about · email me · subscribe
Spurious correlation #2,944 · 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 'google' and the second variable is Warner Bros. Discovery's stock price (WBD).  The chart goes from 2006 to 2023, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

People were searching for the latest tech trends and stumbled upon the news about the merger, leading to a surge in interest and investment. It seems like the search for success was indeed 'Googling' well for Warner Bros. Discovery!

Model: dalle-3
Prompt: Generate an image of an office space filled with vibrant colors, where a group of people are gathered around a table, each typing "google" into their laptops. As the iconic Google search bar fills the screen, one person accidentally mistypes and searches for "googl." Suddenly, the screen displays the Warner Bros. Discovery stock price (WBD) chart, causing their eyes to widen in surprise. Meanwhile, in another part of the scene, the stock price chart for Warner Bros. Discovery (WBD) is displayed, with the line graph showing a noticeable upward trend, indicating a surge in interest and price due to the unintentional attention from the mistyped google searches. Capture the moment of shock and surprise on the person's face as they realize the impact of their mistyped search. The vibrant office setting and the contrasting reactions of the individuals will add an interesting dynamic to this humorous visual. 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 'google' and Warner Bros. Discovery's stock price (WBD). 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: Hyper-realistic Charcoal inspired by bauhaus a funny image you would see on reddit Brutalism
ChatGPT: a funny image you would see on reddit

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 'google' and Warner Bros. Discovery's stock price (WBD), in the following situation: Because as people searched for "Google" on Google, they accidentally discovered the "Warner Bros. Discovery" stock price by mistyping. This led to a surge in interest in WBD as investors googled the latest news, causing the stock price to rise due to the unintentional attention.. Keep the description simple.
ChatGPT: In a vibrant office setting, we see a group of people typing "google" into their laptops, as the iconic Google search bar fills the screen. Suddenly, one person accidentally mistypes and searches for "googl" and stumbles upon the Warner Bros. Discovery stock price (WBD) chart, which pops up on their screen, causing their eyes to widen in surprise. Meanwhile, in another part of the scene, the stock price chart for Warner Bros. Discovery (WBD) is displayed, with the line graph showing a noticeable upward trend, indicating a surge in interest and price due to the unintentional attention from the mistyped google searches.

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 funny image you would see on reddit ] and depicting this scene: In a vibrant office setting, we see a group of people typing "google" into their laptops, as the iconic Google search bar fills the screen. Suddenly, one person accidentally mistypes and searches for "googl" and stumbles upon the Warner Bros. Discovery stock price (WBD) chart, which pops up on their screen, causing their eyes to widen in surprise. Meanwhile, in another part of the scene, the stock price chart for Warner Bros. Discovery (WBD) is displayed, with the line graph showing a noticeable upward trend, indicating a surge in interest and price due to the unintentional attention from the mistyped google searches. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of an office space filled with vibrant colors, where a group of people are gathered around a table, each typing "google" into their laptops. As the iconic Google search bar fills the screen, one person accidentally mistypes and searches for "googl." Suddenly, the screen displays the Warner Bros. Discovery stock price (WBD) chart, causing their eyes to widen in surprise. Meanwhile, in another part of the scene, the stock price chart for Warner Bros. Discovery (WBD) is displayed, with the line graph showing a noticeable upward trend, indicating a surge in interest and price due to the unintentional attention from the mistyped google searches. Capture the moment of shock and surprise on the person's face as they realize the impact of their mistyped search. The vibrant office setting and the contrasting reactions of the individuals will add an interesting dynamic to this humorous visual.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in google (Google searches for 'google') caused Warner Bros. Discovery's stock price (WBD) to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
Googling Warner Bros. Discovery: A Search for Stock Market Connections

Journal of Quirky Financial 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 researcher writing an academic paper.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 'google' and Warner Bros. Discovery's stock price (WBD). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from Google Trends and LSEG Analytics (Refinitiv) to assess this nagging question. You found a correlation coefficient of 0.8695553 and p < 0.01 for 2006 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]]
Googling Warner Bros. Discovery: A Search for Stock Market Connections

[[ABSTRACT]]
In this study, we investigate the curious relationship between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) to uncover any potential correlations. Our research team employed data from Google Trends and LSEG Analytics (Refinitiv) to rigorously analyze this seemingly improbable association. Surprisingly, our findings reveal a remarkably high correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 during the period from 2006 to 2023, suggesting an intriguing bond between online search behavior and stock market performance. This unexpected linkage between "googling" and Warner Bros. Discovery's stock price prompts us to consider the impact of digital curiosity on financial markets, unveiling the unexplored territory between internet search trends and investment dynamics. Our results shed light on a peculiar correlation that defies conventional financial wisdom and beckons us to reassess the role of online search activities in shaping stock market behaviors.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 'google' and Warner Bros. Discovery's stock price (WBD). 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.

Here is the title and abstract of the paper:
[[TITLE]]
Googling Warner Bros. Discovery: A Search for Stock Market Connections

[[ABSTRACT]]
In this study, we investigate the curious relationship between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) to uncover any potential correlations. Our research team employed data from Google Trends and LSEG Analytics (Refinitiv) to rigorously analyze this seemingly improbable association. Surprisingly, our findings reveal a remarkably high correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 during the period from 2006 to 2023, suggesting an intriguing bond between online search behavior and stock market performance. This unexpected linkage between "googling" and Warner Bros. Discovery's stock price prompts us to consider the impact of digital curiosity on financial markets, unveiling the unexplored territory between internet search trends and investment dynamics. Our results shed light on a peculiar correlation that defies conventional financial wisdom and beckons us to reassess the role of online search activities in shaping stock market behaviors.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:

INTRODUCTION

The world of finance and investing is often portrayed as a realm of cold, hard numbers and rational decision-making. However, as with most things, reality is rarely that straightforward. In this study, we delve into the intriguing realm of internet search behavior and its potential impact on stock market dynamics. Specifically, we set our sights on the unlikely pairing of Google searches for the term 'google' and the stock price of Warner Bros. Discovery (WBD). The juxtaposition of an internet search giant and a media conglomerate offers an unexpected, almost whimsical connection that piques our scientific curiosity.

As researchers, we are used to analyzing trends, crunching numbers, and elucidating the true drivers of market movements. However, every now and then, an anomaly arises that challenges our preconceptions and unleashes our inner statisticians on a quest for understanding. The relationship between online search activity and stock prices is one such anomaly, leading us down a rabbit hole of data points and statistical models in a quest to unravel the enigma.

When we embarked on this research, we were met with skepticism and raised eyebrows. After all, how could the number of internet users typing the word 'google' into their search engines possibly bear significance to the fluctuations of a media company's stock price? Yet, as our analysis took shape, we found ourselves confronted with patterns that dared us to think outside the box and consider the possibility of a deeper, uncharted connection between the virtual and financial realms.

So, dear reader, join us as we navigate the intricacies of internet search trends and stock market performances. Prepare to set aside your assumptions and be captivated by the unexpected correlations that emerge from the depths of data analysis. After all, in the uncharted waters of academic research, sometimes the most astonishing discoveries are found in the most unlikely places.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 'google' and Warner Bros. Discovery's stock price (WBD). 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Googling Warner Bros. Discovery: A Search for Stock Market Connections

[[ABSTRACT]]
In this study, we investigate the curious relationship between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) to uncover any potential correlations. Our research team employed data from Google Trends and LSEG Analytics (Refinitiv) to rigorously analyze this seemingly improbable association. Surprisingly, our findings reveal a remarkably high correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 during the period from 2006 to 2023, suggesting an intriguing bond between online search behavior and stock market performance. This unexpected linkage between "googling" and Warner Bros. Discovery's stock price prompts us to consider the impact of digital curiosity on financial markets, unveiling the unexplored territory between internet search trends and investment dynamics. Our results shed light on a peculiar correlation that defies conventional financial wisdom and beckons us to reassess the role of online search activities in shaping stock market behaviors.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The world of finance and investing is often portrayed as a realm of cold, hard numbers and rational decision-making. However, as with most things, reality is rarely that straightforward. In this study, we delve into the intriguing realm of internet search behavior and its potential impact on stock market dynamics. Specifically, we set our sights on the unlikely pairing of Google searches for the term 'google' and the stock price of Warner Bros. Discovery (WBD). The juxtaposition of an internet search giant and a media conglomerate offers an unexpected, almost whimsical connection that piques our scientific curiosity.
As researchers, we are used to analyzing trends, crunching numbers, and elucidating the true drivers of market movements. However, every now and then, an anomaly arises that challenges our preconceptions and unleashes our inner statisticians on a quest for understanding. The relationship between online search activity and stock prices is one such anomaly, leading us down a rabbit hole of data points and statistical models in a quest to unravel the enigma.
When we embarked on this research, we were met with skepticism and raised eyebrows. After all, how could the number of internet users typing the word 'google' into their search engines possibly bear significance to the fluctuations of a media company's stock price? Yet, as our analysis took shape, we found ourselves confronted with patterns that dared us to think outside the box and consider the possibility of a deeper, uncharted connection between the virtual and financial realms.
So, dear reader, join us as we navigate the intricacies of internet search trends and stock market performances. Prepare to set aside your assumptions and be captivated by the unexpected correlations that emerge from the depths of data analysis. After all, in the uncharted waters of academic research, sometimes the most astonishing discoveries are found in the most unlikely places.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Our investigation into the perplexing correlation between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) calls upon a diverse array of scholarly works and unconventional sources to contextualize and comprehend this unlikely relationship. Firstly, Smith and Doe (2015) lay the foundation for our exploration by elucidating the impact of digital footprints on market dynamics, providing a framework for understanding the interplay between online activities and financial outcomes. Jones et al. (2018) further expound on the concept of non-traditional indicators in financial forecasting, offering insights into the unorthodox yet revealing nature of auxiliary data in market analysis.

Moving beyond the confines of traditional academic literature, our quest for understanding beckons us to explore the realms of non-fiction books that, while seemingly unrelated, may harbor hidden parallels to our inquiry. In "Thinking, Fast and Slow" by Daniel Kahneman, the authors touch upon the intricate workings of human cognition and decision-making, signaling the potential ramifications of online search behavior on investor sentiment and market movements. Similarly, "Freakonomics" by Steven D. Levitt and Stephen J. Dubner prompts us to question the conventional boundaries of economic analysis, urging us to consider the unforeseen relationships that underpin seemingly unrelated phenomena.

As our pursuit of knowledge ventures into more unconventional territories, we draw inspiration from fiction literature that offers an alternate lens through which to contemplate the enigmatic juxtaposition of 'googling' and stock market performance. In Mary Shelley's "Frankenstein," the narrative of a creation spiraling out of control serves as a metaphor for the unforeseen consequences that may arise from seemingly innocuous actions, inviting us to ponder the unintended outcomes of digital curiosity on market behavior. Additionally, the fantastical world of J.K. Rowling's "Harry Potter" series sparks our imagination as we reckon with the peculiar and unexpected alliances that permeate both the magical realm and the domain of financial analysis.

Furthermore, our scholarly journey takes an unconventional turn as we turn our attention to animated and children's television programs, seeking insight that transcends conventional academia. Through diligent observation of "Looney Tunes," we glean valuable lessons in the interplay of seemingly discordant elements, mirroring our endeavor to discern the underlying harmony within the seemingly disparate worlds of online search trends and stock prices. Similarly, the whimsical escapades in "SpongeBob SquarePants" offer a playful yet enlightening perspective on the unfathomable connections that may lie beneath the surface of seemingly nonsensical correlations.

In the spirited pursuit of knowledge, our examination transcends traditional barriers to uncover the unexpected and unravel the intertwining threads of internet search activity and market dynamics. Our diversely informed approach not only enriches our understanding but also infuses levity into the rigors of academic inquiry, reminding us that amidst the serious pursuit of knowledge, a touch of whimsy and unexpected discovery is never out of place.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 'google' and Warner Bros. Discovery's stock price (WBD). 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 Google Trends and LSEG Analytics (Refinitiv) . You used data from 2006 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]]
Googling Warner Bros. Discovery: A Search for Stock Market Connections

[[ABSTRACT]]
In this study, we investigate the curious relationship between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) to uncover any potential correlations. Our research team employed data from Google Trends and LSEG Analytics (Refinitiv) to rigorously analyze this seemingly improbable association. Surprisingly, our findings reveal a remarkably high correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 during the period from 2006 to 2023, suggesting an intriguing bond between online search behavior and stock market performance. This unexpected linkage between "googling" and Warner Bros. Discovery's stock price prompts us to consider the impact of digital curiosity on financial markets, unveiling the unexplored territory between internet search trends and investment dynamics. Our results shed light on a peculiar correlation that defies conventional financial wisdom and beckons us to reassess the role of online search activities in shaping stock market behaviors.

[[INTRODUCTION]]
INTRODUCTION
The world of finance and investing is often portrayed as a realm of cold, hard numbers and rational decision-making. However, as with most things, reality is rarely that straightforward. In this study, we delve into the intriguing realm of internet search behavior and its potential impact on stock market dynamics. Specifically, we set our sights on the unlikely pairing of Google searches for the term 'google' and the stock price of Warner Bros. Discovery (WBD). The juxtaposition of an internet search giant and a media conglomerate offers an unexpected, almost whimsical connection that piques our scientific curiosity.
As researchers, we are used to analyzing trends, crunching numbers, and elucidating the true drivers of market movements. However, every now and then, an anomaly arises that challenges our preconceptions and unleashes our inner statisticians on a quest for understanding. The relationship between online search activity and stock prices is one such anomaly, leading us down a rabbit hole of data points and statistical models in a quest to unravel the enigma.
When we embarked on this research, we were met with skepticism and raised eyebrows. After all, how could the number of internet users typing the word 'google' into their search engines possibly bear significance to the fluctuations of a media company's stock price? Yet, as our analysis took shape, we found ourselves confronted with patterns that dared us to think outside the box and consider the possibility of a deeper, uncharted connection between the virtual and financial realms.
So, dear reader, join us as we navigate the intricacies of internet search trends and stock market performances. Prepare to set aside your assumptions and be captivated by the unexpected correlations that emerge from the depths of data analysis. After all, in the uncharted waters of academic research, sometimes the most astonishing discoveries are found in the most unlikely places.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data for this study was harvested from the bountiful fields of the internet, where we embarked on a digital treasure hunt across online platforms, code repositories, and data archives. Our primary sources included Google Trends, the beacon of digital curiosity, and LSEG Analytics (Refinitiv), the venerable oracle of stock market data. We diligently scoured through years of information, from 2006 to 2023, to capture the ebb and flow of online searches for the term 'google' and the corresponding undulations of Warner Bros. Discovery's stock price (WBD).

Algorithmic Acrobatics:
To uncover the hidden dance between 'googling' and stock price movements, we employed complex mathematical machinations and statistical sorcery. Our team of data wizards invoked the incantations of time series analysis, rolling correlations, and data transformation spells to reveal the concealed patterns lurking within the labyrinth of our datasets. These mystical methods allowed us to discern the subtle choreography between internet queries and market valuations, transcending the mundane world of conventional financial analysis.

Normalization Necromancy:
In an attempt to harmonize disparate data streams and bring order to the chaos of online search trends and stock price fluctuations, we delved into the arcane art of data normalization. Just as alchemists sought to transmute base metals into gold, we endeavored to transmute raw data into standardized scales, ensuring a fair comparison of the diverse metrics at play. Through this act of statistical transfiguration, we sought to distill the essence of 'googling' behavior and WBD stock performance into a unified framework, allowing for meaningful comparisons and interpretations.

Cross-Validation Conjuring:
To fortify the robustness of our findings and guard against the whims of statistical outliers, we summoned the ritual of cross-validation, a sacred rite in the realm of predictive modeling. By partitioning our data into training and testing domains, we invoked the candid counsel of statistical deities to assess the generalizability of our observed correlations and fend off the lurking specters of overfitting and spurious associations. This ritualistic practice served as a crucial crucible to temper the strength of our results and fortify their resilience under the scrutiny of empirical scrutiny.

Quantitative Quest:
Eager to gauge the strength of the tenuous bond between 'googling' and stock price movements, we turned to the venerable instruments of quantitative analysis. Armed with regression models and correlation coefficients, we sought to quantify the degree of their cosmic alignment, shedding light on the gravitational forces that tether internet search trends to the financial cosmos. Through this numerical odyssey, we unearthed the numerical signatures of their celestial tango, unveiling the surprisingly robust correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 that defied the expectations of conventional wisdom.

In our quest for enlightenment, we ventured beyond the confinements of traditional statistical techniques, daring to pierce the veil between the digital and financial domains. The amalgamation of data-driven sorcery, esoteric normalization rituals, and the quantitative pursuit of hidden connections has brought us closer to unraveling the mysterious bond between 'googling' and Warner Bros. Discovery's stock price, challenging the boundaries of empirical inquiry and beckoning us into uncharted territories of research intrigue.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 'google' and Warner Bros. Discovery's stock price (WBD). 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 Google Trends and LSEG Analytics (Refinitiv) .

For the time period 2006 to 2023, you found a correlation 0.8695553, r-squared of 0.7561264, 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]]
Googling Warner Bros. Discovery: A Search for Stock Market Connections

[[ABSTRACT]]
In this study, we investigate the curious relationship between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) to uncover any potential correlations. Our research team employed data from Google Trends and LSEG Analytics (Refinitiv) to rigorously analyze this seemingly improbable association. Surprisingly, our findings reveal a remarkably high correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 during the period from 2006 to 2023, suggesting an intriguing bond between online search behavior and stock market performance. This unexpected linkage between "googling" and Warner Bros. Discovery's stock price prompts us to consider the impact of digital curiosity on financial markets, unveiling the unexplored territory between internet search trends and investment dynamics. Our results shed light on a peculiar correlation that defies conventional financial wisdom and beckons us to reassess the role of online search activities in shaping stock market behaviors.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The world of finance and investing is often portrayed as a realm of cold, hard numbers and rational decision-making. However, as with most things, reality is rarely that straightforward. In this study, we delve into the intriguing realm of internet search behavior and its potential impact on stock market dynamics. Specifically, we set our sights on the unlikely pairing of Google searches for the term 'google' and the stock price of Warner Bros. Discovery (WBD). The juxtaposition of an internet search giant and a media conglomerate offers an unexpected, almost whimsical connection that piques our scientific curiosity.
As researchers, we are used to analyzing trends, crunching numbers, and elucidating the true drivers of market movements. However, every now and then, an anomaly arises that challenges our preconceptions and unleashes our inner statisticians on a quest for understanding. The relationship between online search activity and stock prices is one such anomaly, leading us down a rabbit hole of data points and statistical models in a quest to unravel the enigma.
When we embarked on this research, we were met with skepticism and raised eyebrows. After all, how could the number of internet users typing the word 'google' into their search engines possibly bear significance to the fluctuations of a media company's stock price? Yet, as our analysis took shape, we found ourselves confronted with patterns that dared us to think outside the box and consider the possibility of a deeper, uncharted connection between the virtual and financial realms.
So, dear reader, join us as we navigate the intricacies of internet search trends and stock market performances. Prepare to set aside your assumptions and be captivated by the unexpected correlations that emerge from the depths of data analysis. After all, in the uncharted waters of academic research, sometimes the most astonishing discoveries are found in the most unlikely places.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis revealed a striking correlation between Google searches for the term 'google' and Warner Bros. Discovery's stock price, with a correlation coefficient of 0.8695553, indicating a strong positive relationship between the two variables. The coefficient of determination (r-squared) of 0.7561264 further emphasizes the substantial proportion of variance in Warner Bros. Discovery's stock price that can be explained by the fluctuations in 'google' searches. Additionally, the statistically significant result with p < 0.01 underscores the robustness of the observed association, confirming that the correlation is unlikely to have occurred by chance.

When we plotted the data points on a scatterplot (Fig. 1), the connection between 'google' searches and Warner Bros. Discovery's stock price became visually apparent. The points demonstrated a clear pattern, with an upward trend that illustrated the positive correlation between the two variables. As advocates of evidence-based research, we must acknowledge that the figures don't lie - or in this case, the scatterplot doesn't fib - and they unequivocally assert the presence of a noteworthy relationship.

Considering the conventional wisdom that stock market movements are predominantly influenced by economic indicators, industry news, and corporate performance, the unearthing of such a compelling link with internet search activity certainly raises eyebrows. It may appear as though we've stumbled into a parallel universe where the digital footprints of internet users are leaving a tangible mark on the financial landscape.

Our results prompt us to ponder the possible mechanisms underlying this unexpected correlation. Could the frequency of 'google' searches serve as a barometer for public interest in online content, potentially reflecting the popularity of Warner Bros. Discovery's media offerings and driving investor sentiment? Despite the oblique nature of this association, our statistical findings compel us to recognize the relevance of online search behavior in the context of stock market dynamics.

In light of these revelations, we urge fellow researchers and practitioners to embrace a broader perspective that encompasses the interplay between virtual engagement and financial markets. The quirks and eccentricities of our data remind us of the unforeseen revelations that can emerge from interrogating seemingly unrelated variables, underscoring the delightful unpredictability of scientific inquiry.

As we conclude this phase of investigation, we find ourselves reminiscing on the words of the great physicist, Niels Bohr, who once proclaimed, "Prediction is very difficult, especially if it's about the future." While our research may not have predicted the precise trajectory of 'google' searches or Warner Bros. Discovery's stock price, it has illuminated an unanticipated connection that inspires further exploration into the uncharted territories of internet-driven financial influences.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 'google' and Warner Bros. Discovery's stock price (WBD). 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]]
Googling Warner Bros. Discovery: A Search for Stock Market Connections

[[ABSTRACT]]
In this study, we investigate the curious relationship between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) to uncover any potential correlations. Our research team employed data from Google Trends and LSEG Analytics (Refinitiv) to rigorously analyze this seemingly improbable association. Surprisingly, our findings reveal a remarkably high correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 during the period from 2006 to 2023, suggesting an intriguing bond between online search behavior and stock market performance. This unexpected linkage between "googling" and Warner Bros. Discovery's stock price prompts us to consider the impact of digital curiosity on financial markets, unveiling the unexplored territory between internet search trends and investment dynamics. Our results shed light on a peculiar correlation that defies conventional financial wisdom and beckons us to reassess the role of online search activities in shaping stock market behaviors.

[[LITERATURE REVIEW]]
Our investigation into the perplexing correlation between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) calls upon a diverse array of scholarly works and unconventional sources to contextualize and comprehend this unlikely relationship. Firstly, Smith and Doe (2015) lay the foundation for our exploration by elucidating the impact of digital footprints on market dynamics, providing a framework for understanding the interplay between online activities and financial outcomes. Jones et al. (2018) further expound on the concept of non-traditional indicators in financial forecasting, offering insights into the unorthodox yet revealing nature of auxiliary data in market analysis.
Moving beyond the confines of traditional academic literature, our quest for understanding beckons us to explore the realms of non-fiction books that, while seemingly unrelated, may harbor hidden parallels to our inquiry. In "Thinking, Fast and Slow" by Daniel Kahneman, the authors touch upon the intricate workings of human cognition and decision-making, signaling the potential ramifications of online search behavior on investor sentiment and market movements. Similarly, "Freakonomics" by Steven D. Levitt and Stephen J. Dubner prompts us to question the conventional boundaries of economic analysis, urging us to consider the unforeseen relationships that underpin seemingly unrelated phenomena.
As our pursuit of knowledge ventures into more unconventional territories, we draw inspiration from fiction literature that offers an alternate lens through which to contemplate the enigmatic juxtaposition of 'googling' and stock market performance. In Mary Shelley's "Frankenstein," the narrative of a creation spiraling out of control serves as a metaphor for the unforeseen consequences that may arise from seemingly innocuous actions, inviting us to ponder the unintended outcomes of digital curiosity on market behavior. Additionally, the fantastical world of J.K. Rowling's "Harry Potter" series sparks our imagination as we reckon with the peculiar and unexpected alliances that permeate both the magical realm and the domain of financial analysis.
Furthermore, our scholarly journey takes an unconventional turn as we turn our attention to animated and children's television programs, seeking insight that transcends conventional academia. Through diligent observation of "Looney Tunes," we glean valuable lessons in the interplay of seemingly discordant elements, mirroring our endeavor to discern the underlying harmony within the seemingly disparate worlds of online search trends and stock prices. Similarly, the whimsical escapades in "SpongeBob SquarePants" offer a playful yet enlightening perspective on the unfathomable connections that may lie beneath the surface of seemingly nonsensical correlations.
In the spirited pursuit of knowledge, our examination transcends traditional barriers to uncover the unexpected and unravel the intertwining threads of internet search activity and market dynamics. Our diversely informed approach not only enriches our understanding but also infuses levity into the rigors of academic inquiry, reminding us that amidst the serious pursuit of knowledge, a touch of whimsy and unexpected discovery is never out of place.

[[RESULTS]]
Our analysis revealed a striking correlation between Google searches for the term 'google' and Warner Bros. Discovery's stock price, with a correlation coefficient of 0.8695553, indicating a strong positive relationship between the two variables. The coefficient of determination (r-squared) of 0.7561264 further emphasizes the substantial proportion of variance in Warner Bros. Discovery's stock price that can be explained by the fluctuations in 'google' searches. Additionally, the statistically significant result with p < 0.01 underscores the robustness of the observed association, confirming that the correlation is unlikely to have occurred by chance.
When we plotted the data points on a scatterplot (Fig. 1), the connection between 'google' searches and Warner Bros. Discovery's stock price became visually apparent. The points demonstrated a clear pattern, with an upward trend that illustrated the positive correlation between the two variables. As advocates of evidence-based research, we must acknowledge that the figures don't lie - or in this case, the scatterplot doesn't fib - and they unequivocally assert the presence of a noteworthy relationship.
Considering the conventional wisdom that stock market movements are predominantly influenced by economic indicators, industry news, and corporate performance, the unearthing of such a compelling link with internet search activity certainly raises eyebrows. It may appear as though we've stumbled into a parallel universe where the digital footprints of internet users are leaving a tangible mark on the financial landscape.
Our results prompt us to ponder the possible mechanisms underlying this unexpected correlation. Could the frequency of 'google' searches serve as a barometer for public interest in online content, potentially reflecting the popularity of Warner Bros. Discovery's media offerings and driving investor sentiment? Despite the oblique nature of this association, our statistical findings compel us to recognize the relevance of online search behavior in the context of stock market dynamics.
In light of these revelations, we urge fellow researchers and practitioners to embrace a broader perspective that encompasses the interplay between virtual engagement and financial markets. The quirks and eccentricities of our data remind us of the unforeseen revelations that can emerge from interrogating seemingly unrelated variables, underscoring the delightful unpredictability of scientific inquiry.
As we conclude this phase of investigation, we find ourselves reminiscing on the words of the great physicist, Niels Bohr, who once proclaimed, "Prediction is very difficult, especially if it's about the future." While our research may not have predicted the precise trajectory of 'google' searches or Warner Bros. Discovery's stock price, it has illuminated an unanticipated connection that inspires further exploration into the uncharted territories of internet-driven financial influences.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings offer a whimsical twist on conventional market analysis, unveiling a correlation that seems right out of a "Looney Tunes" episode - unexpected, yet undeniably present. The relationship between Google searches for 'google' and Warner Bros. Discovery's stock price (WBD) surpasses the bounds of traditional economic indicators, ushering in an era where online search behavior dances hand in hand with stock market gyrations. In a world where hard numbers often reign supreme, the lighthearted romp with 'google' searches and stock prices infuses an unexpected dash of playfulness and curiosity into the serious business of financial analysis.

Returning to our scholarly escapades in the literature review, we pause to ponder the enchanting parallels with "Harry Potter" and its unexpected alliances. Similarly, our own findings reveal a magical intertwining of unrelated realms – the enchanting realm of 'googling' and the financial sorcery of Warner Bros. Discovery's stock price. This revelation serves as a testament to the unforeseen connections that underpin the tapestry of market movements, echoing J.K. Rowling's insightful musings on the unfathomable alliances that permeate both magical and monetary domains.

Furthermore, our results provide a playful nod to the lessons gleaned from "SpongeBob SquarePants," illustrating the comical yet enlightening perspective on the unfathomable connections that may lie beneath the surface of seemingly nonsensical correlations. The unorthodox relationship between 'google' searches and Warner Bros. Discovery's stock price embodies the whimsical escapades of Bikini Bottom – a delightful quirk that encourages us to embrace the unexpected and appreciate the unanticipated revelations that emerge from our statistical inquiries.

Our findings not only solemnly affirm the scholarly works on the impact of digital footprints on market dynamics, but they also contribute a roguish flair to the stately corridors of financial research. The robust correlation coefficient and statistically significant results underscore the formidable presence of this unexpected alliance, inviting scholars and practitioners alike to indulge in a discerning chuckle at the delightful caprices of economic inquiry. As we delight in the unforeseen revelations that emerge from interrogating seemingly unrelated variables, we invite our esteemed colleagues to revel in the quirkiness of our findings and to recognize the delightful unpredictability that infuses the scientific pursuit.



Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 'google' and Warner Bros. Discovery's stock price (WBD). 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]]
Googling Warner Bros. Discovery: A Search for Stock Market Connections

[[ABSTRACT]]
In this study, we investigate the curious relationship between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) to uncover any potential correlations. Our research team employed data from Google Trends and LSEG Analytics (Refinitiv) to rigorously analyze this seemingly improbable association. Surprisingly, our findings reveal a remarkably high correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 during the period from 2006 to 2023, suggesting an intriguing bond between online search behavior and stock market performance. This unexpected linkage between "googling" and Warner Bros. Discovery's stock price prompts us to consider the impact of digital curiosity on financial markets, unveiling the unexplored territory between internet search trends and investment dynamics. Our results shed light on a peculiar correlation that defies conventional financial wisdom and beckons us to reassess the role of online search activities in shaping stock market behaviors.

[[INTRDUCTION]]
INTRODUCTION
The world of finance and investing is often portrayed as a realm of cold, hard numbers and rational decision-making. However, as with most things, reality is rarely that straightforward. In this study, we delve into the intriguing realm of internet search behavior and its potential impact on stock market dynamics. Specifically, we set our sights on the unlikely pairing of Google searches for the term 'google' and the stock price of Warner Bros. Discovery (WBD). The juxtaposition of an internet search giant and a media conglomerate offers an unexpected, almost whimsical connection that piques our scientific curiosity.
As researchers, we are used to analyzing trends, crunching numbers, and elucidating the true drivers of market movements. However, every now and then, an anomaly arises that challenges our preconceptions and unleashes our inner statisticians on a quest for understanding. The relationship between online search activity and stock prices is one such anomaly, leading us down a rabbit hole of data points and statistical models in a quest to unravel the enigma.
When we embarked on this research, we were met with skepticism and raised eyebrows. After all, how could the number of internet users typing the word 'google' into their search engines possibly bear significance to the fluctuations of a media company's stock price? Yet, as our analysis took shape, we found ourselves confronted with patterns that dared us to think outside the box and consider the possibility of a deeper, uncharted connection between the virtual and financial realms.
So, dear reader, join us as we navigate the intricacies of internet search trends and stock market performances. Prepare to set aside your assumptions and be captivated by the unexpected correlations that emerge from the depths of data analysis. After all, in the uncharted waters of academic research, sometimes the most astonishing discoveries are found in the most unlikely places.

[[RESULTS]]
Our analysis revealed a striking correlation between Google searches for the term 'google' and Warner Bros. Discovery's stock price, with a correlation coefficient of 0.8695553, indicating a strong positive relationship between the two variables. The coefficient of determination (r-squared) of 0.7561264 further emphasizes the substantial proportion of variance in Warner Bros. Discovery's stock price that can be explained by the fluctuations in 'google' searches. Additionally, the statistically significant result with p < 0.01 underscores the robustness of the observed association, confirming that the correlation is unlikely to have occurred by chance.
When we plotted the data points on a scatterplot (Fig. 1), the connection between 'google' searches and Warner Bros. Discovery's stock price became visually apparent. The points demonstrated a clear pattern, with an upward trend that illustrated the positive correlation between the two variables. As advocates of evidence-based research, we must acknowledge that the figures don't lie - or in this case, the scatterplot doesn't fib - and they unequivocally assert the presence of a noteworthy relationship.
Considering the conventional wisdom that stock market movements are predominantly influenced by economic indicators, industry news, and corporate performance, the unearthing of such a compelling link with internet search activity certainly raises eyebrows. It may appear as though we've stumbled into a parallel universe where the digital footprints of internet users are leaving a tangible mark on the financial landscape.
Our results prompt us to ponder the possible mechanisms underlying this unexpected correlation. Could the frequency of 'google' searches serve as a barometer for public interest in online content, potentially reflecting the popularity of Warner Bros. Discovery's media offerings and driving investor sentiment? Despite the oblique nature of this association, our statistical findings compel us to recognize the relevance of online search behavior in the context of stock market dynamics.
In light of these revelations, we urge fellow researchers and practitioners to embrace a broader perspective that encompasses the interplay between virtual engagement and financial markets. The quirks and eccentricities of our data remind us of the unforeseen revelations that can emerge from interrogating seemingly unrelated variables, underscoring the delightful unpredictability of scientific inquiry.
As we conclude this phase of investigation, we find ourselves reminiscing on the words of the great physicist, Niels Bohr, who once proclaimed, "Prediction is very difficult, especially if it's about the future." While our research may not have predicted the precise trajectory of 'google' searches or Warner Bros. Discovery's stock price, it has illuminated an unanticipated connection that inspires further exploration into the uncharted territories of internet-driven financial influences.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research elucidates the seemingly improbable yet substantial association between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD). While this linkage may initially appear as incongruous as wearing a lab coat to a comedy club, our findings undeniably highlight a significant correlation, challenging the status quo of traditional financial analysis. The robust correlation coefficient and the statistically significant results boldly proclaim the existence of a connection that could rival even the most captivating of bumbling science experiments.

As we reflect on our unexpected foray into the interplay between online search behavior and stock market dynamics, we cannot help but marvel at the whimsical nature of statistical discoveries. Just as a double-blind study can reveal unanticipated side effects, our research has unveiled an unlikely relationship that tickles the fancy of both financial analysts and data enthusiasts alike.

Pardon the pun, but our results resoundingly demonstrate that the "Google" is indeed alive and kicking in the realm of stock market assessments. With an r-squared value that could make even the most effervescent physicist beam with excitement, our statistical findings leave little room for doubt regarding the influence of internet search trends on investment sentiments.

In the spirit of scientific inquiry, we assert that this study opens the door to a realm of research that not only defies convention but also invites scholars to traverse unchartered territories where the digital and financial realms converge. However, with the utmost conviction and a touch of whimsy, we declare that further research on this connection may yield diminishing returns akin to the plight of an overworked lab assistant. Hence, we entertain the notion that the curtain should fall on this particular avenue of investigation, leaving this peculiar alliance between Google searches for 'google' and Warner Bros. Discovery's stock price to linger in the annals of academic curiosities, much like the mystery of the missing sock in a pair.


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 Googling Warner Bros. Discovery: A Search for Stock Market Connections. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Financial 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 Googling Warner Bros. Discovery: A Search for Stock Market Connections. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Media Conglomerate Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Googling Warner Bros. Discovery: A Search for Stock Market Connections with an abstract of In this study, we investigate the curious relationship between Google searches for the term 'google' and Warner Bros. Discovery's stock price (WBD) to uncover any potential correlations. Our research team employed data from Google Trends and LSEG Analytics (Refinitiv) to rigorously analyze this seemingly improbable association. Surprisingly, our findings reveal a remarkably high correlation coefficient of 0.8695553 and statistically significant results with p < 0.01 during the period from 2006 to 2023, suggesting an intriguing bond between online search behavior and stock market performance. This unexpected linkage between "googling" and Warner Bros. Discovery's stock price prompts us to consider the impact of digital curiosity on financial markets, unveiling the unexplored territory between internet search trends and investment dynamics. Our results shed light on a peculiar correlation that defies conventional financial wisdom and beckons us to reassess the role of online search activities in shaping stock market behaviors.

ChatGPT:

Google search trends, Warner Bros. Discovery, stock price correlation, digital curiosity, financial markets, online search behavior, investment dynamics, Google Trends data, LSEG Analytics, Refinitiv, correlation coefficient, stock market performance, internet search trends

*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 'google'
Detailed data title: Relative volume of Google searches for 'google' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'google'

Warner Bros. Discovery's stock price (WBD)
Detailed data title: Opening price of Warner Bros. Discovery (WBD) on the first trading day of the year
Source: LSEG Analytics (Refinitiv)
Additional Info: Via Microsoft Excel Stockhistory function

See what else correlates with Warner Bros. Discovery's stock price (WBD)

Correlation r = 0.8695553 (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 = 0.7561264 (Coefficient of determination)
This means 75.6% of the change in the one variable (i.e., Warner Bros. Discovery's stock price (WBD)) is predictable based on the change in the other (i.e., Google searches for 'google') over the 18 years from 2006 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.8E-6. 0.0000027773153911351993000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.87 in 0.00028% of random cases. Said differently, if you correlated 360,060 random variables You don't actually need 360 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 17 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 17 because we have two variables measured over a period of 18 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.

[ 0.68, 0.95 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200620072008200920102011201220132014201520162017201820192020202120222023
Google searches for 'google' (Rel. search volume)2327.916730.666738.083344.333354.83336286.083391.583389.16677264.083357.7554.916757.083348.416751.666748.8889
Warner Bros. Discovery's stock price (WBD) (Stock price)7.017.4911.587.2215.6921.4621.4433.2346.0834.6326.1327.6622.9624.3732.8231.0723.99.65




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.




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([23,27.9167,30.6667,38.0833,44.3333,54.8333,62,86.0833,91.5833,89.1667,72,64.0833,57.75,54.9167,57.0833,48.4167,51.6667,48.8889,])
array_2 = np.array([7.01,7.49,11.58,7.22,15.69,21.46,21.44,33.23,46.08,34.63,26.13,27.66,22.96,24.37,32.82,31.07,23.9,9.65,])
array_1_name = "Google searches for 'google'"
array_2_name = "Warner Bros. Discovery's stock price (WBD)"

# 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?

Your rating is much appreciated!


Correlation ID: 2944 · Black Variable ID: 1479 · Red Variable ID: 1845
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0