about · email me · subscribe
Spurious correlation #4,300 · 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 Republican Senators in Oklahoma and the second variable is The number of transportation, storage, and distribution managers in Oklahoma.  The chart goes from 2003 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As more Republican Senators were elected, the demand for "efficient and streamlined" transportation and distribution systems grew. This led to a surge in the need for managers to organize the frequent traffic jams of political maneuvering and ensure the smooth delivery of promises to the public. It's a case of political votes driving the need for logistical devotees!

Model: dalle-3
Prompt: Generate an image of the bustling city of Oklahoma with a vibrant pop art style. The State Capitol building stands prominently in the background, with a group of Republican senators gathered in discussion outside. The energy of their decision-making is visually represented through bold, colorful lines and shapes that radiate from them. Just outside the Capitol, a team of transportation, storage, and distribution managers can be seen coordinating the flow of goods and services, with swirling patterns and dynamic movement accentuating the logistical coordination. The traffic of political decisions and promises intertwines with the logistical devotees, creating a visually striking scene that captures the dynamic interplay between political votes and logistical coordination. The colors and shapes should evoke the energy and dynamism of the bustling city scene, creating a unique and engaging pop art interpretation. 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: Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma. 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: Symbolism Art nouveau a Polaroid photo Pop art Cutsy art illustration
ChatGPT: Pop art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma, in the following situation: As more Republican Senators were elected, the demand for "efficient and streamlined" transportation and distribution systems grew. This led to a surge in the need for managers to organize the frequent traffic jams of political maneuvering and ensure the smooth delivery of promises to the public. It's a case of political votes driving the need for logistical devotees!. Keep the description simple.
ChatGPT: In the bustling city of Oklahoma, a group of Republican senators gather in the State Capitol to cast their votes. The energy of their decision-making fills the air, while just outside the Capitol, a team of transportation, storage, and distribution managers work together to coordinate the smooth flow of goods and services across the state. The traffic of political decisions and promises intertwines with the logistical coordination, creating a dynamic scene of political votes driving the need for logistical devotees.

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: [ Pop art ] and depicting this scene: In the bustling city of Oklahoma, a group of Republican senators gather in the State Capitol to cast their votes. The energy of their decision-making fills the air, while just outside the Capitol, a team of transportation, storage, and distribution managers work together to coordinate the smooth flow of goods and services across the state. The traffic of political decisions and promises intertwines with the logistical coordination, creating a dynamic scene of political votes driving the need for logistical devotees. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of the bustling city of Oklahoma with a vibrant pop art style. The State Capitol building stands prominently in the background, with a group of Republican senators gathered in discussion outside. The energy of their decision-making is visually represented through bold, colorful lines and shapes that radiate from them. Just outside the Capitol, a team of transportation, storage, and distribution managers can be seen coordinating the flow of goods and services, with swirling patterns and dynamic movement accentuating the logistical coordination. The traffic of political decisions and promises intertwines with the logistical devotees, creating a visually striking scene that captures the dynamic interplay between political votes and logistical coordination. The colors and shapes should evoke the energy and dynamism of the bustling city scene, creating a unique and engaging pop art interpretation.

*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 an increase in Republican votes for Senators in Oklahoma caused The number of transportation, storage, and distribution managers in Oklahoma to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)
Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State

The Journal of Political Econometrics

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 silly 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 Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma. Make lots of jokes, goofy observations, and puns.

Make the title seem clever.

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 0.9769079 and p < 0.01 for 2003 to 2020.

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]]
"Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State"

[[ABSTRACT]]
This paper delves into the unexpected correlations and connections between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers. Our team takes a lighthearted but data-driven approach to uncover the intriguing relationship between political preferences and occupational distribution in the Sooner State. Through the use of sophisticated statistical analysis, our findings reveal a remarkably high correlation coefficient (0.9769079) and a significant p-value (< 0.01) for the period spanning from 2003 to 2020. The results of this study are sure to provide both amusement and insight for political enthusiasts and labor market analysts alike. After all, who would have thought that political trends and professional networks could be so intertwined? Our analysis uncovers a perhaps unexpected parallel between the voting patterns and professional pursuits of Oklahomans, highlighting the unique dynamics at play in the state's socio-political fabric. So, buckle up and join us on this journey through the offbeat yet enlightening landscape of political and labor market connections!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State"

[[ABSTRACT]]
This paper delves into the unexpected correlations and connections between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers. Our team takes a lighthearted but data-driven approach to uncover the intriguing relationship between political preferences and occupational distribution in the Sooner State. Through the use of sophisticated statistical analysis, our findings reveal a remarkably high correlation coefficient (0.9769079) and a significant p-value (< 0.01) for the period spanning from 2003 to 2020. The results of this study are sure to provide both amusement and insight for political enthusiasts and labor market analysts alike. After all, who would have thought that political trends and professional networks could be so intertwined? Our analysis uncovers a perhaps unexpected parallel between the voting patterns and professional pursuits of Oklahomans, highlighting the unique dynamics at play in the state's socio-political fabric. So, buckle up and join us on this journey through the offbeat yet enlightening landscape of political and labor market connections!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the bustling world of political research, one might assume that the only connections worth noting are those between policymakers and their constituents. However, as any self-respecting statistician will tell you, the devil is in the details, and sometimes those details lead us to unexpected and downright wacky correlations. In this paper, we endeavor to unravel the enigmatic link between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state. Yes, you read that right - we're embarking on a statistical escapade that traverses the realms of politics and professional pursuits, armed with nothing but our trusty spreadsheets and a penchant for uncovering the absurd. So, grab your calculators and strap in for a bumpy ride through the wild world of data analysis!

Now, before you roll your eyes and dismiss our research as a mere exercise in statistical tomfoolery, consider this: the intersection of political ideologies and occupational demographics is not as straightforward as one might assume. We're not merely crunching numbers for the sake of it; we're diving headfirst into the intricate web of human behavior and societal dynamics. After all, who wouldn't want to know if there's a connection between casting ballots and managing boxes? It's the sort of quirky question that keeps researchers up at night - along with the occasional failed regression analysis.

With a cosmos of data at our fingertips, we set out to explore this intriguing nexus, armed with the knowledge that correlation does not necessarily imply causation, but hey, it sure does make for an entertaining research journey. So, fear not, dear reader, for we promise that in between the scatter plots and regression lines, there'll be a healthy dose of humor and lighthearted musings. After all, what's research without a few puns and unexpected revelations? We invite you to join us on this whimsical expedition as we unravel the fabric of Oklahoma's political and labor market landscape, one statistical quirk at a time. Fasten your seatbelts, the ride is about to get statistically wild!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
"Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State"

[[ABSTRACT]]
This paper delves into the unexpected correlations and connections between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers. Our team takes a lighthearted but data-driven approach to uncover the intriguing relationship between political preferences and occupational distribution in the Sooner State. Through the use of sophisticated statistical analysis, our findings reveal a remarkably high correlation coefficient (0.9769079) and a significant p-value (< 0.01) for the period spanning from 2003 to 2020. The results of this study are sure to provide both amusement and insight for political enthusiasts and labor market analysts alike. After all, who would have thought that political trends and professional networks could be so intertwined? Our analysis uncovers a perhaps unexpected parallel between the voting patterns and professional pursuits of Oklahomans, highlighting the unique dynamics at play in the state's socio-political fabric. So, buckle up and join us on this journey through the offbeat yet enlightening landscape of political and labor market connections!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the bustling world of political research, one might assume that the only connections worth noting are those between policymakers and their constituents. However, as any self-respecting statistician will tell you, the devil is in the details, and sometimes those details lead us to unexpected and downright wacky correlations. In this paper, we endeavor to unravel the enigmatic link between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state. Yes, you read that right - we're embarking on a statistical escapade that traverses the realms of politics and professional pursuits, armed with nothing but our trusty spreadsheets and a penchant for uncovering the absurd. So, grab your calculators and strap in for a bumpy ride through the wild world of data analysis!
Now, before you roll your eyes and dismiss our research as a mere exercise in statistical tomfoolery, consider this: the intersection of political ideologies and occupational demographics is not as straightforward as one might assume. We're not merely crunching numbers for the sake of it; we're diving headfirst into the intricate web of human behavior and societal dynamics. After all, who wouldn't want to know if there's a connection between casting ballots and managing boxes? It's the sort of quirky question that keeps researchers up at night - along with the occasional failed regression analysis.
With a cosmos of data at our fingertips, we set out to explore this intriguing nexus, armed with the knowledge that correlation does not necessarily imply causation, but hey, it sure does make for an entertaining research journey. So, fear not, dear reader, for we promise that in between the scatter plots and regression lines, there'll be a healthy dose of humor and lighthearted musings. After all, what's research without a few puns and unexpected revelations? We invite you to join us on this whimsical expedition as we unravel the fabric of Oklahoma's political and labor market landscape, one statistical quirk at a time. Fasten your seatbelts, the ride is about to get statistically wild!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In the pursuit of unraveling the curious correlation between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state, our team has scoured the annals of academia to unearth any inkling of insight into this delightfully quirky nexus. We embarked on our quest with the solemn determination of a geologist, carefully sifting through layers of scholarly literature in search of the proverbial nuggets of wisdom. Our journey through the literature began with esteemed works by Smith, Doe, and Jones, who, while not directly addressing our specific inquiry, provided foundational knowledge on statistical correlations and the intricate tapestry of socio-political dynamics.

Smith's seminal work "The Statistical Marvels of Political Peculiarities" offers a comprehensive exploration of the unexpected intersections between political phenomena and diverse societal indicators. Admittedly, Smith's focus lies more on the broader canvas of political idiosyncrasies, but the underlying principles of statistical analysis laid the groundwork for our own methodological approach. Meanwhile, Doe's treatise "Socio-Political Quirks: A Statistical Odyssey" delves into the uncharted realms of statistical anomalies within the political landscape, providing valuable insights into the art of uncovering correlations that defy conventional expectations. As for Jones, in "The Interconnected Webs of Occupation and Ideology," the author sheds light on the intricate interplay between occupations and ideological leanings, though regrettably, the focus remains more generalized, failing to zero in on the delightful eccentricities of the Oklahoma scenario.

Transitioning from the serious realm of academic literature to more accessible sources, we turned our attention to non-fiction works that could potentially shed light on the unexpected symbiosis of political allegiance and managerial vocations. "The Art of Box Management" by Rick Steves, while ostensibly a travel guide, inadvertently invoked our curiosity with its tantalizing discussions of logistics and, yes, the management of boxes. Now, you may wonder, what does box management have to do with Republican votes? Well, dear reader, we're just as intrigued as you are.

As our pursuit of knowledge took an increasingly whimsical turn, we encountered literary works of fiction that, while not grounded in empirical research, tantalizingly mirrored the theme of our investigation. "The Senator's Logistic Dilemma" by Jane Austen, though a departure from her usual romance-laden oeuvre, paints a whimsical picture of political intrigue and logistical conundrums that left us pondering the improbable intersections of political ambition and supply chain management. Similarly, "The Transportation Tales" by J.R.R. Tolkien (a lesser-known companion to his more famous opus) regaled us with fantastical accounts of adventurous journeys and the logistical challenges that befell the intrepid characters. Though undoubtedly works of fiction, these narratives sparked a subtle curiosity in the uncanny parallels between political decisions and the logistics of, well, anything from transporting magical rings to managing regular cargo.

Venturing into the realm of popular culture, we found ourselves conducting "research" that involved marathoning children's shows and cartoons in a valiant effort to capture the essence of Oklahoma's socio-political landscape. The strategic maneuvers of "Paw Patrol" instilled in us a newfound appreciation for the logistics of managing a diverse team, albeit one composed of animated puppies. And let's not forget the enigmatic allure of "SpongeBob SquarePants," which, while ostensibly a lighthearted portrayal of underwater shenanigans, slyly hinted at the intricacies of supply chain management within the confines of Bikini Bottom. As unconventional as our methods may have seemed, we assure you that every episode watched was in the pursuit of scholarly enlightenment.

With this eclectic mix of literature, both scholarly and otherwise, we stand poised to present our own findings, armed with a treasure trove of inspiration and a healthy dose of whimsy. So, dear reader, with a twinkle in our eyes and a spring in our step, we invite you to journey with us into the statistical rabbit hole of political and professional curiosities. Prepare for a rollercoaster ride of correlations and quips, where the unexpected reigns supreme, and statistical analysis takes a delightfully fantastical turn.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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 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]]
"Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State"

[[ABSTRACT]]
This paper delves into the unexpected correlations and connections between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers. Our team takes a lighthearted but data-driven approach to uncover the intriguing relationship between political preferences and occupational distribution in the Sooner State. Through the use of sophisticated statistical analysis, our findings reveal a remarkably high correlation coefficient (0.9769079) and a significant p-value (< 0.01) for the period spanning from 2003 to 2020. The results of this study are sure to provide both amusement and insight for political enthusiasts and labor market analysts alike. After all, who would have thought that political trends and professional networks could be so intertwined? Our analysis uncovers a perhaps unexpected parallel between the voting patterns and professional pursuits of Oklahomans, highlighting the unique dynamics at play in the state's socio-political fabric. So, buckle up and join us on this journey through the offbeat yet enlightening landscape of political and labor market connections!

[[INTRODUCTION]]
In the bustling world of political research, one might assume that the only connections worth noting are those between policymakers and their constituents. However, as any self-respecting statistician will tell you, the devil is in the details, and sometimes those details lead us to unexpected and downright wacky correlations. In this paper, we endeavor to unravel the enigmatic link between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state. Yes, you read that right - we're embarking on a statistical escapade that traverses the realms of politics and professional pursuits, armed with nothing but our trusty spreadsheets and a penchant for uncovering the absurd. So, grab your calculators and strap in for a bumpy ride through the wild world of data analysis!
Now, before you roll your eyes and dismiss our research as a mere exercise in statistical tomfoolery, consider this: the intersection of political ideologies and occupational demographics is not as straightforward as one might assume. We're not merely crunching numbers for the sake of it; we're diving headfirst into the intricate web of human behavior and societal dynamics. After all, who wouldn't want to know if there's a connection between casting ballots and managing boxes? It's the sort of quirky question that keeps researchers up at night - along with the occasional failed regression analysis.
With a cosmos of data at our fingertips, we set out to explore this intriguing nexus, armed with the knowledge that correlation does not necessarily imply causation, but hey, it sure does make for an entertaining research journey. So, fear not, dear reader, for we promise that in between the scatter plots and regression lines, there'll be a healthy dose of humor and lighthearted musings. After all, what's research without a few puns and unexpected revelations? We invite you to join us on this whimsical expedition as we unravel the fabric of Oklahoma's political and labor market landscape, one statistical quirk at a time. Fasten your seatbelts, the ride is about to get statistically wild!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Before diving into the nitty-gritty of our methodological escapade, let's be clear - this research journey involved a combination of convoluted statistical maneuvers, unabashed data mining, and the occasional spontaneous dancing to break the monotony. Our team began by gathering data from reliable sources such as the MIT Election Data and Science Lab, Harvard Dataverse, and the Bureau of Labor Statistics. Armed with our laptops and a relentless quest for peculiar connections, we meticulously collected information spanning the years 2003 to 2020.

With our data all lined up like obedient soldiers, it was time to unleash the statistical artillery. We opted for a time-series analysis, as our objective was to capture any potential evolution of the relationship over the years. We employed a combination of linear regression models, propensity score matching techniques, and the occasional celebratory dab upon discovering an interesting trend.

To add spice to the mix, we had a cup of bootstrapping to ensure the robustness of our findings and sprinkled in a touch of Monte Carlo simulations for good measure. Some may call it excessive, but we saw it as an opportunity to give those statistics textbooks a run for their money.

Lest we forget, controlling for confounding variables was a crucial part of our journey. We made sure to account for factors such as population density, economic indicators, and the occasional unexpected interruption from the office dog. After all, a research endeavor without a few distractions is like a hypothesis without an alternate hypothesis – it just lacks novelty and surprise.

Once our statistical acrobatics were complete, we marveled at our correlation coefficients and p-values like kids in a statistical candy store. The results were eye-opening, to say the least, and left us pondering the whimsical dance of numbers and human behavior. So, gear up for a methodological odyssey like no other, as our findings are sure to leave you both enlightened and chuckling at the absurdity of it all.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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 2020, you found a correlation 0.9769079, r-squared of 0.9543491, 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]]
"Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State"

[[ABSTRACT]]
This paper delves into the unexpected correlations and connections between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers. Our team takes a lighthearted but data-driven approach to uncover the intriguing relationship between political preferences and occupational distribution in the Sooner State. Through the use of sophisticated statistical analysis, our findings reveal a remarkably high correlation coefficient (0.9769079) and a significant p-value (< 0.01) for the period spanning from 2003 to 2020. The results of this study are sure to provide both amusement and insight for political enthusiasts and labor market analysts alike. After all, who would have thought that political trends and professional networks could be so intertwined? Our analysis uncovers a perhaps unexpected parallel between the voting patterns and professional pursuits of Oklahomans, highlighting the unique dynamics at play in the state's socio-political fabric. So, buckle up and join us on this journey through the offbeat yet enlightening landscape of political and labor market connections!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the bustling world of political research, one might assume that the only connections worth noting are those between policymakers and their constituents. However, as any self-respecting statistician will tell you, the devil is in the details, and sometimes those details lead us to unexpected and downright wacky correlations. In this paper, we endeavor to unravel the enigmatic link between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state. Yes, you read that right - we're embarking on a statistical escapade that traverses the realms of politics and professional pursuits, armed with nothing but our trusty spreadsheets and a penchant for uncovering the absurd. So, grab your calculators and strap in for a bumpy ride through the wild world of data analysis!
Now, before you roll your eyes and dismiss our research as a mere exercise in statistical tomfoolery, consider this: the intersection of political ideologies and occupational demographics is not as straightforward as one might assume. We're not merely crunching numbers for the sake of it; we're diving headfirst into the intricate web of human behavior and societal dynamics. After all, who wouldn't want to know if there's a connection between casting ballots and managing boxes? It's the sort of quirky question that keeps researchers up at night - along with the occasional failed regression analysis.
With a cosmos of data at our fingertips, we set out to explore this intriguing nexus, armed with the knowledge that correlation does not necessarily imply causation, but hey, it sure does make for an entertaining research journey. So, fear not, dear reader, for we promise that in between the scatter plots and regression lines, there'll be a healthy dose of humor and lighthearted musings. After all, what's research without a few puns and unexpected revelations? We invite you to join us on this whimsical expedition as we unravel the fabric of Oklahoma's political and labor market landscape, one statistical quirk at a time. Fasten your seatbelts, the ride is about to get statistically wild!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

As we delved into the data with the eagerness of explorers in uncharted statistical territory, we made a bewildering discovery - a striking correlation between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state. With a correlation coefficient of 0.9769079, our jaws dropped faster than the p-value as we marveled at the strength of this unexpected relationship. The r-squared value of 0.9543491 further reinforced the robustness of this entangled web of political allegiance and professional career choices. It's safe to say; we were left shaking our heads and wondering what other surprising connections lay hidden within the realms of electoral trends and the labor market.

In Fig. 1, we present a scatterplot that visually encapsulates the remarkable correlation we uncovered. When we gazed upon this plot, the only thing scattered more than the data points were our preconceived notions of the demarcation between political inclinations and occupational pursuits. It's as if the data decided to take a joyride on the highway of correlation, leaving us all in a state of statistical bewilderment.

The significance of the p-value being less than 0.01 made us exclaim, "Well, isn't that statistically marvelous!" It seems that the intricate dance between political choices and professional roles in Oklahoma is not just a happenstance – at least not according to our data analysis.

So, there you have it – our statistical sleuthing has led us to an unexpected yet undeniable connection between Republican votes and the employment landscape in the Sooner State. If this doesn't make you go "hmm" and contemplate the whimsical nature of human decision-making, then we're not sure what will. Our findings serve as a reminder that in the world of research, one must always expect the unexpected – after all, uncertainty is the only certainty in statistics.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State"

[[ABSTRACT]]
This paper delves into the unexpected correlations and connections between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers. Our team takes a lighthearted but data-driven approach to uncover the intriguing relationship between political preferences and occupational distribution in the Sooner State. Through the use of sophisticated statistical analysis, our findings reveal a remarkably high correlation coefficient (0.9769079) and a significant p-value (< 0.01) for the period spanning from 2003 to 2020. The results of this study are sure to provide both amusement and insight for political enthusiasts and labor market analysts alike. After all, who would have thought that political trends and professional networks could be so intertwined? Our analysis uncovers a perhaps unexpected parallel between the voting patterns and professional pursuits of Oklahomans, highlighting the unique dynamics at play in the state's socio-political fabric. So, buckle up and join us on this journey through the offbeat yet enlightening landscape of political and labor market connections!

[[LITERATURE REVIEW]]
In the pursuit of unraveling the curious correlation between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state, our team has scoured the annals of academia to unearth any inkling of insight into this delightfully quirky nexus. We embarked on our quest with the solemn determination of a geologist, carefully sifting through layers of scholarly literature in search of the proverbial nuggets of wisdom. Our journey through the literature began with esteemed works by Smith, Doe, and Jones, who, while not directly addressing our specific inquiry, provided foundational knowledge on statistical correlations and the intricate tapestry of socio-political dynamics.
Smith's seminal work "The Statistical Marvels of Political Peculiarities" offers a comprehensive exploration of the unexpected intersections between political phenomena and diverse societal indicators. Admittedly, Smith's focus lies more on the broader canvas of political idiosyncrasies, but the underlying principles of statistical analysis laid the groundwork for our own methodological approach. Meanwhile, Doe's treatise "Socio-Political Quirks: A Statistical Odyssey" delves into the uncharted realms of statistical anomalies within the political landscape, providing valuable insights into the art of uncovering correlations that defy conventional expectations. As for Jones, in "The Interconnected Webs of Occupation and Ideology," the author sheds light on the intricate interplay between occupations and ideological leanings, though regrettably, the focus remains more generalized, failing to zero in on the delightful eccentricities of the Oklahoma scenario.
Transitioning from the serious realm of academic literature to more accessible sources, we turned our attention to non-fiction works that could potentially shed light on the unexpected symbiosis of political allegiance and managerial vocations. "The Art of Box Management" by Rick Steves, while ostensibly a travel guide, inadvertently invoked our curiosity with its tantalizing discussions of logistics and, yes, the management of boxes. Now, you may wonder, what does box management have to do with Republican votes? Well, dear reader, we're just as intrigued as you are.
As our pursuit of knowledge took an increasingly whimsical turn, we encountered literary works of fiction that, while not grounded in empirical research, tantalizingly mirrored the theme of our investigation. "The Senator's Logistic Dilemma" by Jane Austen, though a departure from her usual romance-laden oeuvre, paints a whimsical picture of political intrigue and logistical conundrums that left us pondering the improbable intersections of political ambition and supply chain management. Similarly, "The Transportation Tales" by J.R.R. Tolkien (a lesser-known companion to his more famous opus) regaled us with fantastical accounts of adventurous journeys and the logistical challenges that befell the intrepid characters. Though undoubtedly works of fiction, these narratives sparked a subtle curiosity in the uncanny parallels between political decisions and the logistics of, well, anything from transporting magical rings to managing regular cargo.
Venturing into the realm of popular culture, we found ourselves conducting "research" that involved marathoning children's shows and cartoons in a valiant effort to capture the essence of Oklahoma's socio-political landscape. The strategic maneuvers of "Paw Patrol" instilled in us a newfound appreciation for the logistics of managing a diverse team, albeit one composed of animated puppies. And let's not forget the enigmatic allure of "SpongeBob SquarePants," which, while ostensibly a lighthearted portrayal of underwater shenanigans, slyly hinted at the intricacies of supply chain management within the confines of Bikini Bottom. As unconventional as our methods may have seemed, we assure you that every episode watched was in the pursuit of scholarly enlightenment.
With this eclectic mix of literature, both scholarly and otherwise, we stand poised to present our own findings, armed with a treasure trove of inspiration and a healthy dose of whimsy. So, dear reader, with a twinkle in our eyes and a spring in our step, we invite you to journey with us into the statistical rabbit hole of political and professional curiosities. Prepare for a rollercoaster ride of correlations and quips, where the unexpected reigns supreme, and statistical analysis takes a delightfully fantastical turn.

[[RESULTS]]
As we delved into the data with the eagerness of explorers in uncharted statistical territory, we made a bewildering discovery - a striking correlation between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state. With a correlation coefficient of 0.9769079, our jaws dropped faster than the p-value as we marveled at the strength of this unexpected relationship. The r-squared value of 0.9543491 further reinforced the robustness of this entangled web of political allegiance and professional career choices. It's safe to say; we were left shaking our heads and wondering what other surprising connections lay hidden within the realms of electoral trends and the labor market.
In Fig. 1, we present a scatterplot that visually encapsulates the remarkable correlation we uncovered. When we gazed upon this plot, the only thing scattered more than the data points were our preconceived notions of the demarcation between political inclinations and occupational pursuits. It's as if the data decided to take a joyride on the highway of correlation, leaving us all in a state of statistical bewilderment.
The significance of the p-value being less than 0.01 made us exclaim, "Well, isn't that statistically marvelous!" It seems that the intricate dance between political choices and professional roles in Oklahoma is not just a happenstance – at least not according to our data analysis.
So, there you have it – our statistical sleuthing has led us to an unexpected yet undeniable connection between Republican votes and the employment landscape in the Sooner State. If this doesn't make you go "hmm" and contemplate the whimsical nature of human decision-making, then we're not sure what will. Our findings serve as a reminder that in the world of research, one must always expect the unexpected – after all, uncertainty is the only certainty in statistics.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

In the spirit of scholarly inquiry and statistical revelry, let's revel in the revelatory nature of our findings. Our results affirm the whimsical musings brought forth in our literature review, indicating that the interrelationships between political proclivities and professional pursuits are indeed more than just statistical happenstance. As we tango through the tumultuous terrain of statistics, it becomes increasingly clear that the unfathomable link between Republican votes and the number of transportation, storage, and distribution managers in Oklahoma is not merely a facetious figment of statistical mischief, but a tangible, albeit quirky, reality.

Upon reflecting on the seemingly outlandish yet resoundingly verifiable correlation, we are prompted to ponder the extent to which political predilections influence occupational choices and vice versa. Could it be that the orchestration of political rallies serendipitously fuels the collective ardor for careers in transportation management, inspiring a harmonious symphony of political passion and logistical prowess? Be it the logistics of moving boxes, managing Paw Patrol missions, or shepherding supplies through Bikini Bottom, the allure of transportation, storage, and distribution management seems to share an uncanny resonance with the political vibrato of partisan votes.

Our findings lend credence to the notion that the socio-political landscape of Oklahoma undoubtedly waltzes to its own statistical beat, frolicking through the meadows of probability with a whimsical abandon. The robustness of the correlation coefficient (0.9769079) and the compelling r-squared value (0.9543491) accentuate the undeniable gravity of this peculiar relationship, leaving us chuckling at the statistical peculiarity of it all.

As we peel back the layers of this statistical enigma, we are left ruminating on the colorful tapestry of human decision-making. After all, it appears that the people of Oklahoma have been waltzing in political sync with the ebb and flow of the transportation, storage, and distribution profession, perhaps without even realizing it. This delightful interplay of statistical surprise underscores the captivating complexity of human behavior, reminding us that in the whimsical land of statistics, the unexpected is not merely a possibility but a statistical inevitability.

In the grand tradition of scholarly levity, our discussions traverse the terrain between the comical and the factual, reveling in the delightful dance of statistical analyses and human idiosyncrasies. So, as we bid adieu to this quirky rendezvous with statistical correlations, may our findings stand as a testament to the inextricable interdependence of political phenomena and career proclivities. After all, in the offbeat world of statistical exploration, one must always be prepared for a chuckle or two amidst the serious pursuit of knowledge.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Republican votes for Senators in Oklahoma and The number of transportation, storage, and distribution managers in Oklahoma. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State"

[[ABSTRACT]]
This paper delves into the unexpected correlations and connections between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers. Our team takes a lighthearted but data-driven approach to uncover the intriguing relationship between political preferences and occupational distribution in the Sooner State. Through the use of sophisticated statistical analysis, our findings reveal a remarkably high correlation coefficient (0.9769079) and a significant p-value (< 0.01) for the period spanning from 2003 to 2020. The results of this study are sure to provide both amusement and insight for political enthusiasts and labor market analysts alike. After all, who would have thought that political trends and professional networks could be so intertwined? Our analysis uncovers a perhaps unexpected parallel between the voting patterns and professional pursuits of Oklahomans, highlighting the unique dynamics at play in the state's socio-political fabric. So, buckle up and join us on this journey through the offbeat yet enlightening landscape of political and labor market connections!

[[INTRDUCTION]]
In the bustling world of political research, one might assume that the only connections worth noting are those between policymakers and their constituents. However, as any self-respecting statistician will tell you, the devil is in the details, and sometimes those details lead us to unexpected and downright wacky correlations. In this paper, we endeavor to unravel the enigmatic link between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state. Yes, you read that right - we're embarking on a statistical escapade that traverses the realms of politics and professional pursuits, armed with nothing but our trusty spreadsheets and a penchant for uncovering the absurd. So, grab your calculators and strap in for a bumpy ride through the wild world of data analysis!
Now, before you roll your eyes and dismiss our research as a mere exercise in statistical tomfoolery, consider this: the intersection of political ideologies and occupational demographics is not as straightforward as one might assume. We're not merely crunching numbers for the sake of it; we're diving headfirst into the intricate web of human behavior and societal dynamics. After all, who wouldn't want to know if there's a connection between casting ballots and managing boxes? It's the sort of quirky question that keeps researchers up at night - along with the occasional failed regression analysis.
With a cosmos of data at our fingertips, we set out to explore this intriguing nexus, armed with the knowledge that correlation does not necessarily imply causation, but hey, it sure does make for an entertaining research journey. So, fear not, dear reader, for we promise that in between the scatter plots and regression lines, there'll be a healthy dose of humor and lighthearted musings. After all, what's research without a few puns and unexpected revelations? We invite you to join us on this whimsical expedition as we unravel the fabric of Oklahoma's political and labor market landscape, one statistical quirk at a time. Fasten your seatbelts, the ride is about to get statistically wild!

[[RESULTS]]
As we delved into the data with the eagerness of explorers in uncharted statistical territory, we made a bewildering discovery - a striking correlation between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers in the state. With a correlation coefficient of 0.9769079, our jaws dropped faster than the p-value as we marveled at the strength of this unexpected relationship. The r-squared value of 0.9543491 further reinforced the robustness of this entangled web of political allegiance and professional career choices. It's safe to say; we were left shaking our heads and wondering what other surprising connections lay hidden within the realms of electoral trends and the labor market.
In Fig. 1, we present a scatterplot that visually encapsulates the remarkable correlation we uncovered. When we gazed upon this plot, the only thing scattered more than the data points were our preconceived notions of the demarcation between political inclinations and occupational pursuits. It's as if the data decided to take a joyride on the highway of correlation, leaving us all in a state of statistical bewilderment.
The significance of the p-value being less than 0.01 made us exclaim, "Well, isn't that statistically marvelous!" It seems that the intricate dance between political choices and professional roles in Oklahoma is not just a happenstance – at least not according to our data analysis.
So, there you have it – our statistical sleuthing has led us to an unexpected yet undeniable connection between Republican votes and the employment landscape in the Sooner State. If this doesn't make you go "hmm" and contemplate the whimsical nature of human decision-making, then we're not sure what will. Our findings serve as a reminder that in the world of research, one must always expect the unexpected – after all, uncertainty is the only certainty in statistics.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our statistical escapade has unraveled a delightfully bizarre connection between the Republican vote for senators in Oklahoma and the number of transportation, storage, and distribution managers - it seems the Sooner State's political landscapes and cargo crates are more entwined than a tangled slinky. Our findings showcase a correlation coefficient that practically makes the stars align, and a p-value that's rarer than a statistically significant unicorn. It's almost as if the voting booths and warehouse lots are engaged in a secret, synchronized dance - who knew politics and logistics had so much in common?

This whimsical journey through offbeat statistical realms has left us with more "aha" moments than a Eureka convention. While our results might leave some scratching their heads, we can't deny the allure of uncovering unexpected connections in the vast expanse of data. As much as we'd love to delve deeper into the intricacies of this wacky nexus, it seems that our findings have wrapped up this particular research yarn with a neat bow. There's no need to keep beating this statistical dead horse; our quest for quirky correlations has been satiated, at least for now.

So, dear readers and fellow data enthusiasts, it's time to bid adieu to this curious conundrum of Oklahoma's political preferences and professional pursuits. As we stow away our spreadsheets and bid farewell to the realm of statistical enchantment, let's not forget the lessons learned - in the enigmatic web of numbers, there's always room for the unexpected. After all, in the world of research, some statistical mysteries are best left to bask in their quirkiness. With that said, it's time for this statistical circus to raise its curtains and make way for new wonders beyond the confines of Oklahoma's Republican votes and managerial realms. Thank you for joining us on this comedic rollercoaster ride through the wild world of correlation and causation - until next time, may your data always lead you to delightful surprises and statistical merriment. And remember, when it comes to research, it's always best to expect the unexpected.


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 Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Econometrics


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 Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Economic and Political Analysis


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 Driven by Politics: The Republican Vote-Supply Chain Employment Nexus in the Sooner State with an abstract of This paper delves into the unexpected correlations and connections between Republican votes for Senators in Oklahoma and the number of transportation, storage, and distribution managers. Our team takes a lighthearted but data-driven approach to uncover the intriguing relationship between political preferences and occupational distribution in the Sooner State. Through the use of sophisticated statistical analysis, our findings reveal a remarkably high correlation coefficient (0.9769079) and a significant p-value (< 0.01) for the period spanning from 2003 to 2020. The results of this study are sure to provide both amusement and insight for political enthusiasts and labor market analysts alike. After all, who would have thought that political trends and professional networks could be so intertwined? Our analysis uncovers a perhaps unexpected parallel between the voting patterns and professional pursuits of Oklahomans, highlighting the unique dynamics at play in the state's socio-political fabric. So, buckle up and join us on this journey through the offbeat yet enlightening landscape of political and labor market connections!

ChatGPT:

Republican vote, Oklahoma, transportation managers, storage managers, distribution managers, political preferences, occupational distribution, statistical analysis, correlation coefficient, p-value, labor market, political trends, professional networks, voting patterns, socio-political fabric

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

The number of transportation, storage, and distribution managers in Oklahoma
Detailed data title: BLS estimate of transportation, storage, and distribution managers in Oklahoma
Source: Bureau of Larbor Statistics
See what else correlates with The number of transportation, storage, and distribution managers in Oklahoma

Correlation r = 0.9769079 (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 = 0.9543491 (Coefficient of determination)
This means 95.4% of the change in the one variable (i.e., The number of transportation, storage, and distribution managers in Oklahoma) is predictable based on the change in the other (i.e., Votes for Republican Senators in Oklahoma) over the 6 years from 2003 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00079. 0.0007937085138176157000000000
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 0.98 in 0.079% of random cases. Said differently, if you correlated 1,260 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.

[ 0.8, 1 ] 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.
200420082010201420162020
Votes for Republican Senators in Oklahoma (Total votes)7634337633757184821115170980892979140
The number of transportation, storage, and distribution managers in Oklahoma (Laborers)9701060950137012801210




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.




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([763433,763375,718482,1115170,980892,979140,])
array_2 = np.array([970,1060,950,1370,1280,1210,])
array_1_name = "Votes for Republican Senators in Oklahoma"
array_2_name = "The number of transportation, storage, and distribution managers in Oklahoma"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating is stellar!


Correlation ID: 4300 · Black Variable ID: 26301 · Red Variable ID: 13035
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0