Spurious correlation #5,352 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Grocery store spend in Georgia and the second variable is The average number of likes on LockPickingLawyer YouTube videos. The chart goes from 2015 to 2020, 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 Grocery store spend in Georgia and the second variable is The average number of likes on LockPickingLawyer YouTube videos. The chart goes from 2015 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As grocery store spend in Georgia increased, more people were able to afford nuts. This led to an uptick in the average number of likes on LockPickingLawyer's videos, as viewers found his content truly riveting and 'key' to their interests. The correlation is clear: when it comes to likes, it all boils down to having the right 'combination' of snacks while watching lock-picking in action.

^{Show image generation prompt} Model: dalle-3
Prompt: [ a meme ] A simple, yet intriguing visual: In a brightly lit grocery store in Georgia, rows of neatly stocked shelves showcase an assortment of nuts – almonds, cashews, and more, all attractively packaged. Customers, with expressions of delight, reach for bags of nuts, their arms filled with their chosen snacks. In the background, a large screen displays a LockPickingLawyer video, captivating the onlookers who are fully engrossed in the content. Some customers give enthusiastic thumbs up and hit the like button, clearly enjoying the combination of affordable nuts and the fascination of LockPickingLawyer's videos. 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: Grocery store spend in Georgia and The average number of likes on LockPickingLawyer YouTube videos. 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: a funny image macro A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Photorealism Hyper-realistic a meme
ChatGPT: a meme

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 Grocery store spend in Georgia and The average number of likes on LockPickingLawyer YouTube videos, in the following situation: As grocery store spend in Georgia increased, more people were able to afford nuts. This led to an uptick in the average number of likes on LockPickingLawyer's videos, as viewers found his content truly riveting and 'key' to their interests. The correlation is clear: when it comes to likes, it all boils down to having the right 'combination' of snacks while watching lock-picking in action.. Keep the description simple.
ChatGPT: In a grocery store in Georgia, shelves are stocked with various nuts, and customers are seen happily picking up bags of almonds and cashews. Meanwhile, on a screen in the store, a LockPickingLawyer video is playing, and viewers are engrossed, with many giving the video a thumbs up and hitting the like button. The scene illustrates how the increased affordability of nuts due to grocery store spend in Georgia is leading to more viewers finding LockPickingLawyer's content riveting, as they enjoy the right 'combination' of snacks while watching the lock-picking action.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ a meme ] and depicting this scene: In a grocery store in Georgia, shelves are stocked with various nuts, and customers are seen happily picking up bags of almonds and cashews. Meanwhile, on a screen in the store, a LockPickingLawyer video is playing, and viewers are engrossed, with many giving the video a thumbs up and hitting the like button. The scene illustrates how the increased affordability of nuts due to grocery store spend in Georgia is leading to more viewers finding LockPickingLawyer's content riveting, as they enjoy the right 'combination' of snacks while watching the lock-picking action. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ a meme ] A simple, yet intriguing visual: In a brightly lit grocery store in Georgia, rows of neatly stocked shelves showcase an assortment of nuts – almonds, cashews, and more, all attractively packaged. Customers, with expressions of delight, reach for bags of nuts, their arms filled with their chosen snacks. In the background, a large screen displays a LockPickingLawyer video, captivating the onlookers who are fully engrossed in the content. Some customers give enthusiastic thumbs up and hit the like button, clearly enjoying the combination of affordable nuts and the fascination of LockPickingLawyer's videos.

*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 Grocery store spend in Georgia caused The average number of likes on LockPickingLawyer YouTube videos to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos

Journal of Unconventional Consumption Studies

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 Grocery store spend in Georgia and The average number of likes on LockPickingLawyer YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
"Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos"

[[ABSTRACT]]
In this study, we delve into the unlikely connection between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos. Utilizing data from the USDA and YouTube, our research team tackles this seemingly disparate relationship with fervor. Much to our surprise, our analysis reveals a correlation coefficient of 0.9987553 and p < 0.01 for the time period from 2015 to 2020. While these results may appear as unexpected as finding a pineapple in the cereal aisle, they underscore the need to explore unusual connections and correlations in the research landscape. Our findings not only shed light on this unanticipated association but highlight the need for researchers to keep an open mind and embrace the unexpected, much like finding an extra-long receipt at the self-checkout.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The pursuit of knowledge often takes researchers down unexpected paths, much like navigating a packed grocery store on a Sunday afternoon. In the realm of scientific inquiry, it is not uncommon to stumble upon seemingly unrelated phenomena that, upon closer inspection, reveal surprising connections. Our study embarks on just such a quest, exploring the intersection of grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos.
The initial reaction to this research endeavor might mirror the bafflement one experiences upon finding a single lime nestled amidst a sea of lemons in the produce section. However, as we delved deeper into the data, a striking correlation emerged, akin to stumbling upon an elusive item on the top shelf just as you were about to abandon all hope.
By harnessing data from the USDA—a repository of agricultural and economic statistics—and the captivating world of YouTube analytics, we sought to unearth any semblance of coherence between these seemingly disparate variables. Our investigation, much like a meticulous shopper comparing prices and scrutinizing expiration dates, yielded compelling findings that defy conventional wisdom and challenge preconceptions about the predictability of consumer behavior.
As our analysis unfolded, we encountered statistical measures that reinforced the unanticipated relationship between grocery expenditures and the digital admiration for lock-picking prowess. The correlation coefficient of 0.9987553, akin to hitting every green light on the way to the supermarket, astounded even the most seasoned members of our research team. Moreover, the p-value of less than 0.01 provided further validation of the robustness of the observed association, leaving us pondering whether statistical significance might be lurking in unexpected aisles of the scientific supermarket.
While this correlation may initially appear as incongruous as matching a carton of eggs with a cartwheel in the checkout line, our findings compel us to contemplate the intricacies of human behavior and the unforeseen connections that underpin our consumer choices and online preferences. As we present our investigation's findings, we invite fellow researchers to embrace curiosity, for, much like stumbling upon an innovative snack choice in the clearance section, the most significant discoveries often arise from the unexpected.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The investigation of consumer behavior and its unexpected correlations has been a topic of interest in various scholarly works. Smith (2017) delved into the intricacies of consumer spending habits, shedding light on the factors influencing purchasing decisions in different regions. Meanwhile, Doe (2018) examined the growing influence of online platforms on consumer choices, offering insight into the digital landscape's impact on traditional markets. Jones (2019) took a different route, focusing on the psychology of online engagement and the factors driving user interaction with digital content.

Moving beyond the traditional academic sources, the connection between consumer behavior and unanticipated correlations can also be found in non-fiction literature. "Freakonomics" by Steven D. Levitt and Stephen J. Dubner offers intriguing insights into the hidden side of economics, uncovering unexpected connections between seemingly unrelated phenomena. Similarly, "The Tipping Point" by Malcolm Gladwell explores how small changes can lead to significant shifts in behavior, shedding light on the subtle influences that drive consumer choices.

On a more imaginative note, fictional narratives have also toyed with the theme of unexpected connections. In "The Da Vinci Code" by Dan Brown, the protagonist unravels a series of mysterious links between historical symbols and modern-day secrets, echoing the surprising correlations uncovered in our own investigation. Likewise, in "American Gods" by Neil Gaiman, the intertwining of mythology and contemporary society reflects the unexpected convergence of grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos.

As part of the research process, the authors also expanded their inquiries beyond traditional literature to immerse themselves in relevant media content. TV shows such as "Supermarket Sweep" and "How It's Made" provided valuable insights into consumer behavior and the production processes behind everyday products, informing the broader context of our investigation.

In the following sections, we present our own findings, which not only contribute to the existing discourse on consumer behavior but add a whimsical twist to the pursuit of unexpected correlations in the realm of empirical research.

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 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 Grocery store spend in Georgia and The average number of likes on LockPickingLawyer YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 UDSA and YouTube . You used data from 2015 to 2020

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos"

[[ABSTRACT]]
In this study, we delve into the unlikely connection between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos. Utilizing data from the USDA and YouTube, our research team tackles this seemingly disparate relationship with fervor. Much to our surprise, our analysis reveals a correlation coefficient of 0.9987553 and p < 0.01 for the time period from 2015 to 2020. While these results may appear as unexpected as finding a pineapple in the cereal aisle, they underscore the need to explore unusual connections and correlations in the research landscape. Our findings not only shed light on this unanticipated association but highlight the need for researchers to keep an open mind and embrace the unexpected, much like finding an extra-long receipt at the self-checkout.

[[INTRODUCTION]]
The pursuit of knowledge often takes researchers down unexpected paths, much like navigating a packed grocery store on a Sunday afternoon. In the realm of scientific inquiry, it is not uncommon to stumble upon seemingly unrelated phenomena that, upon closer inspection, reveal surprising connections. Our study embarks on just such a quest, exploring the intersection of grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos.
The initial reaction to this research endeavor might mirror the bafflement one experiences upon finding a single lime nestled amidst a sea of lemons in the produce section. However, as we delved deeper into the data, a striking correlation emerged, akin to stumbling upon an elusive item on the top shelf just as you were about to abandon all hope.
By harnessing data from the USDA—a repository of agricultural and economic statistics—and the captivating world of YouTube analytics, we sought to unearth any semblance of coherence between these seemingly disparate variables. Our investigation, much like a meticulous shopper comparing prices and scrutinizing expiration dates, yielded compelling findings that defy conventional wisdom and challenge preconceptions about the predictability of consumer behavior.
As our analysis unfolded, we encountered statistical measures that reinforced the unanticipated relationship between grocery expenditures and the digital admiration for lock-picking prowess. The correlation coefficient of 0.9987553, akin to hitting every green light on the way to the supermarket, astounded even the most seasoned members of our research team. Moreover, the p-value of less than 0.01 provided further validation of the robustness of the observed association, leaving us pondering whether statistical significance might be lurking in unexpected aisles of the scientific supermarket.
While this correlation may initially appear as incongruous as matching a carton of eggs with a cartwheel in the checkout line, our findings compel us to contemplate the intricacies of human behavior and the unforeseen connections that underpin our consumer choices and online preferences. As we present our investigation's findings, we invite fellow researchers to embrace curiosity, for, much like stumbling upon an innovative snack choice in the clearance section, the most significant discoveries often arise from the unexpected.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

In this study, our methodology was as intentional and methodical as a shopper meticulously comparing prices and examining expiration dates before making a purchase. We sought to capture the essence of grocery store spend in Georgia and the digital fandom surrounding LockPickingLawyer's YouTube videos, and to do so, we crafted a research approach as carefully curated as a gourmet cheese selection.

Data Collection:
Our research team scoured the digital landscape, much like determined treasure hunters, to procure the necessary data for our analysis. We leaned heavily on the USDA for comprehensive information on grocery store spending patterns, treating it like a reliable shopping list that guided our data collection efforts. Additionally, we tapped into the captivating world of YouTube analytics, utilizing the treasure trove of video engagement metrics to quantify the average number of likes on LockPickingLawyer's YouTube videos. It was akin to embarking on a shopping spree through the internet, navigating the aisles of information to find the perfect ingredients for our study.

Statistical Analysis:
With our data in hand, we employed statistical techniques as precise as a master chef's knife skills to extract meaningful insights. We meticulously calculated the correlation coefficient between grocery store spend in Georgia and the average number of likes on LockPickingLawyer's YouTube videos, treating it like a delicate balance of flavors in a complex culinary dish. Our analysis spanned the timeframe from 2015 to 2020, ensuring a comprehensive examination of the relationship between these seemingly incongruent variables. We utilized advanced statistical software, handling the data with as much care as one handles a fragile glass jar of pickles, to derive robust measures of association, including the correlation coefficient and the elusive p-value.

Quality Control:
To maintain the integrity of our analysis, we implemented rigorous quality control measures reminiscent of a discerning shopper surveying the produce section for the freshest fruits and vegetables. Data validation, robustness checks, and sensitivity analyses were conducted with the precision of a seasoned shopper inspecting product labels for nutritional information. We ensured that our findings were as ripe and reliable as the selection of artisanal bread in a gourmet bakery.

Ethical Considerations:
In aligning with the ethical standards governing research conduct, we safeguarded the anonymity and confidentiality of the data sources, treating them with the same respect as one would accord to a trusted recipe passed down through generations. Moreover, we upheld the principles of academic integrity, ensuring that our methodology adhered to the highest standards of scientific inquiry, much like a diligent chef adhering to time-honored culinary traditions.

Limitations:
As with any study, our research had its limitations, much like a gourmet dish constrained by the availability of ingredients. While we strived for comprehensive coverage of grocery store spend in Georgia and LockPickingLawyer's YouTube videos, the complexity of consumer behavior and the digital landscape may have introduced nuances that eluded our analysis. Additionally, the study's scope was confined to a specific timeframe and geographical region, much like a signature dish that can only be savored in a particular locale.

By employing this meticulous methodology, our research aimed to dish out substantive insights into the surprising connection between grocery store spend in Georgia and the digital appreciation for LockPickingLawyer's YouTube videos. Just as a delightful fusion of flavors can elevate a culinary offering, our novel approach to this investigation aimed to unravel the unexpected correlations hidden in the scientific supermarket of research.

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 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 Grocery store spend in Georgia and The average number of likes on LockPickingLawyer YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 UDSA and YouTube .

For the time period 2015 to 2020, you found a correlation 0.9987553, r-squared of 0.9975122, 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]]
"Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos"

[[ABSTRACT]]
In this study, we delve into the unlikely connection between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos. Utilizing data from the USDA and YouTube, our research team tackles this seemingly disparate relationship with fervor. Much to our surprise, our analysis reveals a correlation coefficient of 0.9987553 and p < 0.01 for the time period from 2015 to 2020. While these results may appear as unexpected as finding a pineapple in the cereal aisle, they underscore the need to explore unusual connections and correlations in the research landscape. Our findings not only shed light on this unanticipated association but highlight the need for researchers to keep an open mind and embrace the unexpected, much like finding an extra-long receipt at the self-checkout.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The pursuit of knowledge often takes researchers down unexpected paths, much like navigating a packed grocery store on a Sunday afternoon. In the realm of scientific inquiry, it is not uncommon to stumble upon seemingly unrelated phenomena that, upon closer inspection, reveal surprising connections. Our study embarks on just such a quest, exploring the intersection of grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos.
The initial reaction to this research endeavor might mirror the bafflement one experiences upon finding a single lime nestled amidst a sea of lemons in the produce section. However, as we delved deeper into the data, a striking correlation emerged, akin to stumbling upon an elusive item on the top shelf just as you were about to abandon all hope.
By harnessing data from the USDA—a repository of agricultural and economic statistics—and the captivating world of YouTube analytics, we sought to unearth any semblance of coherence between these seemingly disparate variables. Our investigation, much like a meticulous shopper comparing prices and scrutinizing expiration dates, yielded compelling findings that defy conventional wisdom and challenge preconceptions about the predictability of consumer behavior.
As our analysis unfolded, we encountered statistical measures that reinforced the unanticipated relationship between grocery expenditures and the digital admiration for lock-picking prowess. The correlation coefficient of 0.9987553, akin to hitting every green light on the way to the supermarket, astounded even the most seasoned members of our research team. Moreover, the p-value of less than 0.01 provided further validation of the robustness of the observed association, leaving us pondering whether statistical significance might be lurking in unexpected aisles of the scientific supermarket.
While this correlation may initially appear as incongruous as matching a carton of eggs with a cartwheel in the checkout line, our findings compel us to contemplate the intricacies of human behavior and the unforeseen connections that underpin our consumer choices and online preferences. As we present our investigation's findings, we invite fellow researchers to embrace curiosity, for, much like stumbling upon an innovative snack choice in the clearance section, the most significant discoveries often arise from the unexpected.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The statistical analysis of the relationship between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos yielded intriguing results that are as unexpected as finding an empty shelf where the toilet paper should be. The correlation coefficient of 0.9987553 suggests an exceptionally strong positive linear relationship between these seemingly unrelated variables. In simpler terms, it's as if these two elements are holding hands and skipping down the statistical pathway together.

The r-squared value of 0.9975122 further emphasizes the tightness of this connection, indicating that a whopping 99.75122% of the variation in YouTube likes can be explained by the amount spent in grocery stores. It's like finding out that 99.75122% of your grocery list consists of items that you can't find in stock.

Not to mention, the p-value of less than 0.01 provides overwhelming evidence to reject the null hypothesis, reinforcing the legitimacy of this unexpected association. This p-value is so low, it's as if the statistical software handed us a coupon for an unbelievable discount on this correlation.

To visually capture the essence of this remarkable correlation, we present Fig. 1, a scatterplot that portrays the alignment of grocery store spend and LockPickingLawyer YouTube video likes. The strong upward trend displayed in the plot is as striking as finding a ripe avocado on the first try.

Overall, our findings suggest that there is more to the consumer psyche than meets the eye, and our statistical analysis has unearthed a relationship as surprising as finding a live cooking demonstration in the middle of a hardware store.

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 Grocery store spend in Georgia and The average number of likes on LockPickingLawyer YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos"

[[ABSTRACT]]
In this study, we delve into the unlikely connection between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos. Utilizing data from the USDA and YouTube, our research team tackles this seemingly disparate relationship with fervor. Much to our surprise, our analysis reveals a correlation coefficient of 0.9987553 and p < 0.01 for the time period from 2015 to 2020. While these results may appear as unexpected as finding a pineapple in the cereal aisle, they underscore the need to explore unusual connections and correlations in the research landscape. Our findings not only shed light on this unanticipated association but highlight the need for researchers to keep an open mind and embrace the unexpected, much like finding an extra-long receipt at the self-checkout.

[[LITERATURE REVIEW]]
The investigation of consumer behavior and its unexpected correlations has been a topic of interest in various scholarly works. Smith (2017) delved into the intricacies of consumer spending habits, shedding light on the factors influencing purchasing decisions in different regions. Meanwhile, Doe (2018) examined the growing influence of online platforms on consumer choices, offering insight into the digital landscape's impact on traditional markets. Jones (2019) took a different route, focusing on the psychology of online engagement and the factors driving user interaction with digital content.
Moving beyond the traditional academic sources, the connection between consumer behavior and unanticipated correlations can also be found in non-fiction literature. "Freakonomics" by Steven D. Levitt and Stephen J. Dubner offers intriguing insights into the hidden side of economics, uncovering unexpected connections between seemingly unrelated phenomena. Similarly, "The Tipping Point" by Malcolm Gladwell explores how small changes can lead to significant shifts in behavior, shedding light on the subtle influences that drive consumer choices.
On a more imaginative note, fictional narratives have also toyed with the theme of unexpected connections. In "The Da Vinci Code" by Dan Brown, the protagonist unravels a series of mysterious links between historical symbols and modern-day secrets, echoing the surprising correlations uncovered in our own investigation. Likewise, in "American Gods" by Neil Gaiman, the intertwining of mythology and contemporary society reflects the unexpected convergence of grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos.
As part of the research process, the authors also expanded their inquiries beyond traditional literature to immerse themselves in relevant media content. TV shows such as "Supermarket Sweep" and "How It's Made" provided valuable insights into consumer behavior and the production processes behind everyday products, informing the broader context of our investigation.
In the following sections, we present our own findings, which not only contribute to the existing discourse on consumer behavior but add a whimsical twist to the pursuit of unexpected correlations in the realm of empirical research.

[[RESULTS]]
The statistical analysis of the relationship between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos yielded intriguing results that are as unexpected as finding an empty shelf where the toilet paper should be. The correlation coefficient of 0.9987553 suggests an exceptionally strong positive linear relationship between these seemingly unrelated variables. In simpler terms, it's as if these two elements are holding hands and skipping down the statistical pathway together.
The r-squared value of 0.9975122 further emphasizes the tightness of this connection, indicating that a whopping 99.75122% of the variation in YouTube likes can be explained by the amount spent in grocery stores. It's like finding out that 99.75122% of your grocery list consists of items that you can't find in stock.
Not to mention, the p-value of less than 0.01 provides overwhelming evidence to reject the null hypothesis, reinforcing the legitimacy of this unexpected association. This p-value is so low, it's as if the statistical software handed us a coupon for an unbelievable discount on this correlation.
To visually capture the essence of this remarkable correlation, we present Fig. 1, a scatterplot that portrays the alignment of grocery store spend and LockPickingLawyer YouTube video likes. The strong upward trend displayed in the plot is as striking as finding a ripe avocado on the first try.
Overall, our findings suggest that there is more to the consumer psyche than meets the eye, and our statistical analysis has unearthed a relationship as surprising as finding a live cooking demonstration in the middle of a hardware store.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of this study have unearthed a correlation between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos that is as captivating as discovering a flash sale on mystery novels in the produce aisle. Our findings not only affirm the existence of this unexpected association but also contribute to the broader discourse on consumer behavior with a dash of whimsy, much like stumbling upon an unexpected clearance section while conducting routine grocery shopping.

Our results align with prior research exploring unanticipated correlations in consumer behavior. The work of Smith (2017) on consumer spending habits and Doe's (2018) investigation into digital influences on consumer choices resonate with our findings, reinforcing the interconnectedness of seemingly disparate elements in the marketplace. Harnessing the spirit of unconventional exploration akin to uncovering a rare spice in the spice aisle, our study has cemented this unexpected connection between grocery store spend and YouTube engagement, echoing the unconventional correlations explored in "The Tipping Point" by Malcolm Gladwell and the unexpected discoveries in "The Da Vinci Code" by Dan Brown.

While our research may seem as surprising as discovering an unlisted item in the self-checkout area, the robust statistical support for the correlation coefficient of 0.9987553 and the minute p-value leaves little room for doubt, much like finding clear directions in a bewildering maze of grocery aisles. The r-squared value of 0.9975122 elucidates the extent to which grocery store spend explains the variation in YouTube likes, highlighting an interdependence as remarkable as a perfectly stacked display of canned goods.

Moreover, Fig. 1 visually captures the striking alignment between grocery store spend and YouTube likes, analogous to spotting a perfectly arranged grocery display. These intricate statistical nuances underscore the depth and significance of the relationship uncovered, much like discerning the subtle flavor notes in an unexpected grocery aisle product.

In summary, our findings not only accentuate the need for researchers to delve into unexplored connections reminiscent of finding a new flavor of ice cream at the store but also underscore the richness of unexpected correlations that permeate consumer behavior – a delightful revelation akin to discovering a forgotten treat at the bottom of the grocery bag.

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 Grocery store spend in Georgia and The average number of likes on LockPickingLawyer YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos"

[[ABSTRACT]]
In this study, we delve into the unlikely connection between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos. Utilizing data from the USDA and YouTube, our research team tackles this seemingly disparate relationship with fervor. Much to our surprise, our analysis reveals a correlation coefficient of 0.9987553 and p < 0.01 for the time period from 2015 to 2020. While these results may appear as unexpected as finding a pineapple in the cereal aisle, they underscore the need to explore unusual connections and correlations in the research landscape. Our findings not only shed light on this unanticipated association but highlight the need for researchers to keep an open mind and embrace the unexpected, much like finding an extra-long receipt at the self-checkout.

[[INTRDUCTION]]
The pursuit of knowledge often takes researchers down unexpected paths, much like navigating a packed grocery store on a Sunday afternoon. In the realm of scientific inquiry, it is not uncommon to stumble upon seemingly unrelated phenomena that, upon closer inspection, reveal surprising connections. Our study embarks on just such a quest, exploring the intersection of grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos.
The initial reaction to this research endeavor might mirror the bafflement one experiences upon finding a single lime nestled amidst a sea of lemons in the produce section. However, as we delved deeper into the data, a striking correlation emerged, akin to stumbling upon an elusive item on the top shelf just as you were about to abandon all hope.
By harnessing data from the USDA—a repository of agricultural and economic statistics—and the captivating world of YouTube analytics, we sought to unearth any semblance of coherence between these seemingly disparate variables. Our investigation, much like a meticulous shopper comparing prices and scrutinizing expiration dates, yielded compelling findings that defy conventional wisdom and challenge preconceptions about the predictability of consumer behavior.
As our analysis unfolded, we encountered statistical measures that reinforced the unanticipated relationship between grocery expenditures and the digital admiration for lock-picking prowess. The correlation coefficient of 0.9987553, akin to hitting every green light on the way to the supermarket, astounded even the most seasoned members of our research team. Moreover, the p-value of less than 0.01 provided further validation of the robustness of the observed association, leaving us pondering whether statistical significance might be lurking in unexpected aisles of the scientific supermarket.
While this correlation may initially appear as incongruous as matching a carton of eggs with a cartwheel in the checkout line, our findings compel us to contemplate the intricacies of human behavior and the unforeseen connections that underpin our consumer choices and online preferences. As we present our investigation's findings, we invite fellow researchers to embrace curiosity, for, much like stumbling upon an innovative snack choice in the clearance section, the most significant discoveries often arise from the unexpected.

[[RESULTS]]
The statistical analysis of the relationship between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos yielded intriguing results that are as unexpected as finding an empty shelf where the toilet paper should be. The correlation coefficient of 0.9987553 suggests an exceptionally strong positive linear relationship between these seemingly unrelated variables. In simpler terms, it's as if these two elements are holding hands and skipping down the statistical pathway together.
The r-squared value of 0.9975122 further emphasizes the tightness of this connection, indicating that a whopping 99.75122% of the variation in YouTube likes can be explained by the amount spent in grocery stores. It's like finding out that 99.75122% of your grocery list consists of items that you can't find in stock.
Not to mention, the p-value of less than 0.01 provides overwhelming evidence to reject the null hypothesis, reinforcing the legitimacy of this unexpected association. This p-value is so low, it's as if the statistical software handed us a coupon for an unbelievable discount on this correlation.
To visually capture the essence of this remarkable correlation, we present Fig. 1, a scatterplot that portrays the alignment of grocery store spend and LockPickingLawyer YouTube video likes. The strong upward trend displayed in the plot is as striking as finding a ripe avocado on the first try.
Overall, our findings suggest that there is more to the consumer psyche than meets the eye, and our statistical analysis has unearthed a relationship as surprising as finding a live cooking demonstration in the middle of a hardware store.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has illuminated a remarkable and unexpected association between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos. This correlation, with a coefficient as strong as a shopping cart wheeling through the aisles on a sale day, underscores the need for researchers to keep their eyes peeled for unconventional connections in the vast landscape of data analysis. Our findings not only highlight the potential for unanticipated correlations lurking amidst the shelves of statistical significance but also reinforce the importance of exploring seemingly disparate variables, much like stumbling upon a grocery item in an unexpected section of the store.

The implications of our research stretch further than a receipt at the checkout, as they challenge conventional wisdom and beckon scientists to embrace the unexpected with open arms. Our statistical analysis has laid bare a connection as surprising as finding a gourmet cheese selection in a convenience store, urging the scientific community to approach research with a flexible and open-minded perspective. Just as one might find an unexpected delight in the grocery store's clearance section, so too can researchers stumble upon novel insights through venturing into uncharted statistical territory.

With a correlation coefficient as strong as a jar of pickles refusing to budge from the top shelf, and a p-value as rare as a golden apple in the produce section, our findings stand as a testament to the quirky and unpredictable nature of consumer behavior. Therefore, we assert that no further research is needed in this area, as our study has definitively cracked the code on this curious correlation, much like finding the last item on a crowded shelf.

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 Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Unconventional Consumption Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Data Analysis

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos with an abstract of In this study, we delve into the unlikely connection between grocery store spend in Georgia and the average number of likes on LockPickingLawyer YouTube videos. Utilizing data from the USDA and YouTube, our research team tackles this seemingly disparate relationship with fervor. Much to our surprise, our analysis reveals a correlation coefficient of 0.9987553 and p < 0.01 for the time period from 2015 to 2020. While these results may appear as unexpected as finding a pineapple in the cereal aisle, they underscore the need to explore unusual connections and correlations in the research landscape. Our findings not only shed light on this unanticipated association but highlight the need for researchers to keep an open mind and embrace the unexpected, much like finding an extra-long receipt at the self-checkout.

ChatGPT:

grocery store spend Georgia, LockPickingLawyer YouTube videos, correlation between grocery store spend and YouTube likes, USDA data analysis, unusual connections in research, unexpected correlations, correlation coefficient analysis, data analysis 2015-2020

*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

Grocery store spend in Georgia
Detailed data title: Per capita spending on food at home in Georgia
Source: UDSA
Additional Info: ^{See full details} Measured in nominal dollars, including tax & tip. Includes all "food-at-home" sources.

See what else correlates with Grocery store spend in Georgia

The average number of likes on LockPickingLawyer YouTube videos
Detailed data title: The average number of likes on LockPickingLawyer YouTube videos.
Source: YouTube
See what else correlates with The average number of likes on LockPickingLawyer YouTube videos

Correlation r = 0.9987553 (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 = 0.9975122 (Coefficient of determination)
This means 99.8% of the change in the one variable (i.e., The average number of likes on LockPickingLawyer YouTube videos) is predictable based on the change in the other (i.e., Grocery store spend in Georgia) over the 6 years from 2015 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.3E-6.^Show 0.0000023229013811465194000000
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 1 in 0.00023% of random cases. Said differently, if you correlated 430,496 random variables^Note You don't actually need 430 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 5 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 5 because we have two variables measured over a period of 6 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.99, 1 ] 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.

	2015	2016	2017	2018	2019	2020
Grocery store spend in Georgia (Per capita spend)	2166.17	2158.51	2210.9	2323.03	2374.97	2554.58
The average number of likes on LockPickingLawyer YouTube videos (Average likes)	2462.08	1751.78	9534.84	20437.1	28255.2	50838.2

Why this works

Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
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.
Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
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. ^Note 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. ^{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([2166.17,2158.51,2210.9,2323.03,2374.97,2554.58,])
array_2 = np.array([2462.08,1751.78,9534.84,20437.1,28255.2,50838.2,])
array_1_name = "Grocery store spend in Georgia"
array_2_name = "The average number of likes on LockPickingLawyer YouTube videos"

# 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 Grocery store spend in Georgia
Line chart for only The average number of likes on LockPickingLawyer YouTube videos
AI-generated correlation image
The spurious research paper: Cracking the Code: The Correlation Between Grocery Store Spend in Georgia and the Average Number of Likes on LockPickingLawyer YouTube Videos

View another random correlation

How fun was this correlation?

Your rating skills are top-notch!

Correlation ID: 5352 · Black Variable ID: 962 · Red Variable ID: 25757


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