about · email me · subscribe
Spurious correlation #5,828 · 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 The number of sewing machine operators in Wisconsin.  The chart goes from 2004 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As XL tee shirt sales shrank, so did the workforce in Wisconsin, it seems they just couldn't 'measure up' to the demand anymore. We'd have thought they could have 'sewn' up the market, but it looks like they 'unraveled' instead.

Model: dalle-3
Prompt: [ Data cyber art ] Generate an image of a Wisconsin factory floor where a small group of dejected sewing machine operators are standing by their workstations. They are inspecting a stack of unsold XL tee shirts, with visible disappointment on their faces. In the background, the factory manager is seen looking at a computer screen displaying decreasing Google searches for "XL tee shirts." The composition should reflect the dwindling demand for their products through the diminishing number of employees. Ensure that the scene depicts a sense of fading industrial relevance and echoes the poignant transition to a changing market landscape. 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 The number of sewing machine operators in Wisconsin. 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: 3D Pixar Style Woodblock painting Scalar art Realistic Data cyber art
ChatGPT: Data cyber art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Google searches for 'XL tee shirts' and The number of sewing machine operators in Wisconsin, in the following situation: As XL tee shirt sales shrank, so did the workforce in Wisconsin, it seems they just couldn't 'measure up' to the demand anymore. We'd have thought they could have 'sewn' up the market, but it looks like they 'unraveled' instead.. Keep the description simple.
ChatGPT: A small group of sewing machine operators in a Wisconsin factory stand by their workstations, looking disappointed as they examine a stack of XL tee shirts with "unsold" labels. The factory manager looks at a computer screen displaying Google searches for "XL tee shirts" gradually decreasing. The dwindling number of employees reflects the decreasing demand for their products.

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: [ Data cyber art ] and depicting this scene: A small group of sewing machine operators in a Wisconsin factory stand by their workstations, looking disappointed as they examine a stack of XL tee shirts with "unsold" labels. The factory manager looks at a computer screen displaying Google searches for "XL tee shirts" gradually decreasing. The dwindling number of employees reflects the decreasing demand for their products. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Data cyber art ] Generate an image of a Wisconsin factory floor where a small group of dejected sewing machine operators are standing by their workstations. They are inspecting a stack of unsold XL tee shirts, with visible disappointment on their faces. In the background, the factory manager is seen looking at a computer screen displaying decreasing Google searches for "XL tee shirts." The composition should reflect the dwindling demand for their products through the diminishing number of employees. Ensure that the scene depicts a sense of fading industrial relevance and echoes the poignant transition to a changing market landscape.

*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 a decrease in XL tee shirts (Google searches for 'XL tee shirts') caused The number of sewing machine operators in Wisconsin to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)
The Sew What? Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin

Journal of Whimsical Social Science Research

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 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 The number of sewing machine operators in Wisconsin. 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 Bureau of Larbor Statistics to assess this nagging question. You found a correlation coefficient of 0.8694324 and p < 0.01 for 2004 to 2022.

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 "Sew What?" Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin

[[ABSTRACT]]
This paper delves into the seemingly unrelated realms of online fashion interest and the labor market, uncovering a surprising and statistically significant connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the state of Wisconsin. Utilizing data from Google Trends and the Bureau of Labor Statistics, a correlation coefficient of 0.8694324 and p < 0.01 for the years 2004 to 2022 was found, indicating a strong relationship between the two variables. This unexpected linkage prompts further investigation and discussion on the intertwined nature of consumer behavior and employment trends. The findings suggest that behind every online search for the perfect oversized tee, lies a potential impact on the garment industry workforce. Such quirky discoveries reaffirm the whimsical and unpredictable nature of statistical analysis, encouraging researchers to stay curious and find delight in uncovering correlations that might lead to unforeseen humor in the threads of data.


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 The number of sewing machine operators in Wisconsin. 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 "Sew What?" Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin

[[ABSTRACT]]
This paper delves into the seemingly unrelated realms of online fashion interest and the labor market, uncovering a surprising and statistically significant connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the state of Wisconsin. Utilizing data from Google Trends and the Bureau of Labor Statistics, a correlation coefficient of 0.8694324 and p < 0.01 for the years 2004 to 2022 was found, indicating a strong relationship between the two variables. This unexpected linkage prompts further investigation and discussion on the intertwined nature of consumer behavior and employment trends. The findings suggest that behind every online search for the perfect oversized tee, lies a potential impact on the garment industry workforce. Such quirky discoveries reaffirm the whimsical and unpredictable nature of statistical analysis, encouraging researchers to stay curious and find delight in uncovering correlations that might lead to unforeseen humor in the threads of data.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

If statistics was a fabric, the study of correlations would be the stitching that holds the tapestry of data together. In the intricate world of statistical analysis, we often find unexpected patterns and relationships that seem as unrelated as polka dots and plaid. Our own curiosity led us down the rabbit hole of Google searches and labor market trends, where we stumbled upon an unlikely connection between online fashion interest and the number of sewing machine operators in the cheese-loving state of Wisconsin.

This study, affectionately titled "The 'Sew What?' Connection," ventures into the unexplored territory where the clicks of online shoppers meet the hum of sewing machines. From the pursuit of the perfect 'XL tee shirts' to the workforce behind the stitches, we embark on a whimsical journey through the land of data analysis and thread the needle of correlation.

The aim of this study is to not only shed light on the intersecting realms of consumer behavior and employment, but also to showcase the unpredictable charm of statistical research. As we unravel the connection between Google searches for oversized garments and the labor force in Wisconsin, we hope to inspire fellow researchers to embrace the playfulness of data analysis and find joy in discovering correlations that may lead to unexpected humor in the fabric of statistics.

So, grab your measurement tape and don your statistical spectacles, as we embark on a quest to uncover the underlying threads that weave together the world of online fashion trends and the skilled artisans of the sewing industry. This tale of unexpected correlations is sure to tickle your statistical funny bone and leave you in stitches – both figuratively and literally.


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 The number of sewing machine operators in Wisconsin. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
The "Sew What?" Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin

[[ABSTRACT]]
This paper delves into the seemingly unrelated realms of online fashion interest and the labor market, uncovering a surprising and statistically significant connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the state of Wisconsin. Utilizing data from Google Trends and the Bureau of Labor Statistics, a correlation coefficient of 0.8694324 and p < 0.01 for the years 2004 to 2022 was found, indicating a strong relationship between the two variables. This unexpected linkage prompts further investigation and discussion on the intertwined nature of consumer behavior and employment trends. The findings suggest that behind every online search for the perfect oversized tee, lies a potential impact on the garment industry workforce. Such quirky discoveries reaffirm the whimsical and unpredictable nature of statistical analysis, encouraging researchers to stay curious and find delight in uncovering correlations that might lead to unforeseen humor in the threads of data.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
If statistics was a fabric, the study of correlations would be the stitching that holds the tapestry of data together. In the intricate world of statistical analysis, we often find unexpected patterns and relationships that seem as unrelated as polka dots and plaid. Our own curiosity led us down the rabbit hole of Google searches and labor market trends, where we stumbled upon an unlikely connection between online fashion interest and the number of sewing machine operators in the cheese-loving state of Wisconsin.
This study, affectionately titled "The 'Sew What?' Connection," ventures into the unexplored territory where the clicks of online shoppers meet the hum of sewing machines. From the pursuit of the perfect 'XL tee shirts' to the workforce behind the stitches, we embark on a whimsical journey through the land of data analysis and thread the needle of correlation.
The aim of this study is to not only shed light on the intersecting realms of consumer behavior and employment, but also to showcase the unpredictable charm of statistical research. As we unravel the connection between Google searches for oversized garments and the labor force in Wisconsin, we hope to inspire fellow researchers to embrace the playfulness of data analysis and find joy in discovering correlations that may lead to unexpected humor in the fabric of statistics.
So, grab your measurement tape and don your statistical spectacles, as we embark on a quest to uncover the underlying threads that weave together the world of online fashion trends and the skilled artisans of the sewing industry. This tale of unexpected correlations is sure to tickle your statistical funny bone and leave you in stitches – both figuratively and literally.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith and Doe (2010) examined the relationship between online fashion interest and labor market dynamics, offering a comprehensive analysis of consumer behavior and its potential impact on employment trends. Their findings hinted at a curious connection between the demand for oversized garments and the workforce involved in garment production, laying the groundwork for further exploration in this quirky intersection of statistics and fashion.

Expanding upon this foundation, Jones (2015) delved into the intricacies of online search patterns and their implications for regional labor markets. While their study did not specifically focus on the niche market of 'XL tee shirts,' it paved the way for our investigation into the state-specific correlation between Google searches for oversized apparel and the number of sewing machine operators in Wisconsin.

As we weave our way through the fabric of literature on this peculiar topic, it is essential to consider the broader context of consumer trends and their potential impact on the labor force. In "Fashion Frenzy: The Economics of Clothing Choices" by Green (2018), the author discusses the role of online search behavior in shaping the demand for various clothing sizes, shedding light on the paradoxical allure of oversized apparel and its influence on market dynamics.

Moving into the realm of fiction, "Threads of Fate" by Weaver (2007) presents a whimsical tale of interconnected destinies, hinting at the enigmatic threads that bind seemingly unrelated elements in unexpected ways. While purely fictional, the themes of serendipitous connections and unforeseen correlations resonate with our exploration of the relationship between Google searches for 'XL tee shirts' and the sewing machine operators of Wisconsin.

In a surprising twist, our quest for understanding led us to explore unlikely sources of inspiration, including the whimsical world of children's cartoons. Through the lens of "Stitch and Switch: Adventures in Textile Land," a popular animated series, we gained insight into the fantastical possibilities of anthropomorphic textiles and their potential to unravel mysteries that extend beyond the realm of traditional statistical analysis.

With a playful spirit and an unwavering dedication to uncovering the unexpected, we set out to untangle the web of correlations between online fashion trends and the labor market. The subsequent sections of this paper will illuminate the findings of our investigation, unraveling the peculiar yet compelling connection between Google searches for 'XL tee shirts' and the labor force of Wisconsin's garment industry.


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 The number of sewing machine operators in Wisconsin. 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 Bureau of Larbor Statistics . You used data from 2004 to 2022

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 "Sew What?" Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin

[[ABSTRACT]]
This paper delves into the seemingly unrelated realms of online fashion interest and the labor market, uncovering a surprising and statistically significant connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the state of Wisconsin. Utilizing data from Google Trends and the Bureau of Labor Statistics, a correlation coefficient of 0.8694324 and p < 0.01 for the years 2004 to 2022 was found, indicating a strong relationship between the two variables. This unexpected linkage prompts further investigation and discussion on the intertwined nature of consumer behavior and employment trends. The findings suggest that behind every online search for the perfect oversized tee, lies a potential impact on the garment industry workforce. Such quirky discoveries reaffirm the whimsical and unpredictable nature of statistical analysis, encouraging researchers to stay curious and find delight in uncovering correlations that might lead to unforeseen humor in the threads of data.

[[INTRODUCTION]]
INTRODUCTION
If statistics was a fabric, the study of correlations would be the stitching that holds the tapestry of data together. In the intricate world of statistical analysis, we often find unexpected patterns and relationships that seem as unrelated as polka dots and plaid. Our own curiosity led us down the rabbit hole of Google searches and labor market trends, where we stumbled upon an unlikely connection between online fashion interest and the number of sewing machine operators in the cheese-loving state of Wisconsin.
This study, affectionately titled "The 'Sew What?' Connection," ventures into the unexplored territory where the clicks of online shoppers meet the hum of sewing machines. From the pursuit of the perfect 'XL tee shirts' to the workforce behind the stitches, we embark on a whimsical journey through the land of data analysis and thread the needle of correlation.
The aim of this study is to not only shed light on the intersecting realms of consumer behavior and employment, but also to showcase the unpredictable charm of statistical research. As we unravel the connection between Google searches for oversized garments and the labor force in Wisconsin, we hope to inspire fellow researchers to embrace the playfulness of data analysis and find joy in discovering correlations that may lead to unexpected humor in the fabric of statistics.
So, grab your measurement tape and don your statistical spectacles, as we embark on a quest to uncover the underlying threads that weave together the world of online fashion trends and the skilled artisans of the sewing industry. This tale of unexpected correlations is sure to tickle your statistical funny bone and leave you in stitches – both figuratively and literally.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the tangled web of data and uncover the whimsical connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the lovely state of Wisconsin, we employed a methodology as intricate as the stitches on a finely tailored garment.

First, we donned our digital Sherlock Holmes hats and ventured into the virtual realm of Google Trends. With an eagle eye for online fashion interest, we tracked the search interest in 'XL tee shirts' from 2004 to 2022, harnessing the power of Google's algorithms to unveil the peaks and valleys of sartorial fascination. We also delved into the vast expanse of the Bureau of Labor Statistics, where we rummaged through troves of labor market data to extract the number of sewing machine operators in the cheese paradise of Wisconsin over the same time period.

Once we had corralled our data from the wild web, we forged ahead with a statistical waltz, twirling around correlation coefficients and p-values with the finesse of a ballroom dancer. Employing the age-old charm of Pearson's correlation coefficient, we quantified the relationship between online searches for oversized tees and the workforce behind the scenes. With p-values whispering statistical secrets in our ears, we uncovered a correlation coefficient of 0.8694324 and oh-so-delightful p < 0.01, affirming the robustness of the connection and the statistical charm of our findings.

In this dance of data analysis, we also embraced the enchanting art of time series analysis, tracing the ebbs and flows of online fashion fascination and the labor market over the span of nearly two decades. Through this convoluted yet captivating dance, we wove the narrative of correlation and causation, acknowledging the limitations and confounding variables that lurked in the shadows, like mischievous fashion gnomes playing tricks on our statistical endeavors.

The tapestry of our methodology, though embroidered with complexities and statistical acrobatics, ultimately laid bare the enchanting connection between Google searches for 'XL tee shirts' and the labor force in Wisconsin, inviting fellow researchers to join us in this delightful adventure through the quirks and curiosities of statistical analysis.


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 The number of sewing machine operators in Wisconsin. 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 Bureau of Larbor Statistics .

For the time period 2004 to 2022, you found a correlation 0.8694324, r-squared of 0.7559127, 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 "Sew What?" Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin

[[ABSTRACT]]
This paper delves into the seemingly unrelated realms of online fashion interest and the labor market, uncovering a surprising and statistically significant connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the state of Wisconsin. Utilizing data from Google Trends and the Bureau of Labor Statistics, a correlation coefficient of 0.8694324 and p < 0.01 for the years 2004 to 2022 was found, indicating a strong relationship between the two variables. This unexpected linkage prompts further investigation and discussion on the intertwined nature of consumer behavior and employment trends. The findings suggest that behind every online search for the perfect oversized tee, lies a potential impact on the garment industry workforce. Such quirky discoveries reaffirm the whimsical and unpredictable nature of statistical analysis, encouraging researchers to stay curious and find delight in uncovering correlations that might lead to unforeseen humor in the threads of data.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
If statistics was a fabric, the study of correlations would be the stitching that holds the tapestry of data together. In the intricate world of statistical analysis, we often find unexpected patterns and relationships that seem as unrelated as polka dots and plaid. Our own curiosity led us down the rabbit hole of Google searches and labor market trends, where we stumbled upon an unlikely connection between online fashion interest and the number of sewing machine operators in the cheese-loving state of Wisconsin.
This study, affectionately titled "The 'Sew What?' Connection," ventures into the unexplored territory where the clicks of online shoppers meet the hum of sewing machines. From the pursuit of the perfect 'XL tee shirts' to the workforce behind the stitches, we embark on a whimsical journey through the land of data analysis and thread the needle of correlation.
The aim of this study is to not only shed light on the intersecting realms of consumer behavior and employment, but also to showcase the unpredictable charm of statistical research. As we unravel the connection between Google searches for oversized garments and the labor force in Wisconsin, we hope to inspire fellow researchers to embrace the playfulness of data analysis and find joy in discovering correlations that may lead to unexpected humor in the fabric of statistics.
So, grab your measurement tape and don your statistical spectacles, as we embark on a quest to uncover the underlying threads that weave together the world of online fashion trends and the skilled artisans of the sewing industry. This tale of unexpected correlations is sure to tickle your statistical funny bone and leave you in stitches – both figuratively and literally.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The correlation analysis revealed a surprisingly strong and positive relationship between Google searches for 'XL tee shirts' and the number of sewing machine operators in Wisconsin for the years 2004 to 2022. The correlation coefficient of 0.8694324 implies a robust connection, resembling the interlocking stitches of a finely crafted garment.

The findings suggest that as the interest in oversized apparel soared in the digital realm, so did the demand for skilled sewing machine operators in the heartland of cheese and craftsmanship. The r-squared value of 0.7559127 indicates that approximately 75.59% of the variation in the number of sewing machine operators can be attributed to the fluctuating trends in 'XL tee shirts' searches, leaving only a small margin for error – much like the precision required in sewing a button on a dress shirt.

Furthermore, with a p-value of less than 0.01, these results are statistically significant, indicating that the observed relationship is not merely a coincidence or a loose thread but rather a substantial and reliable connection, akin to finding a perfect match for a needle and a spool of thread.

To visually illustrate this unexpected correlation, Figure 1 displays a scatterplot that showcases the linear association between the two variables – a web of data points that is as tightly knit as the stitches on a well-crafted tee shirt.

These findings not only underscore the whimsical nature of statistical analysis but also highlight the potential impact of online fashion trends on the labor market. As we unravel the quirky connection between the cyberspace quest for the perfect oversized tee and the skilled hands behind the sewing machines in Wisconsin, we cannot help but marvel at the unexpected humor and charming surprises that statistical analysis has to offer.

In conclusion, our exploration of the "Sew What?" Connection not only enhances our understanding of the intertwined worlds of consumer behavior and employment trends but also reminds us that within the vast tapestry of statistical analysis lies the potential for delightful, amusing, and even punny discoveries. This whimsical revelation encourages researchers to embrace the playful side of data analysis and find joy in uncovering correlations that may lead to unforeseen humor in the threads of statistics.


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 The number of sewing machine operators in Wisconsin. 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 "Sew What?" Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin

[[ABSTRACT]]
This paper delves into the seemingly unrelated realms of online fashion interest and the labor market, uncovering a surprising and statistically significant connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the state of Wisconsin. Utilizing data from Google Trends and the Bureau of Labor Statistics, a correlation coefficient of 0.8694324 and p < 0.01 for the years 2004 to 2022 was found, indicating a strong relationship between the two variables. This unexpected linkage prompts further investigation and discussion on the intertwined nature of consumer behavior and employment trends. The findings suggest that behind every online search for the perfect oversized tee, lies a potential impact on the garment industry workforce. Such quirky discoveries reaffirm the whimsical and unpredictable nature of statistical analysis, encouraging researchers to stay curious and find delight in uncovering correlations that might lead to unforeseen humor in the threads of data.

[[LITERATURE REVIEW]]
In their seminal work, Smith and Doe (2010) examined the relationship between online fashion interest and labor market dynamics, offering a comprehensive analysis of consumer behavior and its potential impact on employment trends. Their findings hinted at a curious connection between the demand for oversized garments and the workforce involved in garment production, laying the groundwork for further exploration in this quirky intersection of statistics and fashion.
Expanding upon this foundation, Jones (2015) delved into the intricacies of online search patterns and their implications for regional labor markets. While their study did not specifically focus on the niche market of 'XL tee shirts,' it paved the way for our investigation into the state-specific correlation between Google searches for oversized apparel and the number of sewing machine operators in Wisconsin.
As we weave our way through the fabric of literature on this peculiar topic, it is essential to consider the broader context of consumer trends and their potential impact on the labor force. In "Fashion Frenzy: The Economics of Clothing Choices" by Green (2018), the author discusses the role of online search behavior in shaping the demand for various clothing sizes, shedding light on the paradoxical allure of oversized apparel and its influence on market dynamics.
Moving into the realm of fiction, "Threads of Fate" by Weaver (2007) presents a whimsical tale of interconnected destinies, hinting at the enigmatic threads that bind seemingly unrelated elements in unexpected ways. While purely fictional, the themes of serendipitous connections and unforeseen correlations resonate with our exploration of the relationship between Google searches for 'XL tee shirts' and the sewing machine operators of Wisconsin.
In a surprising twist, our quest for understanding led us to explore unlikely sources of inspiration, including the whimsical world of children's cartoons. Through the lens of "Stitch and Switch: Adventures in Textile Land," a popular animated series, we gained insight into the fantastical possibilities of anthropomorphic textiles and their potential to unravel mysteries that extend beyond the realm of traditional statistical analysis.
With a playful spirit and an unwavering dedication to uncovering the unexpected, we set out to untangle the web of correlations between online fashion trends and the labor market. The subsequent sections of this paper will illuminate the findings of our investigation, unraveling the peculiar yet compelling connection between Google searches for 'XL tee shirts' and the labor force of Wisconsin's garment industry.

[[RESULTS]]
The correlation analysis revealed a surprisingly strong and positive relationship between Google searches for 'XL tee shirts' and the number of sewing machine operators in Wisconsin for the years 2004 to 2022. The correlation coefficient of 0.8694324 implies a robust connection, resembling the interlocking stitches of a finely crafted garment.
The findings suggest that as the interest in oversized apparel soared in the digital realm, so did the demand for skilled sewing machine operators in the heartland of cheese and craftsmanship. The r-squared value of 0.7559127 indicates that approximately 75.59% of the variation in the number of sewing machine operators can be attributed to the fluctuating trends in 'XL tee shirts' searches, leaving only a small margin for error – much like the precision required in sewing a button on a dress shirt.
Furthermore, with a p-value of less than 0.01, these results are statistically significant, indicating that the observed relationship is not merely a coincidence or a loose thread but rather a substantial and reliable connection, akin to finding a perfect match for a needle and a spool of thread.
To visually illustrate this unexpected correlation, Figure 1 displays a scatterplot that showcases the linear association between the two variables – a web of data points that is as tightly knit as the stitches on a well-crafted tee shirt.
These findings not only underscore the whimsical nature of statistical analysis but also highlight the potential impact of online fashion trends on the labor market. As we unravel the quirky connection between the cyberspace quest for the perfect oversized tee and the skilled hands behind the sewing machines in Wisconsin, we cannot help but marvel at the unexpected humor and charming surprises that statistical analysis has to offer.
In conclusion, our exploration of the "Sew What?" Connection not only enhances our understanding of the intertwined worlds of consumer behavior and employment trends but also reminds us that within the vast tapestry of statistical analysis lies the potential for delightful, amusing, and even punny discoveries. This whimsical revelation encourages researchers to embrace the playful side of data analysis and find joy in uncovering correlations that may lead to unforeseen humor in the threads of statistics.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of our study shed light on the intricate connection between online fashion interest and the labor market, revealing a delightful correlation between Google searches for 'XL tee shirts' and the number of sewing machine operators in Wisconsin. Our results not only reaffirm the serendipitous and whimsical nature of statistical analysis, but they also underscore the potential for unexpected humor and punny discoveries within the fabric of data.

Our research stands on the shoulders of previous studies, including the tongue-in-cheek exploration of the intertwined destinies in "Threads of Fate" by Weaver. While purely fictional, the themes of serendipitous connections and unforeseen correlations resonate with our investigation. We also draw inspiration from the whimsical world of children's cartoons, where "Stitch and Switch: Adventures in Textile Land" offered insight into the fantastical possibilities of anthropomorphic textiles – a reminder of the peculiar yet compelling connection between Google searches for 'XL tee shirts' and Wisconsin's garment industry.

The statistically significant correlation coefficient of 0.8694324, akin to the interlocking stitches of a finely crafted garment, reinforces the robust relationship between online interest in oversized apparel and the demand for skilled sewing machine operators. This unexpected linkage, much like finding a perfect match for a needle and a spool of thread, highlights the delightfully quirky side of statistical analysis.

Our results echo the sentiments of Green's "Fashion Frenzy: The Economics of Clothing Choices," emphasizing the role of online search behavior in shaping the demand for various clothing sizes. The strong correlation coefficient and r-squared value of 0.7559127, reminiscent of the precision required in sewing, suggest that approximately 75.59% of the variation in the number of sewing machine operators can be attributed to the fluctuating trends in 'XL tee shirts' searches. This not only underlines the whimsical nature of statistical analysis but also underscores the potential impact of online fashion trends on the labor market.

The scatterplot, akin to a web of tightly knit stitches, visually illustrates the linear association between the two variables, mirroring the precision and craftsmanship required in both clothing search and garment production. These visual findings further emphasize the unexpected humor and charming surprises that statistical analysis has to offer, accentuating the playful and joyous side of data exploration.

As we continue to unravel the quirky connection between online fashion interest and employment trends, we must remain open to the unexpected, the whimsical, and the delightful surprises that statistical analysis may reveal in the threads of data. Our study encourages researchers to embrace the playful side of data analysis and find joy in uncovering correlations that may lead to unforeseen humor in the fabric of statistics.


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 The number of sewing machine operators in Wisconsin. 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 "Sew What?" Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin

[[ABSTRACT]]
This paper delves into the seemingly unrelated realms of online fashion interest and the labor market, uncovering a surprising and statistically significant connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the state of Wisconsin. Utilizing data from Google Trends and the Bureau of Labor Statistics, a correlation coefficient of 0.8694324 and p < 0.01 for the years 2004 to 2022 was found, indicating a strong relationship between the two variables. This unexpected linkage prompts further investigation and discussion on the intertwined nature of consumer behavior and employment trends. The findings suggest that behind every online search for the perfect oversized tee, lies a potential impact on the garment industry workforce. Such quirky discoveries reaffirm the whimsical and unpredictable nature of statistical analysis, encouraging researchers to stay curious and find delight in uncovering correlations that might lead to unforeseen humor in the threads of data.

[[INTRDUCTION]]
INTRODUCTION
If statistics was a fabric, the study of correlations would be the stitching that holds the tapestry of data together. In the intricate world of statistical analysis, we often find unexpected patterns and relationships that seem as unrelated as polka dots and plaid. Our own curiosity led us down the rabbit hole of Google searches and labor market trends, where we stumbled upon an unlikely connection between online fashion interest and the number of sewing machine operators in the cheese-loving state of Wisconsin.
This study, affectionately titled "The 'Sew What?' Connection," ventures into the unexplored territory where the clicks of online shoppers meet the hum of sewing machines. From the pursuit of the perfect 'XL tee shirts' to the workforce behind the stitches, we embark on a whimsical journey through the land of data analysis and thread the needle of correlation.
The aim of this study is to not only shed light on the intersecting realms of consumer behavior and employment, but also to showcase the unpredictable charm of statistical research. As we unravel the connection between Google searches for oversized garments and the labor force in Wisconsin, we hope to inspire fellow researchers to embrace the playfulness of data analysis and find joy in discovering correlations that may lead to unexpected humor in the fabric of statistics.
So, grab your measurement tape and don your statistical spectacles, as we embark on a quest to uncover the underlying threads that weave together the world of online fashion trends and the skilled artisans of the sewing industry. This tale of unexpected correlations is sure to tickle your statistical funny bone and leave you in stitches – both figuratively and literally.

[[RESULTS]]
The correlation analysis revealed a surprisingly strong and positive relationship between Google searches for 'XL tee shirts' and the number of sewing machine operators in Wisconsin for the years 2004 to 2022. The correlation coefficient of 0.8694324 implies a robust connection, resembling the interlocking stitches of a finely crafted garment.
The findings suggest that as the interest in oversized apparel soared in the digital realm, so did the demand for skilled sewing machine operators in the heartland of cheese and craftsmanship. The r-squared value of 0.7559127 indicates that approximately 75.59% of the variation in the number of sewing machine operators can be attributed to the fluctuating trends in 'XL tee shirts' searches, leaving only a small margin for error – much like the precision required in sewing a button on a dress shirt.
Furthermore, with a p-value of less than 0.01, these results are statistically significant, indicating that the observed relationship is not merely a coincidence or a loose thread but rather a substantial and reliable connection, akin to finding a perfect match for a needle and a spool of thread.
To visually illustrate this unexpected correlation, Figure 1 displays a scatterplot that showcases the linear association between the two variables – a web of data points that is as tightly knit as the stitches on a well-crafted tee shirt.
These findings not only underscore the whimsical nature of statistical analysis but also highlight the potential impact of online fashion trends on the labor market. As we unravel the quirky connection between the cyberspace quest for the perfect oversized tee and the skilled hands behind the sewing machines in Wisconsin, we cannot help but marvel at the unexpected humor and charming surprises that statistical analysis has to offer.
In conclusion, our exploration of the "Sew What?" Connection not only enhances our understanding of the intertwined worlds of consumer behavior and employment trends but also reminds us that within the vast tapestry of statistical analysis lies the potential for delightful, amusing, and even punny discoveries. This whimsical revelation encourages researchers to embrace the playful side of data analysis and find joy in uncovering correlations that may lead to unforeseen humor in the threads of statistics.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In unraveling the "Sew What?" Connection, we've not only embroidered our understanding of the whimsical interplay between online fashion fascination and the labor market but also sewn the seeds of an unexpected correlation. Embracing the playful side of data analysis, we've discovered that every Google search for 'XL tee shirts' may have a ripple effect on the demand for skilled sewing machine operators in the heartland of cheese and quirkiness, Wisconsin. This correlation, with a robust coefficient resembling the interlocking stitches of a finely crafted garment, can surely leave any statistician in stitches. The results, akin to finding a perfect match for a needle and a spool of thread, further underline the unpredictably charming nature of statistical analysis and encourage fellow researchers to find joy in uncovering correlations that may lead to unforeseen humor in the threads of statistics.

The visual representation of this unexpected correlation in Figure 1 resembles a web of data points as tightly knit as the stitches on a well-crafted tee shirt. The r-squared value, much like the precision required in sewing a button on a dress shirt, indicates that approximately 75.59% of the variation in the number of sewing machine operators can be attributed to the fluctuating trends in 'XL tee shirts' searches, leaving only a small margin for error – a thread of statistical certainty in the midst of variability.

As we snip the threads of this study and neatly fold our statistical findings, we assert that no further research is needed in this area. The "Sew What?" Connection has provided ample amusement and insight, reminding us that statistical analysis has the potential for delightful, amusing, and even punny discoveries. This unexpected linkage, behind every online search for the perfect oversized tee, has left us with a stitch in time, underscoring the whimsical nature of statistical analysis and the delightful surprises it may hold.


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 Sew What? Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Whimsical Social Science Research


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Sew What? Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin. Respond only with the name of a fictional organization.

ChatGPT:

National Institute for Domestic Textile Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Sew What? Connection: Exploring the Correlation Between Google Searches for 'XL Tee Shirts' and the Number of Sewing Machine Operators in Wisconsin with an abstract of This paper delves into the seemingly unrelated realms of online fashion interest and the labor market, uncovering a surprising and statistically significant connection between Google searches for 'XL tee shirts' and the number of sewing machine operators in the state of Wisconsin. Utilizing data from Google Trends and the Bureau of Labor Statistics, a correlation coefficient of 0.8694324 and p < 0.01 for the years 2004 to 2022 was found, indicating a strong relationship between the two variables. This unexpected linkage prompts further investigation and discussion on the intertwined nature of consumer behavior and employment trends. The findings suggest that behind every online search for the perfect oversized tee, lies a potential impact on the garment industry workforce. Such quirky discoveries reaffirm the whimsical and unpredictable nature of statistical analysis, encouraging researchers to stay curious and find delight in uncovering correlations that might lead to unforeseen humor in the threads of data.

ChatGPT:

Google Trends, XL tee shirts, sewing machine operators, Wisconsin, fashion interest, labor market, correlation coefficient, consumer behavior, employment trends, online fashion search, Bureau of Labor Statistics, statistical 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

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'

The number of sewing machine operators in Wisconsin
Detailed data title: BLS estimate of sewing machine operators in Wisconsin
Source: Bureau of Larbor Statistics
See what else correlates with The number of sewing machine operators in Wisconsin

Correlation r = 0.8694324 (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 = 0.7559127 (Coefficient of determination)
This means 75.6% of the change in the one variable (i.e., The number of sewing machine operators in Wisconsin) is predictable based on the change in the other (i.e., Google searches for 'XL tee shirts') over the 19 years from 2004 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.3E-6. 0.0000013431057822457053000000
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 0.87 in 0.00013% of random cases. Said differently, if you correlated 744,543 random variables You don't actually need 744 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 18 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 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.

[ 0.69, 0.95 ] 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.
2004200520062007200820092010201120122013201420152016201720182019202020212022
Google searches for 'XL tee shirts' (Rel. search volume)8.4166710.08335.252.416671.833333.666672.254.416672.583333.833334.08333544.5833354.256.166675.416674.33333
The number of sewing machine operators in Wisconsin (Sewing Machine Operators)3970387028602690238024602360233020702290237025302550272027403080293028002670




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. 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([8.41667,10.0833,5.25,2.41667,1.83333,3.66667,2.25,4.41667,2.58333,3.83333,4.08333,5,4,4.58333,5,4.25,6.16667,5.41667,4.33333,])
array_2 = np.array([3970,3870,2860,2690,2380,2460,2360,2330,2070,2290,2370,2530,2550,2720,2740,3080,2930,2800,2670,])
array_1_name = "Google searches for 'XL tee shirts'"
array_2_name = "The number of sewing machine operators in Wisconsin"

# 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?

Big thanks for reviewing!


Correlation ID: 5828 · Black Variable ID: 1439 · Red Variable ID: 16367
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0