Spurious correlation #3,237 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is GMO use in corn grown in Ohio and the second variable is Hollister retail store count worldwide. The chart goes from 2000 to 2022, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is GMO use in corn grown in Ohio and the second variable is Hollister retail store count worldwide. The chart goes from 2000 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As GMO corn in Ohio grew taller, it created a need for more fashionable overalls, prompting a spike in demand for Hollister's clothing line. You could say the corn was really shucking for a new wardrobe!

^{Show image generation prompt} Model: dalle-3
Prompt: An image that looks like it is a scene from A Disney Movie: An enchanting field in Ohio stretches out, with rows of tall GMO corn plants glistening in the sunlight. The corn plants have a mesmerizing shade of denim blue, each kernel reflecting the radiance of the sun. In the distance, a string of Hollister stores emerges, their architecture standing out against the agricultural landscape. From the windows of the stores, denim displays glint, drawing in eager customers searching for the newest jean styles. 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: GMO use in corn grown in Ohio and Hollister retail store count worldwide. 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: Cutsy art illustration Brutalism Cyberpunk An image that looks like it is a scene from A Disney Movie Whimsical illustration
ChatGPT: An image that looks like it is a scene from A Disney Movie

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 GMO use in corn grown in Ohio and Hollister retail store count worldwide, in the following situation: As GMO corn production in Ohio increased, so did the demand for denim, leading to a boom in Hollister stores. The genetically modified corn caused a "jean-etic" mutation, sparking a global fashion frenzy and a "corny" influx of new retail locations.. Keep the description simple.
ChatGPT: A field in Ohio filled with rows of tall GMO corn plants, while in the background a string of Hollister stores can be seen popping up around the world, each with denim displays in their windows. The genetically modified corn shimmers in the sun, its kernels taking on a distinct denim blue color, while customers eagerly flock to the new Hollister stores, excitedly shopping for the latest jean styles.

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: [ An image that looks like it is a scene from A Disney Movie ] and depicting this scene: A field in Ohio filled with rows of tall GMO corn plants, while in the background a string of Hollister stores can be seen popping up around the world, each with denim displays in their windows. The genetically modified corn shimmers in the sun, its kernels taking on a distinct denim blue color, while customers eagerly flock to the new Hollister stores, excitedly shopping for the latest jean styles. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from A Disney Movie: An enchanting field in Ohio stretches out, with rows of tall GMO corn plants glistening in the sunlight. The corn plants have a mesmerizing shade of denim blue, each kernel reflecting the radiance of the sun. In the distance, a string of Hollister stores emerges, their architecture standing out against the agricultural landscape. From the windows of the stores, denim displays glint, drawing in eager customers searching for the newest jean styles.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in GMO use in corn grown in Ohio caused Hollister retail store count worldwide to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

From GMO Corn to Hollister Stores: A Global Affair

The Journal of Consumer Culture

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 GMO use in corn grown in Ohio and Hollister retail store count worldwide. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
"From GMO Corn to Hollister Stores: A Global Affair"

[[ABSTRACT]]
The relationship between GMO use in corn grown in Ohio and the proliferation of Hollister retail stores worldwide has long been a subject of speculation and jest. In this study, we delve into the bizarrely interconnected realms of agriculture and fashion to analyze whether there exists a meaningful correlation between the two. We conducted a comprehensive analysis using USDA crop data and Statista retail information, unearthing surprising insights that even surprised us more than a dad joke at a family reunion.

Our findings revealed a striking correlation coefficient of 0.8647380 and p < 0.01, indicating a strong statistical relationship between the cultivation of GMO corn in the Buckeye State and the spread of Hollister stores on the global stage. It seems that the growth of genetically modified corn and the proliferation of these trendy retail outlets go hand in hand, much like a kernel of corn and its husk - inseparable, yet entirely unexpected companions.

The implications of our research extend beyond the fields of Ohio and the confines of mall storefronts - shedding light on the unfathomable interconnectedness of seemingly disparate domains. As we uncover this curious correlation, we cannot help but marvel at the quirks of our world, where even the most outlandish connections can be unveiled with a dash of statistical analysis and a sprinkle of good humor.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The agriculture and fashion industries may seem like two peas in a pod, but the link between them runs deeper than a cornstalk's roots. At first glance, the notion of a connection between GMO corn and Hollister stores may elicit a chuckle or two, but as we dig into the data, we find that the correlation is no laughing matter - well, maybe just a bit. It's like corny humor, quite literally.
As we delve into this maize of interconnectedness, it's imperative to recognize the gravity of our investigation, while also acknowledging the inherent humor in studying the proliferation of a trendy retail chain alongside the cultivation of genetically modified corn. It's almost as if we're uncovering the fashion secrets of the cornfield, revealing that even the most unexpected pairings can yield fruitful results - much like a good crop of dad jokes.
From the heartland of Ohio to the streets of international fashion districts, our research seeks to unravel the tangled web that binds these seemingly incongruous entities. It's a bit like untangling Christmas lights – a perplexing endeavor that promises both intrigue and, inevitably, a few snags along the way.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their groundbreaking study, Smith et al. (2015) observe the impact of GMO corn cultivation on agricultural productivity, with a focus on the Midwest region. Their findings not only shed light on the economic implications of genetically modified crops but also hint at unforeseen connections to the retail sector - making this study more corny than a field of genetically modified maize on April Fool's Day.

Drawing from the work of Doe and Jones (2017), we gain insight into the global expansion of retail chains and the factors influencing their geographic distribution. Little did they know that their research would set the stage for our investigation into the unexpected relationship between GMO corn in Ohio and the worldwide proliferation of Hollister stores. It's as if they sowed the seeds of curiosity in the fertile soil of academic inquiry.

Taking a departure from the traditional agricultural and retail studies, "The Omnivore's Dilemma" by Michael Pollan (2006) offers a thought-provoking exploration of the modern food industry and the complex web of relationships that underpin it. Though Pollan's work doesn't overtly touch on fashion retail, we couldn't help but draw parallels between the intricate supply chains in the food industry and the unexpectedly intertwined growth of GMO corn and Hollister stores. It's like uncovering a hidden compartment in a seemingly ordinary suitcase - surprising and oddly delightful.

On a fictional note, "The Corn Whisperer" by J.K. Rowling (imaginary, 2021) takes readers on a magical journey through the whimsical world of enchanted cornfields. While purely fictional, the novel's imaginative portrayal of the mystical powers of corn and its potential influence on human affairs speaks to the fantastical allure of our research topic. At this point, we may need a touch of magic to explain the oddly compelling relationship between GMO corn and global fashion retail - it's a mystery worthy of a best-selling novel.

In the realm of board games, "Agricola" and "Retail Tycoon" offer simulated experiences in agriculture and retail management, respectively. While these games are designed for entertainment, their mechanics inadvertently mirror the intricate balance between crop production and retail expansion. It's a bit like playing a game of connect-the-dots, only to discover that the final picture resembles a fashionable ear of corn posing for a Hollister ad campaign.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 GMO use in corn grown in Ohio and Hollister retail store count worldwide. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
"From GMO Corn to Hollister Stores: A Global Affair"

[[ABSTRACT]]
The relationship between GMO use in corn grown in Ohio and the proliferation of Hollister retail stores worldwide has long been a subject of speculation and jest. In this study, we delve into the bizarrely interconnected realms of agriculture and fashion to analyze whether there exists a meaningful correlation between the two. We conducted a comprehensive analysis using USDA crop data and Statista retail information, unearthing surprising insights that even surprised us more than a dad joke at a family reunion.

Our findings revealed a striking correlation coefficient of 0.8647380 and p < 0.01, indicating a strong statistical relationship between the cultivation of GMO corn in the Buckeye State and the spread of Hollister stores on the global stage. It seems that the growth of genetically modified corn and the proliferation of these trendy retail outlets go hand in hand, much like a kernel of corn and its husk - inseparable, yet entirely unexpected companions.

The implications of our research extend beyond the fields of Ohio and the confines of mall storefronts - shedding light on the unfathomable interconnectedness of seemingly disparate domains. As we uncover this curious correlation, we cannot help but marvel at the quirks of our world, where even the most outlandish connections can be unveiled with a dash of statistical analysis and a sprinkle of good humor.

[[LITERATURE REVIEW]]
In their groundbreaking study, Smith et al. (2015) observe the impact of GMO corn cultivation on agricultural productivity, with a focus on the Midwest region. Their findings not only shed light on the economic implications of genetically modified crops but also hint at unforeseen connections to the retail sector - making this study more corny than a field of genetically modified maize on April Fool's Day.
Drawing from the work of Doe and Jones (2017), we gain insight into the global expansion of retail chains and the factors influencing their geographic distribution. Little did they know that their research would set the stage for our investigation into the unexpected relationship between GMO corn in Ohio and the worldwide proliferation of Hollister stores. It's as if they sowed the seeds of curiosity in the fertile soil of academic inquiry.
Taking a departure from the traditional agricultural and retail studies, "The Omnivore's Dilemma" by Michael Pollan (2006) offers a thought-provoking exploration of the modern food industry and the complex web of relationships that underpin it. Though Pollan's work doesn't overtly touch on fashion retail, we couldn't help but draw parallels between the intricate supply chains in the food industry and the unexpectedly intertwined growth of GMO corn and Hollister stores. It's like uncovering a hidden compartment in a seemingly ordinary suitcase - surprising and oddly delightful.
On a fictional note, "The Corn Whisperer" by J.K. Rowling (imaginary, 2021) takes readers on a magical journey through the whimsical world of enchanted cornfields. While purely fictional, the novel's imaginative portrayal of the mystical powers of corn and its potential influence on human affairs speaks to the fantastical allure of our research topic. At this point, we may need a touch of magic to explain the oddly compelling relationship between GMO corn and global fashion retail - it's a mystery worthy of a best-selling novel.
In the realm of board games, "Agricola" and "Retail Tycoon" offer simulated experiences in agriculture and retail management, respectively. While these games are designed for entertainment, their mechanics inadvertently mirror the intricate balance between crop production and retail expansion. It's a bit like playing a game of connect-the-dots, only to discover that the final picture resembles a fashionable ear of corn posing for a Hollister ad campaign.

[[RESULTS]]
The analysis of the data gathered from the USDA and Statista unveiled an eyebrow-raising correlation coefficient of 0.8647380 between the use of GMO corn in Ohio and the proliferation of Hollister stores worldwide. This striking statistical relationship suggests that the cultivation of genetically modified corn and the expansion of this retail chain are as intertwined as a farmer's shoelaces - tightly bound and surprisingly consequential, albeit without the need for a fashion-forward belt.
The r-squared value of 0.7477717 further underscores the robustness of the relationship, indicating that a substantial proportion of the variability in Hollister store count across the world can be explained by the cultivation of GMO corn in the heart of the Midwest. It's like finding the perfect fit - statistically speaking, of course.
Moreover, with a p-value of less than 0.01, the evidence strongly supports the hypothesis that there is indeed a significant association between the growth of genetically modified corn in Ohio and the prevalence of Hollister stores globally. It's almost as convincing as a compelling dad joke - hard to ignore and impossible to refute.
The scatterplot (Fig. 1) visually encapsulates the substantial correlation uncovered in our analysis. It illustrates the unmistakable trend of increasing Hollister store count coinciding with the rise in GMO corn cultivation in Ohio, painting a picture as clear as a blue sky over a cornfield - albeit with more denim and fewer clouds.
Overall, our findings not only provide empirical evidence of the unexpected correlation between GMO corn production and the spread of Hollister stores but also highlight the profound interconnectedness of seemingly unrelated aspects of our world. It's like discovering a hidden pocket in a pair of jeans - surprising, enlightening, and oddly satisfying, much like a good punchline in a statistical analysis.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our study has brought to light a remarkable relationship between GMO corn production in Ohio and the proliferation of Hollister retail stores worldwide. The findings not only affirm the earlier work by Smith et al. and Doe and Jones but also add depth to the unexpected links between agriculture and fashion retail. It's as if our research has unearthed a hidden corn-nection, shedding light on the intertwined growth of genetically modified corn and trendy storefronts with a seriousness rivaling that of an accountant's tie.

This compelling correlation between GMO corn and Hollister store count suggests a synergy that transcends traditional sector boundaries, much like a good old dad joke that spans generations. The robust statistical support, with a high correlation coefficient and a low p-value, reinforces the significance of this unexpected relationship, leaving little room for skepticism - just like the certainty of a dad's insistence on grilling mastery.

When we reflect on the curious findings from the literature review, it's evident that our research has advanced the understanding of these eccentric links. From the corny puns of earlier studies to the unforeseen parallels drawn from literary and fictional works, our investigation has validated and expanded on the uncharted territory of GMO corn and fashion retail relationships, much like discovering a new humor in an old dad joke.

The visual representation of our data in the scatterplot serves as a stark reminder of the convincing nature of the correlation unfolded in our analysis. It provides a vivid illustration of the synchronized growth of GMO corn in Ohio and the expansion of Hollister stores worldwide, akin to a fashionable dance between agriculture and retail, with each step as harmonious as a synchronized swim team.

The implications of our research extend beyond the confines of academia, resonating with the broader understanding of interconnected systems in our world. The unexpected correlation uncovered in our research serves as a reminder that seemingly unrelated domains can hold intriguing connections, as unpredictably delightful as an unexpected punchline in a well-rehearsed dad joke.

In conclusion - well, not quite yet, our research has unraveled a corn-ucopia of intertwining threads between GMO corn production and the global presence of Hollister stores, contributing to an increasingly holistic understanding of the interconnectedness of our world. Just as a good dad joke unites generations, our findings showcase the unexpected harmony between agriculture in the Heartland and fashion on the world's stage.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 GMO use in corn grown in Ohio and Hollister retail store count worldwide. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
"From GMO Corn to Hollister Stores: A Global Affair"

[[ABSTRACT]]
The relationship between GMO use in corn grown in Ohio and the proliferation of Hollister retail stores worldwide has long been a subject of speculation and jest. In this study, we delve into the bizarrely interconnected realms of agriculture and fashion to analyze whether there exists a meaningful correlation between the two. We conducted a comprehensive analysis using USDA crop data and Statista retail information, unearthing surprising insights that even surprised us more than a dad joke at a family reunion.

Our findings revealed a striking correlation coefficient of 0.8647380 and p < 0.01, indicating a strong statistical relationship between the cultivation of GMO corn in the Buckeye State and the spread of Hollister stores on the global stage. It seems that the growth of genetically modified corn and the proliferation of these trendy retail outlets go hand in hand, much like a kernel of corn and its husk - inseparable, yet entirely unexpected companions.

The implications of our research extend beyond the fields of Ohio and the confines of mall storefronts - shedding light on the unfathomable interconnectedness of seemingly disparate domains. As we uncover this curious correlation, we cannot help but marvel at the quirks of our world, where even the most outlandish connections can be unveiled with a dash of statistical analysis and a sprinkle of good humor.

[[INTRDUCTION]]
The agriculture and fashion industries may seem like two peas in a pod, but the link between them runs deeper than a cornstalk's roots. At first glance, the notion of a connection between GMO corn and Hollister stores may elicit a chuckle or two, but as we dig into the data, we find that the correlation is no laughing matter - well, maybe just a bit. It's like corny humor, quite literally.
As we delve into this maize of interconnectedness, it's imperative to recognize the gravity of our investigation, while also acknowledging the inherent humor in studying the proliferation of a trendy retail chain alongside the cultivation of genetically modified corn. It's almost as if we're uncovering the fashion secrets of the cornfield, revealing that even the most unexpected pairings can yield fruitful results - much like a good crop of dad jokes.
From the heartland of Ohio to the streets of international fashion districts, our research seeks to unravel the tangled web that binds these seemingly incongruous entities. It's a bit like untangling Christmas lights – a perplexing endeavor that promises both intrigue and, inevitably, a few snags along the way.

[[RESULTS]]
The analysis of the data gathered from the USDA and Statista unveiled an eyebrow-raising correlation coefficient of 0.8647380 between the use of GMO corn in Ohio and the proliferation of Hollister stores worldwide. This striking statistical relationship suggests that the cultivation of genetically modified corn and the expansion of this retail chain are as intertwined as a farmer's shoelaces - tightly bound and surprisingly consequential, albeit without the need for a fashion-forward belt.
The r-squared value of 0.7477717 further underscores the robustness of the relationship, indicating that a substantial proportion of the variability in Hollister store count across the world can be explained by the cultivation of GMO corn in the heart of the Midwest. It's like finding the perfect fit - statistically speaking, of course.
Moreover, with a p-value of less than 0.01, the evidence strongly supports the hypothesis that there is indeed a significant association between the growth of genetically modified corn in Ohio and the prevalence of Hollister stores globally. It's almost as convincing as a compelling dad joke - hard to ignore and impossible to refute.
The scatterplot (Fig. 1) visually encapsulates the substantial correlation uncovered in our analysis. It illustrates the unmistakable trend of increasing Hollister store count coinciding with the rise in GMO corn cultivation in Ohio, painting a picture as clear as a blue sky over a cornfield - albeit with more denim and fewer clouds.
Overall, our findings not only provide empirical evidence of the unexpected correlation between GMO corn production and the spread of Hollister stores but also highlight the profound interconnectedness of seemingly unrelated aspects of our world. It's like discovering a hidden pocket in a pair of jeans - surprising, enlightening, and oddly satisfying, much like a good punchline in a statistical analysis.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has brought to light a striking and statistically significant correlation between the cultivation of GMO corn in Ohio and the proliferation of Hollister stores worldwide. It appears that the bond between genetically modified corn and trendy retail outlets is as strong as the bond between a dad and his collection of cringe-worthy dad jokes - unbreakable and somewhat perplexing, yet undeniably impactful.

Our findings not only emphasize the unexpected interconnectedness of disparate industries but also serve as a reminder that statistical analysis can uncover hidden relationships as reliably as uncovering spare change in the pockets of last season’s jeans. These unexpected connections, much like a surprise punchline, show that the world is truly rife with inexplicable phenomena.

With such compelling evidence at hand, it seems that further research in this area may be as unnecessary as an extra pocket on a shirt - amusing to ponder, but ultimately superfluous. It's high time we wrap up this study and let these correlations rest, much like a weary researcher reaching for some well-deserved coffee after a long day of crunching data.

And remember, when it comes to unexpected connections, statistical analysis, and dad jokes, the real magic lies in the details - much like finding a corn kernel wedged between the pages of a fashion magazine.

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 From GMO Corn to Hollister Stores: A Global Affair. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Consumer Culture

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 From GMO Corn to Hollister Stores: A Global Affair. Respond only with the name of a fictional organization.

ChatGPT:

The Global Agricultural Research Society

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 From GMO Corn to Hollister Stores: A Global Affair with an abstract of The relationship between GMO use in corn grown in Ohio and the proliferation of Hollister retail stores worldwide has long been a subject of speculation and jest. In this study, we delve into the bizarrely interconnected realms of agriculture and fashion to analyze whether there exists a meaningful correlation between the two. We conducted a comprehensive analysis using USDA crop data and Statista retail information, unearthing surprising insights that even surprised us more than a dad joke at a family reunion.
Our findings revealed a striking correlation coefficient of 0.8647380 and p < 0.01, indicating a strong statistical relationship between the cultivation of GMO corn in the Buckeye State and the spread of Hollister stores on the global stage. It seems that the growth of genetically modified corn and the proliferation of these trendy retail outlets go hand in hand, much like a kernel of corn and its husk - inseparable, yet entirely unexpected companions.
The implications of our research extend beyond the fields of Ohio and the confines of mall storefronts - shedding light on the unfathomable interconnectedness of seemingly disparate domains. As we uncover this curious correlation, we cannot help but marvel at the quirks of our world, where even the most outlandish connections can be unveiled with a dash of statistical analysis and a sprinkle of good humor.

ChatGPT:

GMO corn, Hollister, retail stores, agriculture, fashion, correlation, analysis, USDA crop data, Statista retail information, correlation coefficient, Buckeye State, genetically modified corn, global spread, interconnectedness, statistical analysis, research implications, quirky correlations, statistical insights

*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

GMO use in corn grown in Ohio
Detailed data title: Percent of all corn planted in Ohio that is genetically modified to be herbicide-tolerant (HT), but not insect-resistant (Bt)
Source: USDA
See what else correlates with GMO use in corn grown in Ohio

Hollister retail store count worldwide
Source: Statista
See what else correlates with Hollister retail store count worldwide

Correlation r = 0.8647380 (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 = 0.7477717 (Coefficient of determination)
This means 74.8% of the change in the one variable (i.e., Hollister retail store count worldwide) is predictable based on the change in the other (i.e., GMO use in corn grown in Ohio) over the 23 years from 2000 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.03E-7.^Show 0.0000001026697092140006000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.86 in 1.03E-5% of random cases. Said differently, if you correlated 9,739,971 random variables^Note You don't actually need 9 million 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 22 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 22 because we have two variables measured over a period of 23 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.

[ 0.7, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
GMO use in corn grown in Ohio (GMO corn %)	3	4	3	3	4	7	13	12	17	17	22	13	20	16	14	14	18	14	14	11	13	14	10
Hollister retail store count worldwide (Store count)	5	32	88	167	249	309	383	447	510	525	540	571	589	587	568	553	543	538	542	546	497	505	529

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([3,4,3,3,4,7,13,12,17,17,22,13,20,16,14,14,18,14,14,11,13,14,10,])
array_2 = np.array([5,32,88,167,249,309,383,447,510,525,540,571,589,587,568,553,543,538,542,546,497,505,529,])
array_1_name = "GMO use in corn grown in Ohio"
array_2_name = "Hollister retail store count worldwide"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only GMO use in corn grown in Ohio
Line chart for only Hollister retail store count worldwide
AI-generated correlation image
The spurious research paper: From GMO Corn to Hollister Stores: A Global Affair

View another random correlation

How fun was this correlation?

Your correlation rating is out of this world!

Correlation ID: 3237 · Black Variable ID: 734 · Red Variable ID: 176


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