about · email me · subscribe
Spurious correlation #3,114 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'where to buy toilet paper' and the second variable is Runs scored by the Milwaukee Brewers.  The chart goes from 2004 to 2023, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Every time someone searched for where to buy toilet paper, a tiny bit of their focus and energy was diverted away from the Brewers, leading to a decrease in runs scored. It's as if the team's chances of hitting a home run were being flushed away with each new search. The correlation may seem like a lot of number 2, but it's a striking reminder that even the most seemingly unrelated events can be intertwined in strange and comical ways. It's a real wipeout for the Brewers' offense, and they may need to re-evaluate their strategy to ensure they don't get caught looking for runs in all the wrong places.

Model: dalle-3
Prompt: Generate an image that resembles a scene from a Disney movie where a cozy living room serves as the setting. Inside the room, a TV screen is showing the Milwaukee Brewers playing a game, with the team's supporters cheering in the background. On the coffee table, there's a laptop displaying Google search results for "where to buy toilet paper." The table is adorned with rolls of toilet paper and delicious snacks, illustrating the intertwining of the Google searches for necessities and the fervor of the sports event. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers. 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: Glitch art Concept art Hyper-realistic A Discovery magazine cover image An image that looks like it is a scene from A Disney Movie
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 Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers, in the following situation: Google searches for 'where to buy toilet paper' caused Runs scored by the Milwaukee Brewers because as more people started stocking up on toilet paper, they also stocked up on snacks to watch Brewers games, leading to increased energy and enthusiasm resulting in more runs scored.. Keep the description simple.
ChatGPT: In a living room, a TV shows the Milwaukee Brewers playing a game, while on the coffee table, a laptop displays Google search results for "where to buy toilet paper." The room is filled with the sound of excitement as the Brewers score runs, and the table is shared by both toilet paper and snacks, reflecting the connection between the Google searches and the increased energy and enthusiasm contributing to the team's success.

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: In a living room, a TV shows the Milwaukee Brewers playing a game, while on the coffee table, a laptop displays Google search results for "where to buy toilet paper." The room is filled with the sound of excitement as the Brewers score runs, and the table is shared by both toilet paper and snacks, reflecting the connection between the Google searches and the increased energy and enthusiasm contributing to the team's success. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that resembles a scene from a Disney movie where a cozy living room serves as the setting. Inside the room, a TV screen is showing the Milwaukee Brewers playing a game, with the team's supporters cheering in the background. On the coffee table, there's a laptop displaying Google search results for "where to buy toilet paper." The table is adorned with rolls of toilet paper and delicious snacks, illustrating the intertwining of the Google searches for necessities and the fervor of the sports event.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in where to buy toilet paper (Google searches for 'where to buy toilet paper') negatively influenced Runs scored by the Milwaukee Brewers.

AI academic paper

(Because p < 0.01)
Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers

Journal of Quirky Quantitative Research

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers. Make lots of jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from Google Trends and Baseball-Reference.com to assess this nagging question. You found a correlation coefficient of -0.9152772 and p < 0.01 for 2004 to 2023.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers

[[ABSTRACT]]
In this paper, we delve into the curious connection between the urgency to acquire toilet paper and the performance of the Milwaukee Brewers on the baseball field. By leveraging data from Google Trends and Baseball-Reference.com, we rigorously address this toilet paper turmoil. Our findings reveal a remarkably robust negative correlation with a correlation coefficient of -0.9152772 and p < 0.01 for the years 2004 to 2023. This sheds new light on the idea that when individuals are preoccupied with stocking up on bathroom essentials, the Brewers seem to score fewer runs. We discuss the implications of this unexpected relationship and propose future research directions, like exploring the influence of other household goods on sports performance. Overall, this study unveils an intriguing link between consumer behavior and athletic feats, showing the importance of taking a swing at unconventional connections in our statistical playbook.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers

[[ABSTRACT]]
In this paper, we delve into the curious connection between the urgency to acquire toilet paper and the performance of the Milwaukee Brewers on the baseball field. By leveraging data from Google Trends and Baseball-Reference.com, we rigorously address this toilet paper turmoil. Our findings reveal a remarkably robust negative correlation with a correlation coefficient of -0.9152772 and p < 0.01 for the years 2004 to 2023. This sheds new light on the idea that when individuals are preoccupied with stocking up on bathroom essentials, the Brewers seem to score fewer runs. We discuss the implications of this unexpected relationship and propose future research directions, like exploring the influence of other household goods on sports performance. Overall, this study unveils an intriguing link between consumer behavior and athletic feats, showing the importance of taking a swing at unconventional connections in our statistical playbook.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The world of statistical research is no stranger to uncovering unexpected relationships and peculiar correlations. From the influence of moon phases on human behavior to the connection between the consumption of cheese and the likelihood of death by becoming tangled in bedsheets, researchers have delved into a myriad of offbeat topics with the hope of unearthing meaningful insights. In this vein, we embark on a quest to explore the perplexing bond between the frenzy of Google searches for 'where to buy toilet paper' and the performance of the Milwaukee Brewers on the baseball diamond.

While it may seem like an odd couple, the allure of oddities is not lost on the scientific community. Moreover, as researchers, it is our duty to rigorously investigate and analyze even the most unexpected correlations. In this quest, we aim to employ the tools of statistics, data analysis, and puns (yes, puns) to shine a light on the curious relationship between toilet paper turmoil and runs scored by the Milwaukee Brewers. After all, in the realm of statistical research, we must always be prepared to expect the unexpected and tackle the most bizarre of hypotheses with unwavering scientific curiosity.

Cracking open the metaphorical data vault, we turn to the wealth of information provided by Google Trends and the treasure trove of baseball statistics at Baseball-Reference.com to unravel this enigma. By examining the patterns and trends in these data sources, we strive to lend empirical support to what may initially appear as no more than a whimsical theory.

The amusing image of baseball fans fervently searching for rolls of soft, pillowy toilet paper while simultaneously rooting for their team at the ballpark may elicit a chuckle, yet as researchers, we do not shy away from embracing the unexpected. As we embark on this statistical journey, we invite readers to join us in uncovering the hidden connections within this peculiar pairing of variables. After all, in the game of statistics, there's no such thing as a foul ball when it comes to exploring the unpredictable links that emerge amidst the data. So, without further ado, let's step up to the plate and take a swing at unraveling this captivating conundrum.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers

[[ABSTRACT]]
In this paper, we delve into the curious connection between the urgency to acquire toilet paper and the performance of the Milwaukee Brewers on the baseball field. By leveraging data from Google Trends and Baseball-Reference.com, we rigorously address this toilet paper turmoil. Our findings reveal a remarkably robust negative correlation with a correlation coefficient of -0.9152772 and p < 0.01 for the years 2004 to 2023. This sheds new light on the idea that when individuals are preoccupied with stocking up on bathroom essentials, the Brewers seem to score fewer runs. We discuss the implications of this unexpected relationship and propose future research directions, like exploring the influence of other household goods on sports performance. Overall, this study unveils an intriguing link between consumer behavior and athletic feats, showing the importance of taking a swing at unconventional connections in our statistical playbook.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of statistical research is no stranger to uncovering unexpected relationships and peculiar correlations. From the influence of moon phases on human behavior to the connection between the consumption of cheese and the likelihood of death by becoming tangled in bedsheets, researchers have delved into a myriad of offbeat topics with the hope of unearthing meaningful insights. In this vein, we embark on a quest to explore the perplexing bond between the frenzy of Google searches for 'where to buy toilet paper' and the performance of the Milwaukee Brewers on the baseball diamond.
While it may seem like an odd couple, the allure of oddities is not lost on the scientific community. Moreover, as researchers, it is our duty to rigorously investigate and analyze even the most unexpected correlations. In this quest, we aim to employ the tools of statistics, data analysis, and puns (yes, puns) to shine a light on the curious relationship between toilet paper turmoil and runs scored by the Milwaukee Brewers. After all, in the realm of statistical research, we must always be prepared to expect the unexpected and tackle the most bizarre of hypotheses with unwavering scientific curiosity.
Cracking open the metaphorical data vault, we turn to the wealth of information provided by Google Trends and the treasure trove of baseball statistics at Baseball-Reference.com to unravel this enigma. By examining the patterns and trends in these data sources, we strive to lend empirical support to what may initially appear as no more than a whimsical theory.
The amusing image of baseball fans fervently searching for rolls of soft, pillowy toilet paper while simultaneously rooting for their team at the ballpark may elicit a chuckle, yet as researchers, we do not shy away from embracing the unexpected. As we embark on this statistical journey, we invite readers to join us in uncovering the hidden connections within this peculiar pairing of variables. After all, in the game of statistics, there's no such thing as a foul ball when it comes to exploring the unpredictable links that emerge amidst the data. So, without further ado, let's step up to the plate and take a swing at unraveling this captivating conundrum.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The burgeoning field of offbeat statistical inquiry has seen a gamut of peculiar correlations, from the connection between the number of Nicolas Cage movies released and swimming pool drownings (Smith, 2017) to the relationship between the price of popcorn and the duration of romantic relationships (Doe, 2012). However, the intersection of consumer behavior and sporting performance remains a relatively untapped area of investigation. The present study seeks to fill this void by examining the connection between Google searches for 'where to buy toilet paper' and the runs scored by the Milwaukee Brewers.

In "Toilet Paper Chronicles: A Statistical Odyssey," the authors delve into the idiosyncratic world of consumer behavior during times of shortage, shedding light on the impact of panic-induced online searches for essential household items on various societal phenomena. Similarly, Jones (2015) explores the curious case of sports performance and its relationship to consumer trends in "The Toilet Paper Effect: Unraveling the Intricacies of Market Panic and Athletic Achievement."

Spearheading a novel approach to sports statistical analysis, the current study endeavors to expand this peculiar niche of inquiry, infusing it with a sense of statistical rigor and the occasional pun.

While the literature on this specific nexus of consumer behavior and athletic performance remains thin, it is pertinent to highlight the significance of interdisciplinary research in exploring unconventional connections. We draw inspiration from the works of Kahneman and Tversky (2003) in "Thinking, Fast and Slow," and "Freakonomics" by Levitt and Dubner (2005), which underscore the value of embracing unconventional hypotheses and unearthing unexpected relations within empirical data.

Venturing into the realm of fiction, the concept of unforeseen connections is intricately woven into the narratives of "The Hitchhiker's Guide to the Galaxy" by Douglas Adams and "Cloud Atlas" by David Mitchell. It is in the spirit of such whimsical exploration that we approach the enigmatic amalgamation of toilet paper searches and baseball runs.

Drawing from childhood inspirations, the zany antics of "SpongeBob SquarePants" and the adventurous escapades in "Phineas and Ferb" serve as reminders of the boundless curiosity and creativity that underpin the pursuit of unconventional knowledge.

As we embark on this statistical escapade, we invite readers to join us in embracing the unexpected, for in the world of statistical inquiry, there's always room for a curveball or two. With a wink and a statistical nod, we set forth to unravel the quirk-filled tapestry of toilet paper turmoil and baseball prowess.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Google Trends and Baseball-Reference.com . You used data from 2004 to 2023

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]]
Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers

[[ABSTRACT]]
In this paper, we delve into the curious connection between the urgency to acquire toilet paper and the performance of the Milwaukee Brewers on the baseball field. By leveraging data from Google Trends and Baseball-Reference.com, we rigorously address this toilet paper turmoil. Our findings reveal a remarkably robust negative correlation with a correlation coefficient of -0.9152772 and p < 0.01 for the years 2004 to 2023. This sheds new light on the idea that when individuals are preoccupied with stocking up on bathroom essentials, the Brewers seem to score fewer runs. We discuss the implications of this unexpected relationship and propose future research directions, like exploring the influence of other household goods on sports performance. Overall, this study unveils an intriguing link between consumer behavior and athletic feats, showing the importance of taking a swing at unconventional connections in our statistical playbook.

[[INTRODUCTION]]
The world of statistical research is no stranger to uncovering unexpected relationships and peculiar correlations. From the influence of moon phases on human behavior to the connection between the consumption of cheese and the likelihood of death by becoming tangled in bedsheets, researchers have delved into a myriad of offbeat topics with the hope of unearthing meaningful insights. In this vein, we embark on a quest to explore the perplexing bond between the frenzy of Google searches for 'where to buy toilet paper' and the performance of the Milwaukee Brewers on the baseball diamond.
While it may seem like an odd couple, the allure of oddities is not lost on the scientific community. Moreover, as researchers, it is our duty to rigorously investigate and analyze even the most unexpected correlations. In this quest, we aim to employ the tools of statistics, data analysis, and puns (yes, puns) to shine a light on the curious relationship between toilet paper turmoil and runs scored by the Milwaukee Brewers. After all, in the realm of statistical research, we must always be prepared to expect the unexpected and tackle the most bizarre of hypotheses with unwavering scientific curiosity.
Cracking open the metaphorical data vault, we turn to the wealth of information provided by Google Trends and the treasure trove of baseball statistics at Baseball-Reference.com to unravel this enigma. By examining the patterns and trends in these data sources, we strive to lend empirical support to what may initially appear as no more than a whimsical theory.
The amusing image of baseball fans fervently searching for rolls of soft, pillowy toilet paper while simultaneously rooting for their team at the ballpark may elicit a chuckle, yet as researchers, we do not shy away from embracing the unexpected. As we embark on this statistical journey, we invite readers to join us in uncovering the hidden connections within this peculiar pairing of variables. After all, in the game of statistics, there's no such thing as a foul ball when it comes to exploring the unpredictable links that emerge amidst the data. So, without further ado, let's step up to the plate and take a swing at unraveling this captivating conundrum.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To begin our quest for unraveling the curious relationship between the urgency to procure toilet paper and the performance of the Milwaukee Brewers, we undertook a rigorous and, dare I say, amusing methodology. Our data collection and analysis traversed the vast expanse of the internet, striking a balance between the cosmic domain of Google Trends and the statistical sanctum of Baseball-Reference.com.

Firstly, we plumbed the depths of Google Trends, a digital treasure trove of contemporary searches, to capture the zeitgeist of toilet paper turmoil. We meticulously tracked the frequency and intensity of searches for 'where to buy toilet paper' from the year 2004 to 2023. This time span encapsulates a pivotal period in the evolution of both toilet paper procurement practices and the ebbs and flows of the Brewers' performance on the diamond.

Simultaneously, our research team delved into the cavernous halls of Baseball-Reference.com in pursuit of elucidating the statistical saga of the Milwaukee Brewers' runs scored in the same temporal ambit. Here, we meticulously extracted the quantitative essence of the Brewers' offensive prowess, poring over game logs, player statistics, and the echoes of cheering crowds to capture the ebb and flow of runs across a significant span of baseball history.

Once armed with our data du jour, we plumbed the depths of statistical analysis to uncover the hidden underpinnings of this unlikely duet. Leveraging the arcane arts of correlation analysis, we unfurled the enigmatic tapestry of toilet paper searches and runs scored by the Brewers. Our statistical toolkit gleamed with the implements of Pearson's correlation coefficient, t-tests, and regression analyses, as we sought to quantify the magnitude and direction of the relationship between these seemingly disparate variables.

Moreover, to tackle the intrinsic variability and lighthearted chaos of our chosen variables, we constructed time series analyses to comprehend the temporal dynamics of this unconventional association. The diachronic odyssey of toilet paper searches and runs scored was thus meticulously unwound, revealing the sinuous dance of correlation and causation that underlies this captivating conundrum.

Finally, to lend empirical weight to our findings, we employed assorted statistical models, including autoregressive integrated moving average (ARIMA) models, and the occasional exuberant perusal of scatter plots and lighthearted bar graphs to visually encapsulate the interplay between bathroom essentials and runs across the diamond.

In the alchemic crucible of statistical inquiry, we navigated the rapids of data, analysis, and puns with an unshakable scientific resolve, shedding light on the unexpected link between the pressing matter of toilet paper and the less pressing, yet equally captivating, matter of runs scored by the Milwaukee Brewers. Our methodology, while imbued with a touch of whimsy, stands as a testament to the unyielding pursuit of understanding amidst the capricious connections that emerge within the rich tapestry of statistical research.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Google Trends and Baseball-Reference.com .

For the time period 2004 to 2023, you found a correlation -0.9152772, r-squared of 0.8377324, 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]]
Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers

[[ABSTRACT]]
In this paper, we delve into the curious connection between the urgency to acquire toilet paper and the performance of the Milwaukee Brewers on the baseball field. By leveraging data from Google Trends and Baseball-Reference.com, we rigorously address this toilet paper turmoil. Our findings reveal a remarkably robust negative correlation with a correlation coefficient of -0.9152772 and p < 0.01 for the years 2004 to 2023. This sheds new light on the idea that when individuals are preoccupied with stocking up on bathroom essentials, the Brewers seem to score fewer runs. We discuss the implications of this unexpected relationship and propose future research directions, like exploring the influence of other household goods on sports performance. Overall, this study unveils an intriguing link between consumer behavior and athletic feats, showing the importance of taking a swing at unconventional connections in our statistical playbook.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The world of statistical research is no stranger to uncovering unexpected relationships and peculiar correlations. From the influence of moon phases on human behavior to the connection between the consumption of cheese and the likelihood of death by becoming tangled in bedsheets, researchers have delved into a myriad of offbeat topics with the hope of unearthing meaningful insights. In this vein, we embark on a quest to explore the perplexing bond between the frenzy of Google searches for 'where to buy toilet paper' and the performance of the Milwaukee Brewers on the baseball diamond.
While it may seem like an odd couple, the allure of oddities is not lost on the scientific community. Moreover, as researchers, it is our duty to rigorously investigate and analyze even the most unexpected correlations. In this quest, we aim to employ the tools of statistics, data analysis, and puns (yes, puns) to shine a light on the curious relationship between toilet paper turmoil and runs scored by the Milwaukee Brewers. After all, in the realm of statistical research, we must always be prepared to expect the unexpected and tackle the most bizarre of hypotheses with unwavering scientific curiosity.
Cracking open the metaphorical data vault, we turn to the wealth of information provided by Google Trends and the treasure trove of baseball statistics at Baseball-Reference.com to unravel this enigma. By examining the patterns and trends in these data sources, we strive to lend empirical support to what may initially appear as no more than a whimsical theory.
The amusing image of baseball fans fervently searching for rolls of soft, pillowy toilet paper while simultaneously rooting for their team at the ballpark may elicit a chuckle, yet as researchers, we do not shy away from embracing the unexpected. As we embark on this statistical journey, we invite readers to join us in uncovering the hidden connections within this peculiar pairing of variables. After all, in the game of statistics, there's no such thing as a foul ball when it comes to exploring the unpredictable links that emerge amidst the data. So, without further ado, let's step up to the plate and take a swing at unraveling this captivating conundrum.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The connection between Google searches for 'where to buy toilet paper' and the performance of the Milwaukee Brewers on the baseball field has yielded some ground-shaking results. Through our quantitative analysis, we found a strikingly robust negative correlation between the two variables. The correlation coefficient was calculated to be -0.9152772, indicating a very strong inverse relationship between the urgency to procure toilet paper and the number of runs scored by the Brewers.

The coefficient of determination (r-squared) further emphasizes the substantial connection we uncovered, amounting to an impressive 83.77%. This suggests that a staggering 83.77% of the variability in runs scored by the Brewers can be explained by the corresponding fluctuations in Google searches for 'where to buy toilet paper.' It's as if the two variables are performing a perfectly choreographed statistical tango, albeit with a touch of bathroom humor.

Moreover, the p-value of less than 0.01 lends unequivocal support to the significance of this correlation. The likelihood of such a strong relationship occurring purely by chance is exceedingly remote, reinforcing the validity of our findings. It seems that the statistical stars have aligned to shine a light on this unusual association, and it's not just a statistical blip on the radar.

Additionally, in Figure 1, we present a scatterplot that vividly illustrates the tight negative relationship between the searches for toilet paper and runs scored by the Milwaukee Brewers. This graph not only confirms the strength of the correlation but also serves as a visual testament to the unexpected nature of our findings. It's not every day that one gets to witness a scatterplot that marries bathroom essentials and ballpark heroics so convincingly.

In conclusion, our research has uncovered a statistically sound, albeit slightly comical, link between the urgency to stock up on toilet paper and the scoring prowess of the Brewers. This peculiar association challenges conventional wisdom and underscores the need for a broad-minded statistical approach in unraveling unexpected connections. As we reflect on these results, we are reminded that in the realm of statistics, even the most unlikely variables can step up to the plate and deliver a grand slam of empirical insight.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers

[[ABSTRACT]]
In this paper, we delve into the curious connection between the urgency to acquire toilet paper and the performance of the Milwaukee Brewers on the baseball field. By leveraging data from Google Trends and Baseball-Reference.com, we rigorously address this toilet paper turmoil. Our findings reveal a remarkably robust negative correlation with a correlation coefficient of -0.9152772 and p < 0.01 for the years 2004 to 2023. This sheds new light on the idea that when individuals are preoccupied with stocking up on bathroom essentials, the Brewers seem to score fewer runs. We discuss the implications of this unexpected relationship and propose future research directions, like exploring the influence of other household goods on sports performance. Overall, this study unveils an intriguing link between consumer behavior and athletic feats, showing the importance of taking a swing at unconventional connections in our statistical playbook.

[[LITERATURE REVIEW]]
The burgeoning field of offbeat statistical inquiry has seen a gamut of peculiar correlations, from the connection between the number of Nicolas Cage movies released and swimming pool drownings (Smith, 2017) to the relationship between the price of popcorn and the duration of romantic relationships (Doe, 2012). However, the intersection of consumer behavior and sporting performance remains a relatively untapped area of investigation. The present study seeks to fill this void by examining the connection between Google searches for 'where to buy toilet paper' and the runs scored by the Milwaukee Brewers.
In "Toilet Paper Chronicles: A Statistical Odyssey," the authors delve into the idiosyncratic world of consumer behavior during times of shortage, shedding light on the impact of panic-induced online searches for essential household items on various societal phenomena. Similarly, Jones (2015) explores the curious case of sports performance and its relationship to consumer trends in "The Toilet Paper Effect: Unraveling the Intricacies of Market Panic and Athletic Achievement."
Spearheading a novel approach to sports statistical analysis, the current study endeavors to expand this peculiar niche of inquiry, infusing it with a sense of statistical rigor and the occasional pun.
While the literature on this specific nexus of consumer behavior and athletic performance remains thin, it is pertinent to highlight the significance of interdisciplinary research in exploring unconventional connections. We draw inspiration from the works of Kahneman and Tversky (2003) in "Thinking, Fast and Slow," and "Freakonomics" by Levitt and Dubner (2005), which underscore the value of embracing unconventional hypotheses and unearthing unexpected relations within empirical data.
Venturing into the realm of fiction, the concept of unforeseen connections is intricately woven into the narratives of "The Hitchhiker's Guide to the Galaxy" by Douglas Adams and "Cloud Atlas" by David Mitchell. It is in the spirit of such whimsical exploration that we approach the enigmatic amalgamation of toilet paper searches and baseball runs.
Drawing from childhood inspirations, the zany antics of "SpongeBob SquarePants" and the adventurous escapades in "Phineas and Ferb" serve as reminders of the boundless curiosity and creativity that underpin the pursuit of unconventional knowledge.
As we embark on this statistical escapade, we invite readers to join us in embracing the unexpected, for in the world of statistical inquiry, there's always room for a curveball or two. With a wink and a statistical nod, we set forth to unravel the quirk-filled tapestry of toilet paper turmoil and baseball prowess.

[[RESULTS]]
The connection between Google searches for 'where to buy toilet paper' and the performance of the Milwaukee Brewers on the baseball field has yielded some ground-shaking results. Through our quantitative analysis, we found a strikingly robust negative correlation between the two variables. The correlation coefficient was calculated to be -0.9152772, indicating a very strong inverse relationship between the urgency to procure toilet paper and the number of runs scored by the Brewers.
The coefficient of determination (r-squared) further emphasizes the substantial connection we uncovered, amounting to an impressive 83.77%. This suggests that a staggering 83.77% of the variability in runs scored by the Brewers can be explained by the corresponding fluctuations in Google searches for 'where to buy toilet paper.' It's as if the two variables are performing a perfectly choreographed statistical tango, albeit with a touch of bathroom humor.
Moreover, the p-value of less than 0.01 lends unequivocal support to the significance of this correlation. The likelihood of such a strong relationship occurring purely by chance is exceedingly remote, reinforcing the validity of our findings. It seems that the statistical stars have aligned to shine a light on this unusual association, and it's not just a statistical blip on the radar.
Additionally, in Figure 1, we present a scatterplot that vividly illustrates the tight negative relationship between the searches for toilet paper and runs scored by the Milwaukee Brewers. This graph not only confirms the strength of the correlation but also serves as a visual testament to the unexpected nature of our findings. It's not every day that one gets to witness a scatterplot that marries bathroom essentials and ballpark heroics so convincingly.
In conclusion, our research has uncovered a statistically sound, albeit slightly comical, link between the urgency to stock up on toilet paper and the scoring prowess of the Brewers. This peculiar association challenges conventional wisdom and underscores the need for a broad-minded statistical approach in unraveling unexpected connections. As we reflect on these results, we are reminded that in the realm of statistics, even the most unlikely variables can step up to the plate and deliver a grand slam of empirical insight.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The connection we uncovered between Google searches for 'where to buy toilet paper' and runs scored by the Milwaukee Brewers has certainly sparked a lively debate in both statistical and sporting circles. Our findings not only add a quirky dimension to the burgeoning field of offbeat statistical inquiry but also underscore the unforeseen influence of consumer behavior on athletic performance. Let's unpack the bathroom banter and ballpark brilliance that has emerged from our study.

Our results resonate with prior research that has explored the peculiar interplay between consumer trends and societal phenomena. In "Toilet Paper Chronicles: A Statistical Odyssey," the idiosyncratic world of consumer behavior during times of shortage is delved into, emphasizing the impact of panic-induced online searches for essential household items on various societal facets. Similarly, Jones' (2015) exploration of the 'Toilet Paper Effect' resonates with our findings, affirming the unexpected influence of consumer trends on sporting achievements. It seems that when it comes to statistical curiosities, there's always room for a whimsical correlation or two.

Our robust negative correlation coefficient of -0.9152772 not only validates the atypical connection between toilet paper turmoil and baseball prowess but also contributes to the colorful tapestry of offbeat statistical relationships. With a coefficient of determination (r-squared) of 83.77%, our findings suggest that the fluctuations in runs scored by the Brewers can be largely elucidated by the corresponding variations in searches for toilet paper. It's as if the statistical universe conspired to bring these unlikely bedfellows – bathroom essentials and ballpark exploits – into an unexpectedly captivating statistical tango.

Moreover, the p-value of less than 0.01 provides unambiguous confirmation of the significance of this correlation, underscoring that this statistical tête-à-tête is not a mere statistical fluke. Our scatterplot vividly illustrates the compelling negative relationship between the searches for toilet paper and the scoring prowess of the Brewers, providing both a statistical feast for the eyes and a lively anecdote for the annals of statistical exploration.

As we stride through this statistically whimsical terrain, our findings bear witness to the delightfully unexpected connections that can emerge from the careful scrutiny of empirical data. In the playful spirit of "The Hitchhiker's Guide to the Galaxy" and the zany adventures of "SpongeBob SquarePants," our study serves as a reminder that statistical inquiry can be both insightful and entertaining.

The correlation we have brought to light between toilet paper searches and the performance of the Milwaukee Brewers not only challenges conventional statistical wisdom but also underscores the value of embracing unconventional hypotheses in empirical inquiry. It seems that in the world of statistics, even the most unassuming variables – in this case, the urgent quest for toilet paper – can step up to the plate and deliver a statistical curveball of unexpected insight.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Google searches for 'where to buy toilet paper' and Runs scored by the Milwaukee Brewers. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers

[[ABSTRACT]]
In this paper, we delve into the curious connection between the urgency to acquire toilet paper and the performance of the Milwaukee Brewers on the baseball field. By leveraging data from Google Trends and Baseball-Reference.com, we rigorously address this toilet paper turmoil. Our findings reveal a remarkably robust negative correlation with a correlation coefficient of -0.9152772 and p < 0.01 for the years 2004 to 2023. This sheds new light on the idea that when individuals are preoccupied with stocking up on bathroom essentials, the Brewers seem to score fewer runs. We discuss the implications of this unexpected relationship and propose future research directions, like exploring the influence of other household goods on sports performance. Overall, this study unveils an intriguing link between consumer behavior and athletic feats, showing the importance of taking a swing at unconventional connections in our statistical playbook.

[[INTRDUCTION]]
The world of statistical research is no stranger to uncovering unexpected relationships and peculiar correlations. From the influence of moon phases on human behavior to the connection between the consumption of cheese and the likelihood of death by becoming tangled in bedsheets, researchers have delved into a myriad of offbeat topics with the hope of unearthing meaningful insights. In this vein, we embark on a quest to explore the perplexing bond between the frenzy of Google searches for 'where to buy toilet paper' and the performance of the Milwaukee Brewers on the baseball diamond.
While it may seem like an odd couple, the allure of oddities is not lost on the scientific community. Moreover, as researchers, it is our duty to rigorously investigate and analyze even the most unexpected correlations. In this quest, we aim to employ the tools of statistics, data analysis, and puns (yes, puns) to shine a light on the curious relationship between toilet paper turmoil and runs scored by the Milwaukee Brewers. After all, in the realm of statistical research, we must always be prepared to expect the unexpected and tackle the most bizarre of hypotheses with unwavering scientific curiosity.
Cracking open the metaphorical data vault, we turn to the wealth of information provided by Google Trends and the treasure trove of baseball statistics at Baseball-Reference.com to unravel this enigma. By examining the patterns and trends in these data sources, we strive to lend empirical support to what may initially appear as no more than a whimsical theory.
The amusing image of baseball fans fervently searching for rolls of soft, pillowy toilet paper while simultaneously rooting for their team at the ballpark may elicit a chuckle, yet as researchers, we do not shy away from embracing the unexpected. As we embark on this statistical journey, we invite readers to join us in uncovering the hidden connections within this peculiar pairing of variables. After all, in the game of statistics, there's no such thing as a foul ball when it comes to exploring the unpredictable links that emerge amidst the data. So, without further ado, let's step up to the plate and take a swing at unraveling this captivating conundrum.

[[RESULTS]]
The connection between Google searches for 'where to buy toilet paper' and the performance of the Milwaukee Brewers on the baseball field has yielded some ground-shaking results. Through our quantitative analysis, we found a strikingly robust negative correlation between the two variables. The correlation coefficient was calculated to be -0.9152772, indicating a very strong inverse relationship between the urgency to procure toilet paper and the number of runs scored by the Brewers.
The coefficient of determination (r-squared) further emphasizes the substantial connection we uncovered, amounting to an impressive 83.77%. This suggests that a staggering 83.77% of the variability in runs scored by the Brewers can be explained by the corresponding fluctuations in Google searches for 'where to buy toilet paper.' It's as if the two variables are performing a perfectly choreographed statistical tango, albeit with a touch of bathroom humor.
Moreover, the p-value of less than 0.01 lends unequivocal support to the significance of this correlation. The likelihood of such a strong relationship occurring purely by chance is exceedingly remote, reinforcing the validity of our findings. It seems that the statistical stars have aligned to shine a light on this unusual association, and it's not just a statistical blip on the radar.
Additionally, in Figure 1, we present a scatterplot that vividly illustrates the tight negative relationship between the searches for toilet paper and runs scored by the Milwaukee Brewers. This graph not only confirms the strength of the correlation but also serves as a visual testament to the unexpected nature of our findings. It's not every day that one gets to witness a scatterplot that marries bathroom essentials and ballpark heroics so convincingly.
In conclusion, our research has uncovered a statistically sound, albeit slightly comical, link between the urgency to stock up on toilet paper and the scoring prowess of the Brewers. This peculiar association challenges conventional wisdom and underscores the need for a broad-minded statistical approach in unraveling unexpected connections. As we reflect on these results, we are reminded that in the realm of statistics, even the most unlikely variables can step up to the plate and deliver a grand slam of empirical insight.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has certainly provided a good measure of statistical humor, along with valuable insights into the curious connection between toilet paper searches and the Brewers' run-scoring antics. Who would have thought that the ebb and flow of bathroom essential quests could have such a significant impact on the baseball field? This offbeat correlation really hits it out of the park when it comes to unexpected statistical relationships.

As we wrap up this toilet-themed statistical journey, it's clear that our findings could wipe away any doubts about the substantial link between consumer preoccupations and athletic performance. It's not just a statistical coincidence – there's real substance to this quirky association.

With a correlation coefficient of -0.9152772, it's safe to say that this odd coupling is an absolute statistical home run. And let's not forget the substantial r-squared value of 83.77% – that's a high performer by any statistical standards! Our results lend empirical support to the notion that when it comes to the Brewers' performance, the call of nature for toilet paper seems to deflate their run-scoring prowess.

Our research has shown that even amidst the most unexpected pairings of variables, statistical insights await. From toilet paper turmoil to the box scores at the ballpark, the statistical landscape is full of delightful surprises.

In the wise words of Yogi Berra, "You can observe a lot by just watching," and indeed, our study shows that keen observation of seemingly unrelated variables can yield unexpected outcomes. We've certainly flushed out some intriguing statistical revelations in this study.

Therefore, we assert with confidence that, in the realm of statistical research, no further investigation into the connection between toilet paper searches and Milwaukee Brewers' runs is needed. This peculiar correlation has been thoroughly explored and illuminated, leaving us with a remarkable tale of statistical oddities and, dare we say, a touch of bathroom humor.


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 Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Quantitative Research


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers. Respond only with the name of a fictional organization.

ChatGPT:

Society for Quirky Data Analysis and Research (SQDAR)


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 Swing and S(ear)ch: Exploring the Relationship Between Google Searches for 'Where to Buy Toilet Paper' and Runs Scored by the Milwaukee Brewers with an abstract of In this paper, we delve into the curious connection between the urgency to acquire toilet paper and the performance of the Milwaukee Brewers on the baseball field. By leveraging data from Google Trends and Baseball-Reference.com, we rigorously address this toilet paper turmoil. Our findings reveal a remarkably robust negative correlation with a correlation coefficient of -0.9152772 and p < 0.01 for the years 2004 to 2023. This sheds new light on the idea that when individuals are preoccupied with stocking up on bathroom essentials, the Brewers seem to score fewer runs. We discuss the implications of this unexpected relationship and propose future research directions, like exploring the influence of other household goods on sports performance. Overall, this study unveils an intriguing link between consumer behavior and athletic feats, showing the importance of taking a swing at unconventional connections in our statistical playbook.

ChatGPT:

"Google Trends, toilet paper searches, Milwaukee Brewers, runs scored, correlation analysis, consumer behavior, athletic performance, baseball statistics, Google search data, household goods, statistical analysis, baseball team performance"

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

Google searches for 'where to buy toilet paper'
Detailed data title: Relative volume of Google searches for 'where to buy toilet paper' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'where to buy toilet paper'

Runs scored by the Milwaukee Brewers
Detailed data title: The total number of runs scored during the year by the Milwaukee Brewers
Source: Baseball-Reference.com
See what else correlates with Runs scored by the Milwaukee Brewers

Correlation r = -0.9152772 (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 = 0.8377324 (Coefficient of determination)
This means 83.8% of the change in the one variable (i.e., Runs scored by the Milwaukee Brewers) is predictable based on the change in the other (i.e., Google searches for 'where to buy toilet paper') over the 20 years from 2004 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.6E-8. 0.0000000156563326163425060000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as -0.92 in 1.6E-6% of random cases. Said differently, if you correlated 63,871,918 random variables You don't actually need 63 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 19 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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.

[ -0.97, -0.79 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
20042005200620072008200920102011201220132014201520162017201820192020202120222023
Google searches for 'where to buy toilet paper' (Rel. search volume)0.3333330.5833330.3333330.083333300.3333330.50.2510.83333311111112.5833111
Runs scored by the Milwaukee Brewers (Runs scored)634726730801750785750721776640650655671732754769247738725728




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.333333,0.583333,0.333333,0.0833333,0,0.333333,0.5,0.25,1,0.833333,1,1,1,1,1,1,12.5833,1,1,1,])
array_2 = np.array([634,726,730,801,750,785,750,721,776,640,650,655,671,732,754,769,247,738,725,728,])
array_1_name = "Google searches for 'where to buy toilet paper'"
array_2_name = "Runs scored by the Milwaukee Brewers"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!


Correlation ID: 3114 · Black Variable ID: 1385 · Red Variable ID: 4363
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0