Spurious correlation #1,280 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Solar power generated in Mexico and the second variable is Google searches for 'that is sus'. The chart goes from 2004 to 2021, 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 Solar power generated in Mexico and the second variable is Google searches for 'that is sus'. The chart goes from 2004 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Mexico's solar power output rises, it's creating a massive influx of energy. This has inadvertently led to a surge in 'solar suspicion' worldwide. People are now convinced that even the sun, the original source of solar power, is acting shady or sus. It's a real power struggle as the sun tries to convince everyone that it's just a solar false alarm, but the evidence is glaringly bright.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a small Mexican town, with houses and buildings adorned with an array of solar panels on their rooftops. The sun is shining brightly, casting a warm glow over the scene and creating a dazzling reflection off the solar panels. Curious residents are depicted gathering near their electricity meters, inspecting them closely and engaging in animated conversations with their neighbors about the sudden increase in solar power generation. Some individuals are seen taking notes and beginning to research the source of their electricity, as a sense of suspicion and intrigue sets in. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: Because as solar power generated in Mexico increased, it led to more people becoming suspicious of their energy sources and feeling a need to investigate "watt is sus" in their electricity supply.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Parallax art Symbolism Cubism An image that looks like it is a scene from A Disney Movie An image that looks like it is a scene from A Disney Movie
ChatGPT: Parallax art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. Because as solar power generated in Mexico increased, it led to more people becoming suspicious of their energy sources and feeling a need to investigate "watt is sus" in their electricity supply.
ChatGPT: In a small Mexican town, we see an increase in solar panels adorning the rooftops of houses and buildings. The sun shines brightly, reflecting off the solar panels, generating more energy. As a result, curious residents gather around their electricity meters, inspecting them closely and discussing with their neighbors about the sudden rise in solar power generation. Some people take notes and start researching about the source of their electricity, as they become more suspicious and intrigued by the changes in their energy supply.

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: [ Parallax art ] and depicting this scene: In a small Mexican town, we see an increase in solar panels adorning the rooftops of houses and buildings. The sun shines brightly, reflecting off the solar panels, generating more energy. As a result, curious residents gather around their electricity meters, inspecting them closely and discussing with their neighbors about the sudden rise in solar power generation. Some people take notes and start researching about the source of their electricity, as they become more suspicious and intrigued by the changes in their energy supply. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a small Mexican town, with houses and buildings adorned with an array of solar panels on their rooftops. The sun is shining brightly, casting a warm glow over the scene and creating a dazzling reflection off the solar panels. Curious residents are depicted gathering near their electricity meters, inspecting them closely and engaging in animated conversations with their neighbors about the sudden increase in solar power generation. Some individuals are seen taking notes and beginning to research the source of their electricity, as a sense of suspicion and intrigue sets in.

*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 Solar power generated in Mexico caused that is sus (Google searches for 'that is sus') to increase.

AI academic paper

(Because p < 0.01)

Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'

Journal of Renewable Energy and Behavioral Analysis

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Solar power generated in Mexico and Google searches for 'that is sus'. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'

[[ABSTRACT]]
The relationship between solar power generation in Mexico and the frequency of Google searches for the term 'that is sus' has long been surrounded by speculation and skepticism. In this study, we shed light on this peculiar connection and aim to debunk the mystery surrounding it. By leveraging data from the Energy Information Administration to quantify solar power generation and utilizing Google Trends to track the popularity of the phrase 'that is sus' from 2004 to 2021, we embark on a journey to uncover the unexpected correlation.

Our analysis revealed a surprisingly robust correlation coefficient of 0.9450632 with a significance level of p < 0.01, indicating a strong association between solar power output in Mexico and the public's inclination to question suspicious behavior. The implications of these findings extend beyond the realm of renewable energy and internet searches, posing a quandary for further investigation. Our research stands as a beacon of curiosity in the intersection of solar energy and internet colloquialisms, urging future studies to delve deeper into the enigmatic relationship between 'that is sus' and solar power generation.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The world of academia and research often leads us down unexpected paths, and the correlation between solar power generation in Mexico and the prevalence of Google searches for the phrase 'that is sus' is no exception. While the connection may at first appear as elusive as a solar eclipse, our study aims to shine a light on this enigma and unveil the relationship between these seemingly disparate phenomena.
In recent years, the use of solar energy has surged, illuminating not only our homes and businesses but also our hopes for a cleaner, more sustainable future. Meanwhile, the phrase 'that is sus' has carved out its own niche in the vernacular of internet users, serving as a catch-all expression for anything deemed suspicious or dubious. The convergence of these two seemingly unrelated trends has piqued the curiosity of researchers and armchair detectives alike, prompting us to unravel the mystery lurking within the data.
As we venture into this uncharted territory, it is essential to approach our investigation with a balanced mix of scientific rigor and a healthy dose of skepticism. We must harness the power of statistical analysis and academic inquiry while also remaining open to the whimsical nature of our findings. After all, who would have thought that solar power and internet slang would cross paths in such a captivating manner?
Our endeavor is not simply an exercise in curiosity; it has broader implications for both the fields of renewable energy and digital culture. By delving into the unexplored terrain of solar power and online colloquialisms, we hope to shed light on this unconventional connection and spark conversations that extend beyond the confines of traditional research paradigms.
So, let us embark on this illuminating journey, delving into the depths of solar power generation and the often-shady realm of suspect behavior. Prepare to be enlightened, amused, and perhaps a bit puzzled as we navigate the intersection of science, technology, and internet humor. After all, in the words of the great physicist Albert Einstein, "Once we accept our limits, we go beyond them" – and in this case, those limits may include both solar panels and internet memes.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
**LITERATURE REVIEW**

The quest to unravel the intriguing connection between solar power generation in Mexico and the frequency of Google searches for the phrase 'that is sus' has led researchers down a labyrinth of scholarly investigations and peculiar findings. Smith et al. (2015) undertook a comprehensive analysis of solar energy trends in Mexico, shedding light on the advancements and challenges within the renewable energy sector. Meanwhile, Doe and Jones (2018) delved into the fascinating world of internet colloquialisms, exploring the evolution of digital language and its impact on contemporary communication.

In "The Solar Frontier: The Beginning of a New Era," the authors underscore the transformative potential of solar energy, painting a vivid picture of a world powered by the sun's abundant resources. Simultaneously, "The Algorithmic Mind: Unraveling the Mysteries of Online Language Usage" offers a deep dive into the intricate algorithms that govern the frequency and popularity of internet search terms, providing invaluable insights into the quirks of digital lexicon.

However, as we venture further into the uncharted territory of solar power and suspect behavior, it is essential to recognize the unconventional inspirations that may shed light on this curious connection. Drawing from the fictional realm, the works of literary giants such as Agatha Christie's "Murder on the Solar Express" and Arthur Conan Doyle's "The Hound of the Sus-ervilles" offer intriguing parallels to our investigation, juxtaposing the allure of solar power with the intrigue of mysterious occurrences.

Turning our gaze to the world of board games, the parallels between our research and the game "Clue" become eerily apparent -- could the solar panels have committed the crime in the Study with the candlestick, or is it merely a red herring? As we navigate the intersections of real-world data and whimsical analogies, it becomes evident that our inquiry transcends the boundaries of traditional research paradigms, embracing the enigmatic and the amusing in equal measure.

In the pursuit of scholarly enlightenment, we must not shy away from unconventional sources of inspiration, for it is within the unexpected that we often find the most illuminating connections. Therefore, with a spirit of curiosity and a touch of whimsy, we delve into the literature, poised to unearth the hidden truths that lie at the crossroads of solar power and internet vernacular.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Solar power generated in Mexico and Google searches for 'that is sus'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Energy Information Administration and Google Trends . You used data from 2004 to 2021

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]]
Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'

[[ABSTRACT]]
The relationship between solar power generation in Mexico and the frequency of Google searches for the term 'that is sus' has long been surrounded by speculation and skepticism. In this study, we shed light on this peculiar connection and aim to debunk the mystery surrounding it. By leveraging data from the Energy Information Administration to quantify solar power generation and utilizing Google Trends to track the popularity of the phrase 'that is sus' from 2004 to 2021, we embark on a journey to uncover the unexpected correlation.

Our analysis revealed a surprisingly robust correlation coefficient of 0.9450632 with a significance level of p < 0.01, indicating a strong association between solar power output in Mexico and the public's inclination to question suspicious behavior. The implications of these findings extend beyond the realm of renewable energy and internet searches, posing a quandary for further investigation. Our research stands as a beacon of curiosity in the intersection of solar energy and internet colloquialisms, urging future studies to delve deeper into the enigmatic relationship between 'that is sus' and solar power generation.

[[INTRODUCTION]]
INTRODUCTION
The world of academia and research often leads us down unexpected paths, and the correlation between solar power generation in Mexico and the prevalence of Google searches for the phrase 'that is sus' is no exception. While the connection may at first appear as elusive as a solar eclipse, our study aims to shine a light on this enigma and unveil the relationship between these seemingly disparate phenomena.
In recent years, the use of solar energy has surged, illuminating not only our homes and businesses but also our hopes for a cleaner, more sustainable future. Meanwhile, the phrase 'that is sus' has carved out its own niche in the vernacular of internet users, serving as a catch-all expression for anything deemed suspicious or dubious. The convergence of these two seemingly unrelated trends has piqued the curiosity of researchers and armchair detectives alike, prompting us to unravel the mystery lurking within the data.
As we venture into this uncharted territory, it is essential to approach our investigation with a balanced mix of scientific rigor and a healthy dose of skepticism. We must harness the power of statistical analysis and academic inquiry while also remaining open to the whimsical nature of our findings. After all, who would have thought that solar power and internet slang would cross paths in such a captivating manner?
Our endeavor is not simply an exercise in curiosity; it has broader implications for both the fields of renewable energy and digital culture. By delving into the unexplored terrain of solar power and online colloquialisms, we hope to shed light on this unconventional connection and spark conversations that extend beyond the confines of traditional research paradigms.
So, let us embark on this illuminating journey, delving into the depths of solar power generation and the often-shady realm of suspect behavior. Prepare to be enlightened, amused, and perhaps a bit puzzled as we navigate the intersection of science, technology, and internet humor. After all, in the words of the great physicist Albert Einstein, "Once we accept our limits, we go beyond them" – and in this case, those limits may include both solar panels and internet memes.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

**METHODOLOGY**

Data Collection:

To embark on this quest to uncover the connection between solar power generation in Mexico and the frequency of Google searches for 'that is sus,' we gathered an extensive array of data from reputable sources. Our primary sources of information included the Energy Information Administration (EIA) for data on solar power output in Mexico and Google Trends for the search interest in the phrase 'that is sus.' Additionally, we employed various web scraping techniques to collect complementary data from online forums, social media platforms, and internet memes. This eclectic blend of data sources allowed us to cast a wide net in capturing the nuances of solar generation and internet slang, reminiscent of a fisherman skillfully navigating the waters of digital information.

Solar Power Generation Data:

The EIA provided a treasure trove of data related to solar power generation in Mexico from 2004 to 2021. We meticulously combed through this dataset, analyzing the fluctuations in solar energy output and drawing parallels to the ebb and flow of public interest in suspect behavior. It was akin to tracing the path of a wandering photon as it journeyed from the sun to the solar panels and then metaphorically bounced into the nebulous realm of internet searches for suspicious activities.

Google Searches for 'That is Sus':

In parallel, our investigation delved into the realm of internet queries, with Google Trends serving as our compass in navigating the landscape of 'that is sus' searches. By examining the search interest over time, regional variations, and related search queries, we sought to discern patterns and trends that would illuminate the oscillations in virtual suspicion. It was akin to navigating the labyrinthine corridors of digital curiosity, where every click led to a new revelation, much like delving into a complex maze and emerging with a newfound understanding of internet vernacular.

Statistical Analysis:

A quintessential aspect of our methodology involved employing rigorous statistical analysis to unravel the intricate relationship between solar power generation and the usage of the term 'that is sus.' Through correlation analysis, time series modeling, and regression techniques, we sought to tease out the subtle connections and unveil the underlying dynamics at play. It was akin to peering through the lens of a sophisticated telescope, aiming to capture celestial phenomena that lay hidden beneath the surface, much like uncovering the intricate dance of solar photons and online suspicions. We encountered statistical significance levels, correlation coefficients, and p-values, akin to deciphering the cryptic clues in a thrilling detective novel, each numerical revelation bringing us closer to unraveling the enigma at hand.

In conclusion, our research methodology traversed the realms of solar energy, internet culture, and statistical inquiry, binding them together in an exuberant quest to understand the inexplicable relationship between solar power generation in Mexico and the prevalence of searches for 'that is sus.' Our approach amalgamated scientific rigor with the whimsical nature of internet phenomena, epitomizing the adage that sometimes, the strangest connections lead to the most fascinating discoveries.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Solar power generated in Mexico and Google searches for 'that is sus'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Energy Information Administration and Google Trends .

For the time period 2004 to 2021, you found a correlation 0.9450632, r-squared of 0.8931445, 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]]
Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'

[[ABSTRACT]]
The relationship between solar power generation in Mexico and the frequency of Google searches for the term 'that is sus' has long been surrounded by speculation and skepticism. In this study, we shed light on this peculiar connection and aim to debunk the mystery surrounding it. By leveraging data from the Energy Information Administration to quantify solar power generation and utilizing Google Trends to track the popularity of the phrase 'that is sus' from 2004 to 2021, we embark on a journey to uncover the unexpected correlation.

Our analysis revealed a surprisingly robust correlation coefficient of 0.9450632 with a significance level of p < 0.01, indicating a strong association between solar power output in Mexico and the public's inclination to question suspicious behavior. The implications of these findings extend beyond the realm of renewable energy and internet searches, posing a quandary for further investigation. Our research stands as a beacon of curiosity in the intersection of solar energy and internet colloquialisms, urging future studies to delve deeper into the enigmatic relationship between 'that is sus' and solar power generation.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The world of academia and research often leads us down unexpected paths, and the correlation between solar power generation in Mexico and the prevalence of Google searches for the phrase 'that is sus' is no exception. While the connection may at first appear as elusive as a solar eclipse, our study aims to shine a light on this enigma and unveil the relationship between these seemingly disparate phenomena.
In recent years, the use of solar energy has surged, illuminating not only our homes and businesses but also our hopes for a cleaner, more sustainable future. Meanwhile, the phrase 'that is sus' has carved out its own niche in the vernacular of internet users, serving as a catch-all expression for anything deemed suspicious or dubious. The convergence of these two seemingly unrelated trends has piqued the curiosity of researchers and armchair detectives alike, prompting us to unravel the mystery lurking within the data.
As we venture into this uncharted territory, it is essential to approach our investigation with a balanced mix of scientific rigor and a healthy dose of skepticism. We must harness the power of statistical analysis and academic inquiry while also remaining open to the whimsical nature of our findings. After all, who would have thought that solar power and internet slang would cross paths in such a captivating manner?
Our endeavor is not simply an exercise in curiosity; it has broader implications for both the fields of renewable energy and digital culture. By delving into the unexplored terrain of solar power and online colloquialisms, we hope to shed light on this unconventional connection and spark conversations that extend beyond the confines of traditional research paradigms.
So, let us embark on this illuminating journey, delving into the depths of solar power generation and the often-shady realm of suspect behavior. Prepare to be enlightened, amused, and perhaps a bit puzzled as we navigate the intersection of science, technology, and internet humor. After all, in the words of the great physicist Albert Einstein, "Once we accept our limits, we go beyond them" – and in this case, those limits may include both solar panels and internet memes.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

**RESULTS**

Upon embarking on our investigation, we anticipated a trek through uncharted territory, meandering between solar power generation and the enigmatic world of internet vernacular. What we uncovered was nothing short of illuminating.

Our analysis of the data spanning from 2004 to 2021 yielded a remarkably strong correlation between solar power generation in Mexico and the frequency of Google searches for the phrase 'that is sus.' The correlation coefficient of 0.9450632 indicates a robust positive relationship between these seemingly disparate phenomena. This correlation was further substantiated by an r-squared value of 0.8931445, underscoring the substantial explanatory power of solar power generation on the occurrence of searches for 'that is sus.'

In more relatable terms, the relationship between solar power in Mexico and public skepticism can be likened to the reliable presence of sunlight during the day – glaringly evident and difficult to overlook. The statistical significance of our findings, with a p-value less than 0.01, solidifies the validity of the observed association, leaving little room for doubt.

*Fig. 1: A Scatterplot showing the correlation between Solar Power Generated in Mexico and Google searches for 'that is sus'*

This visual representation, which will be provided in the paper's figures, serves not only as a testament to the strength of the correlation but also as a striking reminder that truth can indeed be stranger than fiction. As we gaze upon the scatterplot, it becomes abundantly clear that the relationship between solar power and suspicions is not merely a flash in the pan – it's a full-blown solar flare of a connection!

For those seeking a more nuanced understanding, the data point to a compelling narrative – one where the sun shines bright, casting a spotlight on questionable behaviors that beckon the attention of the public. The implications of these findings stretch beyond the realms of solar power and internet slang; they beckon us to ponder the broader implications of this unexpected convergence.

In summary, our study has unveiled a resoundingly robust correlation between solar power generation in Mexico and the frequency of Google searches for 'that is sus.' These findings not only shed light on the intersection of renewable energy and internet culture but also serve as a clarion call for continued exploration and contemplation of the countless curiosities lurking within the data.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Solar power generated in Mexico and Google searches for 'that is sus'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'

[[ABSTRACT]]
The relationship between solar power generation in Mexico and the frequency of Google searches for the term 'that is sus' has long been surrounded by speculation and skepticism. In this study, we shed light on this peculiar connection and aim to debunk the mystery surrounding it. By leveraging data from the Energy Information Administration to quantify solar power generation and utilizing Google Trends to track the popularity of the phrase 'that is sus' from 2004 to 2021, we embark on a journey to uncover the unexpected correlation.

Our analysis revealed a surprisingly robust correlation coefficient of 0.9450632 with a significance level of p < 0.01, indicating a strong association between solar power output in Mexico and the public's inclination to question suspicious behavior. The implications of these findings extend beyond the realm of renewable energy and internet searches, posing a quandary for further investigation. Our research stands as a beacon of curiosity in the intersection of solar energy and internet colloquialisms, urging future studies to delve deeper into the enigmatic relationship between 'that is sus' and solar power generation.

[[LITERATURE REVIEW]]
The quest to unravel the intriguing connection between solar power generation in Mexico and the frequency of Google searches for the phrase 'that is sus' has led researchers down a labyrinth of scholarly investigations and peculiar findings. Smith et al. (2015) undertook a comprehensive analysis of solar energy trends in Mexico, shedding light on the advancements and challenges within the renewable energy sector. Meanwhile, Doe and Jones (2018) delved into the fascinating world of internet colloquialisms, exploring the evolution of digital language and its impact on contemporary communication.
In "The Solar Frontier: The Beginning of a New Era," the authors underscore the transformative potential of solar energy, painting a vivid picture of a world powered by the sun's abundant resources. Simultaneously, "The Algorithmic Mind: Unraveling the Mysteries of Online Language Usage" offers a deep dive into the intricate algorithms that govern the frequency and popularity of internet search terms, providing invaluable insights into the quirks of digital lexicon.
However, as we venture further into the uncharted territory of solar power and suspect behavior, it is essential to recognize the unconventional inspirations that may shed light on this curious connection. Drawing from the fictional realm, the works of literary giants such as Agatha Christie's "Murder on the Solar Express" and Arthur Conan Doyle's "The Hound of the Sus-ervilles" offer intriguing parallels to our investigation, juxtaposing the allure of solar power with the intrigue of mysterious occurrences.
Turning our gaze to the world of board games, the parallels between our research and the game "Clue" become eerily apparent -- could the solar panels have committed the crime in the Study with the candlestick, or is it merely a red herring? As we navigate the intersections of real-world data and whimsical analogies, it becomes evident that our inquiry transcends the boundaries of traditional research paradigms, embracing the enigmatic and the amusing in equal measure.
In the pursuit of scholarly enlightenment, we must not shy away from unconventional sources of inspiration, for it is within the unexpected that we often find the most illuminating connections. Therefore, with a spirit of curiosity and a touch of whimsy, we delve into the literature, poised to unearth the hidden truths that lie at the crossroads of solar power and internet vernacular.

[[RESULTS]]
Upon embarking on our investigation, we anticipated a trek through uncharted territory, meandering between solar power generation and the enigmatic world of internet vernacular. What we uncovered was nothing short of illuminating.
Our analysis of the data spanning from 2004 to 2021 yielded a remarkably strong correlation between solar power generation in Mexico and the frequency of Google searches for the phrase 'that is sus.' The correlation coefficient of 0.9450632 indicates a robust positive relationship between these seemingly disparate phenomena. This correlation was further substantiated by an r-squared value of 0.8931445, underscoring the substantial explanatory power of solar power generation on the occurrence of searches for 'that is sus.'
In more relatable terms, the relationship between solar power in Mexico and public skepticism can be likened to the reliable presence of sunlight during the day – glaringly evident and difficult to overlook. The statistical significance of our findings, with a p-value less than 0.01, solidifies the validity of the observed association, leaving little room for doubt.
*Fig. 1: A Scatterplot showing the correlation between Solar Power Generated in Mexico and Google searches for 'that is sus'*
This visual representation, which will be provided in the paper's figures, serves not only as a testament to the strength of the correlation but also as a striking reminder that truth can indeed be stranger than fiction. As we gaze upon the scatterplot, it becomes abundantly clear that the relationship between solar power and suspicions is not merely a flash in the pan – it's a full-blown solar flare of a connection!
For those seeking a more nuanced understanding, the data point to a compelling narrative – one where the sun shines bright, casting a spotlight on questionable behaviors that beckon the attention of the public. The implications of these findings stretch beyond the realms of solar power and internet slang; they beckon us to ponder the broader implications of this unexpected convergence.
In summary, our study has unveiled a resoundingly robust correlation between solar power generation in Mexico and the frequency of Google searches for 'that is sus.' These findings not only shed light on the intersection of renewable energy and internet culture but also serve as a clarion call for continued exploration and contemplation of the countless curiosities lurking within the data.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our investigation have not only illuminated a quirky correlation between solar power generation in Mexico and the frequency of Google searches for 'that is sus' but have also cast a proverbial ray of sunshine on the intersection of renewable energy and internet colloquialism. While the initial notion of drawing parallels between solar power and suspicions might elicit a collective raised eyebrow, our findings stand as a testament to the unexpected connections that lurk within the depths of data analysis.

Harkening back to the unconventional inspirations that guided our inquiry, we find ourselves revisiting the parallels presented in works of literary and ludic stature. The fictional accounts of “Murder on the Solar Express” and “The Hound of the Sus-ervilles” may have initially seemed like whimsical touchstones, but our results have, in a surprising turn of events, lent credence to the notion that the world of fiction might not be so far removed from reality after all.

In light of Smith et al.'s (2015) comprehensive analysis of solar energy trends in Mexico, our findings provide a compelling endorsement of the transformative potential of solar power. The solar energy landscape, much like the spotlight cast by our correlation, appears to hold an intrinsic power to illuminate not only the physical world but also the figurative shadows of ‘sus’ behavior.

Moreover, the peculiar dance between supply and demand within the realm of internet colloquialism, as postulated by Doe and Jones (2018), finds an unexpected partner in the steady rhythm of solar power generation. It seems that just as the sun rises and sets with unfaltering regularity, so too does the public’s inclination to seek out 'sus' behavior with unwavering consistency.

As we contemplate the implications of our findings, it becomes glaringly apparent that the correlation between solar power generation and 'that is sus' searches is more than just a statistical oddity – it is a testament to the uncanny interplay of seemingly disparate phenomena. Much like the improbable plot twists of a gripping mystery novel, the relationship we unearthed between solar energy and suspect behavior strikes a chord with the intriguing plotlines of the literary world.

As we reflect on the findings of our study, it is with a sense of awe and amusement that we recognize the unanticipated interconnectedness of solar power and internet vernacular. While the antics of solar panels might not feature in a round of "Clue," it is evident that the mysteries they harbor have the potential to captivate and confound researchers and enthusiasts alike.

In conclusion, our investigation has not only unveiled a robust correlation between solar power generation in Mexico and the frequency of Google searches for 'that is sus,' but has also set the stage for further exploration into the serendipitous intersections of renewable energy and digital discourse. The whimsy and wonder that accompany our findings serve as a spirited invitation for future studies to delve into the enigmatic and unexpected connections that reside at the crossroads of data analysis and delight.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Solar power generated in Mexico and Google searches for 'that is sus'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'

[[ABSTRACT]]
The relationship between solar power generation in Mexico and the frequency of Google searches for the term 'that is sus' has long been surrounded by speculation and skepticism. In this study, we shed light on this peculiar connection and aim to debunk the mystery surrounding it. By leveraging data from the Energy Information Administration to quantify solar power generation and utilizing Google Trends to track the popularity of the phrase 'that is sus' from 2004 to 2021, we embark on a journey to uncover the unexpected correlation.

Our analysis revealed a surprisingly robust correlation coefficient of 0.9450632 with a significance level of p < 0.01, indicating a strong association between solar power output in Mexico and the public's inclination to question suspicious behavior. The implications of these findings extend beyond the realm of renewable energy and internet searches, posing a quandary for further investigation. Our research stands as a beacon of curiosity in the intersection of solar energy and internet colloquialisms, urging future studies to delve deeper into the enigmatic relationship between 'that is sus' and solar power generation.

[[INTRDUCTION]]
INTRODUCTION
The world of academia and research often leads us down unexpected paths, and the correlation between solar power generation in Mexico and the prevalence of Google searches for the phrase 'that is sus' is no exception. While the connection may at first appear as elusive as a solar eclipse, our study aims to shine a light on this enigma and unveil the relationship between these seemingly disparate phenomena.
In recent years, the use of solar energy has surged, illuminating not only our homes and businesses but also our hopes for a cleaner, more sustainable future. Meanwhile, the phrase 'that is sus' has carved out its own niche in the vernacular of internet users, serving as a catch-all expression for anything deemed suspicious or dubious. The convergence of these two seemingly unrelated trends has piqued the curiosity of researchers and armchair detectives alike, prompting us to unravel the mystery lurking within the data.
As we venture into this uncharted territory, it is essential to approach our investigation with a balanced mix of scientific rigor and a healthy dose of skepticism. We must harness the power of statistical analysis and academic inquiry while also remaining open to the whimsical nature of our findings. After all, who would have thought that solar power and internet slang would cross paths in such a captivating manner?
Our endeavor is not simply an exercise in curiosity; it has broader implications for both the fields of renewable energy and digital culture. By delving into the unexplored terrain of solar power and online colloquialisms, we hope to shed light on this unconventional connection and spark conversations that extend beyond the confines of traditional research paradigms.
So, let us embark on this illuminating journey, delving into the depths of solar power generation and the often-shady realm of suspect behavior. Prepare to be enlightened, amused, and perhaps a bit puzzled as we navigate the intersection of science, technology, and internet humor. After all, in the words of the great physicist Albert Einstein, "Once we accept our limits, we go beyond them" – and in this case, those limits may include both solar panels and internet memes.

[[RESULTS]]
Upon embarking on our investigation, we anticipated a trek through uncharted territory, meandering between solar power generation and the enigmatic world of internet vernacular. What we uncovered was nothing short of illuminating.
Our analysis of the data spanning from 2004 to 2021 yielded a remarkably strong correlation between solar power generation in Mexico and the frequency of Google searches for the phrase 'that is sus.' The correlation coefficient of 0.9450632 indicates a robust positive relationship between these seemingly disparate phenomena. This correlation was further substantiated by an r-squared value of 0.8931445, underscoring the substantial explanatory power of solar power generation on the occurrence of searches for 'that is sus.'
In more relatable terms, the relationship between solar power in Mexico and public skepticism can be likened to the reliable presence of sunlight during the day – glaringly evident and difficult to overlook. The statistical significance of our findings, with a p-value less than 0.01, solidifies the validity of the observed association, leaving little room for doubt.
*Fig. 1: A Scatterplot showing the correlation between Solar Power Generated in Mexico and Google searches for 'that is sus'*
This visual representation, which will be provided in the paper's figures, serves not only as a testament to the strength of the correlation but also as a striking reminder that truth can indeed be stranger than fiction. As we gaze upon the scatterplot, it becomes abundantly clear that the relationship between solar power and suspicions is not merely a flash in the pan – it's a full-blown solar flare of a connection!
For those seeking a more nuanced understanding, the data point to a compelling narrative – one where the sun shines bright, casting a spotlight on questionable behaviors that beckon the attention of the public. The implications of these findings stretch beyond the realms of solar power and internet slang; they beckon us to ponder the broader implications of this unexpected convergence.
In summary, our study has unveiled a resoundingly robust correlation between solar power generation in Mexico and the frequency of Google searches for 'that is sus.' These findings not only shed light on the intersection of renewable energy and internet culture but also serve as a clarion call for continued exploration and contemplation of the countless curiosities lurking within the data.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the perplexing correlation between solar power generation in Mexico and the frequency of Google searches for 'that is sus' has brought to light an unexpected connection that defies conventional wisdom. The robust correlation coefficient of 0.9450632, akin to a bright beacon in the night sky, underscores the undeniable relationship between these disparate phenomena. It seems that the solar energy in Mexico is not only powering homes and businesses but also fueling the public's dubious inclinations, shedding a rather illuminating light on suspect behaviors.

The significance of these findings extends beyond mere statistical intrigue; it beckons us to ponder the broader implications of this unanticipated convergence. Perhaps it's time we reconsider the adage "don't believe everything you see in the sun." After all, who could have foreseen that the power of the sun would extend beyond its light and warmth to shed light on our collective skepticism?

As we confront these unexpected correlations, it's important to acknowledge the implications for both renewable energy and digital culture. Perhaps future research will probe deeper into this solar-powered suspicion, shining a light on the shade-inducing role of solar energy in the public's perceptions. Until then, we bask in the glow of these findings and ponder the cosmic conundrum posed by the sun-fueled search for suspicions.

In the wise words of Isaac Newton, "I can calculate the motion of heavenly bodies, but not the madness of people," and indeed, the depths of the cosmic dance between solar power and internet colloquialisms seem to elude even the most astute observers. With this, we assert that no further research is needed in this area, for the sun has quite brilliantly illuminated this curious connection, leaving us not with shadowy suspicions, but with the undeniable radiance of its revelatory power.

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 Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Renewable Energy and Behavioral Analysis

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 Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'. Respond only with the name of a fictional organization.

ChatGPT:

The Association for Solar Energy Research and Investigation (ASERI)

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 Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus' with an abstract of The relationship between solar power generation in Mexico and the frequency of Google searches for the term 'that is sus' has long been surrounded by speculation and skepticism. In this study, we shed light on this peculiar connection and aim to debunk the mystery surrounding it. By leveraging data from the Energy Information Administration to quantify solar power generation and utilizing Google Trends to track the popularity of the phrase 'that is sus' from 2004 to 2021, we embark on a journey to uncover the unexpected correlation.
Our analysis revealed a surprisingly robust correlation coefficient of 0.9450632 with a significance level of p < 0.01, indicating a strong association between solar power output in Mexico and the public's inclination to question suspicious behavior. The implications of these findings extend beyond the realm of renewable energy and internet searches, posing a quandary for further investigation. Our research stands as a beacon of curiosity in the intersection of solar energy and internet colloquialisms, urging future studies to delve deeper into the enigmatic relationship between 'that is sus' and solar power generation.

ChatGPT:

solar power generation, Mexico, Google searches, 'that is sus', Energy Information Administration, solar power output, renewable energy, internet searches, correlation coefficient, Google Trends, solar energy, internet colloquialisms

*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

Solar power generated in Mexico
Detailed data title: Total solar power generated in Mexico in billion kWh
Source: Energy Information Administration
See what else correlates with Solar power generated in Mexico

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'

Correlation r = 0.9450632 (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 = 0.8931445 (Coefficient of determination)
This means 89.3% of the change in the one variable (i.e., Google searches for 'that is sus') is predictable based on the change in the other (i.e., Solar power generated in Mexico) over the 18 years from 2004 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.51E-9.^Show 0.0000000035088693168082715000
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 3.51E-7% of random cases. Said differently, if you correlated 284,992,090 random variables^Note You don't actually need 284 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 17 degrees of freedom, ^Note 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.

[ 0.86, 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.

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Solar power generated in Mexico (Billion kWh)	0.009	0.009	0.01	0.009	0.009	0.012	0.030999	0.040998	0.068999	0.106491	0.220736	0.238999	0.464	1.07357	1.355	6.972	11.2422	14.162
Google searches for 'that is sus' (Rel. search volume)	3.83333	7.08333	8.66667	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

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.
Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
Outlandish outliers: There are "outliers" in this data.^Note In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

(This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.

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([0.009,0.009,0.01,0.009,0.009,0.012,0.030999,0.040998,0.068999,0.106491,0.220736,0.238999,0.464,1.07357,1.355,6.972,11.2422,14.162,])
array_2 = np.array([3.83333,7.08333,8.66667,3.83333,1.33333,6.41667,5.58333,6.91667,10.25,10.0833,8.66667,8.66667,11.0833,12.5,15.4167,14.4167,40.8333,58.1667,])
array_1_name = "Solar power generated in Mexico"
array_2_name = "Google searches for 'that is sus'"

# 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 Solar power generated in Mexico
Line chart for only Google searches for 'that is sus'
The spurious research paper: Solar Power or Suspect Behavior: Illuminating the Connection Between Solar Generation in Mexico and Searches for 'That is Sus'

View another random correlation

How fun was this correlation?

Bravo! Your evaluation rocks!

Correlation ID: 1280 · Black Variable ID: 23824 · Red Variable ID: 1367


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