about · email me · subscribe
Spurious correlation #4,983 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Democratic Senators in Wisconsin and the second variable is Google searches for 'dr pepper vs mr pibb'.  The chart goes from 2004 to 2018, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Because the more Democrat votes for Senators in Wisconsin, the more Pibb fans realized they had to Dr-ink up their support for their favorite soda to stay a-FIZZ-ed with the political outcome. So, they were really SODA-lighted to show their pop-ular vote for Mr. Pibb. It seems like in this case, political preferences really do DR-ive consumer behavior!

Model: dalle-3
Prompt: Sure, here's an image generation prompt for the described scene: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s. Depict a group of people in Wisconsin holding up signs in support of their favorite soda, with one group cheering for Dr Pepper and another for Mr. Pibb, all while casting their votes for Senators. The soda enthusiasts are engaging in conversations about the political outcome, emphasizing how their support for their preferred soda is closely tied to their political preferences. Keep the visual depiction simple. Do not include any words or speech bubbles. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb'. 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: Charcoal A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s a funny image you would see on reddit Futuristic Realistic
ChatGPT: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb', in the following situation: Because the more Democrat votes for Senators in Wisconsin, the more Pibb fans realized they had to Dr-ink up their support for their favorite soda to stay a-FIZZ-ed with the political outcome. So, they were really SODA-lighted to show their pop-ular vote for Mr. Pibb. It seems like in this case, political preferences really do DR-ive consumer behavior!. Keep the description simple.
ChatGPT: In Wisconsin, as Democrat votes for Senators increased, more people started searching on Google for 'dr pepper vs mr pibb'. In the scene, there is a group of people holding up signs in support of their favorite soda, with one group cheering for Dr Pepper and another for Mr. Pibb, all while casting their votes for the Senators. The soda enthusiasts are engaging in conversations about the political outcome, emphasizing how their support for their preferred soda is closely tied to their political preferences.

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: [ A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s ] and depicting this scene: In Wisconsin, as Democrat votes for Senators increased, more people started searching on Google for 'dr pepper vs mr pibb'. In the scene, there is a group of people holding up signs in support of their favorite soda, with one group cheering for Dr Pepper and another for Mr. Pibb, all while casting their votes for the Senators. The soda enthusiasts are engaging in conversations about the political outcome, emphasizing how their support for their preferred soda is closely tied to their political preferences. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Sure, here's an image generation prompt for the described scene: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s. Depict a group of people in Wisconsin holding up signs in support of their favorite soda, with one group cheering for Dr Pepper and another for Mr. Pibb, all while casting their votes for Senators. The soda enthusiasts are engaging in conversations about the political outcome, emphasizing how their support for their preferred soda is closely tied to their political preferences. Keep the visual depiction simple. Do not include any words or speech bubbles.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Democrat votes for Senators in Wisconsin positively influenced dr pepper vs mr pibb (Google searches for 'dr pepper vs mr pibb'). Include one good pun.

AI academic paper

(Because p < 0.05)
Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'

The Journal of Quirky Political Phenomena

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 Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb'. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to assess this nagging question. You found a correlation coefficient of 0.8406801 and p < 0.05 for 2004 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]]
Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'

[[ABSTRACT]]
This paper endeavors to unravel the enigmatic relationship between the voting behavior of Democrats in Wisconsin and their curiosity regarding the timeless debate of 'Dr Pepper vs Mr Pibb' through the lens of Google search trends. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we found a remarkably robust correlation between the two seemingly unrelated phenomena, with a correlation coefficient of 0.8406801 and p < 0.05 for the years 2004 to 2018. While the causality remains elusive, our findings invite speculation and spark amusement as we delve into the eccentric world of electoral politics and carbonated beverage fandom. This research ignites not only intellectual curiosity but also a craving for scholarly pursuits that teeter on the edge of quirkiness.


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 Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'

[[ABSTRACT]]
This paper endeavors to unravel the enigmatic relationship between the voting behavior of Democrats in Wisconsin and their curiosity regarding the timeless debate of 'Dr Pepper vs Mr Pibb' through the lens of Google search trends. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we found a remarkably robust correlation between the two seemingly unrelated phenomena, with a correlation coefficient of 0.8406801 and p < 0.05 for the years 2004 to 2018. While the causality remains elusive, our findings invite speculation and spark amusement as we delve into the eccentric world of electoral politics and carbonated beverage fandom. This research ignites not only intellectual curiosity but also a craving for scholarly pursuits that teeter on the edge of quirkiness.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of political behavior and consumer preferences has long been a subject of interest, from the correlation between voter turnout and the sale of snack foods to the potential influence of soft drink preferences on electoral choices. In this vein, our research delves into the peculiar milieu of Democrat votes in Wisconsin and the seemingly unrelated but undeniably titillating Google searches for 'Dr Pepper vs Mr Pibb'. While the former may seem a weighty matter of civic duty and governance, the latter represents a quizzical divergence into the realm of carbonated beverage allegiance.

Indeed, the correlation between political sway and soft drink queries may seem like an odd pairing, akin to the discordant fusion of flavors one might encounter in a misguided soda concoction. Yet, as we embarked on this study, we were struck by the whimsical parallels and the potential for hidden layers of connection, much like the nuanced interplay of flavors in a cola-based beverage.

Our investigation, rooted in data garnered from the MIT Election Data and Science Lab, Harvard Dataverse, and the whimsical world of Google Trends, revealed a surprisingly robust correlation of 0.8406801 between Democrat votes in Wisconsin and the fervent quest for knowledge regarding 'Dr Pepper vs Mr Pibb'. This unanticipated coupling prompted both scholarly consternation and a sense of fizzy delight as we endeavored to comprehend the confluence of political inclinations and fizzy drink fervor.

As we delve deeper into the findings, we invite readers to accompany us on a whimsical journey that may challenge preconceived notions and provoke mirthful rumination. The enchanting interplay between political choices and carbonated quandaries offers a respite from the weighty matters of state, a refreshingly effervescent diversion punctuated with the tantalizing allure of nuanced correlations and tickling queries.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb'. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'

[[ABSTRACT]]
This paper endeavors to unravel the enigmatic relationship between the voting behavior of Democrats in Wisconsin and their curiosity regarding the timeless debate of 'Dr Pepper vs Mr Pibb' through the lens of Google search trends. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we found a remarkably robust correlation between the two seemingly unrelated phenomena, with a correlation coefficient of 0.8406801 and p < 0.05 for the years 2004 to 2018. While the causality remains elusive, our findings invite speculation and spark amusement as we delve into the eccentric world of electoral politics and carbonated beverage fandom. This research ignites not only intellectual curiosity but also a craving for scholarly pursuits that teeter on the edge of quirkiness.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of political behavior and consumer preferences has long been a subject of interest, from the correlation between voter turnout and the sale of snack foods to the potential influence of soft drink preferences on electoral choices. In this vein, our research delves into the peculiar milieu of Democrat votes in Wisconsin and the seemingly unrelated but undeniably titillating Google searches for 'Dr Pepper vs Mr Pibb'. While the former may seem a weighty matter of civic duty and governance, the latter represents a quizzical divergence into the realm of carbonated beverage allegiance.
Indeed, the correlation between political sway and soft drink queries may seem like an odd pairing, akin to the discordant fusion of flavors one might encounter in a misguided soda concoction. Yet, as we embarked on this study, we were struck by the whimsical parallels and the potential for hidden layers of connection, much like the nuanced interplay of flavors in a cola-based beverage.
Our investigation, rooted in data garnered from the MIT Election Data and Science Lab, Harvard Dataverse, and the whimsical world of Google Trends, revealed a surprisingly robust correlation of 0.8406801 between Democrat votes in Wisconsin and the fervent quest for knowledge regarding 'Dr Pepper vs Mr Pibb'. This unanticipated coupling prompted both scholarly consternation and a sense of fizzy delight as we endeavored to comprehend the confluence of political inclinations and fizzy drink fervor.
As we delve deeper into the findings, we invite readers to accompany us on a whimsical journey that may challenge preconceived notions and provoke mirthful rumination. The enchanting interplay between political choices and carbonated quandaries offers a respite from the weighty matters of state, a refreshingly effervescent diversion punctuated with the tantalizing allure of nuanced correlations and tickling queries.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The scholarly exploration of seemingly incongruous phenomena such as political behavior and consumer predilections has been a subject of keen interest among researchers. Smith et al. (2010) expounded upon the correlation between voter turnout and the sale of snack foods, shedding light on the tantalizing intersection of civic engagement and culinary cravings. Building upon this tradition of scholarly inquiry, Doe and Jones (2015) delved into the potential influence of soft drink preferences on electoral choices, uncovering intriguing connections between carbonated beverage inclinations and political predilections.

Furthermore, in "Soda Wars: A Beverage Battle for the Ages," the authors delve into the storied rivalry between different carbonated beverages and the fervent allegiance of their respective enthusiasts, offering an insightful foray into the cultural fascination with fizzy drink fandom and the fervent debates surrounding particular soda brands. Similarly, "Fizz Fandom: The Cultural Phenomenon of Carbonated Beverages" provides a captivating exploration of the whimsical world of soda aficionados and the fervent loyalty they exhibit toward their preferred effervescent libations.

Moving from non-fiction to fiction, the literary world offers a wealth of imaginative works that tangentially touch upon the peculiar nexus between political choices and carbonated conundrums. "The Pop Politics Chronicles: A Tale of Two Sodas" whimsically weaves a narrative that follows the intertwining fates of a political maverick and a fervent advocate for a niche soda brand, spotlighting the unexpected ways in which fizzy fervor intersects with electoral endeavors. In a similar vein, "Soda Shenanigans: A Carbonated Comedy of Political Proportions" offers a delightful romp through the whimsical shenanigans that transpire when electoral antics collide with the zany world of soda aficionados.

In the realm of cinema, the celluloid medium has also dabbled in the droll intersection of political machinations and fizzy drink fervor. "The Carbonated Campaign: A Tale of Electoral Elixirs" showcases the delightful absurdity that unfolds when political contenders find themselves embroiled in a battle not only for votes but also for the fervent allegiance of soda enthusiasts. This cinematic portrayal offers a whimsical exploration of the unexpected parallels between political battles and bubbly rivalries, inviting viewers to revel in the fizzy frolic that unfolds on the silver screen.


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 Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends . You used data from 2004 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]]
Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'

[[ABSTRACT]]
This paper endeavors to unravel the enigmatic relationship between the voting behavior of Democrats in Wisconsin and their curiosity regarding the timeless debate of 'Dr Pepper vs Mr Pibb' through the lens of Google search trends. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we found a remarkably robust correlation between the two seemingly unrelated phenomena, with a correlation coefficient of 0.8406801 and p < 0.05 for the years 2004 to 2018. While the causality remains elusive, our findings invite speculation and spark amusement as we delve into the eccentric world of electoral politics and carbonated beverage fandom. This research ignites not only intellectual curiosity but also a craving for scholarly pursuits that teeter on the edge of quirkiness.

[[INTRODUCTION]]
The intersection of political behavior and consumer preferences has long been a subject of interest, from the correlation between voter turnout and the sale of snack foods to the potential influence of soft drink preferences on electoral choices. In this vein, our research delves into the peculiar milieu of Democrat votes in Wisconsin and the seemingly unrelated but undeniably titillating Google searches for 'Dr Pepper vs Mr Pibb'. While the former may seem a weighty matter of civic duty and governance, the latter represents a quizzical divergence into the realm of carbonated beverage allegiance.
Indeed, the correlation between political sway and soft drink queries may seem like an odd pairing, akin to the discordant fusion of flavors one might encounter in a misguided soda concoction. Yet, as we embarked on this study, we were struck by the whimsical parallels and the potential for hidden layers of connection, much like the nuanced interplay of flavors in a cola-based beverage.
Our investigation, rooted in data garnered from the MIT Election Data and Science Lab, Harvard Dataverse, and the whimsical world of Google Trends, revealed a surprisingly robust correlation of 0.8406801 between Democrat votes in Wisconsin and the fervent quest for knowledge regarding 'Dr Pepper vs Mr Pibb'. This unanticipated coupling prompted both scholarly consternation and a sense of fizzy delight as we endeavored to comprehend the confluence of political inclinations and fizzy drink fervor.
As we delve deeper into the findings, we invite readers to accompany us on a whimsical journey that may challenge preconceived notions and provoke mirthful rumination. The enchanting interplay between political choices and carbonated quandaries offers a respite from the weighty matters of state, a refreshingly effervescent diversion punctuated with the tantalizing allure of nuanced correlations and tickling queries.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
The empirical data utilized in this research endeavor was procured from a diverse array of sources, accentuating the comprehensive nature of our investigative approach. The primary repositories harnessed for this purpose were the MIT Election Data and Science Lab, the Harvard Dataverse, and the vibrant, effervescent realm of Google Trends. This trifecta of data fountains provided a well-rounded and interdisciplinary foundation, akin to the balanced blend of flavors one might encounter in a well-crafted soda beverage.

Time Frame:
The temporal horizon of this study spanned from the year 2004 to 2018, encapsulating a quinquennial kaleidoscope of electoral dynamics and digital reverberations. This broad temporal scope allowed us to capture the nuances of electoral cycles, tempering the transience of ephemeral political fervor with the enduring effervescence of carbonated curiosity.

Quantitative Analysis:
A nuanced amalgamation of quantitative techniques was employed to disentangle the enigmatic relationship between the electoral disposition of Democrat voters in Wisconsin and their inquisitive musings on the perennial debate of 'Dr Pepper vs Mr Pibb'. The correlation coefficient was calculated to gauge the strength and direction of the relationship, unveiling an unexpectedly robust correlation of 0.8406801. Through meticulous statistical scrutiny, we sought to unearth the subtle nuances and effervescent ruminations hidden within the troves of data, mirroring the meticulous craftsmanship of a seasoned soda mixologist.

Cross-Domain Integration:
Transforming digital reverberations into meaningful inferences necessitated a convergence of political science and digital analytics. The integration of political data from esteemed repositories with the idiosyncratic trends of carbonated quibbles furnished a kaleidoscopic canvas, painting a tableau of electoral intrigue punctuated by whimsical carbonation. This interdisciplinary synergy mirrored the playful dance of bubbles rising to the surface in a carbonated beverage, as we sought to compose a symphony of insights from seemingly discordant melodies.

Robustness Checks:
To substantiate the veracity of our findings, robustness checks were conducted to ensure the sustainability and resilience of our results in the face of methodological perturbations. Sensitivity analyses and model diagnostics served as the bedrock of our methodological prudence, akin to the meticulous tinkering and tweaking inherent in the pursuit of crafting the perfect soda concoction.


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 Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 2004 to 2018, you found a correlation 0.8406801, r-squared of 0.7067430, and p < 0.05.

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]]
Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'

[[ABSTRACT]]
This paper endeavors to unravel the enigmatic relationship between the voting behavior of Democrats in Wisconsin and their curiosity regarding the timeless debate of 'Dr Pepper vs Mr Pibb' through the lens of Google search trends. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we found a remarkably robust correlation between the two seemingly unrelated phenomena, with a correlation coefficient of 0.8406801 and p < 0.05 for the years 2004 to 2018. While the causality remains elusive, our findings invite speculation and spark amusement as we delve into the eccentric world of electoral politics and carbonated beverage fandom. This research ignites not only intellectual curiosity but also a craving for scholarly pursuits that teeter on the edge of quirkiness.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of political behavior and consumer preferences has long been a subject of interest, from the correlation between voter turnout and the sale of snack foods to the potential influence of soft drink preferences on electoral choices. In this vein, our research delves into the peculiar milieu of Democrat votes in Wisconsin and the seemingly unrelated but undeniably titillating Google searches for 'Dr Pepper vs Mr Pibb'. While the former may seem a weighty matter of civic duty and governance, the latter represents a quizzical divergence into the realm of carbonated beverage allegiance.
Indeed, the correlation between political sway and soft drink queries may seem like an odd pairing, akin to the discordant fusion of flavors one might encounter in a misguided soda concoction. Yet, as we embarked on this study, we were struck by the whimsical parallels and the potential for hidden layers of connection, much like the nuanced interplay of flavors in a cola-based beverage.
Our investigation, rooted in data garnered from the MIT Election Data and Science Lab, Harvard Dataverse, and the whimsical world of Google Trends, revealed a surprisingly robust correlation of 0.8406801 between Democrat votes in Wisconsin and the fervent quest for knowledge regarding 'Dr Pepper vs Mr Pibb'. This unanticipated coupling prompted both scholarly consternation and a sense of fizzy delight as we endeavored to comprehend the confluence of political inclinations and fizzy drink fervor.
As we delve deeper into the findings, we invite readers to accompany us on a whimsical journey that may challenge preconceived notions and provoke mirthful rumination. The enchanting interplay between political choices and carbonated quandaries offers a respite from the weighty matters of state, a refreshingly effervescent diversion punctuated with the tantalizing allure of nuanced correlations and tickling queries.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data revealed a striking correlation between Democrat votes for Senators in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb'. The correlation coefficient was found to be 0.8406801, indicating a strong positive relationship between the two variables. The r-squared value of 0.7067430 further attested to the robustness of this correlation. The p-value being less than 0.05 suggests that this relationship is statistically significant.

The Figure 1 scatterplot (not included) visually depicts the compelling correlation between Democrat votes for Senators in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb'. The pattern of the data points further underscores the substantial link between these seemingly incongruous domains, reminiscent of the effervescent interplay of bubbles in a carbonated beverage.

The strength of this correlation offers an intriguing insight into the intersections of consumer culture and political behavior, illuminating a facet of human curiosity that transcends the conventional bounds of electoral analysis and quenches the thirst for unconventional correlations. While our findings do not establish causality, they beckon to the whimsical and the unexpected, inviting scholarly reflection on the capricious nature of human preferences and the delightful intricacies of electoral participation.

In conclusion, the results of this study not only underscore the remarkable correlation between Democrat votes in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb' but also infuse a spirit of whimsy into the otherwise staid domain of electoral research. The confluence of political engagement and the quest for carbonated enlightenment constitutes a delightful enigma that tantalizes the intellect and tickles the fancy, leaving scholars and enthusiasts alike effervescent with a zest for the unconventional.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'

[[ABSTRACT]]
This paper endeavors to unravel the enigmatic relationship between the voting behavior of Democrats in Wisconsin and their curiosity regarding the timeless debate of 'Dr Pepper vs Mr Pibb' through the lens of Google search trends. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we found a remarkably robust correlation between the two seemingly unrelated phenomena, with a correlation coefficient of 0.8406801 and p < 0.05 for the years 2004 to 2018. While the causality remains elusive, our findings invite speculation and spark amusement as we delve into the eccentric world of electoral politics and carbonated beverage fandom. This research ignites not only intellectual curiosity but also a craving for scholarly pursuits that teeter on the edge of quirkiness.

[[LITERATURE REVIEW]]
The scholarly exploration of seemingly incongruous phenomena such as political behavior and consumer predilections has been a subject of keen interest among researchers. Smith et al. (2010) expounded upon the correlation between voter turnout and the sale of snack foods, shedding light on the tantalizing intersection of civic engagement and culinary cravings. Building upon this tradition of scholarly inquiry, Doe and Jones (2015) delved into the potential influence of soft drink preferences on electoral choices, uncovering intriguing connections between carbonated beverage inclinations and political predilections.
Furthermore, in "Soda Wars: A Beverage Battle for the Ages," the authors delve into the storied rivalry between different carbonated beverages and the fervent allegiance of their respective enthusiasts, offering an insightful foray into the cultural fascination with fizzy drink fandom and the fervent debates surrounding particular soda brands. Similarly, "Fizz Fandom: The Cultural Phenomenon of Carbonated Beverages" provides a captivating exploration of the whimsical world of soda aficionados and the fervent loyalty they exhibit toward their preferred effervescent libations.
Moving from non-fiction to fiction, the literary world offers a wealth of imaginative works that tangentially touch upon the peculiar nexus between political choices and carbonated conundrums. "The Pop Politics Chronicles: A Tale of Two Sodas" whimsically weaves a narrative that follows the intertwining fates of a political maverick and a fervent advocate for a niche soda brand, spotlighting the unexpected ways in which fizzy fervor intersects with electoral endeavors. In a similar vein, "Soda Shenanigans: A Carbonated Comedy of Political Proportions" offers a delightful romp through the whimsical shenanigans that transpire when electoral antics collide with the zany world of soda aficionados.
In the realm of cinema, the celluloid medium has also dabbled in the droll intersection of political machinations and fizzy drink fervor. "The Carbonated Campaign: A Tale of Electoral Elixirs" showcases the delightful absurdity that unfolds when political contenders find themselves embroiled in a battle not only for votes but also for the fervent allegiance of soda enthusiasts. This cinematic portrayal offers a whimsical exploration of the unexpected parallels between political battles and bubbly rivalries, inviting viewers to revel in the fizzy frolic that unfolds on the silver screen.

[[RESULTS]]
The analysis of the data revealed a striking correlation between Democrat votes for Senators in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb'. The correlation coefficient was found to be 0.8406801, indicating a strong positive relationship between the two variables. The r-squared value of 0.7067430 further attested to the robustness of this correlation. The p-value being less than 0.05 suggests that this relationship is statistically significant.
The Figure 1 scatterplot (not included) visually depicts the compelling correlation between Democrat votes for Senators in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb'. The pattern of the data points further underscores the substantial link between these seemingly incongruous domains, reminiscent of the effervescent interplay of bubbles in a carbonated beverage.
The strength of this correlation offers an intriguing insight into the intersections of consumer culture and political behavior, illuminating a facet of human curiosity that transcends the conventional bounds of electoral analysis and quenches the thirst for unconventional correlations. While our findings do not establish causality, they beckon to the whimsical and the unexpected, inviting scholarly reflection on the capricious nature of human preferences and the delightful intricacies of electoral participation.
In conclusion, the results of this study not only underscore the remarkable correlation between Democrat votes in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb' but also infuse a spirit of whimsy into the otherwise staid domain of electoral research. The confluence of political engagement and the quest for carbonated enlightenment constitutes a delightful enigma that tantalizes the intellect and tickles the fancy, leaving scholars and enthusiasts alike effervescent with a zest for the unconventional.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study contribute to the growing body of research that explores the whimsical dance of correlations between seemingly unrelated phenomena. Our results, robustly supported by a correlation coefficient of 0.8406801 and a statistically significant p-value of < 0.05, align with the spirited investigations of Smith et al. (2010) into the overlapping spheres of civic participation and gastronomic preferences. Just as the consumption of snack foods appears to coalesce with voter turnout, our study unveils a delightful confluence of political proclivities with the fervent pondering over the subtleties of carbonated elixirs.

The parallels between our findings and those of Doe and Jones (2015) are equally striking, as both studies seek to unravel the mystique surrounding the influence of consumer choices on electoral leanings. In this vein, the unmistakable correlation we have uncovered between Democrat votes in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb' adds a fizzy dimension to the world of political comportment and consumer predilections.

Our analysis not only fortifies the link between political behavior and carbonated musings but also echoes the sentiment of "The Pop Politics Chronicles: A Tale of Two Sodas," where the colorful interplay between a political maverick and a fervent soda advocate mirrors the symbiotic relationship between the electoral tendencies of Democrats in Wisconsin and their intriguing proclivity to explore the nuances of fizzy libations via online searches.

Our results further mirror the cinematic romp depicted in "The Carbonated Campaign: A Tale of Electoral Elixirs," with the captivating correlation between Democrat votes and 'Dr Pepper vs Mr Pibb' searches serving as a delightful analogue to the spirited on-screen portrayal of political contenders vying for the allegiance of fervent soda enthusiasts. Just as the celluloid medium artfully captures the whimsy of electoral shenanigans interwoven with the zany world of soda aficionados, our research animates the academic landscape with a robust correlation that sizzles with unexpected amusement.

In conclusion, our study not only enriches the discourse on the uncharted terrain of electoral curiosities and beverage predilections but also proffers a lighthearted interplay of correlations that beckon to the capricious side of human fascination. As we toast to the unexpected nexus between political engagements and the quest for carbonated enlightenment, our research invites scholars and enthusiasts to savor the tantalizing flavors of unconventional correlations and revel in the effervescent interplay of human curiosities.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Democrat votes for Senators in Wisconsin and Google searches for 'dr pepper vs mr pibb'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'

[[ABSTRACT]]
This paper endeavors to unravel the enigmatic relationship between the voting behavior of Democrats in Wisconsin and their curiosity regarding the timeless debate of 'Dr Pepper vs Mr Pibb' through the lens of Google search trends. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we found a remarkably robust correlation between the two seemingly unrelated phenomena, with a correlation coefficient of 0.8406801 and p < 0.05 for the years 2004 to 2018. While the causality remains elusive, our findings invite speculation and spark amusement as we delve into the eccentric world of electoral politics and carbonated beverage fandom. This research ignites not only intellectual curiosity but also a craving for scholarly pursuits that teeter on the edge of quirkiness.

[[INTRDUCTION]]
The intersection of political behavior and consumer preferences has long been a subject of interest, from the correlation between voter turnout and the sale of snack foods to the potential influence of soft drink preferences on electoral choices. In this vein, our research delves into the peculiar milieu of Democrat votes in Wisconsin and the seemingly unrelated but undeniably titillating Google searches for 'Dr Pepper vs Mr Pibb'. While the former may seem a weighty matter of civic duty and governance, the latter represents a quizzical divergence into the realm of carbonated beverage allegiance.
Indeed, the correlation between political sway and soft drink queries may seem like an odd pairing, akin to the discordant fusion of flavors one might encounter in a misguided soda concoction. Yet, as we embarked on this study, we were struck by the whimsical parallels and the potential for hidden layers of connection, much like the nuanced interplay of flavors in a cola-based beverage.
Our investigation, rooted in data garnered from the MIT Election Data and Science Lab, Harvard Dataverse, and the whimsical world of Google Trends, revealed a surprisingly robust correlation of 0.8406801 between Democrat votes in Wisconsin and the fervent quest for knowledge regarding 'Dr Pepper vs Mr Pibb'. This unanticipated coupling prompted both scholarly consternation and a sense of fizzy delight as we endeavored to comprehend the confluence of political inclinations and fizzy drink fervor.
As we delve deeper into the findings, we invite readers to accompany us on a whimsical journey that may challenge preconceived notions and provoke mirthful rumination. The enchanting interplay between political choices and carbonated quandaries offers a respite from the weighty matters of state, a refreshingly effervescent diversion punctuated with the tantalizing allure of nuanced correlations and tickling queries.

[[RESULTS]]
The analysis of the data revealed a striking correlation between Democrat votes for Senators in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb'. The correlation coefficient was found to be 0.8406801, indicating a strong positive relationship between the two variables. The r-squared value of 0.7067430 further attested to the robustness of this correlation. The p-value being less than 0.05 suggests that this relationship is statistically significant.
The Figure 1 scatterplot (not included) visually depicts the compelling correlation between Democrat votes for Senators in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb'. The pattern of the data points further underscores the substantial link between these seemingly incongruous domains, reminiscent of the effervescent interplay of bubbles in a carbonated beverage.
The strength of this correlation offers an intriguing insight into the intersections of consumer culture and political behavior, illuminating a facet of human curiosity that transcends the conventional bounds of electoral analysis and quenches the thirst for unconventional correlations. While our findings do not establish causality, they beckon to the whimsical and the unexpected, inviting scholarly reflection on the capricious nature of human preferences and the delightful intricacies of electoral participation.
In conclusion, the results of this study not only underscore the remarkable correlation between Democrat votes in Wisconsin and Google searches for 'Dr Pepper vs Mr Pibb' but also infuse a spirit of whimsy into the otherwise staid domain of electoral research. The confluence of political engagement and the quest for carbonated enlightenment constitutes a delightful enigma that tantalizes the intellect and tickles the fancy, leaving scholars and enthusiasts alike effervescent with a zest for the unconventional.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In contemplating our findings, we find ourselves immersed in the delightful conundrum of the correlation between Democrat votes in Wisconsin and the query for 'Dr Pepper vs Mr Pibb'. The robustness of the relationship between these phenomena, akin to the effervescent dance of bubbles in a fizzy drink, elicits both scholarly curiosity and a sense of whimsical amusement.

The unexpected nature of this correlation tickles the intellect much like carbonation titillates the taste buds, leaving us both bemused and invigorated by the peculiar interplay of political inclinations and carbonated curiosities. As we ponder the potential ramifications and underlying motivations for this correlation, we cannot help but revel in the delightful enigma that this juxtaposition presents.

Our research invites not only scholarly reflection but also the mirthful indulgence of pondering the quixotic connections that underpin human behavior. The playful dance between political choices and the quest for fizzy enlightenment opens a realm of intellectual amusement and curious diversion, reminding us that scholarly pursuits can indeed have a lighthearted and effervescent quality.

In light of these findings, we assert that no further research is warranted in this particular domain, as the splendid fusion of political shenanigans and carbonated fervor has been delightfully illuminated through our study. The tale of 'Dr Pepper vs Mr Pibb' and Democrat votes in Wisconsin stands as a testament to the unpredictable tapestry of human interests, infusing the staid realm of electoral research with a delightful dash of whimsy.


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 Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Political Phenomena


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 Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb'. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Social Science 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 Bubbly Battles and Political Shenanigans: The Curious Case of Democrat Votes in Wisconsin and Google Searches for 'Dr Pepper vs Mr Pibb' with an abstract of This paper endeavors to unravel the enigmatic relationship between the voting behavior of Democrats in Wisconsin and their curiosity regarding the timeless debate of 'Dr Pepper vs Mr Pibb' through the lens of Google search trends. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we found a remarkably robust correlation between the two seemingly unrelated phenomena, with a correlation coefficient of 0.8406801 and p < 0.05 for the years 2004 to 2018. While the causality remains elusive, our findings invite speculation and spark amusement as we delve into the eccentric world of electoral politics and carbonated beverage fandom. This research ignites not only intellectual curiosity but also a craving for scholarly pursuits that teeter on the edge of quirkiness.

ChatGPT:

Democrat votes Wisconsin, Google search trends, Dr Pepper vs Mr Pibb, MIT Election Data and Science Lab, Harvard Dataverse, correlation coefficient, electoral politics, carbonated beverage fandom, Google Trends, causality, correlation analysis

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

Google searches for 'dr pepper vs mr pibb'
Detailed data title: Relative volume of Google searches for 'dr pepper vs mr pibb' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'dr pepper vs mr pibb'

Correlation r = 0.8406801 (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 = 0.7067430 (Coefficient of determination)
This means 70.7% of the change in the one variable (i.e., Google searches for 'dr pepper vs mr pibb') is predictable based on the change in the other (i.e., Votes for Democratic Senators in Wisconsin) over the 6 years from 2004 through 2018.

p < 0.05, which statistically significant(Null hypothesis significance test)
The p-value is 0.0361. 0.0360522578044902800000000000
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 0.84 in 3.61% of random cases. Said differently, if you correlated 28 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.

[ 0.09, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200420062010201220162018
Votes for Democratic Senators in Wisconsin (Percentage of votes)55.350567.306547.019951.408946.81155.4177
Google searches for 'dr pepper vs mr pibb' (Rel. search volume)8.3333310.91673.166671.6666744.41667




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([55.3505,67.3065,47.0199,51.4089,46.811,55.4177,])
array_2 = np.array([8.33333,10.9167,3.16667,1.66667,4,4.41667,])
array_1_name = "Votes for Democratic Senators in Wisconsin"
array_2_name = "Google searches for 'dr pepper vs mr pibb'"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating is stellar!


Correlation ID: 4983 · Black Variable ID: 26483 · Red Variable ID: 1363
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0