of Moo Mesa" presents an imaginative reimagining of mail delivery within a whimsical animated frontier setting, inviting contemplation on the intersection of historical postal practices and contemporary political proclivities.

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 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 Libertarian votes for Senators in New Hampshire and Customer satisfaction with The U.S. Postal Service. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and American Customer Satisfaction Index . You used data from 1994 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]]
Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction

[[ABSTRACT]]
This study investigates the perplexing relationship between the votes for Libertarian candidates for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Customer Satisfaction Index, we conducted a thorough analysis spanning from 1994 to 2020. Our findings reveal a surprisingly robust correlation coefficient of 0.8947189 with a p-value less than 0.01, sparking intrigue and amusement in the scholarly community. The study raises the question: do citizens with a penchant for political independence also exhibit greater enjoyment in the delivery of their mail? This post-ulatory examination provides a peculiar yet intriguing insight into the forces at play in the intersection of civic engagement and daily correspondence satisfaction.

[[INTRODUCTION]]
The U.S. Postal Service, a stalwart institution in the daily lives of Americans, has long been a subject of public scrutiny and occasional comic relief. Despite the advent of email, text messaging, and carrier pigeons (well, maybe not the last one), the Postal Service remains a crucial component of the nation’s communication infrastructure. As for the political scene in New Hampshire, the state is known for its “Live Free or Die” spirit and its occasional love affair with third-party candidates, including those affiliated with the Libertarian party. The intersection of these two seemingly disparate domains – postal satisfaction and libertarian voting patterns – has brought forth a curious and somewhat unexpected avenue of investigation.
In this post-allytical review, we delve into the intriguing question of whether there exists a substantive relationship between citizens' political leanings and their experiences with mail delivery. Can the act of casting a vote for a Libertarian senatorial candidate be seen as an indicator of a predisposition toward greater contentment with the postal services? Such an inquiry may initially appear as whimsical as choosing to send a letter via carrier pigeon in the digital age, but as we dig into the data, an unexpected pattern begins to emerge.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection:
The first step in our post-allytical examination involved collecting a plethora of data from reputable sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and the American Customer Satisfaction Index. Our diligent team scoured the internet, navigating through the virtual labyrinth of information, much like a postal carrier navigating through a maze of doorbells and mail slots. We meticulously gathered information on the votes cast for Libertarian candidates for Senators in New Hampshire, as well as the customer satisfaction scores related to the U.S. Postal Service, spanning the years 1994 to 2020.

Data Cleaning:
Following the arduous task of data collection, our team engaged in a meticulous process of data cleaning. This involved removing any duplicate records, addressing missing data points, and ensuring the accuracy and consistency of the datasets. We scrubbed the data with the fervor of a dedicated postman cleaning off the stamps before affixing them to envelopes, ensuring that our analysis would not be compromised by any impurities or inaccuracies.

Variable Selection and Measurement:
To elucidate the relationship between Libertarian votes for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service, we carefully selected relevant variables. The number of votes garnered by Libertarian candidates for Senators in New Hampshire served as our indicator of political preference, reflecting the state's propensity for non-traditional political leanings. Meanwhile, the customer satisfaction scores from the American Customer Satisfaction Index provided a quantitative measure of individuals' contentment with the delivery of their mail, like measuring the weight of a shipment to ensure it meets postal regulations.

Statistical Analysis:
With the datasets prepared, we embarked on a series of statistical analyses to assess the magnitude and significance of the relationship between libertarian voting patterns and postal satisfaction. Utilizing robust regression models and hypothesis testing, we sought to unveil any discernible patterns amidst the sea of data. Our approach was as precise as a postal sorting machine, meticulously categorizing parcels into their designated slots.

Control Variables:
In addition to examining the direct relationship between Libertarian votes and postal satisfaction, we incorporated control variables such as population density, urbanization, and economic indicators to ensure that any observed relationship was not confounded by external factors. These control variables served as the proverbial stamps of verification, ensuring that our findings would withstand scrutiny and not be return-to-sender.

Ethical Considerations:
Throughout the course of this investigation, ethical principles governing data usage and privacy were upheld with the utmost diligence. We handled the data with the care and confidentiality befitting of entrusted mail, safeguarding the anonymity and integrity of the individuals whose experiences and voting preferences formed the basis of our 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 Libertarian votes for Senators in New Hampshire and Customer satisfaction with The U.S. Postal Service. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction

[[ABSTRACT]]
This study investigates the perplexing relationship between the votes for Libertarian candidates for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Customer Satisfaction Index, we conducted a thorough analysis spanning from 1994 to 2020. Our findings reveal a surprisingly robust correlation coefficient of 0.8947189 with a p-value less than 0.01, sparking intrigue and amusement in the scholarly community. The study raises the question: do citizens with a penchant for political independence also exhibit greater enjoyment in the delivery of their mail? This post-ulatory examination provides a peculiar yet intriguing insight into the forces at play in the intersection of civic engagement and daily correspondence satisfaction.

[[LITERATURE REVIEW]]
We commence our exploration of the peculiar nexus of postal satisfaction and political affiliation by examining relevant literature. In "Politics and Mailboxes: A Survey of Libertarian Voters' Attitudes toward Postal Services," Jones et al. uncovered a noteworthy association between libertarian voting patterns and sentiments towards mail delivery. Their survey of Libertarian voters in New Hampshire revealed a statistically significant preference for the U.S. Postal Service in comparison to other delivery methods. Furthermore, Doe and Smith, in their seminal work "The Free Market and Postal Pleasure: An Exploratory Study," conducted in-depth interviews with self-identified Libertarians, noting a propensity for robust enthusiasm regarding the delivery of their packages and mail.
Expanding beyond the narrow confines of academic research, "Stamped from the Beginning: The Definitive History of Racist Ideas in America" by Ibram X. Kendi provides a historical perspective on the role of the Postal Service in shaping civic life, albeit lacking a direct focus on Libertarian voting. In a similar vein, "Neither Snow nor Rain: A History of the United States Postal Service" by Devin Leonard presents a comprehensive account of the challenges and triumphs of the nation’s mail delivery system, offering a backdrop against which to situate our investigation.
Turning to fiction literature, the novel "The Postman" by David Brin explores the concept of postal service in a post-apocalyptic world, shedding light on the significance of communication and correspondence in societal reconstruction. Additionally, "You've Got Mail: A Romantic Comedy Analysis" by Nora Ephron uniquely captures the charm and intrigue of interpersonal communication, albeit through electronic means rather than traditional mail.
Lastly, drawing from the wide spectrum of children's programming, the characters of SpongeBob SquarePants and Patrick Star in "SpongeBob SquarePants" exhibit various modes of mail delivery, offering a lighthearted yet thought-provoking portrayal of the postal system's multifaceted nature. Moreover, the Pony Express segment in "Wild West C.O.W.-Boys of Moo Mesa" presents an imaginative reimagining of mail delivery within a whimsical animated frontier setting, inviting contemplation on the intersection of historical postal practices and contemporary political proclivities.

[[RESULTS]]
Upon conducting the analysis, a strong positive correlation between the percent of votes for Libertarian candidates for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service was revealed. The correlation coefficient of 0.8947189 and the r-squared value of 0.8005220 indicate a remarkably robust relationship between these two seemingly unrelated factors. The p-value of less than 0.01 further underscores the statistical significance of this connection, prompting both scholarly intrigue and a sense of bemusement.
Fig. 1 presents a visual depiction of this surprising correlation. The scatterplot illustrates a clear and upward-sloping trend, providing compelling evidence of the association between increased Libertarian support and heightened satisfaction with mail delivery. As the saying goes, a picture is worth a thousand words, and in this case, it certainly holds true.
It's worth noting that this relationship may initially appear as puzzling as deciphering handwritten addresses on letters, especially considering the often colorful and divergent political landscape in the Live Free or Die state. Nevertheless, the data persistently support the postulated connection, challenging preconceived notions and stirring ripples of curiosity within the research community.
The magnitude of the observed correlation raises thought-provoking questions about the underlying factors at play. Could it be that individuals with a propensity for political autonomy also harbor a heightened sense of appreciation for the art of snail mail? The unexpected coherence between these variables calls for further exploration and invites a whimsical yet meaningful discourse on the intersection of civic engagement and mundane mail-related merriment.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]
The substantial correlation between the percentage of votes for Libertarian candidates for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service defies conventional expectations and invokes a sense of wonderment. These findings resonate with prior research, transcending the realm of curiosity and integrating with the established body of literature.

Jones et al.'s investigation of Libertarian voters' attitudes toward postal services in New Hampshire aligns closely with our findings, illuminating a synergistic relationship between political inclination and postal predilection. The statistically significant preference for the U.S. Postal Service among Libertarian voters neatly corresponds with the robust association elucidated in our study, corroborating the notion that political proclivities may intertwine with mail-related contentment.

Doe and Smith's work, delving into the enthusiastic sentiments of self-identified Libertarians regarding postal services, echoes the unexpected coherence unearthed in our analysis. The proclivity for robust enthusiasm towards mail delivery among Libertarians harmonizes with the pronounced positive correlation revealed in our study, further underscoring the intertwining of political autonomy and postal pleasure.

Although perhaps initially startling, the observed connection appears consistent with the peculiarity of human behavior, akin to the confounding state of trying to locate the post office during an unfamiliar stroll through a labyrinthine neighborhood. The inexplicable magnetism between Libertarian voting patterns and postal satisfaction challenges conventional understanding, prompting an intellectual dance of discombobulation and delight.

This study's results support the post-ulatory musings of prior literature, offering a compelling narrative on the perceptible alignment between civic engagement and the appreciation of postal services. The interplay between political autonomy and postal satisfaction beckons an exploration of the whimsical and the profound, nudging the scholarly community to delve deeper into the multifaceted nature of human preferences and their intricate entanglements.

The unexpected coherence between the seemingly disparate domains of political inclination and mail-related merriment engenders a fresh wave of scholarly pondering and infuses the discourse with a spirited pulse of inquisitiveness. These findings open the door to a realm of untrodden curiosity and invite a chuckling contemplation of the whimsies hidden within the fabric of human behavior.

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 Libertarian votes for Senators in New Hampshire and Customer satisfaction with The U.S. Postal Service. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction

[[ABSTRACT]]
This study investigates the perplexing relationship between the votes for Libertarian candidates for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Customer Satisfaction Index, we conducted a thorough analysis spanning from 1994 to 2020. Our findings reveal a surprisingly robust correlation coefficient of 0.8947189 with a p-value less than 0.01, sparking intrigue and amusement in the scholarly community. The study raises the question: do citizens with a penchant for political independence also exhibit greater enjoyment in the delivery of their mail? This post-ulatory examination provides a peculiar yet intriguing insight into the forces at play in the intersection of civic engagement and daily correspondence satisfaction.

[[INTRDUCTION]]
The U.S. Postal Service, a stalwart institution in the daily lives of Americans, has long been a subject of public scrutiny and occasional comic relief. Despite the advent of email, text messaging, and carrier pigeons (well, maybe not the last one), the Postal Service remains a crucial component of the nation’s communication infrastructure. As for the political scene in New Hampshire, the state is known for its “Live Free or Die” spirit and its occasional love affair with third-party candidates, including those affiliated with the Libertarian party. The intersection of these two seemingly disparate domains – postal satisfaction and libertarian voting patterns – has brought forth a curious and somewhat unexpected avenue of investigation.
In this post-allytical review, we delve into the intriguing question of whether there exists a substantive relationship between citizens' political leanings and their experiences with mail delivery. Can the act of casting a vote for a Libertarian senatorial candidate be seen as an indicator of a predisposition toward greater contentment with the postal services? Such an inquiry may initially appear as whimsical as choosing to send a letter via carrier pigeon in the digital age, but as we dig into the data, an unexpected pattern begins to emerge.

[[RESULTS]]
Upon conducting the analysis, a strong positive correlation between the percent of votes for Libertarian candidates for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service was revealed. The correlation coefficient of 0.8947189 and the r-squared value of 0.8005220 indicate a remarkably robust relationship between these two seemingly unrelated factors. The p-value of less than 0.01 further underscores the statistical significance of this connection, prompting both scholarly intrigue and a sense of bemusement.
Fig. 1 presents a visual depiction of this surprising correlation. The scatterplot illustrates a clear and upward-sloping trend, providing compelling evidence of the association between increased Libertarian support and heightened satisfaction with mail delivery. As the saying goes, a picture is worth a thousand words, and in this case, it certainly holds true.
It's worth noting that this relationship may initially appear as puzzling as deciphering handwritten addresses on letters, especially considering the often colorful and divergent political landscape in the Live Free or Die state. Nevertheless, the data persistently support the postulated connection, challenging preconceived notions and stirring ripples of curiosity within the research community.
The magnitude of the observed correlation raises thought-provoking questions about the underlying factors at play. Could it be that individuals with a propensity for political autonomy also harbor a heightened sense of appreciation for the art of snail mail? The unexpected coherence between these variables calls for further exploration and invites a whimsical yet meaningful discourse on the intersection of civic engagement and mundane mail-related merriment.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the results of this post-ulatory examination have provided an unexpectedly robust and statistically significant link between Libertarian votes for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service. The connection, reminiscent of the improbable friendship between a cat and a dog, challenges conventional assumptions and tickles the intellectual fancy. While the nature of this association may prompt as much head-scratching as deciphering smudged postmarks, the correlation persists with a resolute defiance, much like a misplaced package in the postal system. This peculiar yet intriguing insight into the intertwining realms of political inclination and letter-laden elation sheds light on the whimsical interplay of human behaviors in seemingly unrelated domains.

This study engenders an array of tantalizing questions, akin to unwrapping a mystery package: What underlying mechanisms drive this curious relationship? Does political independence breed a fondness for the tangible act of mailing correspondence, or is there an element of rebellion against modernity at play? The unforeseen coherence between political sentiment and postal satisfaction piques the curiosity of scholars and enthusiasts alike, much like an enigmatic riddle waiting to be unraveled.

However, it must be noted that correlation does not imply causation, just as owning a mailbox doesn't automatically bestow a penchant for sending postcards. As such, the extrapolation of these findings should be approached with caution, akin to handling fragile porcelain in transit.

Nevertheless, in a world often colored in shades of serious discourse, this quirky correlation provides a welcome splash of whimsy and an invitation to toy with unorthodox connections. With that said, it is the opinion of this post-ulatory review that no further research in this area is warranted. It's about time for this peculiar postal tale to be stamped and delivered, much like a letter destined for an awaiting mailbox.

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 Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Postal Politics and Public Opinion

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 Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Postal Policy and Libertarian 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 Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction with an abstract of This study investigates the perplexing relationship between the votes for Libertarian candidates for Senators in New Hampshire and customer satisfaction with the U.S. Postal Service. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and the American Customer Satisfaction Index, we conducted a thorough analysis spanning from 1994 to 2020. Our findings reveal a surprisingly robust correlation coefficient of 0.8947189 with a p-value less than 0.01, sparking intrigue and amusement in the scholarly community. The study raises the question: do citizens with a penchant for political independence also exhibit greater enjoyment in the delivery of their mail? This post-ulatory examination provides a peculiar yet intriguing insight into the forces at play in the intersection of civic engagement and daily correspondence satisfaction.

ChatGPT:

Libertarian candidates, Senator votes, New Hampshire, customer satisfaction, Postal Service, MIT Election Data and Science Lab, Harvard Dataverse, American Customer Satisfaction Index, correlation coefficient, political independence, civic engagement, daily correspondence satisfaction, analysis, postal delivery, US Postal Service, scholarly community, New Hampshire elections

*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

Votes for Libertarian Senators in New Hampshire
Detailed data title: Total number of votes cast for Federal Libertarian Senate candidates in New Hampshire
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for Libertarian Senators in New Hampshire

Customer satisfaction with The U.S. Postal Service
Source: American Customer Satisfaction Index
See what else correlates with Customer satisfaction with The U.S. Postal Service

Correlation r = 0.8947189 (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 = 0.8005220 (Coefficient of determination)
This means 80.1% of the change in the one variable (i.e., Customer satisfaction with The U.S. Postal Service) is predictable based on the change in the other (i.e., Votes for Libertarian Senators in New Hampshire) over the 7 years from 1994 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0065.^Show 0.0065220577314388050000000000
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 0.89 in 0.65% of random cases. Said differently, if you correlated 153 random variables^Note Which I absolutely did.
with the same 6 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 6 because we have two variables measured over a period of 7 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.

[ 0.43, 0.98 ] 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.

	1996	1998	2002	2008	2010	2016	2020
Votes for Libertarian Senators in New Hampshire (Total votes)	22261	7603	9835	21516	4753	12597	18421
Customer satisfaction with The U.S. Postal Service (Consumer Satisfaction)	74	71	73	74	71	73	73

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.
Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting 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([22261,7603,9835,21516,4753,12597,18421,])
array_2 = np.array([74,71,73,74,71,73,73,])
array_1_name = "Votes for Libertarian Senators in New Hampshire"
array_2_name = "Customer satisfaction with The U.S. Postal Service"

# 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 Votes for Libertarian Senators in New Hampshire
Line chart for only Customer satisfaction with The U.S. Postal Service
AI-generated correlation image
The spurious research paper: Delivering the Vote: A Post-allytical Review of Libertarian Influence on Postal Satisfaction

View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!

Correlation ID: 5157 · Black Variable ID: 26279 · Red Variable ID: 19861


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