Spurious correlation #4,413 · 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 Oklahoma and the second variable is The number of cabinetmakers in Oklahoma. The chart goes from 2003 to 2020, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Democratic Senators in Oklahoma and the second variable is The number of cabinetmakers in Oklahoma. The chart goes from 2003 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Democrat votes for Senators in Oklahoma decreased, there was a subsequent decline in political cabinet reshuffling. This led to less demand for new cabinets, ultimately impacting the number of cabinetmakers in the state. Politics and woodworking truly do have more in common than we think!

^{Show image generation prompt} Model: dalle-3
Prompt: [ Concept art ] In a cozy woodworking shop in Oklahoma, a group of Democratic voters gathers to discuss the latest Senate election results. On a nearby television screen, the decreasing number of Democrat votes for Senators in Oklahoma is mirrored by a decline in political cabinet reshufflings. This decrease in political activity is seen to have a tangible impact on the demand for new cabinets, reflected in the declining number of busy cabinetmakers working diligently in the shop. The interconnectedness of politics and woodworking is starkly evident in this local 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: Democrat votes for Senators in Oklahoma and The number of cabinetmakers 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: Brutalism Concept art Low poly a meme Cutsy graphics
ChatGPT: Concept 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 Democrat votes for Senators in Oklahoma and The number of cabinetmakers in Oklahoma, in the following situation: As Democrat votes for Senators in Oklahoma decreased, there was a subsequent decline in political cabinet reshuffling. This led to less demand for new cabinets, ultimately impacting the number of cabinetmakers in the state. Politics and woodworking truly do have more in common than we think!. Keep the description simple.
ChatGPT: In a cozy woodworking shop in Oklahoma, we see a group of Democratic voters discussing the latest Senate election results. As the number of Democrat votes for Senators in Oklahoma decreases, we observe a decrease in the number of political cabinet reshufflings on a nearby television screen. This decrease in political activity subsequently influences the demand for new cabinets, causing a decline in the number of busy cabinetmakers working diligently in the shop. The connection between politics and woodworking becomes clear in this local 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: [ Concept art ] and depicting this scene: In a cozy woodworking shop in Oklahoma, we see a group of Democratic voters discussing the latest Senate election results. As the number of Democrat votes for Senators in Oklahoma decreases, we observe a decrease in the number of political cabinet reshufflings on a nearby television screen. This decrease in political activity subsequently influences the demand for new cabinets, causing a decline in the number of busy cabinetmakers working diligently in the shop. The connection between politics and woodworking becomes clear in this local scene. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Concept art ] In a cozy woodworking shop in Oklahoma, a group of Democratic voters gathers to discuss the latest Senate election results. On a nearby television screen, the decreasing number of Democrat votes for Senators in Oklahoma is mirrored by a decline in political cabinet reshufflings. This decrease in political activity is seen to have a tangible impact on the demand for new cabinets, reflected in the declining number of busy cabinetmakers working diligently in the shop. The interconnectedness of politics and woodworking is starkly evident in this local 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.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Democrat votes for Senators in Oklahoma caused The number of cabinetmakers in Oklahoma to decrease.

AI academic paper

(Because p < 0.05)

Cabinetmakers and the OK Correlation: A Panel Data Analysis of Democrat Votes for Senators in Oklahoma

The Journal of Quirky Political Science Research

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Oklahoma and The number of cabinetmakers in Oklahoma. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Cabinetmakers and the OK Correlation: A Panel Data Analysis of Democrat Votes for Senators in Oklahoma

[[ABSTRACT]]
This research paper presents the surprising findings of the relationship between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team conducted a comprehensive analysis of the period from 2003 to 2020. Strangely enough, a robust correlation coefficient of 0.8785025 and a statistically significant p-value of less than 0.05 were observed, suggesting a connection between political preferences and the woodworking industry in the Sooner State.

The results of this study add a new dimension to our understanding of political behavior and economic activity. It seems that in Oklahoma, as the saying goes, "where there's a vote, there's a way... to make cabinets." Our findings may inspire further investigation into the peculiar intersection of partisan support and artisanal craftsmanship, while also shedding light on the unexplored dynamics of state-level political economies.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The field of political science has long been fascinated with uncovering the multitude of factors that influence voting behavior. From demographic characteristics to economic conditions, researchers have sought to untangle the complex web of influences that shape citizens' choices at the polls. However, one factor that has garnered surprisingly little attention in the literature is the relationship between the woodworking industry and political preferences. It's time to shed some light on this delightful woodwork of fate.
In the state of Oklahoma, where the wind comes sweepin' down the plain and the waving wheat sure smells sweet, there has been a notable pattern emerging in recent decades. While it's no secret that Oklahoma has a rich tradition of craftsmanship, particularly in the art of cabinetmaking, our research sheds new light on the unexpected connection between the number of artisanal cabinetmakers and the voting behavior of Democrats in the state. Who knew that a love for handcrafted furniture could also influence political decisions? It seems that in Oklahoma, even the humble cabinet holds a key to understanding the political landscape. Cabinets may store dishes, but they also seem to hold political wishes.
This study aims to explore this curious relationship by utilizing sophisticated panel data analysis methods, combining data from the MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics. By examining the period from 2003 to 2020, a comprehensive understanding of the correlation between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state will be elucidated. This is not just another tenuous link; it's the real wood deal.
By delving into this novel intersection of political behavior and economic activity, our research contributes to the fields of political science and economics, while also injecting a sense of whimsy into the otherwise serious world of academic research. After all, who would have thought that the halls of governance could be inadvertently influenced by the halls of cabinetry? Sometimes, it seems, the wooden path to understanding leads to the voting booth.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The scholarly inquiry into the connection between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state has been notably scant, with researchers predominantly focusing on more conventional determinants of political support. Smith et al. (2015) examined the influence of demographic characteristics and economic conditions on voting behavior, neglecting to consider the potential impact of woodworking activities. Meanwhile, Doe and Jones (2018) delved into the dynamics of political economies at the state level, but did not venture into the realm of artisanal craftsmanship and its intersection with partisan allegiances.

In "Woodworking and Political Ties" by Carpenter (2013), the author posits a tangential connection between the woodworking industry and political preferences, albeit in a more abstract sense. However, the empirical investigation of this postulation remains a lacuna in the existing literature. With the emergence of our research, the proverbial sawdust of neglect surrounding this enthralling link is finally being swept away.

Drawing on real-life and fictional literary works, the present authors find unexpected sources that shed light on the potential nexus between cabinetmaking and political attitudes. "Cabinets and Senators: A Tale of Two Fixtures" by Ellis examines the coalescence of state politics and fine carpentry, weaving an engrossing narrative that provides a fictional yet stirring portrayal of the conjectured relationship. Similarly, "Wooden Ballots: An Artisan's Perspective" by Hemingway offers a literary exploration of the wooden path to understanding political preferences, affirming the captivating allure of woodworking in the realm of democratic decision-making.

Further adding to the eclectic sources contributing to this area of investigation, the whimsical yet insightful cartoons and children's shows of yesteryears resonate with the theme at hand. The lovable duo from "The Woodpecker and the Pollster" impart subtle hints at the peculiar connection between woodworking and electoral choices, perhaps more inadvertently than intentionally. Moreover, the timeless lessons from "Bob the Builder" and his cohorts offer an animated commentary on the constructive nature of political participation, albeit in a markedly metaphorical sense.

As the scholarly exploration delves into uncharted territories, the unexpected humor and levity that accompany the findings are akin to a well-crafted dovetail joint – seamlessly integrating with the serious intent of academic inquiry. With an arsenal of puns and comedic asides, the present analysis aims to chisel away at the stoic facade of scholarly writing, unveiling the effervescent charm of a topic that has remained hidden in plain sight. After all, as every woodworker knows, a good joke is like a well-oiled saw: it cuts to the chase.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Oklahoma and The number of cabinetmakers in Oklahoma. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Cabinetmakers and the OK Correlation: A Panel Data Analysis of Democrat Votes for Senators in Oklahoma

[[ABSTRACT]]
This research paper presents the surprising findings of the relationship between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team conducted a comprehensive analysis of the period from 2003 to 2020. Strangely enough, a robust correlation coefficient of 0.8785025 and a statistically significant p-value of less than 0.05 were observed, suggesting a connection between political preferences and the woodworking industry in the Sooner State.

The results of this study add a new dimension to our understanding of political behavior and economic activity. It seems that in Oklahoma, as the saying goes, "where there's a vote, there's a way... to make cabinets." Our findings may inspire further investigation into the peculiar intersection of partisan support and artisanal craftsmanship, while also shedding light on the unexplored dynamics of state-level political economies.

[[LITERATURE REVIEW]]
The scholarly inquiry into the connection between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state has been notably scant, with researchers predominantly focusing on more conventional determinants of political support. Smith et al. (2015) examined the influence of demographic characteristics and economic conditions on voting behavior, neglecting to consider the potential impact of woodworking activities. Meanwhile, Doe and Jones (2018) delved into the dynamics of political economies at the state level, but did not venture into the realm of artisanal craftsmanship and its intersection with partisan allegiances.
In "Woodworking and Political Ties" by Carpenter (2013), the author posits a tangential connection between the woodworking industry and political preferences, albeit in a more abstract sense. However, the empirical investigation of this postulation remains a lacuna in the existing literature. With the emergence of our research, the proverbial sawdust of neglect surrounding this enthralling link is finally being swept away.
Drawing on real-life and fictional literary works, the present authors find unexpected sources that shed light on the potential nexus between cabinetmaking and political attitudes. "Cabinets and Senators: A Tale of Two Fixtures" by Ellis examines the coalescence of state politics and fine carpentry, weaving an engrossing narrative that provides a fictional yet stirring portrayal of the conjectured relationship. Similarly, "Wooden Ballots: An Artisan's Perspective" by Hemingway offers a literary exploration of the wooden path to understanding political preferences, affirming the captivating allure of woodworking in the realm of democratic decision-making.
Further adding to the eclectic sources contributing to this area of investigation, the whimsical yet insightful cartoons and children's shows of yesteryears resonate with the theme at hand. The lovable duo from "The Woodpecker and the Pollster" impart subtle hints at the peculiar connection between woodworking and electoral choices, perhaps more inadvertently than intentionally. Moreover, the timeless lessons from "Bob the Builder" and his cohorts offer an animated commentary on the constructive nature of political participation, albeit in a markedly metaphorical sense.
As the scholarly exploration delves into uncharted territories, the unexpected humor and levity that accompany the findings are akin to a well-crafted dovetail joint – seamlessly integrating with the serious intent of academic inquiry. With an arsenal of puns and comedic asides, the present analysis aims to chisel away at the stoic facade of scholarly writing, unveiling the effervescent charm of a topic that has remained hidden in plain sight. After all, as every woodworker knows, a good joke is like a well-oiled saw: it cuts to the chase.

[[RESULTS]]
The analysis of the data revealed a strong positive correlation between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. The correlation coefficient was calculated to be 0.8785025, indicating a robust relationship between these seemingly disparate variables. It appears that in the land of Oklahoma, where the skies are so blue, there's also a link between political inclinations and the craftsmanship of cabinets. Perhaps we should start calling it the "OK Cabinet Correlation."
Furthermore, the r-squared value of 0.7717666 suggests that approximately 77.18% of the variation in Democrat votes for Senators in Oklahoma can be explained by the variation in the number of cabinetmakers in the state. This substantial explanatory power indicates that the presence of artisanal cabinetmakers has a considerable influence on the political landscape of Oklahoma, adding a new layer of depth to the phrase "carving out a political niche."
In addition, the p-value of less than 0.05 provides compelling evidence to reject the null hypothesis of no relationship between the variables. This result further strengthens the case for a significant association between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. It seems there's no need for a recount when the numbers speak for themselves in such a convincing manner.
These findings are visually depicted in Figure 1, a scatterplot illustrating the remarkably strong correlation between Democrat votes for Senators and the number of cabinetmakers in Oklahoma. The plot showcases the undeniable trend, leaving little room for doubt about the surprising interconnectedness of political preferences and the woodworking trade. It's a plot twist that even the most seasoned political analysts might not have seen coming.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study present a compelling case for the existence of a strong positive correlation between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. The robust correlation coefficient of 0.8785025 and the statistically significant p-value provide persuasive evidence of this peculiar relationship. It appears that in the "Sooner State," there is indeed a remarkable bond between political leanings and the craft of cabinetmaking. One could say that, in Oklahoma, the political landscape is not just cut and dried, but also carefully carved and crafted.

These results substantiate the prior research that has ventured into the unexplored territory of artisanal craftsmanship intersecting with political behaviors. While previous studies have primarily focused on conventional determinants of political support, such as demographic characteristics and economic conditions, our findings suggest that the influence of woodworking activities cannot be brushed aside. As the saying goes, "Where there's a will, there's a woodworking skill."

Our study complements and extends the work of Carpenter (2013), who had speculated on the tangential connection between the woodworking industry and political preferences. The empirical evidence in our research offers a solid foothold in the realm of artisanal craftsmanship and its intersection with partisan allegiances, paving the way for a more nuanced understanding of the intricate interplay between the two domains. Much like a precision-crafted dovetail joint, the findings fit neatly into the existing body of literature, adding substance to Carpenter's theoretical foundation.

Furthermore, our results align with the whimsical yet insightful sources identified in the literature review, such as the fictional narratives and lovable characters from noteworthy literary works and children's shows. The unexpected humor and levity accompanying the findings enrich the scholarly discourse, akin to the finishing touches on a well-crafted piece of furniture. As Bob the Builder would say, "Can we correlate it? Yes, we can!"

The substantial explanatory power of approximately 77.18%, as indicated by the r-squared value, underscores the influential role of artisanal cabinetmakers in shaping the political landscape of Oklahoma. Much like the careful precision required in woodworking, the presence of cabinetmakers seems to intricately carve out a significant influence on political preferences, chiseling a new dimension into the understanding of state-level political economies.

In light of these results, it becomes evident that the "OK Cabinet Correlation" is not merely a surprising statistical artefact but a meaningful and substantial relationship with real-world implications. The scatterplot in Figure 1 serves as a visual testament to this unexpected interconnectedness, leaving no room for doubt about the curious bond between political inclinations and the woodworking trade. It seems that when it comes to politics and craftsmanship in Oklahoma, there's a lot more than meets the eye, much like a well-hidden dovetail joint waiting to be discovered.

In conclusion, our study not only adds an intriguing nuance to the understanding of political behavior and economic activity but also highlights the significance of exploring unconventional factors that may shape political preferences. The unexpected correlation between Democrat votes for Senators and the number of cabinetmakers in Oklahoma paves the way for further interdisciplinary inquiry into the enthralling link between woodworking and electoral choices. As we unravel the layers of this unexpected relationship, it becomes increasingly clear that in the boundless landscape of political inquiry, truth can indeed be stranger than fiction.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Oklahoma and The number of cabinetmakers in Oklahoma. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Cabinetmakers and the OK Correlation: A Panel Data Analysis of Democrat Votes for Senators in Oklahoma

[[ABSTRACT]]
This research paper presents the surprising findings of the relationship between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team conducted a comprehensive analysis of the period from 2003 to 2020. Strangely enough, a robust correlation coefficient of 0.8785025 and a statistically significant p-value of less than 0.05 were observed, suggesting a connection between political preferences and the woodworking industry in the Sooner State.

The results of this study add a new dimension to our understanding of political behavior and economic activity. It seems that in Oklahoma, as the saying goes, "where there's a vote, there's a way... to make cabinets." Our findings may inspire further investigation into the peculiar intersection of partisan support and artisanal craftsmanship, while also shedding light on the unexplored dynamics of state-level political economies.

[[INTRDUCTION]]
The field of political science has long been fascinated with uncovering the multitude of factors that influence voting behavior. From demographic characteristics to economic conditions, researchers have sought to untangle the complex web of influences that shape citizens' choices at the polls. However, one factor that has garnered surprisingly little attention in the literature is the relationship between the woodworking industry and political preferences. It's time to shed some light on this delightful woodwork of fate.
In the state of Oklahoma, where the wind comes sweepin' down the plain and the waving wheat sure smells sweet, there has been a notable pattern emerging in recent decades. While it's no secret that Oklahoma has a rich tradition of craftsmanship, particularly in the art of cabinetmaking, our research sheds new light on the unexpected connection between the number of artisanal cabinetmakers and the voting behavior of Democrats in the state. Who knew that a love for handcrafted furniture could also influence political decisions? It seems that in Oklahoma, even the humble cabinet holds a key to understanding the political landscape. Cabinets may store dishes, but they also seem to hold political wishes.
This study aims to explore this curious relationship by utilizing sophisticated panel data analysis methods, combining data from the MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics. By examining the period from 2003 to 2020, a comprehensive understanding of the correlation between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state will be elucidated. This is not just another tenuous link; it's the real wood deal.
By delving into this novel intersection of political behavior and economic activity, our research contributes to the fields of political science and economics, while also injecting a sense of whimsy into the otherwise serious world of academic research. After all, who would have thought that the halls of governance could be inadvertently influenced by the halls of cabinetry? Sometimes, it seems, the wooden path to understanding leads to the voting booth.

[[RESULTS]]
The analysis of the data revealed a strong positive correlation between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. The correlation coefficient was calculated to be 0.8785025, indicating a robust relationship between these seemingly disparate variables. It appears that in the land of Oklahoma, where the skies are so blue, there's also a link between political inclinations and the craftsmanship of cabinets. Perhaps we should start calling it the "OK Cabinet Correlation."
Furthermore, the r-squared value of 0.7717666 suggests that approximately 77.18% of the variation in Democrat votes for Senators in Oklahoma can be explained by the variation in the number of cabinetmakers in the state. This substantial explanatory power indicates that the presence of artisanal cabinetmakers has a considerable influence on the political landscape of Oklahoma, adding a new layer of depth to the phrase "carving out a political niche."
In addition, the p-value of less than 0.05 provides compelling evidence to reject the null hypothesis of no relationship between the variables. This result further strengthens the case for a significant association between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. It seems there's no need for a recount when the numbers speak for themselves in such a convincing manner.
These findings are visually depicted in Figure 1, a scatterplot illustrating the remarkably strong correlation between Democrat votes for Senators and the number of cabinetmakers in Oklahoma. The plot showcases the undeniable trend, leaving little room for doubt about the surprising interconnectedness of political preferences and the woodworking trade. It's a plot twist that even the most seasoned political analysts might not have seen coming.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, it is evident that our study has unveiled a compelling relationship between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. The results provide clear support for the notion that in Oklahoma, political inclinations are indeed intertwined with the presence of skilled artisans crafting their way through the woodworking industry. It seems that in the realm of politics, as in the workshop, every vote and every chisel make a difference. These findings certainly drive home the point that in Oklahoma, when it comes to politics, there's more than one "cabinet" reshuffling going on.

Furthermore, our research underscores the importance of considering unconventional factors in understanding political behaviors at the state level. As the old adage goes, "the devil is in the details," and it appears that even intricate woodworking has a devilish influence on political decision-making in Oklahoma. It seems that when it comes to voter preferences, the state's residents are not just choosing Senators; they are also shaping the contours of artisanal craftsmanship – a testament to the depth and breadth of democratic expression.

This study raises some important questions for future research. For instance, we may ponder how the influence of cabinetmakers in Oklahoma compares to other craft industries, or whether similar patterns exist in states with rich traditions of woodworking. One thing is for sure: when it comes to political analysis, it's time to stop "sawing" what's obvious and start "hammering out" the less apparent connections – and that's no "joint" decision!

In light of these findings, it is clear that further study in this area is unnecessary. We can confidently "nail" down the understanding that in Oklahoma, Democrat votes for Senators and the number of cabinetmakers are, indeed, significantly correlated. It seems there's "wood" be little point in continuing to "polish" this research topic any further.

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 Cabinetmakers and the OK Correlation: A Panel Data Analysis of Democrat Votes for Senators in Oklahoma. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Political Science Research

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 Cabinetmakers and the OK Correlation: A Panel Data Analysis of Democrat Votes for Senators in Oklahoma. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Historical Woodworking Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Cabinetmakers and the OK Correlation: A Panel Data Analysis of Democrat Votes for Senators in Oklahoma with an abstract of This research paper presents the surprising findings of the relationship between Democrat votes for Senators in Oklahoma and the number of cabinetmakers in the state. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Bureau of Labor Statistics, our research team conducted a comprehensive analysis of the period from 2003 to 2020. Strangely enough, a robust correlation coefficient of 0.8785025 and a statistically significant p-value of less than 0.05 were observed, suggesting a connection between political preferences and the woodworking industry in the Sooner State.
The results of this study add a new dimension to our understanding of political behavior and economic activity. It seems that in Oklahoma, as the saying goes, "where there's a vote, there's a way... to make cabinets." Our findings may inspire further investigation into the peculiar intersection of partisan support and artisanal craftsmanship, while also shedding light on the unexplored dynamics of state-level political economies.

ChatGPT:

Democrat votes, Senators, Oklahoma, cabinetmakers, panel data analysis, MIT Election Data and Science Lab, Harvard Dataverse, Bureau of Labor Statistics, political preferences, woodworking industry, correlation coefficient, p-value, political behavior, economic activity, partisan support, artisanal craftsmanship, state-level political economies

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

The number of cabinetmakers in Oklahoma
Detailed data title: BLS estimate of cabinetmakers and bench carpenters in Oklahoma
Source: Bureau of Larbor Statistics
See what else correlates with The number of cabinetmakers in Oklahoma

Correlation r = 0.8785025 (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 = 0.7717666 (Coefficient of determination)
This means 77.2% of the change in the one variable (i.e., The number of cabinetmakers in Oklahoma) is predictable based on the change in the other (i.e., Votes for Democratic Senators in Oklahoma) over the 6 years from 2003 through 2020.

p < 0.05, which statistically significant(Null hypothesis significance test)
The p-value is 0.021.^Show 0.0212457261262156380000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.88 in 2.1% of random cases. Said differently, if you correlated 47 random variables^Note Which I absolutely did.
with the same 5 degrees of freedom, ^Note 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.

[ 0.23, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2004	2008	2010	2014	2016	2020
Votes for Democratic Senators in Oklahoma (Total votes)	596750	527736	265814	472230	355911	509763
The number of cabinetmakers in Oklahoma (Laborers)	1570	1520	740	900	950	1480

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([596750,527736,265814,472230,355911,509763,])
array_2 = np.array([1570,1520,740,900,950,1480,])
array_1_name = "Votes for Democratic Senators in Oklahoma"
array_2_name = "The number of cabinetmakers 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. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Votes for Democratic Senators in Oklahoma
Line chart for only The number of cabinetmakers in Oklahoma
AI-generated correlation image
The spurious research paper: Cabinetmakers and the OK Correlation: A Panel Data Analysis of Democrat Votes for Senators in Oklahoma

View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!

Correlation ID: 4413 · Black Variable ID: 26299 · Red Variable ID: 13252


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