about · email me · subscribe
Spurious correlation #5,276 · 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 Democratic Senators in Florida and the second variable is The number of septic tank servicers and sewer pipe cleaners in Florida.  The chart goes from 2003 to 2018, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The higher the Democrat votes, the more they were willing to get their hands dirty, leading to a surge in demand for septic tank servicers and sewer pipe cleaners! Looks like the political landscape wasn't the only thing getting a deep clean!

Model: dalle-3
Prompt: Generate a low poly image of a bustling Florida neighborhood with a voting station where people are lining up to cast their votes for Democratic senators. Among them, a team of hardworking septic tank servicers and sewer pipe cleaners are seen rolling up their sleeves to respond to the increased demand. The streets are filled with lively activity as political engagement and practical labor intersect, creating a vibrant and dynamic scene. 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: Votes for Democratic Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida. 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: inspired by bauhaus A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s An image that looks like it is a scene from A Disney Movie Voxel art 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 Votes for Democratic Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida, in the following situation: The higher the Democrat votes, the more they were willing to get their hands dirty, leading to a surge in demand for septic tank servicers and sewer pipe cleaners! Looks like the political landscape wasn't the only thing getting a deep clean!. Keep the description simple.
ChatGPT: In a bustling Florida neighborhood, people line up outside a voting station, visible support for the Democratic senators. Alongside them, a team of hardworking septic tank servicers and sewer pipe cleaners eagerly roll up their sleeves and get to work, responding to the increased demand. The streets are alive with activity as political engagement and practical labor intersect, creating a vibrant and dynamic scene.

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 a bustling Florida neighborhood, people line up outside a voting station, visible support for the Democratic senators. Alongside them, a team of hardworking septic tank servicers and sewer pipe cleaners eagerly roll up their sleeves and get to work, responding to the increased demand. The streets are alive with activity as political engagement and practical labor intersect, creating a vibrant and dynamic scene. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a low poly image of a bustling Florida neighborhood with a voting station where people are lining up to cast their votes for Democratic senators. Among them, a team of hardworking septic tank servicers and sewer pipe cleaners are seen rolling up their sleeves to respond to the increased demand. The streets are filled with lively activity as political engagement and practical labor intersect, creating a vibrant and dynamic scene.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Democrat votes for Senators in Florida positively influenced The number of septic tank servicers and sewer pipe cleaners in Florida. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Democrat Votes in Florida: Do They Relate to the State's Septic State?

Journal of Political Hygiene

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Bureau of Larbor Statistics to assess this nagging question. You found a correlation coefficient of 0.9253580 and p < 0.01 for 2003 to 2018.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Democrat Votes in Florida: Do They Relate to the State's Septic State?

[[ABSTRACT]]
In this study, we delved deep into the sewers of Florida to uncover the correlation between the voting behavior of Democrats in the state and the number of septic tank servicers and sewer pipe cleaners. While at first glance one might think these two factors are as unrelated as a gator and a flamingo, our research team found a surprising connection. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, we uncovered a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. Our findings suggest that there may indeed be a fecal matter... I mean, a fruitful relationship between these seemingly disparate variables. This paper not only sheds light on the dynamics of Florida politics and plumbing, but also provokes contemplation on the intricate ways in which the political landscape and sewage infrastructure intertwine. So, as we flush out the details of this study, may it serve as a reminder that in the world of research, even the most unexpected connections can surface if you just keep digging.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Democrat Votes in Florida: Do They Relate to the State's Septic State?

[[ABSTRACT]]
In this study, we delved deep into the sewers of Florida to uncover the correlation between the voting behavior of Democrats in the state and the number of septic tank servicers and sewer pipe cleaners. While at first glance one might think these two factors are as unrelated as a gator and a flamingo, our research team found a surprising connection. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, we uncovered a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. Our findings suggest that there may indeed be a fecal matter... I mean, a fruitful relationship between these seemingly disparate variables. This paper not only sheds light on the dynamics of Florida politics and plumbing, but also provokes contemplation on the intricate ways in which the political landscape and sewage infrastructure intertwine. So, as we flush out the details of this study, may it serve as a reminder that in the world of research, even the most unexpected connections can surface if you just keep digging.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Politics and plumbing - two seemingly unrelated aspects of society that, as it turns out, may not be as separate as one might think. In this study, we embarked on a journey through the labyrinthine world of Florida's electoral politics and sewage infrastructure to ascertain whether the voting patterns of Democrats in the state could be linked to the number of septic tank servicers and sewer pipe cleaners. While one might initially envision a political landscape filled with partisan divides and a sewage system brimming with, well, sewage, our research sought to uncover any underlying connections between these peculiar bedfellows.

As any Floridian can attest, the state's political climate has often been characterized by its unique blend of sunshine and, shall we say, more murky elements. Meanwhile, the plumbing needs of a state known for its wetlands, swamps, and gator-laden waters have always been a critical aspect of its infrastructure. Yet, the question remained: is there a deeper, unexplored interconnection between these seemingly incongruent spheres?

The overarching goal of this study was to peel back the layers of Floridian politicking and piping to reveal any potential correlation between Democrat votes for Senators in Florida and the prevalence of septic tank servicers and sewer pipe cleaners across the state. As these seemingly unrelated elements converged under the microscope of our analysis, we aimed to uncover insights that could shed light on the intricate dynamics of the state's sociopolitical landscape and its sewage infrastructure.

By traversing the statistically fertile grounds of MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team endeavored to unveil any discernible patterns or connections between the electoral choices of Democrats and the availability of services related to the less glamorous aspects of sanitation. Our findings, which we will expound upon in detail, revealed a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. This discovery, while unexpected, prompts a reevaluation of the intricate ways in which political preferences and the less visible aspects of infrastructure intersect.

In the pages that follow, we invite readers to join us on this unconventional exploration as we unearth the unsuspected parallels between Florida's political allegiances and its wastewater management landscape. While the path we tread may at first glance seem unconventional, our findings provide a compelling case that even in the unlikeliest of terrains, the connections that emerge are both thought-provoking and, dare we say, delightful. So, let us embark on this odyssey of research – for in the realm of scholarly inquiry, as in life, one must always be prepared to navigate unexpected twists and turns, whether they emerge from the ballot box or the bowels of civilization.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Democrat Votes in Florida: Do They Relate to the State's Septic State?

[[ABSTRACT]]
In this study, we delved deep into the sewers of Florida to uncover the correlation between the voting behavior of Democrats in the state and the number of septic tank servicers and sewer pipe cleaners. While at first glance one might think these two factors are as unrelated as a gator and a flamingo, our research team found a surprising connection. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, we uncovered a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. Our findings suggest that there may indeed be a fecal matter... I mean, a fruitful relationship between these seemingly disparate variables. This paper not only sheds light on the dynamics of Florida politics and plumbing, but also provokes contemplation on the intricate ways in which the political landscape and sewage infrastructure intertwine. So, as we flush out the details of this study, may it serve as a reminder that in the world of research, even the most unexpected connections can surface if you just keep digging.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Politics and plumbing - two seemingly unrelated aspects of society that, as it turns out, may not be as separate as one might think. In this study, we embarked on a journey through the labyrinthine world of Florida's electoral politics and sewage infrastructure to ascertain whether the voting patterns of Democrats in the state could be linked to the number of septic tank servicers and sewer pipe cleaners. While one might initially envision a political landscape filled with partisan divides and a sewage system brimming with, well, sewage, our research sought to uncover any underlying connections between these peculiar bedfellows.
As any Floridian can attest, the state's political climate has often been characterized by its unique blend of sunshine and, shall we say, more murky elements. Meanwhile, the plumbing needs of a state known for its wetlands, swamps, and gator-laden waters have always been a critical aspect of its infrastructure. Yet, the question remained: is there a deeper, unexplored interconnection between these seemingly incongruent spheres?
The overarching goal of this study was to peel back the layers of Floridian politicking and piping to reveal any potential correlation between Democrat votes for Senators in Florida and the prevalence of septic tank servicers and sewer pipe cleaners across the state. As these seemingly unrelated elements converged under the microscope of our analysis, we aimed to uncover insights that could shed light on the intricate dynamics of the state's sociopolitical landscape and its sewage infrastructure.
By traversing the statistically fertile grounds of MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team endeavored to unveil any discernible patterns or connections between the electoral choices of Democrats and the availability of services related to the less glamorous aspects of sanitation. Our findings, which we will expound upon in detail, revealed a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. This discovery, while unexpected, prompts a reevaluation of the intricate ways in which political preferences and the less visible aspects of infrastructure intersect.
In the pages that follow, we invite readers to join us on this unconventional exploration as we unearth the unsuspected parallels between Florida's political allegiances and its wastewater management landscape. While the path we tread may at first glance seem unconventional, our findings provide a compelling case that even in the unlikeliest of terrains, the connections that emerge are both thought-provoking and, dare we say, delightful. So, let us embark on this odyssey of research – for in the realm of scholarly inquiry, as in life, one must always be prepared to navigate unexpected twists and turns, whether they emerge from the ballot box or the bowels of civilization.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The investigation into the correlation, if any, between Democrat votes for Senators in Florida and the number of septic tank servicers and sewer pipe cleaners has yielded a diverse array of scholarly perspectives. Smith and Doe (2015) shed light on the intricate socio-political landscapes of Florida, but much like searching for a needle in a septic tank, finding direct references to this unlikely connection proved to be a challenge.

The works of Jones (2018) and Lee (2017) explore the plumbing infrastructure of various states in fascinating detail, but alas, they flush over the specific relationship between political inclinations and the demand for septic services in Florida. As we delved deeper into the literature, it became increasingly apparent that the intersection of sewage and politics was, much like a clogged drain, a topic often avoided.

Despite this initial scarcity of directly relevant scholarly work, the research team turned to non-fiction books that, while not explicitly exploring the intricate dance of Florida politics and plumbing, provided valuable insights into the cultural and environmental backdrop of the state. In "The Swamp: The Everglades, Florida, and the Politics of Paradise" by Grunwald (2007), we gained a deeper understanding of Florida's unique ecosystem and the pivotal role of water management. While not a scholarly work per se, Grisham's legal thriller "The Pelican Brief" (1992) wove a narrative set in Florida, capturing the state's political intrigue amidst the backdrop of environmental challenges, perhaps offering allegorical insights into the subject matter at hand.

Moreover, our team found that fiction works, such as "Flush" by Hiaasen (2005) and "Sewer, Gas, & Electric: The Public Works Trilogy" by Matt (1994), surprisingly touched upon themes of environmental activism and infrastructure-related adventures, albeit in a satirical and comical manner.

In an effort to gain a broader perspective on the subject, the research team also revisited pertinent movies, including "The Waterboy" (1998), "The Florida Project" (2017), and "Ace Ventura: Pet Detective" (1994), which provided entertaining yet tangential insights into the Floridian milieu and its, albeit indirectly, interconnected spheres of politics and plumbing.

With a twinkle in our eyes and a plunger in hand, the journey into the depths of academic literature, books, and movies has not only expanded our understanding of Florida's rich tapestry but has also validated our belief that uncovering unexpected connections often involves navigating through unexpected detours.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Bureau of Larbor Statistics . You used data from 2003 to 2018

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]]
Democrat Votes in Florida: Do They Relate to the State's Septic State?

[[ABSTRACT]]
In this study, we delved deep into the sewers of Florida to uncover the correlation between the voting behavior of Democrats in the state and the number of septic tank servicers and sewer pipe cleaners. While at first glance one might think these two factors are as unrelated as a gator and a flamingo, our research team found a surprising connection. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, we uncovered a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. Our findings suggest that there may indeed be a fecal matter... I mean, a fruitful relationship between these seemingly disparate variables. This paper not only sheds light on the dynamics of Florida politics and plumbing, but also provokes contemplation on the intricate ways in which the political landscape and sewage infrastructure intertwine. So, as we flush out the details of this study, may it serve as a reminder that in the world of research, even the most unexpected connections can surface if you just keep digging.

[[INTRODUCTION]]
Politics and plumbing - two seemingly unrelated aspects of society that, as it turns out, may not be as separate as one might think. In this study, we embarked on a journey through the labyrinthine world of Florida's electoral politics and sewage infrastructure to ascertain whether the voting patterns of Democrats in the state could be linked to the number of septic tank servicers and sewer pipe cleaners. While one might initially envision a political landscape filled with partisan divides and a sewage system brimming with, well, sewage, our research sought to uncover any underlying connections between these peculiar bedfellows.
As any Floridian can attest, the state's political climate has often been characterized by its unique blend of sunshine and, shall we say, more murky elements. Meanwhile, the plumbing needs of a state known for its wetlands, swamps, and gator-laden waters have always been a critical aspect of its infrastructure. Yet, the question remained: is there a deeper, unexplored interconnection between these seemingly incongruent spheres?
The overarching goal of this study was to peel back the layers of Floridian politicking and piping to reveal any potential correlation between Democrat votes for Senators in Florida and the prevalence of septic tank servicers and sewer pipe cleaners across the state. As these seemingly unrelated elements converged under the microscope of our analysis, we aimed to uncover insights that could shed light on the intricate dynamics of the state's sociopolitical landscape and its sewage infrastructure.
By traversing the statistically fertile grounds of MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team endeavored to unveil any discernible patterns or connections between the electoral choices of Democrats and the availability of services related to the less glamorous aspects of sanitation. Our findings, which we will expound upon in detail, revealed a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. This discovery, while unexpected, prompts a reevaluation of the intricate ways in which political preferences and the less visible aspects of infrastructure intersect.
In the pages that follow, we invite readers to join us on this unconventional exploration as we unearth the unsuspected parallels between Florida's political allegiances and its wastewater management landscape. While the path we tread may at first glance seem unconventional, our findings provide a compelling case that even in the unlikeliest of terrains, the connections that emerge are both thought-provoking and, dare we say, delightful. So, let us embark on this odyssey of research – for in the realm of scholarly inquiry, as in life, one must always be prepared to navigate unexpected twists and turns, whether they emerge from the ballot box or the bowels of civilization.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unearth the elusive connection between Democrat votes for Senators in the Sunshine State and the number of septic tank servicers and sewer pipe cleaners, our research team employed a multifaceted approach that involved equal parts political analysis and plumbing prowess.

Data Collection:
Our first challenge in this turbid odyssey of research was to gather comprehensive and reliable data. We scoured the depths of the internet, navigating through the murky waters of MIT Election Data and Science Lab, the labyrinthine corridors of Harvard Dataverse, and the subterranean archives of the Bureau of Labor Statistics. We emerged victorious, clutching a trove of information spanning the years 2003 to 2018, providing us with a panoramic view of Florida’s political and plumbing landscape. We wrestled with spreadsheets, tickled the keys of calculators, and forged through statistical thickets to distill our findings.

Democrat Votes for Senators:
We meticulously analyzed the voting patterns of Florida Democrats in the elections for Senators, scrutinizing the ebb and flow of their ballots over the years. Armed with bar graphs, pie charts, and a healthy dose of political intrigue, we sought to uncover any underlying trends or correlations that could shed light on the link between political preferences and the less visible aspects of sanitation services.

Septic Tank Servicers and Sewer Pipe Cleaners:
Venturing into the realm of sanitation, we delved into the abundance (or lack thereof) of septic tank servicers and sewer pipe cleaners across the state. Channeling our inner Sherlock Holmes, we surveyed the landscape of pipes, tanks, and unmentionable substances to discern any discernible patterns in the distribution of these vital services.

Statistical Analysis:
With our data in hand and a twinkle of statistical stardust in our eyes, we applied correlation analyses and regression models to disentangle the web of relationships between Democrat votes and the number of septic tank servicers and sewer pipe cleaners. Our journey through the tangled underbrush of statistical analysis led us to uncover a correlation coefficient of 0.9253580 with a p-value of less than 0.01, illuminating the unexpected connection between these seemingly incongruous variables.

By interlacing our statistical savvy with our unflagging pursuit of knowledge, we endeavored to unravel the mysterious interplay between politics and plumbing in the labyrinthine landscape of Florida. While our methods may provoke a chuckle or raise an eyebrow, our findings stand as a testament to the unending adventure of scholarly inquiry, where even the most unlikely paths can lead to fascinating discoveries. So, as we bid adieu to the murky depths of methodology, we invite our readers to join us in uncovering the provocative and, at times, humorous nexus between the ballot box and the bowels of civilization.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Bureau of Larbor Statistics .

For the time period 2003 to 2018, you found a correlation 0.9253580, r-squared of 0.8562875, and p < 0.01.

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

Here is the title and abstract of the paper:
[[TITLE]]
Democrat Votes in Florida: Do They Relate to the State's Septic State?

[[ABSTRACT]]
In this study, we delved deep into the sewers of Florida to uncover the correlation between the voting behavior of Democrats in the state and the number of septic tank servicers and sewer pipe cleaners. While at first glance one might think these two factors are as unrelated as a gator and a flamingo, our research team found a surprising connection. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, we uncovered a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. Our findings suggest that there may indeed be a fecal matter... I mean, a fruitful relationship between these seemingly disparate variables. This paper not only sheds light on the dynamics of Florida politics and plumbing, but also provokes contemplation on the intricate ways in which the political landscape and sewage infrastructure intertwine. So, as we flush out the details of this study, may it serve as a reminder that in the world of research, even the most unexpected connections can surface if you just keep digging.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Politics and plumbing - two seemingly unrelated aspects of society that, as it turns out, may not be as separate as one might think. In this study, we embarked on a journey through the labyrinthine world of Florida's electoral politics and sewage infrastructure to ascertain whether the voting patterns of Democrats in the state could be linked to the number of septic tank servicers and sewer pipe cleaners. While one might initially envision a political landscape filled with partisan divides and a sewage system brimming with, well, sewage, our research sought to uncover any underlying connections between these peculiar bedfellows.
As any Floridian can attest, the state's political climate has often been characterized by its unique blend of sunshine and, shall we say, more murky elements. Meanwhile, the plumbing needs of a state known for its wetlands, swamps, and gator-laden waters have always been a critical aspect of its infrastructure. Yet, the question remained: is there a deeper, unexplored interconnection between these seemingly incongruent spheres?
The overarching goal of this study was to peel back the layers of Floridian politicking and piping to reveal any potential correlation between Democrat votes for Senators in Florida and the prevalence of septic tank servicers and sewer pipe cleaners across the state. As these seemingly unrelated elements converged under the microscope of our analysis, we aimed to uncover insights that could shed light on the intricate dynamics of the state's sociopolitical landscape and its sewage infrastructure.
By traversing the statistically fertile grounds of MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team endeavored to unveil any discernible patterns or connections between the electoral choices of Democrats and the availability of services related to the less glamorous aspects of sanitation. Our findings, which we will expound upon in detail, revealed a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. This discovery, while unexpected, prompts a reevaluation of the intricate ways in which political preferences and the less visible aspects of infrastructure intersect.
In the pages that follow, we invite readers to join us on this unconventional exploration as we unearth the unsuspected parallels between Florida's political allegiances and its wastewater management landscape. While the path we tread may at first glance seem unconventional, our findings provide a compelling case that even in the unlikeliest of terrains, the connections that emerge are both thought-provoking and, dare we say, delightful. So, let us embark on this odyssey of research – for in the realm of scholarly inquiry, as in life, one must always be prepared to navigate unexpected twists and turns, whether they emerge from the ballot box or the bowels of civilization.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

**[[RESULTS]]**

The results of our investigation into the relationship between Democrat votes for Senators in Florida and the number of septic tank servicers and sewer pipe cleaners yield an intriguing revelation. After analyzing data from the period spanning 2003 to 2018, a robust correlation coefficient of 0.9253580 and an r-squared value of 0.8562875 were uncovered, accompanied by a p-value of less than 0.01. These statistical metrics not only attest to the strength of the observed relationship but also underscore the highly significant nature of the results.

Now, let's dive into the nitty-gritty and address the elephant in the room - or should we say, the alligator? Fig. 1 showcases a scatterplot that visually captures the striking correlation between these seemingly incongruent variables, providing compelling evidence to support our findings. This graph, which illustrates the pronounced association between Democrat votes and the prevalence of septic tank servicers and sewer pipe cleaners, serves as a testament to the unexpected ways in which disparate elements can manifest a cohesive narrative.

While some might quip that it's just the state's unique combination of "blue" and "brown" factors at play, our results lead to a broader reflection on the intricate interweaving of political inclinations and infrastructure necessities. Indeed, our discovery prompts contemplation on the ways in which the sociopolitical landscape and the less visible aspects of public services may bear a closer relationship than previously acknowledged. Cue the "flush of realization" moment - there might just be more to Florida's political ecosystem than meets the eye.

The implications of this study extend beyond the immediate surprise factor and delve into uncharted territory, shining a light on the quirky quirks of life that emerge amidst the rigidity of data and analysis. As we wrap up this section, we invite readers to ponder the unexpected alliances that emerge when we venture beyond the surface - whether it be in the realm of politics or plumbing. After all, in the grand scheme of research, it's these unforeseen connections that often lead to the most "piping hot" revelations.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Democrat Votes in Florida: Do They Relate to the State's Septic State?

[[ABSTRACT]]
In this study, we delved deep into the sewers of Florida to uncover the correlation between the voting behavior of Democrats in the state and the number of septic tank servicers and sewer pipe cleaners. While at first glance one might think these two factors are as unrelated as a gator and a flamingo, our research team found a surprising connection. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, we uncovered a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. Our findings suggest that there may indeed be a fecal matter... I mean, a fruitful relationship between these seemingly disparate variables. This paper not only sheds light on the dynamics of Florida politics and plumbing, but also provokes contemplation on the intricate ways in which the political landscape and sewage infrastructure intertwine. So, as we flush out the details of this study, may it serve as a reminder that in the world of research, even the most unexpected connections can surface if you just keep digging.

[[LITERATURE REVIEW]]
The investigation into the correlation, if any, between Democrat votes for Senators in Florida and the number of septic tank servicers and sewer pipe cleaners has yielded a diverse array of scholarly perspectives. Smith and Doe (2015) shed light on the intricate socio-political landscapes of Florida, but much like searching for a needle in a septic tank, finding direct references to this unlikely connection proved to be a challenge.
The works of Jones (2018) and Lee (2017) explore the plumbing infrastructure of various states in fascinating detail, but alas, they flush over the specific relationship between political inclinations and the demand for septic services in Florida. As we delved deeper into the literature, it became increasingly apparent that the intersection of sewage and politics was, much like a clogged drain, a topic often avoided.
Despite this initial scarcity of directly relevant scholarly work, the research team turned to non-fiction books that, while not explicitly exploring the intricate dance of Florida politics and plumbing, provided valuable insights into the cultural and environmental backdrop of the state. In "The Swamp: The Everglades, Florida, and the Politics of Paradise" by Grunwald (2007), we gained a deeper understanding of Florida's unique ecosystem and the pivotal role of water management. While not a scholarly work per se, Grisham's legal thriller "The Pelican Brief" (1992) wove a narrative set in Florida, capturing the state's political intrigue amidst the backdrop of environmental challenges, perhaps offering allegorical insights into the subject matter at hand.
Moreover, our team found that fiction works, such as "Flush" by Hiaasen (2005) and "Sewer, Gas, & Electric: The Public Works Trilogy" by Matt (1994), surprisingly touched upon themes of environmental activism and infrastructure-related adventures, albeit in a satirical and comical manner.
In an effort to gain a broader perspective on the subject, the research team also revisited pertinent movies, including "The Waterboy" (1998), "The Florida Project" (2017), and "Ace Ventura: Pet Detective" (1994), which provided entertaining yet tangential insights into the Floridian milieu and its, albeit indirectly, interconnected spheres of politics and plumbing.
With a twinkle in our eyes and a plunger in hand, the journey into the depths of academic literature, books, and movies has not only expanded our understanding of Florida's rich tapestry but has also validated our belief that uncovering unexpected connections often involves navigating through unexpected detours.

[[RESULTS]]
The results of our investigation into the relationship between Democrat votes for Senators in Florida and the number of septic tank servicers and sewer pipe cleaners yield an intriguing revelation. After analyzing data from the period spanning 2003 to 2018, a robust correlation coefficient of 0.9253580 and an r-squared value of 0.8562875 were uncovered, accompanied by a p-value of less than 0.01. These statistical metrics not only attest to the strength of the observed relationship but also underscore the highly significant nature of the results.
Now, let's dive into the nitty-gritty and address the elephant in the room - or should we say, the alligator? Fig. 1 showcases a scatterplot that visually captures the striking correlation between these seemingly incongruent variables, providing compelling evidence to support our findings. This graph, which illustrates the pronounced association between Democrat votes and the prevalence of septic tank servicers and sewer pipe cleaners, serves as a testament to the unexpected ways in which disparate elements can manifest a cohesive narrative.
While some might quip that it's just the state's unique combination of "blue" and "brown" factors at play, our results lead to a broader reflection on the intricate interweaving of political inclinations and infrastructure necessities. Indeed, our discovery prompts contemplation on the ways in which the sociopolitical landscape and the less visible aspects of public services may bear a closer relationship than previously acknowledged. Cue the "flush of realization" moment - there might just be more to Florida's political ecosystem than meets the eye.
The implications of this study extend beyond the immediate surprise factor and delve into uncharted territory, shining a light on the quirky quirks of life that emerge amidst the rigidity of data and analysis. As we wrap up this section, we invite readers to ponder the unexpected alliances that emerge when we venture beyond the surface - whether it be in the realm of politics or plumbing. After all, in the grand scheme of research, it's these unforeseen connections that often lead to the most "piping hot" revelations.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings, while initially as surprising as finding a treasure trove in a septic tank, align with the hints and glimpses from the literature review that indicated a possible connection between Democrat votes in Florida and the state's septic state. The correlation coefficient of 0.9253580 between Democrat votes for Senators in Florida and the number of septic tank servicers and sewer pipe cleaners paints a picture as clear as a pristine sewer pipeline. It appears that the political leanings of individuals in the Sunshine State have a tangible and statistically significant association with the demand for septic services, just as the shifting sands of politics can influence the tides of public services.

Our results support the prior research that veiled references and hidden innuendos insinuated could exist beyond the surface of scholarly literature. The humorous mention of unexpected detours in the literature review seems apropos, as our findings have indeed taken us through an unexpected yet illuminating journey into the deep underbelly of Florida's political and plumbing landscapes. Much like the journey of a wayward toy flushed down a toilet, our research has emerged from the depths initially unexpected, yet ultimately aligning with the anticipated unusual relationships we were seeking to explore.

In addition, the statistical metrics and the captivating scatterplot not only lend credence to our discoveries but also add color to the vivid tapestry of Florida's socio-political ecosystem. As we navigate the labyrinth of data and analysis, it becomes apparent that the correlation observed is not merely a whimsical anomaly, but rather an integral thread in the intricate fabric of Florida's political quilt.

The unexpected alliances that emerge from this research prompt a re-evaluation of the metaphorical pipelines that connect aspects of public services to the political landscape. Could it be that the electorate and the demand for septic services are akin to the interconnected sewage pipes that lie beneath our streets, silently shaping the flow of Florida's political currents? The implications stretch beyond the surface level, much like the underground networks we have sought to shed light upon, and beckon us to reflect on the quirky quirks of life that intertwine amidst the rigidity of data and analysis. This study serves as a reminder that even in the least anticipated confluences, there lies the possibility of unearthing astonishing revelations.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Florida and The number of septic tank servicers and sewer pipe cleaners in Florida. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Democrat Votes in Florida: Do They Relate to the State's Septic State?

[[ABSTRACT]]
In this study, we delved deep into the sewers of Florida to uncover the correlation between the voting behavior of Democrats in the state and the number of septic tank servicers and sewer pipe cleaners. While at first glance one might think these two factors are as unrelated as a gator and a flamingo, our research team found a surprising connection. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, we uncovered a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. Our findings suggest that there may indeed be a fecal matter... I mean, a fruitful relationship between these seemingly disparate variables. This paper not only sheds light on the dynamics of Florida politics and plumbing, but also provokes contemplation on the intricate ways in which the political landscape and sewage infrastructure intertwine. So, as we flush out the details of this study, may it serve as a reminder that in the world of research, even the most unexpected connections can surface if you just keep digging.

[[INTRDUCTION]]
Politics and plumbing - two seemingly unrelated aspects of society that, as it turns out, may not be as separate as one might think. In this study, we embarked on a journey through the labyrinthine world of Florida's electoral politics and sewage infrastructure to ascertain whether the voting patterns of Democrats in the state could be linked to the number of septic tank servicers and sewer pipe cleaners. While one might initially envision a political landscape filled with partisan divides and a sewage system brimming with, well, sewage, our research sought to uncover any underlying connections between these peculiar bedfellows.
As any Floridian can attest, the state's political climate has often been characterized by its unique blend of sunshine and, shall we say, more murky elements. Meanwhile, the plumbing needs of a state known for its wetlands, swamps, and gator-laden waters have always been a critical aspect of its infrastructure. Yet, the question remained: is there a deeper, unexplored interconnection between these seemingly incongruent spheres?
The overarching goal of this study was to peel back the layers of Floridian politicking and piping to reveal any potential correlation between Democrat votes for Senators in Florida and the prevalence of septic tank servicers and sewer pipe cleaners across the state. As these seemingly unrelated elements converged under the microscope of our analysis, we aimed to uncover insights that could shed light on the intricate dynamics of the state's sociopolitical landscape and its sewage infrastructure.
By traversing the statistically fertile grounds of MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team endeavored to unveil any discernible patterns or connections between the electoral choices of Democrats and the availability of services related to the less glamorous aspects of sanitation. Our findings, which we will expound upon in detail, revealed a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. This discovery, while unexpected, prompts a reevaluation of the intricate ways in which political preferences and the less visible aspects of infrastructure intersect.
In the pages that follow, we invite readers to join us on this unconventional exploration as we unearth the unsuspected parallels between Florida's political allegiances and its wastewater management landscape. While the path we tread may at first glance seem unconventional, our findings provide a compelling case that even in the unlikeliest of terrains, the connections that emerge are both thought-provoking and, dare we say, delightful. So, let us embark on this odyssey of research – for in the realm of scholarly inquiry, as in life, one must always be prepared to navigate unexpected twists and turns, whether they emerge from the ballot box or the bowels of civilization.

[[RESULTS]]
The results of our investigation into the relationship between Democrat votes for Senators in Florida and the number of septic tank servicers and sewer pipe cleaners yield an intriguing revelation. After analyzing data from the period spanning 2003 to 2018, a robust correlation coefficient of 0.9253580 and an r-squared value of 0.8562875 were uncovered, accompanied by a p-value of less than 0.01. These statistical metrics not only attest to the strength of the observed relationship but also underscore the highly significant nature of the results.
Now, let's dive into the nitty-gritty and address the elephant in the room - or should we say, the alligator? Fig. 1 showcases a scatterplot that visually captures the striking correlation between these seemingly incongruent variables, providing compelling evidence to support our findings. This graph, which illustrates the pronounced association between Democrat votes and the prevalence of septic tank servicers and sewer pipe cleaners, serves as a testament to the unexpected ways in which disparate elements can manifest a cohesive narrative.
While some might quip that it's just the state's unique combination of "blue" and "brown" factors at play, our results lead to a broader reflection on the intricate interweaving of political inclinations and infrastructure necessities. Indeed, our discovery prompts contemplation on the ways in which the sociopolitical landscape and the less visible aspects of public services may bear a closer relationship than previously acknowledged. Cue the "flush of realization" moment - there might just be more to Florida's political ecosystem than meets the eye.
The implications of this study extend beyond the immediate surprise factor and delve into uncharted territory, shining a light on the quirky quirks of life that emerge amidst the rigidity of data and analysis. As we wrap up this section, we invite readers to ponder the unexpected alliances that emerge when we venture beyond the surface - whether it be in the realm of politics or plumbing. After all, in the grand scheme of research, it's these unforeseen connections that often lead to the most "piping hot" revelations.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unearthed a rather unexpected and, dare I say, flush-with-surprises connection between Democrat votes for Senators in Florida and the number of septic tank servicers and sewer pipe cleaners. With a correlation coefficient of 0.9253580 and a p-value of less than 0.01, the statistical aroma, I mean, significance of our findings cannot be dismissed as mere coincidence. While at first glance the world of politics and the realm of sewage maintenance may seem as incongruous as oranges and alligators, our research has shown that there's more swirling beneath the surface than meets the eye - perhaps even more than a whirlpool in a septic tank.

The correlation between these seemingly unrelated variables prompts contemplation on the fascinating fecal, I mean, fertile grounds of societal connection. It's a poignant reminder that in the tapestry of data analysis, the most unexpected strands can weave a compelling narrative – even if it does reek of ambiguity at first. As we navigate the clogged pipelines of political inquiry, our study provides not only a fresh perspective on Florida's electoral dynamics but also a stark reminder that in the world of research, even the most unusual links can bubble up if you just keep digging.

So, as we bid adieu to this unusual exploration, it's clear that no more research is needed in this area. As they say, there's no use crying over spilled sewage – or perhaps in this case, there's no use plumbing the depths of this correlation any further. After all, as any good plumber knows, when the pipes are unclogged, it's time to call it a day.


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 Democrat Votes in Florida: Do They Relate to the State's Septic State?. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Political Hygiene


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 Democrat Votes in Florida: Do They Relate to the State's Septic State?. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Political Puzzles and Perplexities


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 Democrat Votes in Florida: Do They Relate to the State's Septic State? with an abstract of In this study, we delved deep into the sewers of Florida to uncover the correlation between the voting behavior of Democrats in the state and the number of septic tank servicers and sewer pipe cleaners. While at first glance one might think these two factors are as unrelated as a gator and a flamingo, our research team found a surprising connection. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, we uncovered a correlation coefficient of 0.9253580 with a p-value of less than 0.01 for the period spanning 2003 to 2018. Our findings suggest that there may indeed be a fecal matter... I mean, a fruitful relationship between these seemingly disparate variables. This paper not only sheds light on the dynamics of Florida politics and plumbing, but also provokes contemplation on the intricate ways in which the political landscape and sewage infrastructure intertwine. So, as we flush out the details of this study, may it serve as a reminder that in the world of research, even the most unexpected connections can surface if you just keep digging.

ChatGPT:

Florida, Democrat votes, septic tank servicers, sewer pipe cleaners, voting behavior, correlation, MIT Election Data and Science Lab, Harvard Dataverse, Bureau of Labor Statistics, Florida politics, plumbing, sewage infrastructure, correlation coefficient, p-value, research findings

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

The number of septic tank servicers and sewer pipe cleaners in Florida
Detailed data title: BLS estimate of septic tank servicers and sewer pipe cleaners in Florida
Source: Bureau of Larbor Statistics
See what else correlates with The number of septic tank servicers and sewer pipe cleaners in Florida

Correlation r = 0.9253580 (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 = 0.8562875 (Coefficient of determination)
This means 85.6% of the change in the one variable (i.e., The number of septic tank servicers and sewer pipe cleaners in Florida) is predictable based on the change in the other (i.e., Votes for Democratic Senators in Florida) over the 6 years from 2003 through 2018.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0081. 0.0081492060966913780000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.93 in 0.81% of random cases. Said differently, if you correlated 123 random variables Which I absolutely did.
with the same 5 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 5 because we have two variables measured over a period of 6 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.

[ 0.46, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200420062010201220162018
Votes for Democratic Senators in Florida (Total votes)359020028905501092940452345041220904089470
The number of septic tank servicers and sewer pipe cleaners in Florida (Laborers)11901170930164014701390




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. 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.
  5. 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. 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. 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([3590200,2890550,1092940,4523450,4122090,4089470,])
array_2 = np.array([1190,1170,930,1640,1470,1390,])
array_1_name = "Votes for Democratic Senators in Florida"
array_2_name = "The number of septic tank servicers and sewer pipe cleaners in Florida"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!


Correlation ID: 5276 · Black Variable ID: 26219 · Red Variable ID: 6623
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0