about · email me · subscribe
Spurious correlation #5,628 · 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 entertainment and the second variable is Votes for Libertarian Senators in New Jersey.  The chart goes from 2000 to 2018, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As household spending on entertainment increased, more families opted for backyard wrestling matches as a thrifty form of amusement. This led to a grassroots surge in support for political candidates who promised to deregulate the wrestling industry, inadvertently bolstering the Libertarian votes for Senators in New Jersey. After all, nothing says "freedom" like organizing your own ladder matches and folding chair smackdowns without government intervention!

Model: dalle-3
Prompt: [Whimsical illustration] Create an image of families in various backyard wrestling matches across the US, with colorful makeshift rings and enthusiastic cheering crowds. In New Jersey, depict voters showing support for Libertarian Senators amidst the lively atmosphere. Highlight the energy and excitement of the wrestling matches while also incorporating hints of political engagement and change in the 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: Annual US household spending on entertainment and Votes for Libertarian Senators in New Jersey. 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: Woodblock painting Whimsical illustration Realistic A scene from Skyrim Photorealism
ChatGPT: Whimsical illustration

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 entertainment and Votes for Libertarian Senators in New Jersey, in the following situation: As household spending on entertainment increased, more families opted for backyard wrestling matches as a thrifty form of amusement. This led to a grassroots surge in support for political candidates who promised to deregulate the wrestling industry, inadvertently bolstering the Libertarian votes for Senators in New Jersey. After all, nothing says "freedom" like organizing your own ladder matches and folding chair smackdowns without government intervention!. Keep the description simple.
ChatGPT: Families across the US are seen hosting backyard wrestling matches, with makeshift rings and cheering crowds, as annual household spending on entertainment increases. Among the cheering crowds in New Jersey, voters show their support for Libertarian Senators, who have promised to deregulate the wrestling industry and champion individual freedom.

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: [ Whimsical illustration ] and depicting this scene: Families across the US are seen hosting backyard wrestling matches, with makeshift rings and cheering crowds, as annual household spending on entertainment increases. Among the cheering crowds in New Jersey, voters show their support for Libertarian Senators, who have promised to deregulate the wrestling industry and champion individual freedom. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [Whimsical illustration] Create an image of families in various backyard wrestling matches across the US, with colorful makeshift rings and enthusiastic cheering crowds. In New Jersey, depict voters showing support for Libertarian Senators amidst the lively atmosphere. Highlight the energy and excitement of the wrestling matches while also incorporating hints of political engagement and change in the scene.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Annual US household spending on entertainment caused Libertarian votes for Senators in New Jersey to increase.

AI academic paper

(Because p < 0.01)
Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey

Journal of Quirky Economic Studies

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Annual US household spending on entertainment and Libertarian votes for Senators in New Jersey. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from Bureau of Labor Statistics and MIT Election Data and Science Lab, Harvard Dataverse to assess this nagging question. You found a correlation coefficient of 0.9898267 and p < 0.01 for 2000 to 2018.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey"

[[ABSTRACT]]
This research examines the intriguing connection between annual US household spending on entertainment and the votes garnered by Libertarian candidates for Senators in New Jersey. Using data from the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, our study delves into this curiously linked pair of variables, with unexpected results.

Examining annual household spending on entertainment and Libertarian votes from 2000 to 2018, a striking correlation coefficient of 0.9898267 and p < 0.01 was observed. This suggests a strong association between these seemingly unrelated factors and initiates a conversation about the potential influence of leisurely pursuits on political preferences.

In many ways, the entertaining relationship between household spending on entertainment and Libertarian votes may remind one of a classic dad joke - seemingly unrelated elements coming together in a surprising and amusing manner, revealing unexpected connections in the process. This study contributes to the understanding of the complex interplay between economic behaviors and political attitudes, while also sprinkling in a touch of lightheartedness to the academic discourse.


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 introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between Annual US household spending on entertainment and Libertarian votes for Senators in New Jersey. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey"

[[ABSTRACT]]
This research examines the intriguing connection between annual US household spending on entertainment and the votes garnered by Libertarian candidates for Senators in New Jersey. Using data from the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, our study delves into this curiously linked pair of variables, with unexpected results.

Examining annual household spending on entertainment and Libertarian votes from 2000 to 2018, a striking correlation coefficient of 0.9898267 and p < 0.01 was observed. This suggests a strong association between these seemingly unrelated factors and initiates a conversation about the potential influence of leisurely pursuits on political preferences.

In many ways, the entertaining relationship between household spending on entertainment and Libertarian votes may remind one of a classic dad joke - seemingly unrelated elements coming together in a surprising and amusing manner, revealing unexpected connections in the process. This study contributes to the understanding of the complex interplay between economic behaviors and political attitudes, while also sprinkling in a touch of lightheartedness to the academic discourse.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of economics and politics often yields unexpected and entertaining findings. In the spirit of exploration, this study delves into the intriguing relationship between household spending on entertainment and the votes garnered by Libertarian candidates for Senators in the state of New Jersey. As we embark on this intellectual journey, we cannot resist the urge to insert a relevant dad joke: Why did the statistician take a fishing rod to the election? For the sense of polling!

Amidst the sea of data and statistical analyses, it becomes evident that seemingly disparate variables can converge in a compelling manner. The literature on political behavior and economic indicators has traditionally focused on more conventional measures, yet our study takes a whimsical turn by examining the influence of entertainment expenditure on political choices. It’s like trying to find the correlation between a bad joke and a groan - they just go hand in hand!

Our investigation seeks to shed light on the interplay between leisurely pursuits and political inclinations, introducing a touch of mirth to the heretofore staid realm of academic research. Much like a well-timed dad joke, our findings aim to prompt a chuckle and a fresh perspective on the dynamics of electoral decision-making, inviting a more light-hearted approach to studying serious subjects. Speaking of dad jokes, what do politicians and clouds have in common? They both change direction when the wind blows!

The connection between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey represents a fertile ground for exploration, yielding unexpected connections and thought-provoking insights. By employing rigorous statistical methods and a hint of levity, our study endeavors to unravel this captivating correlation and contribute to the scholarly dialogue on the intricate relationship between economic behaviors and political preferences. After all, behind every surprising correlation lies a solid dad joke waiting to burst forth!


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 entertainment and Libertarian votes for Senators in New Jersey. 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
"Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey"

[[ABSTRACT]]
This research examines the intriguing connection between annual US household spending on entertainment and the votes garnered by Libertarian candidates for Senators in New Jersey. Using data from the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, our study delves into this curiously linked pair of variables, with unexpected results.

Examining annual household spending on entertainment and Libertarian votes from 2000 to 2018, a striking correlation coefficient of 0.9898267 and p < 0.01 was observed. This suggests a strong association between these seemingly unrelated factors and initiates a conversation about the potential influence of leisurely pursuits on political preferences.

In many ways, the entertaining relationship between household spending on entertainment and Libertarian votes may remind one of a classic dad joke - seemingly unrelated elements coming together in a surprising and amusing manner, revealing unexpected connections in the process. This study contributes to the understanding of the complex interplay between economic behaviors and political attitudes, while also sprinkling in a touch of lightheartedness to the academic discourse.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of economics and politics often yields unexpected and entertaining findings. In the spirit of exploration, this study delves into the intriguing relationship between household spending on entertainment and the votes garnered by Libertarian candidates for Senators in the state of New Jersey. As we embark on this intellectual journey, we cannot resist the urge to insert a relevant dad joke: Why did the statistician take a fishing rod to the election? For the sense of polling!
Amidst the sea of data and statistical analyses, it becomes evident that seemingly disparate variables can converge in a compelling manner. The literature on political behavior and economic indicators has traditionally focused on more conventional measures, yet our study takes a whimsical turn by examining the influence of entertainment expenditure on political choices. It’s like trying to find the correlation between a bad joke and a groan - they just go hand in hand!
Our investigation seeks to shed light on the interplay between leisurely pursuits and political inclinations, introducing a touch of mirth to the heretofore staid realm of academic research. Much like a well-timed dad joke, our findings aim to prompt a chuckle and a fresh perspective on the dynamics of electoral decision-making, inviting a more light-hearted approach to studying serious subjects. Speaking of dad jokes, what do politicians and clouds have in common? They both change direction when the wind blows!
The connection between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey represents a fertile ground for exploration, yielding unexpected connections and thought-provoking insights. By employing rigorous statistical methods and a hint of levity, our study endeavors to unravel this captivating correlation and contribute to the scholarly dialogue on the intricate relationship between economic behaviors and political preferences. After all, behind every surprising correlation lies a solid dad joke waiting to burst forth!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Several studies have delved into the relationship between economic indicators and political behavior. In "Smith et al.'s Analysis of Socioeconomic Variables in Electoral Choices," the authors find a strong correlation between income levels and voting patterns. Similarly, in "Doe and Jones' Examination of Consumer Expenditure and Political Affiliation," the researchers observe a significant association between spending habits and party allegiances.

Turning to the realm of non-fiction literature, books such as "Freakonomics" by Steven D. Levitt and Stephen J. Dubner and "Nudge" by Richard H. Thaler and Cass R. Sunstein explore the intriguing ways in which human behavior influences economic and political decision-making. These works offer valuable insights into the complex interplay between individual choices and larger societal trends.

On the fictional front, novels like "The Hitchhiker's Guide to the Galaxy" by Douglas Adams and "Infinite Jest" by David Foster Wallace capture the whimsical and sometimes absurd nature of human existence, prompting readers to consider the unpredictable and entertaining aspects of life.

However, in a departure from traditional sources, the present study also draws upon unconventional sources such as grocery store receipts, late-night infomercials, and random musings scribbled on napkins. Engaging with these unorthodox materials adds an element of surprise and levity to the scholarly discourse, much like stumbling upon a pun in the midst of a serious academic paper.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Annual US household spending on entertainment and Libertarian votes for Senators in New Jersey. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Labor Statistics and MIT Election Data and Science Lab, Harvard Dataverse . You used data from 2000 to 2018

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey"

[[ABSTRACT]]
This research examines the intriguing connection between annual US household spending on entertainment and the votes garnered by Libertarian candidates for Senators in New Jersey. Using data from the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, our study delves into this curiously linked pair of variables, with unexpected results.

Examining annual household spending on entertainment and Libertarian votes from 2000 to 2018, a striking correlation coefficient of 0.9898267 and p < 0.01 was observed. This suggests a strong association between these seemingly unrelated factors and initiates a conversation about the potential influence of leisurely pursuits on political preferences.

In many ways, the entertaining relationship between household spending on entertainment and Libertarian votes may remind one of a classic dad joke - seemingly unrelated elements coming together in a surprising and amusing manner, revealing unexpected connections in the process. This study contributes to the understanding of the complex interplay between economic behaviors and political attitudes, while also sprinkling in a touch of lightheartedness to the academic discourse.

[[INTRODUCTION]]
The intersection of economics and politics often yields unexpected and entertaining findings. In the spirit of exploration, this study delves into the intriguing relationship between household spending on entertainment and the votes garnered by Libertarian candidates for Senators in the state of New Jersey. As we embark on this intellectual journey, we cannot resist the urge to insert a relevant dad joke: Why did the statistician take a fishing rod to the election? For the sense of polling!
Amidst the sea of data and statistical analyses, it becomes evident that seemingly disparate variables can converge in a compelling manner. The literature on political behavior and economic indicators has traditionally focused on more conventional measures, yet our study takes a whimsical turn by examining the influence of entertainment expenditure on political choices. It’s like trying to find the correlation between a bad joke and a groan - they just go hand in hand!
Our investigation seeks to shed light on the interplay between leisurely pursuits and political inclinations, introducing a touch of mirth to the heretofore staid realm of academic research. Much like a well-timed dad joke, our findings aim to prompt a chuckle and a fresh perspective on the dynamics of electoral decision-making, inviting a more light-hearted approach to studying serious subjects. Speaking of dad jokes, what do politicians and clouds have in common? They both change direction when the wind blows!
The connection between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey represents a fertile ground for exploration, yielding unexpected connections and thought-provoking insights. By employing rigorous statistical methods and a hint of levity, our study endeavors to unravel this captivating correlation and contribute to the scholarly dialogue on the intricate relationship between economic behaviors and political preferences. After all, behind every surprising correlation lies a solid dad joke waiting to burst forth!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

The methodology for this research involved a comprehensive data collection process across a span of 18 years (2000-2018) to ensure a thorough examination of the relationship between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey. The primary sources of data were the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, chosen for their comprehensive coverage and reliability.

The first step in the methodology was to obtain detailed information on annual household spending on entertainment, including expenditures on various forms of leisure activities such as movie tickets, live performances, digital media, and recreational equipment. This data was then cross-referenced with the votes received by Libertarian candidates for Senators in New Jersey to establish a potential correlation between these variables.

To ensure the robustness of the analysis, a series of statistical methods were employed, ranging from simple descriptive statistics to advanced regression models. Linear regression analysis was used to measure the strength and direction of the relationship between household spending on entertainment and Libertarian votes, taking into account potential confounding variables such as income levels, demographic factors, and political climate. It's like using a GPS to navigate through the intricate landscape of data, ensuring that our analysis stays on course and arrives at meaningful conclusions.

Furthermore, a time-series analysis was conducted to assess the dynamic nature of the correlation over the 18-year period, providing insights into any temporal patterns or shifts in the relationship between entertainment spending and political preferences. We unearthed more surprising connections than a comedian at a statistics convention!

In order to address potential endogeneity and omitted variable bias, instrumental variable techniques were also utilized, employing exogenous instruments to mitigate biases in the estimated relationships. Sensitivity analyses were performed to test the robustness of the results and account for any anomalies that could skew the findings. It's like putting on statistical safety goggles to ensure that our vision remains clear amidst the complexities of the data.

Finally, a series of robustness checks were implemented, including bootstrapping methods and Monte Carlo simulations, to verify the stability of the results and assess the potential impact of outliers or extreme data points. We sifted through the data with the precision of a treasure hunter, uncovering nuggets of insight amidst the statistical noise.

The utilization of these diverse and rigorous methodologies enabled a comprehensive investigation into the captivating connection between household spending on entertainment and Libertarian votes in New Jersey, offering a multi-faceted exploration that goes beyond traditional statistical approaches. Just like a good punchline, our methodology aimed to deliver a solid foundation for unveiling the mesmerizing relationship between seemingly unrelated variables.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Annual US household spending on entertainment and Libertarian votes for Senators in New Jersey. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2000 to 2018, you found a correlation 0.9898267, r-squared of 0.9797569, and p < 0.01.

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

Here is the title and abstract of the paper:
[[TITLE]]
"Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey"

[[ABSTRACT]]
This research examines the intriguing connection between annual US household spending on entertainment and the votes garnered by Libertarian candidates for Senators in New Jersey. Using data from the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, our study delves into this curiously linked pair of variables, with unexpected results.

Examining annual household spending on entertainment and Libertarian votes from 2000 to 2018, a striking correlation coefficient of 0.9898267 and p < 0.01 was observed. This suggests a strong association between these seemingly unrelated factors and initiates a conversation about the potential influence of leisurely pursuits on political preferences.

In many ways, the entertaining relationship between household spending on entertainment and Libertarian votes may remind one of a classic dad joke - seemingly unrelated elements coming together in a surprising and amusing manner, revealing unexpected connections in the process. This study contributes to the understanding of the complex interplay between economic behaviors and political attitudes, while also sprinkling in a touch of lightheartedness to the academic discourse.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of economics and politics often yields unexpected and entertaining findings. In the spirit of exploration, this study delves into the intriguing relationship between household spending on entertainment and the votes garnered by Libertarian candidates for Senators in the state of New Jersey. As we embark on this intellectual journey, we cannot resist the urge to insert a relevant dad joke: Why did the statistician take a fishing rod to the election? For the sense of polling!
Amidst the sea of data and statistical analyses, it becomes evident that seemingly disparate variables can converge in a compelling manner. The literature on political behavior and economic indicators has traditionally focused on more conventional measures, yet our study takes a whimsical turn by examining the influence of entertainment expenditure on political choices. It’s like trying to find the correlation between a bad joke and a groan - they just go hand in hand!
Our investigation seeks to shed light on the interplay between leisurely pursuits and political inclinations, introducing a touch of mirth to the heretofore staid realm of academic research. Much like a well-timed dad joke, our findings aim to prompt a chuckle and a fresh perspective on the dynamics of electoral decision-making, inviting a more light-hearted approach to studying serious subjects. Speaking of dad jokes, what do politicians and clouds have in common? They both change direction when the wind blows!
The connection between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey represents a fertile ground for exploration, yielding unexpected connections and thought-provoking insights. By employing rigorous statistical methods and a hint of levity, our study endeavors to unravel this captivating correlation and contribute to the scholarly dialogue on the intricate relationship between economic behaviors and political preferences. After all, behind every surprising correlation lies a solid dad joke waiting to burst forth!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis revealed a remarkably strong positive correlation of 0.9898267 between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey from 2000 to 2018. This finding amusingly suggests that as household entertainment spending increased, so did the propensity of New Jersey residents to endorse Libertarian candidates at the ballot box. It's as if an increase in comedy gigs led to more "stand up" votes for the Libertarians!

The observed r-squared value of 0.9797569 indicates that approximately 98% of the variance in Libertarian votes can be explained by the variation in household spending on entertainment. It's as if the relationship between household spending on entertainment and political preferences is as solid as a well-constructed dad joke - with very little room for uncertainty.

The p-value of less than 0.01 further supports the robustness of the observed correlation, providing compelling evidence against the null hypothesis that there is no relationship between the variables. It's as though this relationship between household entertainment spending and political preferences is statistically significant - no joke!

The scatterplot (Fig. 1) visually portrays the striking relationship between household spending on entertainment and Libertarian votes, highlighting the tightly clustered data points and the clear positive trend. The figure elegantly captures the essence of this unexpected and entertaining correlation, visually demonstrating the gravity of the connection. It's as if this scatterplot is the punchline to a well-crafted statistical analysis, delivering the "wow" factor in one simple image.


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 entertainment and Libertarian votes for Senators in New Jersey. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
"Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey"

[[ABSTRACT]]
This research examines the intriguing connection between annual US household spending on entertainment and the votes garnered by Libertarian candidates for Senators in New Jersey. Using data from the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, our study delves into this curiously linked pair of variables, with unexpected results.

Examining annual household spending on entertainment and Libertarian votes from 2000 to 2018, a striking correlation coefficient of 0.9898267 and p < 0.01 was observed. This suggests a strong association between these seemingly unrelated factors and initiates a conversation about the potential influence of leisurely pursuits on political preferences.

In many ways, the entertaining relationship between household spending on entertainment and Libertarian votes may remind one of a classic dad joke - seemingly unrelated elements coming together in a surprising and amusing manner, revealing unexpected connections in the process. This study contributes to the understanding of the complex interplay between economic behaviors and political attitudes, while also sprinkling in a touch of lightheartedness to the academic discourse.

[[LITERATURE REVIEW]]
Several studies have delved into the relationship between economic indicators and political behavior. In "Smith et al.'s Analysis of Socioeconomic Variables in Electoral Choices," the authors find a strong correlation between income levels and voting patterns. Similarly, in "Doe and Jones' Examination of Consumer Expenditure and Political Affiliation," the researchers observe a significant association between spending habits and party allegiances.
Turning to the realm of non-fiction literature, books such as "Freakonomics" by Steven D. Levitt and Stephen J. Dubner and "Nudge" by Richard H. Thaler and Cass R. Sunstein explore the intriguing ways in which human behavior influences economic and political decision-making. These works offer valuable insights into the complex interplay between individual choices and larger societal trends.
On the fictional front, novels like "The Hitchhiker's Guide to the Galaxy" by Douglas Adams and "Infinite Jest" by David Foster Wallace capture the whimsical and sometimes absurd nature of human existence, prompting readers to consider the unpredictable and entertaining aspects of life.
However, in a departure from traditional sources, the present study also draws upon unconventional sources such as grocery store receipts, late-night infomercials, and random musings scribbled on napkins. Engaging with these unorthodox materials adds an element of surprise and levity to the scholarly discourse, much like stumbling upon a pun in the midst of a serious academic paper.

[[RESULTS]]
The analysis revealed a remarkably strong positive correlation of 0.9898267 between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey from 2000 to 2018. This finding amusingly suggests that as household entertainment spending increased, so did the propensity of New Jersey residents to endorse Libertarian candidates at the ballot box. It's as if an increase in comedy gigs led to more "stand up" votes for the Libertarians!
The observed r-squared value of 0.9797569 indicates that approximately 98% of the variance in Libertarian votes can be explained by the variation in household spending on entertainment. It's as if the relationship between household spending on entertainment and political preferences is as solid as a well-constructed dad joke - with very little room for uncertainty.
The p-value of less than 0.01 further supports the robustness of the observed correlation, providing compelling evidence against the null hypothesis that there is no relationship between the variables. It's as though this relationship between household entertainment spending and political preferences is statistically significant - no joke!
The scatterplot (Fig. 1) visually portrays the striking relationship between household spending on entertainment and Libertarian votes, highlighting the tightly clustered data points and the clear positive trend. The figure elegantly captures the essence of this unexpected and entertaining correlation, visually demonstrating the gravity of the connection. It's as if this scatterplot is the punchline to a well-crafted statistical analysis, delivering the "wow" factor in one simple image.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study offer compelling evidence of a robust and entertaining relationship between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey. The striking correlation coefficient of 0.9898267 indicates a remarkably strong association between these seemingly unrelated variables, akin to the unexpected punchline of a dad joke that leaves you both amused and perplexed. Our results amusingly support the prior research on the influence of economic behaviors on political preferences, adding a touch of humor to the scholarly discourse.

The high r-squared value of 0.9797569 suggests that approximately 98% of the variability in Libertarian votes can be attributed to the variation in household spending on entertainment. In other words, the influence of leisurely pursuits on political affiliations seems as clear-cut and unmistakable as a well-constructed dad joke - leaving little room for doubt or ambiguity. It's as if the relationship between household spending on entertainment and political preferences is the punchline that ties the whole joke together!

The p-value of less than 0.01 further underscores the statistical significance of the observed correlation, emphatically refuting the null hypothesis and providing compelling evidence in support of the alternative hypothesis. The strength of this relationship is no laughing matter - or perhaps it is, given the lighthearted nature of our findings! It's as though this unlikely connection between household entertainment spending and political preferences has delivered a punchline that resonates with statistical significance.

In this context, the scatterplot (Fig. 1) serves as the visual punchline to our analysis, effectively encapsulating the striking relationship between household spending on entertainment and Libertarian votes. The tidy clustering of data points and the clear positive trend depicted in the figure amusingly illustrate the gravity of this unexpected correlation, much like the artful delivery of a well-crafted punchline that elicits both surprise and delight. It's as if this scatterplot is the pièce de résistance of our statistical analysis, providing both visual appeal and a comedic twist to our research findings.


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 entertainment and Libertarian votes for Senators in New Jersey. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
"Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey"

[[ABSTRACT]]
This research examines the intriguing connection between annual US household spending on entertainment and the votes garnered by Libertarian candidates for Senators in New Jersey. Using data from the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, our study delves into this curiously linked pair of variables, with unexpected results.

Examining annual household spending on entertainment and Libertarian votes from 2000 to 2018, a striking correlation coefficient of 0.9898267 and p < 0.01 was observed. This suggests a strong association between these seemingly unrelated factors and initiates a conversation about the potential influence of leisurely pursuits on political preferences.

In many ways, the entertaining relationship between household spending on entertainment and Libertarian votes may remind one of a classic dad joke - seemingly unrelated elements coming together in a surprising and amusing manner, revealing unexpected connections in the process. This study contributes to the understanding of the complex interplay between economic behaviors and political attitudes, while also sprinkling in a touch of lightheartedness to the academic discourse.

[[INTRDUCTION]]
The intersection of economics and politics often yields unexpected and entertaining findings. In the spirit of exploration, this study delves into the intriguing relationship between household spending on entertainment and the votes garnered by Libertarian candidates for Senators in the state of New Jersey. As we embark on this intellectual journey, we cannot resist the urge to insert a relevant dad joke: Why did the statistician take a fishing rod to the election? For the sense of polling!
Amidst the sea of data and statistical analyses, it becomes evident that seemingly disparate variables can converge in a compelling manner. The literature on political behavior and economic indicators has traditionally focused on more conventional measures, yet our study takes a whimsical turn by examining the influence of entertainment expenditure on political choices. It’s like trying to find the correlation between a bad joke and a groan - they just go hand in hand!
Our investigation seeks to shed light on the interplay between leisurely pursuits and political inclinations, introducing a touch of mirth to the heretofore staid realm of academic research. Much like a well-timed dad joke, our findings aim to prompt a chuckle and a fresh perspective on the dynamics of electoral decision-making, inviting a more light-hearted approach to studying serious subjects. Speaking of dad jokes, what do politicians and clouds have in common? They both change direction when the wind blows!
The connection between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey represents a fertile ground for exploration, yielding unexpected connections and thought-provoking insights. By employing rigorous statistical methods and a hint of levity, our study endeavors to unravel this captivating correlation and contribute to the scholarly dialogue on the intricate relationship between economic behaviors and political preferences. After all, behind every surprising correlation lies a solid dad joke waiting to burst forth!

[[RESULTS]]
The analysis revealed a remarkably strong positive correlation of 0.9898267 between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey from 2000 to 2018. This finding amusingly suggests that as household entertainment spending increased, so did the propensity of New Jersey residents to endorse Libertarian candidates at the ballot box. It's as if an increase in comedy gigs led to more "stand up" votes for the Libertarians!
The observed r-squared value of 0.9797569 indicates that approximately 98% of the variance in Libertarian votes can be explained by the variation in household spending on entertainment. It's as if the relationship between household spending on entertainment and political preferences is as solid as a well-constructed dad joke - with very little room for uncertainty.
The p-value of less than 0.01 further supports the robustness of the observed correlation, providing compelling evidence against the null hypothesis that there is no relationship between the variables. It's as though this relationship between household entertainment spending and political preferences is statistically significant - no joke!
The scatterplot (Fig. 1) visually portrays the striking relationship between household spending on entertainment and Libertarian votes, highlighting the tightly clustered data points and the clear positive trend. The figure elegantly captures the essence of this unexpected and entertaining correlation, visually demonstrating the gravity of the connection. It's as if this scatterplot is the punchline to a well-crafted statistical analysis, delivering the "wow" factor in one simple image.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study unexpectedly unraveled a robust and highly amusing correlation between annual US household spending on entertainment and Libertarian votes for Senators in New Jersey from 2000 to 2018. The strikingly high correlation coefficient and r-squared value reflect a remarkably strong association, akin to the connection between a dad and his dad jokes - inseparable and uncannily influential. It's as if more spending on entertainment led to a surge in "free-thinking" votes!

The statistically significant p-value further solidifies the validity of this correlation, leaving no room for doubt - except, of course, for the perennial uncertainty of dad jokes' humor. It's as if this relationship is as unassailable as a punchline delivered by someone who can't tell jokes.

Our findings not only shed light on the unexpected interplay between leisurely pursuits and political preferences but also inject a dash of levity into the typically serious arena of academic research. Just as a well-timed dad joke can lighten the mood, our study offers a whimsical perspective, reminding us that even in the realm of statistics and politics, there's always room for a good laugh.

Ultimately, our research asserts that no further investigations in this area are needed. The evidence is clear: the amusing relationship between household spending on entertainment and Libertarian votes in New Jersey is as solid as a dad joke, and just as entertaining.


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 Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Economic Studies


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 Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Socioeconomic Research


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 Show Me the Money Votes: The Entertaining Relationship Between Household Spending on Entertainment and Libertarian Ballots in New Jersey with an abstract of This research examines the intriguing connection between annual US household spending on entertainment and the votes garnered by Libertarian candidates for Senators in New Jersey. Using data from the Bureau of Labor Statistics and the MIT Election Data and Science Lab's Harvard Dataverse, our study delves into this curiously linked pair of variables, with unexpected results.
Examining annual household spending on entertainment and Libertarian votes from 2000 to 2018, a striking correlation coefficient of 0.9898267 and p < 0.01 was observed. This suggests a strong association between these seemingly unrelated factors and initiates a conversation about the potential influence of leisurely pursuits on political preferences.
In many ways, the entertaining relationship between household spending on entertainment and Libertarian votes may remind one of a classic dad joke - seemingly unrelated elements coming together in a surprising and amusing manner, revealing unexpected connections in the process. This study contributes to the understanding of the complex interplay between economic behaviors and political attitudes, while also sprinkling in a touch of lightheartedness to the academic discourse.

ChatGPT:

household spending on entertainment, Libertarian votes, New Jersey, US household spending, entertainment spending, political preferences, Bureau of Labor Statistics, MIT Election Data, Harvard Dataverse, economic behaviors, political attitudes

*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 entertainment
Detailed data title: Average annual household spend on entertainment
Source: Bureau of Labor Statistics
See what else correlates with Annual US household spending on entertainment

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

Correlation r = 0.9898267 (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 = 0.9797569 (Coefficient of determination)
This means 98% of the change in the one variable (i.e., Votes for Libertarian Senators in New Jersey) is predictable based on the change in the other (i.e., Annual US household spending on entertainment) over the 6 years from 2000 through 2018.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00015. 0.0001547174549969184700000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.99 in 0.015% of random cases. Said differently, if you correlated 6,463 random variables Which I absolutely did.
with the same 5 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 5 because we have two variables measured over a period of 6 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.91, 1 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200220062008201220142018
Annual US household spending on entertainment (Household spend)207923772835260527283226
Votes for Libertarian Senators in New Jersey (Total votes)125581463718810168031672121212




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([2079,2377,2835,2605,2728,3226,])
array_2 = np.array([12558,14637,18810,16803,16721,21212,])
array_1_name = "Annual US household spending on entertainment"
array_2_name = "Votes for Libertarian Senators in New Jersey"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Thanks for being the explorer we needed!


Correlation ID: 5628 · Black Variable ID: 19938 · Red Variable ID: 26282
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0