Spurious correlation #2,280 · 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 'that is sus' and the second variable is Chipotle Mexican Grill's stock price (CMG). The chart goes from 2007 to 2023, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'that is sus' and the second variable is Chipotle Mexican Grill's stock price (CMG). The chart goes from 2007 to 2023, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the Google searches for 'that is sus' increased, so did people's suspicion of their usual lunch choices. This led to a sudden decrease in the consumption of burritos and bowls at Chipotle. To counter this, Chipotle unveiled a new menu item called the 'Sus-erito' which piqued the interest of consumers. The unexpected popularity of the 'Sus-erito' boosted Chipotle's sales and ultimately caused a surge in their stock price.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a bustling Chipotle restaurant filled with cute cartoon customers enjoying their burritos at tables. In the background, a stock ticker displays Chipotle Mexican Grill's stock price rising steadily, while the customers in the foreground are depicted using their phones to search "that is sus" on Google. 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 'that is sus' and Chipotle Mexican Grill's stock price. 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: An image that looks like it is a scene from A Disney Movie Cute cartoon Psychedelic Oragami Macabre
ChatGPT: Cute cartoon

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 'that is sus' and Chipotle Mexican Grill's stock price together. Keep the description simple.
ChatGPT: In a bustling Chipotle restaurant, customers sit at tables and enjoy their burritos while simultaneously typing "that is sus" into their phones to search on Google. Above them, a stock ticker shows Chipotle Mexican Grill's stock price rising steadily.

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: [ Cute cartoon ] and depicting this scene: In a bustling Chipotle restaurant, customers sit at tables and enjoy their burritos while simultaneously typing "that is sus" into their phones to search on Google. Above them, a stock ticker shows Chipotle Mexican Grill's stock price rising steadily. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a bustling Chipotle restaurant filled with cute cartoon customers enjoying their burritos at tables. In the background, a stock ticker displays Chipotle Mexican Grill's stock price rising steadily, while the customers in the foreground are depicted using their phones to search "that is sus" on Google.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in that is sus (Google searches for 'that is sus') caused Chipotle Mexican Grill's stock price (CMG) to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

Unmasking the Guac: A Suspicious Correlation Between Google Searches for That Is Sus and Chipotle Mexican Grill's Stock Price

The Journal of Irreverent Economics and Culinary Research

Jan 2024

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

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

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 'that is sus' and Chipotle Mexican Grill's stock price (CMG). 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
Unmasking the Guac: A Suspicious Correlation Between Google Searches for "That Is Sus" and Chipotle Mexican Grill's Stock Price

[[ABSTRACT]]
This paper investigates the curious association between Google searches for the phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. Utilizing data from Google Trends and LSEG Analytics (Refinitiv), we employed rigorous statistical analyses to unveil a correlation coefficient of 0.9490520 and a significance level of p < 0.01. The implications of these findings are not to be taken with a grain of salt, as they yield interesting insights into the interplay between online pop culture references and the financial performance of a prominent fast-casual dining establishment. Our study sheds new light on the "queso" of the matter and offers food for thought for future research in the field of unconventional stock market indicators.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The peculiarities of financial markets often defy conventional reasoning, prompting researchers to delve into uncharted territories in search of correlations and insights that may have eluded common scrutiny. In this study, we embark on a journey to unravel the cryptic connection between the colloquial phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG). While this inquiry may initially seem far-fetched, the world of finance has a knack for the unexpected, reminiscent of the surprising flavor combinations found in a well-made burrito. As we excavate this curious association, we must approach it with a blend of skepticism and curiosity, much like venturing into uncharted guacamole territory.
The phrase "that is sus" has permeated popular culture, particularly within online gaming communities, where individuals use it to denote suspicious or questionable behavior. Its proliferation in internet vernacular reflects the nuances of modern communication and zeitgeist, mirroring the rapid dissemination of memes and colloquial expressions that ebb and flow in the digital sphere. Meanwhile, Chipotle Mexican Grill has carved out a distinctive niche in the fast-casual dining landscape, cultivating a brand synonymous with fresh ingredients and customizable culinary experiences. The intersection of these seemingly incongruent entities presents an intellectual puzzle that piques our curiosity, much like the thought of a spicy salsa paired with a creamy guacamole.
Drawing inspiration from the realm of unconventional stock market indicators, we are compelled to explore the potential interplay between digital discourse and the financial performance of a prominent dining establishment. As we venture into this uncharted terrain, we must navigate with an analytical rigor reminiscent of a sous-chef meticulously crafting a delicate sauce – ensuring precision and accuracy in our methodologies. While the path ahead may be riddled with skepticism and raised eyebrows, our pursuit of knowledge in this unorthodox endeavor promises to yield appetizing insights, much like the tantalizing aroma of a fresh batch of sizzling fajitas.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith and Doe (2015) examined the impact of online pop culture references on consumer behavior and market trends. Their study, "The Digital Age of Influence," explored the intricate relationship between internet memes and their potential influence on consumer choices. While their focus was primarily on broader consumer markets, their findings shed light on the pervasive influence of digital discourse on individual decision-making processes. Similarly, Jones et al. (2018) investigated the interplay between viral phrases and their impact on brand perception. Their research, "Viral Linguistics: Uncovering the Anatomy of Memes," provided intriguing insights into the ways in which linguistic trends propagate through online communities and leave tangible imprints on consumer associations.

Turning our attention to the literary realm, "The Influencer's Dilemma" by Smith (2020) offered a comprehensive exploration of the power dynamics at play in digital communication. While not explicitly focused on financial markets, Smith's conceptual framework for understanding the dissemination of online phrases holds relevance for our investigation. Furthermore, Doe's "The Language of Stocks: A Linguistic Analysis of Market Behavior" delved into the nuanced ways in which language shapes perceptions and behaviors in the financial domain, albeit without venturing into the realm of colloquial online expressions.

In a more speculative vein, fictional works such as "The Suspicion Principle" by Jane Austen and "The Curious Case of Suspect Stocks" by Sir Arthur Conan Doyle have integrated elements of suspicion and intrigue into their narrative structures. While these works are undoubtedly far removed from the empirical rigor of academic research, their thematic resonance with our study's focus on suspicion warrants a mention in this literature review. In a similar light, social media musings such as "Just saw CMG stock plummet after that sus earnings report, yikes" and "Is it just me, or does Chipotle's guac taste sus today?" have surfaced intermittently, reflecting the informal chatter surrounding our investigative nexus between online vernacular and stock performance.

The aforementioned sources provide a contextual backdrop for our exploration of the enigmatic relationship between Google searches for "that is sus" and Chipotle Mexican Grill's stock price. While the interdisciplinary blend of literature may appear unconventional, it primes us for a comprehensive understanding of the multifaceted dynamics inherent in our research inquiry.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 'that is sus' and Chipotle Mexican Grill's stock price (CMG). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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 2007 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]]
Unmasking the Guac: A Suspicious Correlation Between Google Searches for "That Is Sus" and Chipotle Mexican Grill's Stock Price

[[ABSTRACT]]
This paper investigates the curious association between Google searches for the phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. Utilizing data from Google Trends and LSEG Analytics (Refinitiv), we employed rigorous statistical analyses to unveil a correlation coefficient of 0.9490520 and a significance level of p < 0.01. The implications of these findings are not to be taken with a grain of salt, as they yield interesting insights into the interplay between online pop culture references and the financial performance of a prominent fast-casual dining establishment. Our study sheds new light on the "queso" of the matter and offers food for thought for future research in the field of unconventional stock market indicators.

[[INTRODUCTION]]
The peculiarities of financial markets often defy conventional reasoning, prompting researchers to delve into uncharted territories in search of correlations and insights that may have eluded common scrutiny. In this study, we embark on a journey to unravel the cryptic connection between the colloquial phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG). While this inquiry may initially seem far-fetched, the world of finance has a knack for the unexpected, reminiscent of the surprising flavor combinations found in a well-made burrito. As we excavate this curious association, we must approach it with a blend of skepticism and curiosity, much like venturing into uncharted guacamole territory.
The phrase "that is sus" has permeated popular culture, particularly within online gaming communities, where individuals use it to denote suspicious or questionable behavior. Its proliferation in internet vernacular reflects the nuances of modern communication and zeitgeist, mirroring the rapid dissemination of memes and colloquial expressions that ebb and flow in the digital sphere. Meanwhile, Chipotle Mexican Grill has carved out a distinctive niche in the fast-casual dining landscape, cultivating a brand synonymous with fresh ingredients and customizable culinary experiences. The intersection of these seemingly incongruent entities presents an intellectual puzzle that piques our curiosity, much like the thought of a spicy salsa paired with a creamy guacamole.
Drawing inspiration from the realm of unconventional stock market indicators, we are compelled to explore the potential interplay between digital discourse and the financial performance of a prominent dining establishment. As we venture into this uncharted terrain, we must navigate with an analytical rigor reminiscent of a sous-chef meticulously crafting a delicate sauce – ensuring precision and accuracy in our methodologies. While the path ahead may be riddled with skepticism and raised eyebrows, our pursuit of knowledge in this unorthodox endeavor promises to yield appetizing insights, much like the tantalizing aroma of a fresh batch of sizzling fajitas.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology employed in this investigation involved a fusion of quantitative analysis and algorithmic sleuthing to untangle the enigmatic relationship between Google searches for "that is sus" and Chipotle Mexican Grill's stock price (CMG). The data collection process harnessed the omnipresence of the internet, as information was gathered from a variety of sources, with an emphasis on Google Trends and LSEG Analytics (Refinitiv).

The first step entailed harnessing the search power of Google Trends, which provided insights into the frequency and geographic distribution of searches for the phrase "that is sus." These data were then juxtaposed with the stock price movements of Chipotle Mexican Grill, scrutinizing the ebbs and flows of investor sentiment in response to the ebb and flow of online suspiciousness. The temporality of the data spanned from 2007 to 2023, encapsulating a period that witnessed the emergence and proliferation of the "that is sus" meme, akin to the growth of a sprightly jalapeño plant in the highly volatile ecosystem of digital culture.

Subsequently, LSEG Analytics (Refinitiv) furnished a plethora of financial data pertaining to Chipotle Mexican Grill's stock price, allowing for a meticulous scrutiny of the stock's performance. This windfall of financial data was akin to stumbling upon a treasure trove of rare and exotic spices, just waiting to be blended together to unlock the secret recipe behind the market dynamics.

Following this, a potent cocktail of statistical methods was employed to distill the essence of the relationship between these seemingly incongruent variables. A correlation analysis was conducted to measure the strength and direction of the association between "that is sus" searches and Chipotle's stock price movements, using a time series regression model to disentangle the multi-layered flavors of the data.

In addition, a significance test was performed to discern the validity of the observed correlation. The significance level was set at p < 0.01, akin to a quality assurance check on the authenticity of a batch of freshly made salsa – ensuring that the observed relationship was not merely a fluke of statistical chance.

Furthermore, various sub-analyses were conducted to explore potential confounding variables and alternative explanations for the observed correlation, akin to a discerning connoisseur sampling an array of salsas to pinpoint the subtle nuances in taste and texture.

Throughout this methodological odyssey, the aim was to maintain a balance between meticulousness and open-mindedness, adopting an investigatory approach akin to unraveling the layers of a perfectly rolled burrito – with precision and an appetite for unexpected discoveries.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 'that is sus' and Chipotle Mexican Grill's stock price (CMG). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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 2007 to 2023, you found a correlation 0.9490520, r-squared of 0.9006998, 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]]
Unmasking the Guac: A Suspicious Correlation Between Google Searches for "That Is Sus" and Chipotle Mexican Grill's Stock Price

[[ABSTRACT]]
This paper investigates the curious association between Google searches for the phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. Utilizing data from Google Trends and LSEG Analytics (Refinitiv), we employed rigorous statistical analyses to unveil a correlation coefficient of 0.9490520 and a significance level of p < 0.01. The implications of these findings are not to be taken with a grain of salt, as they yield interesting insights into the interplay between online pop culture references and the financial performance of a prominent fast-casual dining establishment. Our study sheds new light on the "queso" of the matter and offers food for thought for future research in the field of unconventional stock market indicators.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The peculiarities of financial markets often defy conventional reasoning, prompting researchers to delve into uncharted territories in search of correlations and insights that may have eluded common scrutiny. In this study, we embark on a journey to unravel the cryptic connection between the colloquial phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG). While this inquiry may initially seem far-fetched, the world of finance has a knack for the unexpected, reminiscent of the surprising flavor combinations found in a well-made burrito. As we excavate this curious association, we must approach it with a blend of skepticism and curiosity, much like venturing into uncharted guacamole territory.
The phrase "that is sus" has permeated popular culture, particularly within online gaming communities, where individuals use it to denote suspicious or questionable behavior. Its proliferation in internet vernacular reflects the nuances of modern communication and zeitgeist, mirroring the rapid dissemination of memes and colloquial expressions that ebb and flow in the digital sphere. Meanwhile, Chipotle Mexican Grill has carved out a distinctive niche in the fast-casual dining landscape, cultivating a brand synonymous with fresh ingredients and customizable culinary experiences. The intersection of these seemingly incongruent entities presents an intellectual puzzle that piques our curiosity, much like the thought of a spicy salsa paired with a creamy guacamole.
Drawing inspiration from the realm of unconventional stock market indicators, we are compelled to explore the potential interplay between digital discourse and the financial performance of a prominent dining establishment. As we venture into this uncharted terrain, we must navigate with an analytical rigor reminiscent of a sous-chef meticulously crafting a delicate sauce – ensuring precision and accuracy in our methodologies. While the path ahead may be riddled with skepticism and raised eyebrows, our pursuit of knowledge in this unorthodox endeavor promises to yield appetizing insights, much like the tantalizing aroma of a fresh batch of sizzling fajitas.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The meticulous examination of the data unearthed a striking correlation between Google searches for "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. The correlation coefficient of 0.9490520 indicates a remarkably strong positive relationship between the two variables. This finding suggests that the frequency of Google searches for "that is sus" is closely linked to fluctuations in CMG's stock price, highlighting an intriguing interplay between online vernacular and financial performance.

Furthermore, the r-squared value of 0.9006998 denotes that approximately 90.07% of the variability in CMG's stock price can be explained by fluctuations in Google searches for "that is sus." This substantial proportion underscores the significance of this unconventional indicator in capturing movements in Chipotle's stock price. The results notably surpass expectations, akin to stumbling upon a well-hidden jalapeño pepper in a dish.

The statistical significance of the correlation is underscored by the p-value of less than 0.01, indicating a strong level of confidence in the observed relationship. The implications of this finding are substantial, akin to the discovery of a hitherto unnoticed extra dollop of sour cream atop an eagerly anticipated burrito.

The scatterplot (Fig. 1) provides a visual depiction of the robust correlation between Google searches for "that is sus" and CMG's stock price, emphasizing the compelling nature of this association. Its visual representation elucidates the remarkable synchrony between the two variables, prompting further contemplation on the unexpected connections that permeate the financial landscape.

In conclusion, the findings of this study elucidate a thought-provoking correlation between a colloquial online expression and the stock price of a prominent fast-casual dining establishment. While the origins of this association may remain enigmatic, the observed relationship prompts a reevaluation of the potential impact of digital discourse on financial markets. These results serve as a testament to the inimitable flavor profiles that emerge from unorthodox investigative pursuits and offer a delectable platter of insights for researchers delving into the unconventional intersections of culture and finance.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 'that is sus' and Chipotle Mexican Grill's stock price (CMG). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
Unmasking the Guac: A Suspicious Correlation Between Google Searches for "That Is Sus" and Chipotle Mexican Grill's Stock Price

[[ABSTRACT]]
This paper investigates the curious association between Google searches for the phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. Utilizing data from Google Trends and LSEG Analytics (Refinitiv), we employed rigorous statistical analyses to unveil a correlation coefficient of 0.9490520 and a significance level of p < 0.01. The implications of these findings are not to be taken with a grain of salt, as they yield interesting insights into the interplay between online pop culture references and the financial performance of a prominent fast-casual dining establishment. Our study sheds new light on the "queso" of the matter and offers food for thought for future research in the field of unconventional stock market indicators.

[[LITERATURE REVIEW]]
In their seminal work, Smith and Doe (2015) examined the impact of online pop culture references on consumer behavior and market trends. Their study, "The Digital Age of Influence," explored the intricate relationship between internet memes and their potential influence on consumer choices. While their focus was primarily on broader consumer markets, their findings shed light on the pervasive influence of digital discourse on individual decision-making processes. Similarly, Jones et al. (2018) investigated the interplay between viral phrases and their impact on brand perception. Their research, "Viral Linguistics: Uncovering the Anatomy of Memes," provided intriguing insights into the ways in which linguistic trends propagate through online communities and leave tangible imprints on consumer associations.
Turning our attention to the literary realm, "The Influencer's Dilemma" by Smith (2020) offered a comprehensive exploration of the power dynamics at play in digital communication. While not explicitly focused on financial markets, Smith's conceptual framework for understanding the dissemination of online phrases holds relevance for our investigation. Furthermore, Doe's "The Language of Stocks: A Linguistic Analysis of Market Behavior" delved into the nuanced ways in which language shapes perceptions and behaviors in the financial domain, albeit without venturing into the realm of colloquial online expressions.
In a more speculative vein, fictional works such as "The Suspicion Principle" by Jane Austen and "The Curious Case of Suspect Stocks" by Sir Arthur Conan Doyle have integrated elements of suspicion and intrigue into their narrative structures. While these works are undoubtedly far removed from the empirical rigor of academic research, their thematic resonance with our study's focus on suspicion warrants a mention in this literature review. In a similar light, social media musings such as "Just saw CMG stock plummet after that sus earnings report, yikes" and "Is it just me, or does Chipotle's guac taste sus today?" have surfaced intermittently, reflecting the informal chatter surrounding our investigative nexus between online vernacular and stock performance.
The aforementioned sources provide a contextual backdrop for our exploration of the enigmatic relationship between Google searches for "that is sus" and Chipotle Mexican Grill's stock price. While the interdisciplinary blend of literature may appear unconventional, it primes us for a comprehensive understanding of the multifaceted dynamics inherent in our research inquiry.

[[RESULTS]]
The meticulous examination of the data unearthed a striking correlation between Google searches for "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. The correlation coefficient of 0.9490520 indicates a remarkably strong positive relationship between the two variables. This finding suggests that the frequency of Google searches for "that is sus" is closely linked to fluctuations in CMG's stock price, highlighting an intriguing interplay between online vernacular and financial performance.
Furthermore, the r-squared value of 0.9006998 denotes that approximately 90.07% of the variability in CMG's stock price can be explained by fluctuations in Google searches for "that is sus." This substantial proportion underscores the significance of this unconventional indicator in capturing movements in Chipotle's stock price. The results notably surpass expectations, akin to stumbling upon a well-hidden jalapeño pepper in a dish.
The statistical significance of the correlation is underscored by the p-value of less than 0.01, indicating a strong level of confidence in the observed relationship. The implications of this finding are substantial, akin to the discovery of a hitherto unnoticed extra dollop of sour cream atop an eagerly anticipated burrito.
The scatterplot (Fig. 1) provides a visual depiction of the robust correlation between Google searches for "that is sus" and CMG's stock price, emphasizing the compelling nature of this association. Its visual representation elucidates the remarkable synchrony between the two variables, prompting further contemplation on the unexpected connections that permeate the financial landscape.
In conclusion, the findings of this study elucidate a thought-provoking correlation between a colloquial online expression and the stock price of a prominent fast-casual dining establishment. While the origins of this association may remain enigmatic, the observed relationship prompts a reevaluation of the potential impact of digital discourse on financial markets. These results serve as a testament to the inimitable flavor profiles that emerge from unorthodox investigative pursuits and offer a delectable platter of insights for researchers delving into the unconventional intersections of culture and finance.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The robust correlation between Google searches for "that is sus" and Chipotle Mexican Grill's stock price (CMG) has yielded a veritable feast of intriguing insights. Our findings, which intertwine the realms of digital vernacular and financial performance, are not to be "burrito-ed" away lightly. The emergence of this association may at first glance appear as unexpected as discovering a surprise ingredient in a queso dip, but it aligns with previous research on the influence of online pop culture references on consumer behavior and market trends.

Building upon the work of Smith and Doe (2015), we have illuminated the substantial impact of internet memes and linguistic trends on individual decision-making processes, and even the stock market dynamics. Similarly, the linguistic analysis of market behavior by Doe (2020) has set the stage for our investigation by highlighting the nuanced ways in which language shapes perceptions and behaviors in the financial domain. These conceptual underpinnings germinated in the fertile soil of digital culture, resonating with our findings on the intersection of online vernacular and stock price movements.

Moreover, our results align with the thematic resonance of works such as "The Curious Case of Suspect Stocks" by Sir Arthur Conan Doyle, highlighting the intricacies of suspicion and intrigue in financial domains. While not directly applicable to empirical research, these literary resonances add a layer of depth to the thematic undercurrents of our study. The emergence of our observed correlation between online expressions and stock prices encapsulates the unpredictable and intriguing nature of financial markets, akin to uncovering hidden flavors in a complex dish.

In essence, our study has added a dash of spice to the traditional understanding of stock market indicators, underscoring the need to consider unconventional sources, much like the unexpected zest of a tangy salsa verde. As we veer into uncharted territory at the intersection of digital discourse and financial analysis, our findings beckon further exploration of the unorthodox connections that underpin market movements. With this in mind, we invite researchers to savor the captivating fusion of culture and finance and indulge in the rich tapestry of unconventional indicators that await investigation.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 'that is sus' and Chipotle Mexican Grill's stock price (CMG). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
Unmasking the Guac: A Suspicious Correlation Between Google Searches for "That Is Sus" and Chipotle Mexican Grill's Stock Price

[[ABSTRACT]]
This paper investigates the curious association between Google searches for the phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. Utilizing data from Google Trends and LSEG Analytics (Refinitiv), we employed rigorous statistical analyses to unveil a correlation coefficient of 0.9490520 and a significance level of p < 0.01. The implications of these findings are not to be taken with a grain of salt, as they yield interesting insights into the interplay between online pop culture references and the financial performance of a prominent fast-casual dining establishment. Our study sheds new light on the "queso" of the matter and offers food for thought for future research in the field of unconventional stock market indicators.

[[INTRDUCTION]]
The peculiarities of financial markets often defy conventional reasoning, prompting researchers to delve into uncharted territories in search of correlations and insights that may have eluded common scrutiny. In this study, we embark on a journey to unravel the cryptic connection between the colloquial phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG). While this inquiry may initially seem far-fetched, the world of finance has a knack for the unexpected, reminiscent of the surprising flavor combinations found in a well-made burrito. As we excavate this curious association, we must approach it with a blend of skepticism and curiosity, much like venturing into uncharted guacamole territory.
The phrase "that is sus" has permeated popular culture, particularly within online gaming communities, where individuals use it to denote suspicious or questionable behavior. Its proliferation in internet vernacular reflects the nuances of modern communication and zeitgeist, mirroring the rapid dissemination of memes and colloquial expressions that ebb and flow in the digital sphere. Meanwhile, Chipotle Mexican Grill has carved out a distinctive niche in the fast-casual dining landscape, cultivating a brand synonymous with fresh ingredients and customizable culinary experiences. The intersection of these seemingly incongruent entities presents an intellectual puzzle that piques our curiosity, much like the thought of a spicy salsa paired with a creamy guacamole.
Drawing inspiration from the realm of unconventional stock market indicators, we are compelled to explore the potential interplay between digital discourse and the financial performance of a prominent dining establishment. As we venture into this uncharted terrain, we must navigate with an analytical rigor reminiscent of a sous-chef meticulously crafting a delicate sauce – ensuring precision and accuracy in our methodologies. While the path ahead may be riddled with skepticism and raised eyebrows, our pursuit of knowledge in this unorthodox endeavor promises to yield appetizing insights, much like the tantalizing aroma of a fresh batch of sizzling fajitas.

[[RESULTS]]
The meticulous examination of the data unearthed a striking correlation between Google searches for "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. The correlation coefficient of 0.9490520 indicates a remarkably strong positive relationship between the two variables. This finding suggests that the frequency of Google searches for "that is sus" is closely linked to fluctuations in CMG's stock price, highlighting an intriguing interplay between online vernacular and financial performance.
Furthermore, the r-squared value of 0.9006998 denotes that approximately 90.07% of the variability in CMG's stock price can be explained by fluctuations in Google searches for "that is sus." This substantial proportion underscores the significance of this unconventional indicator in capturing movements in Chipotle's stock price. The results notably surpass expectations, akin to stumbling upon a well-hidden jalapeño pepper in a dish.
The statistical significance of the correlation is underscored by the p-value of less than 0.01, indicating a strong level of confidence in the observed relationship. The implications of this finding are substantial, akin to the discovery of a hitherto unnoticed extra dollop of sour cream atop an eagerly anticipated burrito.
The scatterplot (Fig. 1) provides a visual depiction of the robust correlation between Google searches for "that is sus" and CMG's stock price, emphasizing the compelling nature of this association. Its visual representation elucidates the remarkable synchrony between the two variables, prompting further contemplation on the unexpected connections that permeate the financial landscape.
In conclusion, the findings of this study elucidate a thought-provoking correlation between a colloquial online expression and the stock price of a prominent fast-casual dining establishment. While the origins of this association may remain enigmatic, the observed relationship prompts a reevaluation of the potential impact of digital discourse on financial markets. These results serve as a testament to the inimitable flavor profiles that emerge from unorthodox investigative pursuits and offer a delectable platter of insights for researchers delving into the unconventional intersections of culture and finance.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

The investigation into the correlation between Google searches for "that is sus" and Chipotle Mexican Grill's stock price has revealed a robust and tantalizing association. The remarkable correlation coefficient of 0.9490520 and the r-squared value of 0.9006998 indicate a strong link between the frequency of "that is sus" searches and the variability in CMG's stock price. The significance of this unorthodox indicator in capturing movements in Chipotle's stock price cannot be overstated, much like the discovery of an unexpected dollop of guacamole in a burrito. The scatterplot visualizes the compelling synchrony between the two variables, prompting contemplation on the unexpected connections that permeate the financial landscape, perhaps akin to pondering the unexpected harmonious combination of flavors in Mexican cuisine.

These findings shed light on the intriguing interplay between online vernacular and financial performance, offering a delectable platter of insights for researchers delving into the unconventional intersections of culture and finance. The unexpected nature of this correlation serves as a testament to the curious flavor combinations found in a well-made burrito, and prompts a reevaluation of the potential impact of digital discourse on financial markets. Thus, it is evident that further exploration in this area promises to yield appetizing insights and uncover even more unexpected connections, much like the joy of finding the perfect ratio of salsa to guacamole in a dish.

In light of these sumptuous findings, it can be asserted that no more research is needed in this area.

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 Unmasking the Guac: A Suspicious Correlation Between Google Searches for That Is Sus and Chipotle Mexican Grill's Stock Price. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Irreverent Economics and Culinary 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 Unmasking the Guac: A Suspicious Correlation Between Google Searches for That Is Sus and Chipotle Mexican Grill's Stock Price. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Gastronomic Economic Research (SGER)

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 Unmasking the Guac: A Suspicious Correlation Between Google Searches for That Is Sus and Chipotle Mexican Grill's Stock Price with an abstract of This paper investigates the curious association between Google searches for the phrase "that is sus" and the stock price of Chipotle Mexican Grill (CMG) over the period from 2007 to 2023. Utilizing data from Google Trends and LSEG Analytics (Refinitiv), we employed rigorous statistical analyses to unveil a correlation coefficient of 0.9490520 and a significance level of p < 0.01. The implications of these findings are not to be taken with a grain of salt, as they yield interesting insights into the interplay between online pop culture references and the financial performance of a prominent fast-casual dining establishment. Our study sheds new light on the "queso" of the matter and offers food for thought for future research in the field of unconventional stock market indicators.

ChatGPT:

"Google searches, Chipotle stock price, correlation coefficient, significance level, online pop culture references, financial performance, fast-casual dining, unconventional stock market indicators"

*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 'that is sus'
Detailed data title: Relative volume of Google searches for 'that is sus' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'that is sus'

Chipotle Mexican Grill's stock price (CMG)
Detailed data title: Opening price of Chipotle Mexican Grill (CMG) on the first trading day of the year
Source: LSEG Analytics (Refinitiv)
Additional Info: ^{See full details} Via Microsoft Excel Stockhistory function

See what else correlates with Chipotle Mexican Grill's stock price (CMG)

Correlation r = 0.9490520 (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 = 0.9006998 (Coefficient of determination)
This means 90.1% of the change in the one variable (i.e., Chipotle Mexican Grill's stock price (CMG)) is predictable based on the change in the other (i.e., Google searches for 'that is sus') over the 17 years from 2007 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.4E-9.^Show 0.0000000063638635119268650000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.95 in 6.4E-7% of random cases. Said differently, if you correlated 157,137,248 random variables^Note You don't actually need 157 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 16 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 16 because we have two variables measured over a period of 17 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.

[ 0.86, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Google searches for 'that is sus' (Rel. search volume)	3.83333	1.33333	6.41667	5.58333	6.91667	10.25	10.0833	8.66667	8.66667	11.0833	12.5	15.4167	14.4167	40.8333	58.1667	81.6667	79.6
Chipotle Mexican Grill's stock price (CMG) (Stock price)	56.9	147.1	61.89	89.6	215.26	343.7	304.26	530	686	468.7	379.11	290.9	427.83	839.97	1386.68	1740	1400.3

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([3.83333,1.33333,6.41667,5.58333,6.91667,10.25,10.0833,8.66667,8.66667,11.0833,12.5,15.4167,14.4167,40.8333,58.1667,81.6667,79.6,])
array_2 = np.array([56.9,147.1,61.89,89.6,215.26,343.7,304.26,530,686,468.7,379.11,290.9,427.83,839.97,1386.68,1740,1400.3,])
array_1_name = "Google searches for 'that is sus'"
array_2_name = "Chipotle Mexican Grill's stock price (CMG)"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Google searches for 'that is sus'
Line chart for only Chipotle Mexican Grill's stock price (CMG)
AI-generated correlation image
The spurious research paper: Unmasking the Guac: A Suspicious Correlation Between Google Searches for That Is Sus and Chipotle Mexican Grill's Stock Price

View another random correlation

How fun was this correlation?

Your correlation rating is out of this world!

Correlation ID: 2280 · Black Variable ID: 1367 · Red Variable ID: 1722


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