Spurious correlation #4,464 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Annual US household spending on tobacco products and smoking supplies and the second variable is Votes for Democratic Senators in Minnesota. The chart goes from 2000 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 Annual US household spending on tobacco products and smoking supplies and the second variable is Votes for Democratic Senators in Minnesota. The chart goes from 2000 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As household spending on tobacco products and smoking supplies increased, there was a corresponding increase in the production of smoke. This led to the formation of smoke signals, inadvertently influencing the voters in Minnesota. The correlation suggests that as more smoke filled the air, it carried subliminal messages favoring Democratic senators, ultimately swaying the election outcomes. This is, of course, a preposterous and whimsical notion with no scientific basis.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a cozy Minnesota neighborhood, where houses are nestled among vibrant trees. In the backyard of a home, a family's spending on tobacco products and smoking supplies is increasing. As smoke rises from the backyard, it mingles in the air with the autumn breeze, forming gentle, whimsical smoke signals. These signals carry across the neighborhood, weaving through the air, ultimately reaching the Minnesotan voters. The smoke creates a mystical ambiance, subtly influencing the voters' choice in favor of the Democratic senators. The style of the image should evoke elements of Brutalism. 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: Annual US household spending on tobacco products and smoking supplies and Democrat votes for Senators in Minnesota. 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 Cutsy graphics Cute cartoon Cute 2D animation Concept art
ChatGPT: Brutalism

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 Annual US household spending on tobacco products and smoking supplies and Democrat votes for Senators in Minnesota, in the following situation: As household spending on tobacco products and smoking supplies increased, there was a corresponding increase in the production of smoke. This led to the formation of smoke signals, inadvertently influencing the voters in Minnesota. The correlation suggests that as more smoke filled the air, it carried subliminal messages favoring Democratic senators, ultimately swaying the election outcomes. This is, of course, a preposterous and whimsical notion with no scientific basis.. Keep the description simple.
ChatGPT: Imagine a cozy Minnesota neighborhood, with houses nestled among vibrant trees. In the backyard of a home, you see a family's annual spending on tobacco products and smoking supplies increase. As smoke rises from the backyard, it mingles in the air with the autumn breeze, forming gentle, whimsical smoke signals. These signals carry across the neighborhood, weaving through the air, ultimately reaching the Minnesotan voters. The smoke creates a mystical ambiance, subtly influencing the voters' choice in favor of the Democratic senators.

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: [ Brutalism ] and depicting this scene: Imagine a cozy Minnesota neighborhood, with houses nestled among vibrant trees. In the backyard of a home, you see a family's annual spending on tobacco products and smoking supplies increase. As smoke rises from the backyard, it mingles in the air with the autumn breeze, forming gentle, whimsical smoke signals. These signals carry across the neighborhood, weaving through the air, ultimately reaching the Minnesotan voters. The smoke creates a mystical ambiance, subtly influencing the voters' choice in favor of the Democratic senators. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a cozy Minnesota neighborhood, where houses are nestled among vibrant trees. In the backyard of a home, a family's spending on tobacco products and smoking supplies is increasing. As smoke rises from the backyard, it mingles in the air with the autumn breeze, forming gentle, whimsical smoke signals. These signals carry across the neighborhood, weaving through the air, ultimately reaching the Minnesotan voters. The smoke creates a mystical ambiance, subtly influencing the voters' choice in favor of the Democratic senators. The style of the image should evoke elements of Brutalism.

*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 increases in Annual US household spending on tobacco products and smoking supplies positively influenced Democrat votes for Senators in Minnesota.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

Up in Smoke: An Analysis of the Relationship Between Tobacco Spending and Democratic Votes in Minnesota

The Journal of Whimsical Political Science

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 Annual US household spending on tobacco products and smoking supplies and Democrat votes for Senators in Minnesota. 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]]
"Up in Smoke: An Analysis of the Relationship Between Tobacco Spending and Democratic Votes in Minnesota"

[[ABSTRACT]]
This research paper delves into the intriguing correlation between annual US household spending on tobacco products and smoking supplies and the votes for Democratic senators in the state of Minnesota. By utilizing data from the Bureau of Labor Statistics and MIT Election Data and Science Lab, Harvard Dataverse, we sought to uncover the potential connection between these seemingly unrelated variables. Our findings revealed a remarkably high correlation coefficient of 0.9570897, with a p-value of less than 0.01 for the years 2000 to 2020, suggesting a compelling association between smoking-related expenditures and political preferences. This unexpected correlation sparks curiosity and raises questions about the nuanced dynamics of consumer behavior and its implications for electoral outcomes. Our analysis prompts further investigation into the underlying mechanisms driving this relationship, shedding light on the potential influences of smoking culture on political affiliations in the Land of 10,000 Lakes.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The smoke has cleared, and what remains is a remarkable correlation between annual US household spending on tobacco products and smoking supplies and the votes for Democratic senators in the state of Minnesota. This unexpected relationship has piqued our curiosity and left us pondering the nuanced dynamics of consumer behavior and its connection to political inclinations.
Upon first hearing of this correlation, one might think, "That's a lot of smoke and mirrors!" But alas, our analysis, based on data from the Bureau of Labor Statistics and MIT Election Data and Science Lab, Harvard Dataverse, has revealed a correlation coefficient so high, it might as well be chain-smoking at a statistical significance level. With a correlation coefficient of 0.9570897 and a p-value of less than 0.01 for the years 2000 to 2020, it appears that there's more than just smoke signals at play here.
As researchers, we have become accustomed to dealing with smoke and mirrors, but the strength of this correlation has us pondering whether there might be a "smoking gun" lurking in the data. Could it be that the aroma of tobacco spending wafts through the political landscape, influencing voting preferences without us even realizing it? Such unexpected findings prompt us to delve deeper into the potential influences of smoking culture on political affiliations in the Land of 10,000 Lakes.
Stay tuned as we embark on a journey to unravel the mystery behind this peculiar relationship, shedding light on how something as seemingly unrelated as tobacco spending could have a significant impact on political behaviors. This paper aims to ignite further interest and discussion on the intersection of consumer behavior and political outcomes, reminding us that in the world of research, sometimes the most unexpected connections can lead to the most enlightening discoveries.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The relationship between consumer behavior and political affiliations has long been a subject of interest for researchers in various fields. Smith (2010) conducted a detailed analysis of household expenditure patterns and their potential influence on voting preferences. Their work introduced the idea that consumer habits could extend beyond mere economic implications, offering valuable insights into the behavioral underpinnings of electoral decisions. Building upon this foundation, Doe and Jones (2015) further explored the intricate connections between seemingly unrelated consumer expenditures and political inclinations, paving the way for a deeper understanding of the complex interplay between consumer behavior and democratic processes.

Moving beyond traditional academic sources, the authors draw inspiration from non-fiction literature to explore the broader cultural and societal influences that may underpin the observed relationship. In "The Economics of Vice" by Teeman (2019), the author delves into the economic impact of indulgences such as smoking and the potential implications for broader socio-political trends. The interdisciplinary nature of this research necessitates an exploration of unconventional sources that shed light on the multifaceted dimensions of the topic at hand.

In the realm of fiction, the authors draw attention to literary works that, albeit not grounded in empirical research, offer intriguing narratives that touch upon the intersection of consumer habits and political dynamics. Fictional narratives have the power to capture societal nuances and mirror the complexities of human behavior, offering valuable insights that transcend the boundaries of empirical analyses. In "The Smoke Thief" by Abe, the intertwining of smoke - albeit of a different kind - with political intrigue serves as a thought-provoking departure point for considering the unexpected ways in which seemingly unrelated elements can converge.

From literature to popular culture, the authors expand their inquiry to include non-traditional sources of insight. Television series such as "Mad Men" and "Breaking Bad" offer intriguing portrayals of the societal dynamics surrounding smoking culture, providing an unconventional lens through which to examine the potential influences of tobacco expenditure on political preferences. Furthermore, cartoons such as "The Flintstones," with its playful yet emblematic depiction of smoking culture, prompt the rethinking of the societal perceptions and implications of tobacco-related expenditures.

In uncovering the association between annual US household spending on tobacco products and smoking supplies and Democratic votes for Senators in Minnesota, the authors draw upon an eclectic array of sources, encompassing academic literature, non-fiction works, fiction narratives, and popular culture. This integrative approach serves to illuminate the multifaceted nature of the topic and underscores the potential for unexpected insights to emerge from diverse sources, offering a scholarly journey that transcends the usual confines of academic inquiry.

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 Annual US household spending on tobacco products and smoking supplies and Democrat votes for Senators in Minnesota. 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]]
"Up in Smoke: An Analysis of the Relationship Between Tobacco Spending and Democratic Votes in Minnesota"

[[ABSTRACT]]
This research paper delves into the intriguing correlation between annual US household spending on tobacco products and smoking supplies and the votes for Democratic senators in the state of Minnesota. By utilizing data from the Bureau of Labor Statistics and MIT Election Data and Science Lab, Harvard Dataverse, we sought to uncover the potential connection between these seemingly unrelated variables. Our findings revealed a remarkably high correlation coefficient of 0.9570897, with a p-value of less than 0.01 for the years 2000 to 2020, suggesting a compelling association between smoking-related expenditures and political preferences. This unexpected correlation sparks curiosity and raises questions about the nuanced dynamics of consumer behavior and its implications for electoral outcomes. Our analysis prompts further investigation into the underlying mechanisms driving this relationship, shedding light on the potential influences of smoking culture on political affiliations in the Land of 10,000 Lakes.

[[LITERATURE REVIEW]]
The relationship between consumer behavior and political affiliations has long been a subject of interest for researchers in various fields. Smith (2010) conducted a detailed analysis of household expenditure patterns and their potential influence on voting preferences. Their work introduced the idea that consumer habits could extend beyond mere economic implications, offering valuable insights into the behavioral underpinnings of electoral decisions. Building upon this foundation, Doe and Jones (2015) further explored the intricate connections between seemingly unrelated consumer expenditures and political inclinations, paving the way for a deeper understanding of the complex interplay between consumer behavior and democratic processes.
Moving beyond traditional academic sources, the authors draw inspiration from non-fiction literature to explore the broader cultural and societal influences that may underpin the observed relationship. In "The Economics of Vice" by Teeman (2019), the author delves into the economic impact of indulgences such as smoking and the potential implications for broader socio-political trends. The interdisciplinary nature of this research necessitates an exploration of unconventional sources that shed light on the multifaceted dimensions of the topic at hand.
In the realm of fiction, the authors draw attention to literary works that, albeit not grounded in empirical research, offer intriguing narratives that touch upon the intersection of consumer habits and political dynamics. Fictional narratives have the power to capture societal nuances and mirror the complexities of human behavior, offering valuable insights that transcend the boundaries of empirical analyses. In "The Smoke Thief" by Abe, the intertwining of smoke - albeit of a different kind - with political intrigue serves as a thought-provoking departure point for considering the unexpected ways in which seemingly unrelated elements can converge.
From literature to popular culture, the authors expand their inquiry to include non-traditional sources of insight. Television series such as "Mad Men" and "Breaking Bad" offer intriguing portrayals of the societal dynamics surrounding smoking culture, providing an unconventional lens through which to examine the potential influences of tobacco expenditure on political preferences. Furthermore, cartoons such as "The Flintstones," with its playful yet emblematic depiction of smoking culture, prompt the rethinking of the societal perceptions and implications of tobacco-related expenditures.
In uncovering the association between annual US household spending on tobacco products and smoking supplies and Democratic votes for Senators in Minnesota, the authors draw upon an eclectic array of sources, encompassing academic literature, non-fiction works, fiction narratives, and popular culture. This integrative approach serves to illuminate the multifaceted nature of the topic and underscores the potential for unexpected insights to emerge from diverse sources, offering a scholarly journey that transcends the usual confines of academic inquiry.

[[RESULTS]]
The results of our analysis unveiled a striking correlation between annual US household spending on tobacco products and smoking supplies and the votes for Democratic senators in Minnesota. The correlation coefficient of 0.9570897 indicates a remarkably strong positive relationship between these variables. This finding suggests that as tobacco spending and smoking supplies increase, Democratic votes for senators in Minnesota also tend to rise, creating a smokin' hot association that may have political implications hotter than a lit cigarette.
The high r-squared value of 0.9160206 suggests that a substantial proportion of the variation in Democrat votes for senators in Minnesota can be explained by the variation in annual household spending on tobacco products and smoking supplies. It seems that as tobacco spending goes up, so does the democratic vote count – a statistical trend more consistent than a pack-a-day smoker's routine.
Furthermore, with a p-value of less than 0.01, the likelihood of observing such a strong correlation by random chance alone is about as rare as finding a clove cigarette in a haystack. This level of statistical significance suggests that there's a robust relationship between tobacco spending and political preference in Minnesota, proving that this correlation is more than just a statistical smokescreen.
Fig. 1 presents a visual representation of this remarkable correlation, displaying a scatterplot that showcases the tight relationship between annual US household spending on tobacco products and smoking supplies and Democrat votes for Senators in Minnesota. The data points are as tightly packed as a fresh pack of cigarettes, leaving no room for doubt about the strength of this relationship.
In conclusion, our findings highlight the unexpected impact of tobacco spending on political preferences in Minnesota. This unusual connection sparks further inquiry into the underlying mechanisms driving this relationship, demonstrating the potential influences of smoking culture on political affiliations in the state. As research continues, the aroma of tobacco spending in the political landscape continues to intrigue and beguile, reminding us that sometimes the unlikeliest pairings can yield the most illuminating insights.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have unearthed a rather surprising relationship between annual US household spending on tobacco products and smoking supplies and Democratic votes for Senators in Minnesota. This unexpected correlation, with a correlation coefficient of 0.9570897 and a p-value of less than 0.01, suggests a connection that is as undeniable as the urge for a post-lunch smoke break.

Our findings complement the previous research by Smith (2010) and Doe and Jones (2015), who laid the groundwork for understanding how consumer behavior may extend its tendrils into the political realm. As we grapple with the implications of our results, it becomes clear that the impact of smoking culture on political alliances may be more than just blowing smoke – it could be a determining factor in electoral outcomes.

Harkening back to our literature review, we recall the insights gleaned from "The Smoke Thief" by Abe, albeit a fictional work. The intertwining of smoke – albeit of a different kind – with political intrigue now resonates more profoundly, as our empirical findings lend credence to the notion that seemingly unrelated elements can converge in unexpected ways. Similarly, the societal dynamics portrayed in television series such as "Mad Men" and "Breaking Bad" take on a new significance, as they provide a lens through which to examine the potential influences of tobacco expenditure on political preferences. Who would have thought that Don Draper's cigarette breaks could hold such sway over political leanings?

On a statistical note, the remarkably high correlation coefficient and r-squared value underscore the robustness of the relationship uncovered in our analysis. The level of statistical significance, with a p-value of less than 0.01, solidifies the credibility of our findings, demonstrating that the association between tobacco spending and Democratic votes for Senators in Minnesota is more than just a statistical anomaly. It seems that the aroma of tobacco spending wafts through the voting booths in Minnesota, leaving an imprint on electoral outcomes that is as pronounced and undeniable as the smell of cigar smoke in a small room.

As we continue to unravel the nuances of this unexpected correlation, engaging in further inquiry and analysis, it is evident that the influence of tobacco spending on political preferences in Minnesota presents a realm of exploration that is as tantalizing as a forbidden puff on a cigar. Our study marks a significant step in understanding the intricate dance between consumer behavior and political affiliations, shedding light on the unanticipated ways in which the two domains intersect – and perhaps, sparking a flicker of curiosity in the minds of researchers and policymakers alike, akin to the glow of a freshly lit cigarette in the twilight.

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 Annual US household spending on tobacco products and smoking supplies and Democrat votes for Senators in Minnesota. 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]]
"Up in Smoke: An Analysis of the Relationship Between Tobacco Spending and Democratic Votes in Minnesota"

[[ABSTRACT]]
This research paper delves into the intriguing correlation between annual US household spending on tobacco products and smoking supplies and the votes for Democratic senators in the state of Minnesota. By utilizing data from the Bureau of Labor Statistics and MIT Election Data and Science Lab, Harvard Dataverse, we sought to uncover the potential connection between these seemingly unrelated variables. Our findings revealed a remarkably high correlation coefficient of 0.9570897, with a p-value of less than 0.01 for the years 2000 to 2020, suggesting a compelling association between smoking-related expenditures and political preferences. This unexpected correlation sparks curiosity and raises questions about the nuanced dynamics of consumer behavior and its implications for electoral outcomes. Our analysis prompts further investigation into the underlying mechanisms driving this relationship, shedding light on the potential influences of smoking culture on political affiliations in the Land of 10,000 Lakes.

[[INTRDUCTION]]
The smoke has cleared, and what remains is a remarkable correlation between annual US household spending on tobacco products and smoking supplies and the votes for Democratic senators in the state of Minnesota. This unexpected relationship has piqued our curiosity and left us pondering the nuanced dynamics of consumer behavior and its connection to political inclinations.
Upon first hearing of this correlation, one might think, "That's a lot of smoke and mirrors!" But alas, our analysis, based on data from the Bureau of Labor Statistics and MIT Election Data and Science Lab, Harvard Dataverse, has revealed a correlation coefficient so high, it might as well be chain-smoking at a statistical significance level. With a correlation coefficient of 0.9570897 and a p-value of less than 0.01 for the years 2000 to 2020, it appears that there's more than just smoke signals at play here.
As researchers, we have become accustomed to dealing with smoke and mirrors, but the strength of this correlation has us pondering whether there might be a "smoking gun" lurking in the data. Could it be that the aroma of tobacco spending wafts through the political landscape, influencing voting preferences without us even realizing it? Such unexpected findings prompt us to delve deeper into the potential influences of smoking culture on political affiliations in the Land of 10,000 Lakes.
Stay tuned as we embark on a journey to unravel the mystery behind this peculiar relationship, shedding light on how something as seemingly unrelated as tobacco spending could have a significant impact on political behaviors. This paper aims to ignite further interest and discussion on the intersection of consumer behavior and political outcomes, reminding us that in the world of research, sometimes the most unexpected connections can lead to the most enlightening discoveries.

[[RESULTS]]
The results of our analysis unveiled a striking correlation between annual US household spending on tobacco products and smoking supplies and the votes for Democratic senators in Minnesota. The correlation coefficient of 0.9570897 indicates a remarkably strong positive relationship between these variables. This finding suggests that as tobacco spending and smoking supplies increase, Democratic votes for senators in Minnesota also tend to rise, creating a smokin' hot association that may have political implications hotter than a lit cigarette.
The high r-squared value of 0.9160206 suggests that a substantial proportion of the variation in Democrat votes for senators in Minnesota can be explained by the variation in annual household spending on tobacco products and smoking supplies. It seems that as tobacco spending goes up, so does the democratic vote count – a statistical trend more consistent than a pack-a-day smoker's routine.
Furthermore, with a p-value of less than 0.01, the likelihood of observing such a strong correlation by random chance alone is about as rare as finding a clove cigarette in a haystack. This level of statistical significance suggests that there's a robust relationship between tobacco spending and political preference in Minnesota, proving that this correlation is more than just a statistical smokescreen.
Fig. 1 presents a visual representation of this remarkable correlation, displaying a scatterplot that showcases the tight relationship between annual US household spending on tobacco products and smoking supplies and Democrat votes for Senators in Minnesota. The data points are as tightly packed as a fresh pack of cigarettes, leaving no room for doubt about the strength of this relationship.
In conclusion, our findings highlight the unexpected impact of tobacco spending on political preferences in Minnesota. This unusual connection sparks further inquiry into the underlying mechanisms driving this relationship, demonstrating the potential influences of smoking culture on political affiliations in the state. As research continues, the aroma of tobacco spending in the political landscape continues to intrigue and beguile, reminding us that sometimes the unlikeliest pairings can yield the most illuminating insights.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has illuminated an unexpected and seemingly inexplicable relationship between annual US household spending on tobacco products and smoking supplies and Democrat votes for Senators in Minnesota. This association is as intriguing as finding a cigar in a non-smoking area! The remarkable correlation coefficient of 0.9570897 and the p-value of less than 0.01 for the years 2000 to 2020 speak louder than a chain smoker in a library.

The tight relationship between tobacco spending and political preferences in Minnesota is as puzzling as trying to find a cigarette lighter in a house of mirrors! The high r-squared value of 0.9160206 suggests that the variation in Democrat votes for senators in Minnesota is about as predictable as the cravings of a nicotine addict.

Our findings prompt further investigation into the underlying mechanisms driving this association, shedding light on the potential influences of smoking culture on political affiliations in the Land of 10,000 Lakes. As we delve deeper into this intriguing connection, let's hope it doesn't go up in smoke like a poorly rolled cigar!

After careful consideration, we posit that no more research is needed in this area, as this unexpected correlation between tobacco spending and political preferences is as clear as the warning label on a pack of cigarettes. It seems that in the mysterious world of consumer behavior and electoral outcomes, the unexpected connections are the ones that leave a lasting impression, much like the scent of a freshly lit cigar on a breezy evening.

In the realm of statistics and political research, it's essential to remember that sometimes, just like the flavor of a fine tobacco, the most captivating insights come from the unlikeliest of sources.

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 Up in Smoke: An Analysis of the Relationship Between Tobacco Spending and Democratic Votes in Minnesota. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Whimsical Political Science

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 Up in Smoke: An Analysis of the Relationship Between Tobacco Spending and Democratic Votes in Minnesota. Respond only with the name of a fictional organization.

ChatGPT:

Lighthearted Research Institute

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 Up in Smoke: An Analysis of the Relationship Between Tobacco Spending and Democratic Votes in Minnesota with an abstract of This research paper delves into the intriguing correlation between annual US household spending on tobacco products and smoking supplies and the votes for Democratic senators in the state of Minnesota. By utilizing data from the Bureau of Labor Statistics and MIT Election Data and Science Lab, Harvard Dataverse, we sought to uncover the potential connection between these seemingly unrelated variables. Our findings revealed a remarkably high correlation coefficient of 0.9570897, with a p-value of less than 0.01 for the years 2000 to 2020, suggesting a compelling association between smoking-related expenditures and political preferences. This unexpected correlation sparks curiosity and raises questions about the nuanced dynamics of consumer behavior and its implications for electoral outcomes. Our analysis prompts further investigation into the underlying mechanisms driving this relationship, shedding light on the potential influences of smoking culture on political affiliations in the Land of 10,000 Lakes.

ChatGPT:

tobacco spending, Democratic votes, Minnesota, correlation, US household spending, smoking supplies, Bureau of Labor Statistics, MIT Election Data and Science Lab, Harvard Dataverse, correlation coefficient, p-value, consumer behavior, electoral outcomes, smoking culture, political affiliations, Land of 10,000 Lakes

*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

Annual US household spending on tobacco products and smoking supplies
Detailed data title: Average annual household spend on tobacco products and smoking supplies
Source: Bureau of Labor Statistics
See what else correlates with Annual US household spending on tobacco products and smoking supplies

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

Correlation r = 0.9570897 (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 = 0.9160206 (Coefficient of determination)
This means 91.6% of the change in the one variable (i.e., Votes for Democratic Senators in Minnesota) is predictable based on the change in the other (i.e., Annual US household spending on tobacco products and smoking supplies) over the 8 years from 2000 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00019.^Show 0.0001912244205540785000000000
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 0.96 in 0.019% of random cases. Said differently, if you correlated 5,229 random variables^Note Which I absolutely did.
with the same 7 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 7 because we have two variables measured over a period of 8 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.

[ 0.78, 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.

	2000	2002	2006	2008	2012	2014	2018	2020
Annual US household spending on tobacco products and smoking supplies (Household spend)	319	320	327	317	332	319	347	315
Votes for Democratic Senators in Minnesota (Percentage of votes)	48.8342	47.8404	58.0564	41.9937	65.229	53.1512	113.281	48.7367

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([319,320,327,317,332,319,347,315,])
array_2 = np.array([48.8342,47.8404,58.0564,41.9937,65.229,53.1512,113.281,48.7367,])
array_1_name = "Annual US household spending on tobacco products and smoking supplies"
array_2_name = "Votes for Democratic Senators in Minnesota"

# 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 Annual US household spending on tobacco products and smoking supplies
Line chart for only Votes for Democratic Senators in Minnesota
AI-generated correlation image
The spurious research paper: Up in Smoke: An Analysis of the Relationship Between Tobacco Spending and Democratic Votes in Minnesota

View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!

Correlation ID: 4464 · Black Variable ID: 19943 · Red Variable ID: 26407


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