about · email me · subscribe
Spurious correlation #5,961 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'XL tee shirts' and the second variable is Republican votes for Senators in Michigan.  The chart goes from 2004 to 2020, and the two variables track closely in value over that time. Small Image

AI explanation

As XL tee shirt popularity grew, so did the number of people wearing them to Michigan's Upper Peninsula, known for its support of Republican candidates. The correlation is clear: more fabric meant more conservative votes, as the region became a stronghold for the GOP, or rather, the Grand Old Polo (shirt).

Model: dalle-3
Prompt: Prompt: Generate a whimsical, cute cartoon-style illustration of a lively town hall meeting in Michigan's Upper Peninsula. Depict a bustling room filled with adorable, chubby-cheeked characters wearing oversized XL tee shirts. The walls are decorated with colorful signs supporting Republican candidates, and the characters are enthusiastically searching for last-minute political information on their smartphones. Capture the palpable energy and excitement in the room, emphasizing the correlation between the popularity of XL tee shirts and the region's Republican stronghold. Ensure that the scene radiates a cheerful and vibrant atmosphere, with a focus on capturing the animated interactions and adorable expressions of the characters. 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: Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. 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: Cybernetic art Cute cartoon Parallax art Hyper-realistic Macabre
ChatGPT: Cute cartoon

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 Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan, in the following situation: As XL tee shirt popularity grew, so did the number of people wearing them to Michigan's Upper Peninsula, known for its support of Republican candidates. The correlation is clear: more fabric meant more conservative votes, as the region became a stronghold for the GOP, or rather, the Grand Old Polo (shirt).. Keep the description simple.
ChatGPT: In Michigan's Upper Peninsula, a crowded town hall was filled with people wearing XL tee shirts. The walls were adorned with signs supporting Republican candidates, and the room buzzed with excitement as people eagerly searched on their phones for last-minute information. The correlation between the popularity of XL tee shirts and the Republican stronghold in the region was evident.

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: [ Cute cartoon ] and depicting this scene: In Michigan's Upper Peninsula, a crowded town hall was filled with people wearing XL tee shirts. The walls were adorned with signs supporting Republican candidates, and the room buzzed with excitement as people eagerly searched on their phones for last-minute information. The correlation between the popularity of XL tee shirts and the Republican stronghold in the region was evident. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate a whimsical, cute cartoon-style illustration of a lively town hall meeting in Michigan's Upper Peninsula. Depict a bustling room filled with adorable, chubby-cheeked characters wearing oversized XL tee shirts. The walls are decorated with colorful signs supporting Republican candidates, and the characters are enthusiastically searching for last-minute political information on their smartphones. Capture the palpable energy and excitement in the room, emphasizing the correlation between the popularity of XL tee shirts and the region's Republican stronghold. Ensure that the scene radiates a cheerful and vibrant atmosphere, with a focus on capturing the animated interactions and adorable expressions of the characters.

*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 XL tee shirts (Google searches for 'XL tee shirts') caused Republican votes for Senators in Michigan to increase.

AI academic paper

(Because p < 0.01)
The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections

The Journal of Political Fashion Analysis

Jan 2024
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 witty academic researcher. Your writing sounds like it belongs in a statistics 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 Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Make lots of jokes, goofy observations, and puns.

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

Your research team used data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to assess this nagging question. You found a correlation coefficient of 0.9321040 and p < 0.01 for 2004 to 2020.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections"

[[ABSTRACT]]
In this study, we investigate the surprising correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. We delved deep into the data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to explore this seemingly whimsical link. Our analysis revealed a striking correlation coefficient of 0.9321040 with a p-value less than 0.01, suggesting a statistically significant relationship between these disparate variables. Our findings challenge conventional wisdom and invite further investigation into the potential influence of fashion preferences on political behavior. Whether voters were seeking larger sizes to accommodate post-election stress eating or simply demonstrating a penchant for roomier apparel, our research adds a new dimension to the understanding of voter behavior.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections"

[[ABSTRACT]]
In this study, we investigate the surprising correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. We delved deep into the data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to explore this seemingly whimsical link. Our analysis revealed a striking correlation coefficient of 0.9321040 with a p-value less than 0.01, suggesting a statistically significant relationship between these disparate variables. Our findings challenge conventional wisdom and invite further investigation into the potential influence of fashion preferences on political behavior. Whether voters were seeking larger sizes to accommodate post-election stress eating or simply demonstrating a penchant for roomier apparel, our research adds a new dimension to the understanding of voter behavior.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

The intersection of fashion and politics is not a topic commonly explored in academic research. However, in the world of statistics, even the most unlikely relationships can reveal surprising insights. In this paper, we delve into the curious connection between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Yes, you read that correctly – we're about to take a statistical journey through the wardrobe of Michigan voters and its potential impact on their political preferences.

We live in an era where every click, tap, and swipe leaves behind a digital footprint, and these breadcrumbs of data offer tantalizing possibilities for uncovering unexpected correlations. As researchers, it's our duty to peer into the abyss of information and emerge with meaningful insights – or at least some entertaining anecdotes to share at academic conferences.

Our quest began with a simple yet quirky question: Could there be a link between an uptick in online searches for generously sized garments and the political leanings of Michigan residents? Armed with an arsenal of statistical tools and a love for unconventional investigations, we embarked on this journey to unravel the mysteries lurking beneath the hems of XL tee shirts.

The idea that fashion preferences could sway political allegiances might initially seem far-fetched, akin to a statistical unicorn prancing through a data meadow. However, as every seasoned researcher knows, the whims of statistical significance can sometimes lead us down unexpected paths. We set out to scrutinize this unlikely pairing with the seriousness of a researcher on a mission – albeit a mission with a healthy dose of whimsy and wonder.

This unusual inquiry was born from a hunch that in the intricate web of human behavior, hidden threads might connect seemingly unrelated aspects of our lives. Our quest was not merely to satisfy academic curiosity, but to shed light on the curious fabric of human decision-making – pun fully intended.

Now, buckle up as we embark on an empirical escapade through the realms of search trends and political landscapes. Our findings may surprise, bewilder, or perhaps even elicit a chuckle or two. After all, in the world of research, unexpected discoveries are akin to finding a statistical diamond in the rough.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. 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]]
"The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections"

[[ABSTRACT]]
In this study, we investigate the surprising correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. We delved deep into the data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to explore this seemingly whimsical link. Our analysis revealed a striking correlation coefficient of 0.9321040 with a p-value less than 0.01, suggesting a statistically significant relationship between these disparate variables. Our findings challenge conventional wisdom and invite further investigation into the potential influence of fashion preferences on political behavior. Whether voters were seeking larger sizes to accommodate post-election stress eating or simply demonstrating a penchant for roomier apparel, our research adds a new dimension to the understanding of voter behavior.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The intersection of fashion and politics is not a topic commonly explored in academic research. However, in the world of statistics, even the most unlikely relationships can reveal surprising insights. In this paper, we delve into the curious connection between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Yes, you read that correctly – we're about to take a statistical journey through the wardrobe of Michigan voters and its potential impact on their political preferences.
We live in an era where every click, tap, and swipe leaves behind a digital footprint, and these breadcrumbs of data offer tantalizing possibilities for uncovering unexpected correlations. As researchers, it's our duty to peer into the abyss of information and emerge with meaningful insights – or at least some entertaining anecdotes to share at academic conferences.
Our quest began with a simple yet quirky question: Could there be a link between an uptick in online searches for generously sized garments and the political leanings of Michigan residents? Armed with an arsenal of statistical tools and a love for unconventional investigations, we embarked on this journey to unravel the mysteries lurking beneath the hems of XL tee shirts.
The idea that fashion preferences could sway political allegiances might initially seem far-fetched, akin to a statistical unicorn prancing through a data meadow. However, as every seasoned researcher knows, the whims of statistical significance can sometimes lead us down unexpected paths. We set out to scrutinize this unlikely pairing with the seriousness of a researcher on a mission – albeit a mission with a healthy dose of whimsy and wonder.
This unusual inquiry was born from a hunch that in the intricate web of human behavior, hidden threads might connect seemingly unrelated aspects of our lives. Our quest was not merely to satisfy academic curiosity, but to shed light on the curious fabric of human decision-making – pun fully intended.
Now, buckle up as we embark on an empirical escapade through the realms of search trends and political landscapes. Our findings may surprise, bewilder, or perhaps even elicit a chuckle or two. After all, in the world of research, unexpected discoveries are akin to finding a statistical diamond in the rough.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The interplay between fashion and political behavior, while not a traditional focus of academic inquiry, has captured the attention of researchers seeking to unravel the complex tapestry of human decision-making. Our investigation into the correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan builds on prior studies that have grappled with unexpected associations in the realm of societal influences on electoral outcomes.

Smith et al. (2015) conducted a pioneering study that explored the impact of clothing trends on voter predispositions in electoral contests. Their research shed light on the subtle ways in which sartorial choices may intersect with political leanings, prompting our curiosity about the specific relationship between oversized apparel and conservative ballots cast in Michigan.

Building on this foundation, Doe and Jones (2018) delved into the conspicuous connection between consumer shopping habits and political affiliations, offering a thought-provoking analysis of the potential implications of retail preferences on electoral outcomes. Their work inspired us to expand the scope of our inquiry to the virtual realm of online searches and its reflection of voters' ideological inclinations.

As we venture further into this whimsical landscape, it is worth considering the broader influences that may shape our understanding of this unlikely relationship. "Fashion and Politics: The Unlikely Pair" by Taylor (2017) provides an insightful exploration of the ways in which attire can serve as a form of expressive communication, offering potential insights into the relationship between clothing preferences and political choices – though the specific case of XL tee shirts eluded the scope of Taylor's scrutiny.

Turning to the fictional realm, "The Clothes Make the Candidate" by Austen (1813) presents a satirical exploration of the role of fashion in political posturing, offering a lighthearted yet shrewd commentary on the influence of sartorial selections in the pursuit of power. While a work of fiction, the themes woven into Austen's narrative serve as a whimsical backdrop to our empirical journey through the digital corridors of Google searches and political allegiances.

In the cinematic realm, "The Devil Wears Prada" (2006) offers a tantalizing glimpse into the intricacies of fashion and societal perceptions, albeit in the context of the high-stakes world of haute couture rather than the more modest domain of XL tee shirts. Yet, in the spirit of embracing unexpected parallels, this film reminds us of the nuanced interplay between style and personal identity, echoing the undercurrents of individual expression that may reverberate in the choices reflected in search queries and ballot decisions alike.

As we navigate the borderlands of fashion and politics in our pursuit of understanding the XL tee shirt phenomenon and its correlation to Republican votes in Michigan, it is with both scholarly rigor and a penchant for whimsy that we embark on this analytical odyssey. The literature reviewed here offers a mere glimpse into the mosaic of influences that inform our investigation, serving as a springboard for the empirical revelations that await in our quest to unravel the threads connecting garment dimensions and political inclinations.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse . You used data from 2004 to 2020

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections"

[[ABSTRACT]]
In this study, we investigate the surprising correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. We delved deep into the data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to explore this seemingly whimsical link. Our analysis revealed a striking correlation coefficient of 0.9321040 with a p-value less than 0.01, suggesting a statistically significant relationship between these disparate variables. Our findings challenge conventional wisdom and invite further investigation into the potential influence of fashion preferences on political behavior. Whether voters were seeking larger sizes to accommodate post-election stress eating or simply demonstrating a penchant for roomier apparel, our research adds a new dimension to the understanding of voter behavior.

[[INTRODUCTION]]
INTRODUCTION
The intersection of fashion and politics is not a topic commonly explored in academic research. However, in the world of statistics, even the most unlikely relationships can reveal surprising insights. In this paper, we delve into the curious connection between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Yes, you read that correctly – we're about to take a statistical journey through the wardrobe of Michigan voters and its potential impact on their political preferences.
We live in an era where every click, tap, and swipe leaves behind a digital footprint, and these breadcrumbs of data offer tantalizing possibilities for uncovering unexpected correlations. As researchers, it's our duty to peer into the abyss of information and emerge with meaningful insights – or at least some entertaining anecdotes to share at academic conferences.
Our quest began with a simple yet quirky question: Could there be a link between an uptick in online searches for generously sized garments and the political leanings of Michigan residents? Armed with an arsenal of statistical tools and a love for unconventional investigations, we embarked on this journey to unravel the mysteries lurking beneath the hems of XL tee shirts.
The idea that fashion preferences could sway political allegiances might initially seem far-fetched, akin to a statistical unicorn prancing through a data meadow. However, as every seasoned researcher knows, the whims of statistical significance can sometimes lead us down unexpected paths. We set out to scrutinize this unlikely pairing with the seriousness of a researcher on a mission – albeit a mission with a healthy dose of whimsy and wonder.
This unusual inquiry was born from a hunch that in the intricate web of human behavior, hidden threads might connect seemingly unrelated aspects of our lives. Our quest was not merely to satisfy academic curiosity, but to shed light on the curious fabric of human decision-making – pun fully intended.
Now, buckle up as we embark on an empirical escapade through the realms of search trends and political landscapes. Our findings may surprise, bewilder, or perhaps even elicit a chuckle or two. After all, in the world of research, unexpected discoveries are akin to finding a statistical diamond in the rough.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
To unravel the enigmatic link between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan, we embarked on a comical crusade through the digital realm. Our primary source of data was the ever-illuminating Google Trends, a veritable treasure trove of search queries that spans from the whimsical to the weighty – quite fitting for our XL tee shirt pursuit. We meticulously extracted the search trend data for 'XL tee shirts' within the state of Michigan from 2004 to 2020, observing the ebbs and flows of sartorial curiosity amidst the political landscape.

Simultaneously, we sought to capture the political pulse of Michigan voters, for which we turned to the MIT Election Data and Science Lab and the Harvard Dataverse. These esteemed repositories provided us with the splendidly granular electoral data, allowing us to scrutinize the Republican votes for Senators with the fervor of determined fashion critics examining a runway show.

Experimental Design:
In concocting our statistical cocktail to discern the relationship between online searches for ample apparel and political propensities, we applied a medley of techniques that would make even the most seasoned statistician let out a chuckle. Our analysis involved a delightful dance of correlation coefficients, regression models, and a sprinkle of time-series analysis, creating a statistical fiesta that would have made even the most resolute data skeptic twirl with curiosity.

Correlation Assessment:
To gauge the strength of the relationship between 'XL tee shirts' searches and Republican senatorial votes, we sashayed into the realm of correlation analysis. Armed with our trusty statistical software and a splash of whimsy, we calculated the Pearson correlation coefficient, all while donning metaphorical tuxedos and ball gowns to attend this grand statistical soiree. Our fingers danced across the keyboards as we validated our findings with the appropriate t-tests, ensuring that our correlation was not merely a statistical fling, but a meaningful connection worthy of the research runway.

Time-Series Analysis:
Recognizing that the ebb and flow of fashion fads and political fervor are dynamic phenomena, we indulged in a time-series analysis to capture the temporal nuances of this peculiar association. With the grace of a dancer and the precision of a chronometer, we examined the evolution of 'XL tee shirts' searches alongside the senatorial voting tendencies, teasing out the underlying patterns in their delightful statistical waltz.

Regression Modeling:
In our spirited pursuit of understanding the potential impact of XL tee shirt inquiries on Republican voter inclinations, we waltzed into the world of regression modeling. With a twirl and a flourish, we conjured models that encapsulated the variance in senatorial votes as a whimsical ballet of 'XL tee shirts' search intensities. We delighted in the artistry of statistical inference, using the p-values to discern the significance of this unconventional pas de deux.

In sum, our methodology formed a whimsical tapestry of statistics, fashion, and politics, weaving a narrative that befitted the unexpected intersection of XL tee shirts and Michigan Senate elections. Our data exploration was not merely a statistical pursuit but an odyssey into the quirky and the quizzical, where academic rigor intertwined with a lighthearted spirit of inquiry.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2004 to 2020, you found a correlation 0.9321040, r-squared of 0.8688178, 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]]
"The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections"

[[ABSTRACT]]
In this study, we investigate the surprising correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. We delved deep into the data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to explore this seemingly whimsical link. Our analysis revealed a striking correlation coefficient of 0.9321040 with a p-value less than 0.01, suggesting a statistically significant relationship between these disparate variables. Our findings challenge conventional wisdom and invite further investigation into the potential influence of fashion preferences on political behavior. Whether voters were seeking larger sizes to accommodate post-election stress eating or simply demonstrating a penchant for roomier apparel, our research adds a new dimension to the understanding of voter behavior.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The intersection of fashion and politics is not a topic commonly explored in academic research. However, in the world of statistics, even the most unlikely relationships can reveal surprising insights. In this paper, we delve into the curious connection between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Yes, you read that correctly – we're about to take a statistical journey through the wardrobe of Michigan voters and its potential impact on their political preferences.
We live in an era where every click, tap, and swipe leaves behind a digital footprint, and these breadcrumbs of data offer tantalizing possibilities for uncovering unexpected correlations. As researchers, it's our duty to peer into the abyss of information and emerge with meaningful insights – or at least some entertaining anecdotes to share at academic conferences.
Our quest began with a simple yet quirky question: Could there be a link between an uptick in online searches for generously sized garments and the political leanings of Michigan residents? Armed with an arsenal of statistical tools and a love for unconventional investigations, we embarked on this journey to unravel the mysteries lurking beneath the hems of XL tee shirts.
The idea that fashion preferences could sway political allegiances might initially seem far-fetched, akin to a statistical unicorn prancing through a data meadow. However, as every seasoned researcher knows, the whims of statistical significance can sometimes lead us down unexpected paths. We set out to scrutinize this unlikely pairing with the seriousness of a researcher on a mission – albeit a mission with a healthy dose of whimsy and wonder.
This unusual inquiry was born from a hunch that in the intricate web of human behavior, hidden threads might connect seemingly unrelated aspects of our lives. Our quest was not merely to satisfy academic curiosity, but to shed light on the curious fabric of human decision-making – pun fully intended.
Now, buckle up as we embark on an empirical escapade through the realms of search trends and political landscapes. Our findings may surprise, bewilder, or perhaps even elicit a chuckle or two. After all, in the world of research, unexpected discoveries are akin to finding a statistical diamond in the rough.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis revealed a surprising and robust correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. The correlation coefficient of 0.9321040 indicated a strong positive relationship between these seemingly unrelated variables. This finding suggests that as the interest in XL tee shirts increased, so did the Republican support in Michigan Senate elections.

The r-squared value of 0.8688178 further reinforced the strength of this relationship, indicating that approximately 87% of the variation in Republican votes for Senators in Michigan can be explained by the fluctuations in searches for 'XL tee shirts.' To put it in layman's terms, it's as if the fashion choices of Michigan residents were singing in harmony with their political preferences, creating a statistical symphony of sorts.

Furthermore, the p-value falling below 0.01 provided compelling evidence that this correlation was not simply a result of random chance. In scientific parlance, this means that the likelihood of such a strong relationship occurring by fluke is less than 1 in 100, a probability rarer than stumbling upon a statistical unicorn in the wilds of academia.

As an added visual treat, we present Fig. 1, a scatterplot that vividly illustrates the striking correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. The figure showcases the data points dancing in near-perfect alignment, much like synchronized swimmers in a statistical pool.

In summary, our findings underscore the unexpected influence of fashion-related online searches on political behavior. While the notion of voters being swayed by the allure of roomy attire may sound whimsical, our results stand as a testament to the uncharted territories of statistical discovery and the quirky intersections of human behavior.

This research opens the door to a multitude of questions and potential implications. Could the rise in XL tee shirt searches be a predictor of political sentiment in other states? Might candidates consider aligning their campaign strategies with fashion trends? The statistical playground holds endless possibilities for further exploration, and we eagerly anticipate the whimsical avenues that future research may unveil.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections"

[[ABSTRACT]]
In this study, we investigate the surprising correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. We delved deep into the data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to explore this seemingly whimsical link. Our analysis revealed a striking correlation coefficient of 0.9321040 with a p-value less than 0.01, suggesting a statistically significant relationship between these disparate variables. Our findings challenge conventional wisdom and invite further investigation into the potential influence of fashion preferences on political behavior. Whether voters were seeking larger sizes to accommodate post-election stress eating or simply demonstrating a penchant for roomier apparel, our research adds a new dimension to the understanding of voter behavior.

[[LITERATURE REVIEW]]
The interplay between fashion and political behavior, while not a traditional focus of academic inquiry, has captured the attention of researchers seeking to unravel the complex tapestry of human decision-making. Our investigation into the correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan builds on prior studies that have grappled with unexpected associations in the realm of societal influences on electoral outcomes.
Smith et al. (2015) conducted a pioneering study that explored the impact of clothing trends on voter predispositions in electoral contests. Their research shed light on the subtle ways in which sartorial choices may intersect with political leanings, prompting our curiosity about the specific relationship between oversized apparel and conservative ballots cast in Michigan.
Building on this foundation, Doe and Jones (2018) delved into the conspicuous connection between consumer shopping habits and political affiliations, offering a thought-provoking analysis of the potential implications of retail preferences on electoral outcomes. Their work inspired us to expand the scope of our inquiry to the virtual realm of online searches and its reflection of voters' ideological inclinations.
As we venture further into this whimsical landscape, it is worth considering the broader influences that may shape our understanding of this unlikely relationship. "Fashion and Politics: The Unlikely Pair" by Taylor (2017) provides an insightful exploration of the ways in which attire can serve as a form of expressive communication, offering potential insights into the relationship between clothing preferences and political choices – though the specific case of XL tee shirts eluded the scope of Taylor's scrutiny.
Turning to the fictional realm, "The Clothes Make the Candidate" by Austen (1813) presents a satirical exploration of the role of fashion in political posturing, offering a lighthearted yet shrewd commentary on the influence of sartorial selections in the pursuit of power. While a work of fiction, the themes woven into Austen's narrative serve as a whimsical backdrop to our empirical journey through the digital corridors of Google searches and political allegiances.
In the cinematic realm, "The Devil Wears Prada" (2006) offers a tantalizing glimpse into the intricacies of fashion and societal perceptions, albeit in the context of the high-stakes world of haute couture rather than the more modest domain of XL tee shirts. Yet, in the spirit of embracing unexpected parallels, this film reminds us of the nuanced interplay between style and personal identity, echoing the undercurrents of individual expression that may reverberate in the choices reflected in search queries and ballot decisions alike.
As we navigate the borderlands of fashion and politics in our pursuit of understanding the XL tee shirt phenomenon and its correlation to Republican votes in Michigan, it is with both scholarly rigor and a penchant for whimsy that we embark on this analytical odyssey. The literature reviewed here offers a mere glimpse into the mosaic of influences that inform our investigation, serving as a springboard for the empirical revelations that await in our quest to unravel the threads connecting garment dimensions and political inclinations.

[[RESULTS]]
The results of our analysis revealed a surprising and robust correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. The correlation coefficient of 0.9321040 indicated a strong positive relationship between these seemingly unrelated variables. This finding suggests that as the interest in XL tee shirts increased, so did the Republican support in Michigan Senate elections.
The r-squared value of 0.8688178 further reinforced the strength of this relationship, indicating that approximately 87% of the variation in Republican votes for Senators in Michigan can be explained by the fluctuations in searches for 'XL tee shirts.' To put it in layman's terms, it's as if the fashion choices of Michigan residents were singing in harmony with their political preferences, creating a statistical symphony of sorts.
Furthermore, the p-value falling below 0.01 provided compelling evidence that this correlation was not simply a result of random chance. In scientific parlance, this means that the likelihood of such a strong relationship occurring by fluke is less than 1 in 100, a probability rarer than stumbling upon a statistical unicorn in the wilds of academia.
As an added visual treat, we present Fig. 1, a scatterplot that vividly illustrates the striking correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. The figure showcases the data points dancing in near-perfect alignment, much like synchronized swimmers in a statistical pool.
In summary, our findings underscore the unexpected influence of fashion-related online searches on political behavior. While the notion of voters being swayed by the allure of roomy attire may sound whimsical, our results stand as a testament to the uncharted territories of statistical discovery and the quirky intersections of human behavior.
This research opens the door to a multitude of questions and potential implications. Could the rise in XL tee shirt searches be a predictor of political sentiment in other states? Might candidates consider aligning their campaign strategies with fashion trends? The statistical playground holds endless possibilities for further exploration, and we eagerly anticipate the whimsical avenues that future research may unveil.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The emergence of a strong correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan in our study not only defies conventional wisdom but also serves as a testament to the marvels of statistical inquiry. Our findings provide empirical support to the whimsical notions posited in prior literature. As we reflect on the unexpected interplay between fashion inclinations and political leanings, the threads of our investigation intertwine with the colorful tapestry of research in the realms of fashion, politics, and statistical analysis.

The correlation coefficient of 0.9321040, akin to a rare gem in the treasure trove of statistical relationships, demonstrates a profoundly substantial link between the voluminous aspirations of fashion and the electoral choices made by Michiganders. It appears that the allure of expansive apparel is not just a matter of personal comfort but also an intriguing marker of political preference. Our results echo the shrewd observations of Austen (1813), who, albeit in a fictional realm, deftly navigated the nuances of fashion's silent dialogue with power dynamics in a humorous yet thought-provoking manner.

The hefty r-squared value of 0.8688178, reminiscent of a robust oak tree offering both shade and substance, reinforces the robustness of this association. Like a well-crafted garment, our statistical model envelops the intricate fluctuations in searches for 'XL tee shirts' and Republican votes for Senators in Michigan, weaving a compelling narrative of symbiotic trends that cannot be easily dismissed as statistical happenstance.

The p-value below 0.01 emerges as a statistical unicorn, a rarity in the cloistered confines of hypothesis testing. This finding resonates with the whimsy of Taylor's (2017) exploration of attire as a form of expressive communication, shedding light on the hidden messages embedded in the virtual quest for commodious clothing and the manifestation of political allegiances at the ballot box.

Our intimate statistical tango with the data, illustrated in the vivid dance of our scatterplot (Fig. 1), presents a visual spectacle akin to a harmonious ballet of numbers and trends. The figures pirouette in fluid alignment, capturing the whimsical yet robust connection between virtual forays into fashion and real-world political proclivities.

As we confront the amusing verity of the XL tee shirt trend exerting a weighty influence on Michigan Senate elections, our findings invite a whimsical musing on the potential implications for electoral prognostication and campaign strategy. Much like the serendipitous encounters with statistical unicorns, our research beckons further exploration into the idiosyncratic nuances of human behavior and its quirky interactions with the whims of the virtual realm.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections"

[[ABSTRACT]]
In this study, we investigate the surprising correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. We delved deep into the data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to explore this seemingly whimsical link. Our analysis revealed a striking correlation coefficient of 0.9321040 with a p-value less than 0.01, suggesting a statistically significant relationship between these disparate variables. Our findings challenge conventional wisdom and invite further investigation into the potential influence of fashion preferences on political behavior. Whether voters were seeking larger sizes to accommodate post-election stress eating or simply demonstrating a penchant for roomier apparel, our research adds a new dimension to the understanding of voter behavior.

[[INTRDUCTION]]
INTRODUCTION
The intersection of fashion and politics is not a topic commonly explored in academic research. However, in the world of statistics, even the most unlikely relationships can reveal surprising insights. In this paper, we delve into the curious connection between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. Yes, you read that correctly – we're about to take a statistical journey through the wardrobe of Michigan voters and its potential impact on their political preferences.
We live in an era where every click, tap, and swipe leaves behind a digital footprint, and these breadcrumbs of data offer tantalizing possibilities for uncovering unexpected correlations. As researchers, it's our duty to peer into the abyss of information and emerge with meaningful insights – or at least some entertaining anecdotes to share at academic conferences.
Our quest began with a simple yet quirky question: Could there be a link between an uptick in online searches for generously sized garments and the political leanings of Michigan residents? Armed with an arsenal of statistical tools and a love for unconventional investigations, we embarked on this journey to unravel the mysteries lurking beneath the hems of XL tee shirts.
The idea that fashion preferences could sway political allegiances might initially seem far-fetched, akin to a statistical unicorn prancing through a data meadow. However, as every seasoned researcher knows, the whims of statistical significance can sometimes lead us down unexpected paths. We set out to scrutinize this unlikely pairing with the seriousness of a researcher on a mission – albeit a mission with a healthy dose of whimsy and wonder.
This unusual inquiry was born from a hunch that in the intricate web of human behavior, hidden threads might connect seemingly unrelated aspects of our lives. Our quest was not merely to satisfy academic curiosity, but to shed light on the curious fabric of human decision-making – pun fully intended.
Now, buckle up as we embark on an empirical escapade through the realms of search trends and political landscapes. Our findings may surprise, bewilder, or perhaps even elicit a chuckle or two. After all, in the world of research, unexpected discoveries are akin to finding a statistical diamond in the rough.

[[RESULTS]]
The results of our analysis revealed a surprising and robust correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. The correlation coefficient of 0.9321040 indicated a strong positive relationship between these seemingly unrelated variables. This finding suggests that as the interest in XL tee shirts increased, so did the Republican support in Michigan Senate elections.
The r-squared value of 0.8688178 further reinforced the strength of this relationship, indicating that approximately 87% of the variation in Republican votes for Senators in Michigan can be explained by the fluctuations in searches for 'XL tee shirts.' To put it in layman's terms, it's as if the fashion choices of Michigan residents were singing in harmony with their political preferences, creating a statistical symphony of sorts.
Furthermore, the p-value falling below 0.01 provided compelling evidence that this correlation was not simply a result of random chance. In scientific parlance, this means that the likelihood of such a strong relationship occurring by fluke is less than 1 in 100, a probability rarer than stumbling upon a statistical unicorn in the wilds of academia.
As an added visual treat, we present Fig. 1, a scatterplot that vividly illustrates the striking correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan. The figure showcases the data points dancing in near-perfect alignment, much like synchronized swimmers in a statistical pool.
In summary, our findings underscore the unexpected influence of fashion-related online searches on political behavior. While the notion of voters being swayed by the allure of roomy attire may sound whimsical, our results stand as a testament to the uncharted territories of statistical discovery and the quirky intersections of human behavior.
This research opens the door to a multitude of questions and potential implications. Could the rise in XL tee shirt searches be a predictor of political sentiment in other states? Might candidates consider aligning their campaign strategies with fashion trends? The statistical playground holds endless possibilities for further exploration, and we eagerly anticipate the whimsical avenues that future research may unveil.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has peeled back the enigmatic layers of Michigan's political landscape, revealing a surprising entwining of fashion and Republican votes. Who would have thought that the humble XL tee shirt could emerge as a heavyweight player in the realm of political preferences? It appears that the voters of Michigan have been casting not just their ballots, but also their digital searches, in a symphony of statistical harmony.

As we reflect on the implications of our findings, one cannot help but ponder the broader ramifications. Could campaign trail merchandising soon feature slogan tees in XL sizes to sway the undecided voters? Will political analysts now scrutinize runway trends alongside polling data? The future of political strategy may indeed be stitched with threads of sartorial insight.

However, we must approach these discoveries with caution and jest – after all, correlation does not imply couture, and statistical significance is no substitute for political nuance. Let us not forget that amidst the pixels and p-values, there lies the heart and soul of the electorate, with motivations as multifaceted as a designer wardrobe.

With our research, we have woven a tapestry of statistical revelation, shedding light on the unexpected dance between fashion and politics. Yet, as we bid adieu to this peculiar yet illuminating expedition, we assert with statistical certainty that no further research is needed in this area. For now, we shall hang up our lab coats and XL tee shirts, content in the knowledge that in the realm of research, as in fashion, there are always more surprising trends waiting to be uncovered.


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 The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Fashion Analysis


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 The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Democratic Fashion Trends Analysis


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The XL Tee Shirt Trend: A Weighty Influence on Michigan Senate Elections with an abstract of In this study, we investigate the surprising correlation between Google searches for 'XL tee shirts' and Republican votes for Senators in Michigan from 2004 to 2020. We delved deep into the data from Google Trends and MIT Election Data and Science Lab, Harvard Dataverse to explore this seemingly whimsical link. Our analysis revealed a striking correlation coefficient of 0.9321040 with a p-value less than 0.01, suggesting a statistically significant relationship between these disparate variables. Our findings challenge conventional wisdom and invite further investigation into the potential influence of fashion preferences on political behavior. Whether voters were seeking larger sizes to accommodate post-election stress eating or simply demonstrating a penchant for roomier apparel, our research adds a new dimension to the understanding of voter behavior.

ChatGPT:

"XL tee shirts trend," "Michigan Senate elections," "Republican votes Michigan 2004-2020," "Google Trends data analysis," "MIT Election Data and Science Lab," "Harvard Dataverse," "correlation between fashion and political behavior," "voter behavior study," "fashion preferences and political influence," "XL tee shirts and political voting correlation," "post-election stress eating," "voter fashion choices."

*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

Google searches for 'XL tee shirts'
Detailed data title: Relative volume of Google searches for 'XL tee shirts' (United States, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'XL tee shirts'

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

Correlation r = 0.9321040 (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 = 0.8688178 (Coefficient of determination)
This means 86.9% of the change in the one variable (i.e., Republican votes for Senators in Michigan) is predictable based on the change in the other (i.e., Google searches for 'XL tee shirts') over the 6 years from 2004 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0068. 0.0067583141740140930000000000
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 0.93 in 0.68% of random cases. Said differently, if you correlated 148 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.

[ 0.49, 0.99 ] 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.
200620082012201420182020
Google searches for 'XL tee shirts' (Rel. search volume)5.251.833332.583334.0833356.16667
Republican votes for Senators in Michigan (Percentage of votes)41.257633.846137.984541.329145.756348.2184




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([5.25,1.83333,2.58333,4.08333,5,6.16667,])
array_2 = np.array([41.2576,33.8461,37.9845,41.3291,45.7563,48.2184,])
array_1_name = "Google searches for 'XL tee shirts'"
array_2_name = "Republican votes for Senators in Michigan"

# 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?

I'm genuinely thankful for your rating!


Correlation ID: 5961 · Black Variable ID: 1439 · Red Variable ID: 26406
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0