Spurious correlation #1,601 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Biomass power generated in Serbia and the second variable is Google searches for 'i am dizzy'. The chart goes from 2012 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 Biomass power generated in Serbia and the second variable is Google searches for 'i am dizzy'. The chart goes from 2012 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The excessive spinning of the biomass turbines in Serbia is creating a secret wave of dizziness that is being transmitted through the internet, causing people worldwide to frantically search for 'i am dizzy' as they unknowingly tune into this bio-energetic sensation. It's a renewable energy revolution with an unexpected side effect - a global case of the twirlies!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a serene countryside in Serbia with a high-tech twist. In the background, a modern power plant emits billowing steam as it harnesses biomass for electricity. In the foreground, a person is seated at a computer, their face expressing urgency as they frantically type "i am dizzy" into the Google search bar. The juxtaposition of traditional rural scenery and advanced technology should be evident, conveying a sense of urgency and the intersection of modern life and nature. 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: Biomass power generated in Serbia and Google searches for 'i am dizzy'. 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: Cyberpunk Cybernetic art A Discovery magazine cover image A Discovery magazine cover image High-tech
ChatGPT: High-tech

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 Biomass power generated in Serbia and Google searches for 'i am dizzy' together. Keep the description simple.
ChatGPT: In the countryside of Serbia, a power plant emits steam as it burns biomass to generate electricity. Nearby, a person sits in front of a computer, frantically typing "i am dizzy" into the google search bar.

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: [ High-tech ] and depicting this scene: In the countryside of Serbia, a power plant emits steam as it burns biomass to generate electricity. Nearby, a person sits in front of a computer, frantically typing "i am dizzy" into the google search bar. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a serene countryside in Serbia with a high-tech twist. In the background, a modern power plant emits billowing steam as it harnesses biomass for electricity. In the foreground, a person is seated at a computer, their face expressing urgency as they frantically type "i am dizzy" into the Google search bar. The juxtaposition of traditional rural scenery and advanced technology should be evident, conveying a sense of urgency and the intersection of modern life and nature.

*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 Biomass power generated in Serbia caused i am dizzy (Google searches for 'i am dizzy') to increase.

AI academic paper

(Because p < 0.01)

The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy'

Journal of Quirky Neurological 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 Biomass power generated in Serbia and Google searches for 'i am dizzy'. 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
"The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy'"

[[ABSTRACT]]
This paper investigates the unexpected relationship between Biomass power generation in Serbia and the frequency of Google searches for the phrase "I am dizzy." Leveraging data from the Energy Information Administration and Google Trends, our research team sought to shed light on this quirky connection. Unearthing a correlation coefficient of 0.9878804 and p < 0.01 during the time span from 2012 to 2021, our findings suggest an intriguing association that warrants further investigation and perhaps a little dizziness of our own as we contemplate the mysteries of biomass energy and human perception.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The link between environmental factors and human behavior has long been a subject of fascination and inquiry. This study delves into the curious relationship between the production of Biomass power in Serbia and the curious phenomenon of Google searches for the phrase "I am dizzy." While seemingly disparate at first glance, there exists a peculiar association between these two seemingly unrelated variables. Perhaps it's a sign that even in the most unexpected places, a twirl of correlation can be found.
Biomass power, derived from organic materials such as wood, crops, and waste, has gained increasing attention as a renewable energy source in recent years. Serbia, with its dedication to sustainable energy technologies, has been a focal point for biomass power generation. Meanwhile, the phrase "I am dizzy" has cropped up sporadically in Google searches, prompting our curiosity to spin in the direction of this unexpected query.
The aim of this study is to unravel the dizzying conundrum that connects the production of Biomass power in Serbia with the sensation of dizziness that prompts individuals to seek solace in the arms of the Google search bar. As we twirl our way through the findings of this investigation, we shall attempt to navigate the labyrinth of associations and counterintuitive relationships with the grace of a synchronized dancer. In doing so, we hope to shed light on the intricate interplay between renewable energy and the quirks of human cognition.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The authors find that the examination of the interplay between Biomass power generation in Serbia and Google searches for "I am dizzy" has not been extensively addressed in the academic literature. However, several studies have explored the influence of environmental factors on human behavior, providing a suitable foundation for our investigation.

Smith et al. (2015) delve into the psychological impact of renewable energy sources, highlighting the potential for cognitive dissonance when individuals encounter novel forms of sustainable power. Doe and Jones (2018) investigate the physiological effects of exposure to biomass-related activities, offering insights into the potential connections between environmental stimuli and sensory perception.

Turning to the realm of non-fiction literature, "Energy Transitions: Global and National Perspectives" by Brown and Green (2017) and "The Biomass Revolution" by Wood (2016) offer comprehensive analyses of biomass energy production and its implications for the environment and society. These works serve as valuable references for contextualizing the peculiar relationship between Biomass power and dizziness.

On the fictional front, "The Dizzying Heights" by Summit (2019) and "A Spinning Adventure" by Turner (2020) evoke themes of disorientation and surprise, mirroring the unexpected nature of the Biomass-Google search association. While strictly works of fiction, these books inadvertently offer a metaphorical lens through which to approach our investigation.

In a slightly less conventional approach, the researchers also consulted an array of unconventional sources, including the backs of shampoo bottles found in various laboratory bathrooms. Though not scholarly in nature, these texts demonstrate the vast reach of our literature review and serve as a lighthearted reminder of the unexpected places where inspiration can be found.

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 Biomass power generated in Serbia and Google searches for 'i am dizzy'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 2012 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]]
"The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy'"

[[ABSTRACT]]
This paper investigates the unexpected relationship between Biomass power generation in Serbia and the frequency of Google searches for the phrase "I am dizzy." Leveraging data from the Energy Information Administration and Google Trends, our research team sought to shed light on this quirky connection. Unearthing a correlation coefficient of 0.9878804 and p < 0.01 during the time span from 2012 to 2021, our findings suggest an intriguing association that warrants further investigation and perhaps a little dizziness of our own as we contemplate the mysteries of biomass energy and human perception.

[[INTRODUCTION]]
The link between environmental factors and human behavior has long been a subject of fascination and inquiry. This study delves into the curious relationship between the production of Biomass power in Serbia and the curious phenomenon of Google searches for the phrase "I am dizzy." While seemingly disparate at first glance, there exists a peculiar association between these two seemingly unrelated variables. Perhaps it's a sign that even in the most unexpected places, a twirl of correlation can be found.
Biomass power, derived from organic materials such as wood, crops, and waste, has gained increasing attention as a renewable energy source in recent years. Serbia, with its dedication to sustainable energy technologies, has been a focal point for biomass power generation. Meanwhile, the phrase "I am dizzy" has cropped up sporadically in Google searches, prompting our curiosity to spin in the direction of this unexpected query.
The aim of this study is to unravel the dizzying conundrum that connects the production of Biomass power in Serbia with the sensation of dizziness that prompts individuals to seek solace in the arms of the Google search bar. As we twirl our way through the findings of this investigation, we shall attempt to navigate the labyrinth of associations and counterintuitive relationships with the grace of a synchronized dancer. In doing so, we hope to shed light on the intricate interplay between renewable energy and the quirks of human cognition.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The data for this research was collected from two primary sources: the Energy Information Administration for information on Biomass power generation in Serbia and Google Trends for the frequency of searches for the phrase "I am dizzy." The time span for data collection ranged from 2012 to 2021, allowing for a comprehensive analysis of the relationship between these variables.

To establish a clear understanding of Biomass power generation in Serbia, data on electricity production from Biomass sources was extracted from the Energy Information Administration database. This information was then collated and organized to discern patterns and trends in Biomass power output over the specified time period. The primary challenge in this process was navigating through the abundant data to separate the wood from the trees, so to speak, in order to derive meaningful insights.

Simultaneously, the frequency of Google searches for the phrase "I am dizzy" was scrutinized using Google Trends. The search interest over time, regional interest, and related queries were examined to gain a nuanced understanding of the variations and peaks in searches related to dizziness. One could say that this part of the analysis left us feeling slightly lightheaded, navigating through the swirling vortex of search data to pinpoint the moments of peak dizziness-related query activity.

Once the datasets were compiled, the next step involved performing a correlation analysis to ascertain the potential relationship between Biomass power generation and the frequency of "I am dizzy" searches. The Pearson correlation coefficient was calculated, accompanied by a significance test to determine whether any observed association was statistically robust. It's safe to say that this stage had us feeling a bit dizzy ourselves, as we grappled with the intricacies of statistical analysis.

Additionally, to account for potential confounding variables, multivariate regression analysis was conducted to control for other factors that may influence dizziness-related search behavior. This step allowed us to spin through the data with a clearer understanding of how Biomass power generation specifically may be linked to the dizzying searches that crop up on Google.

In summary, the methodology employed in this study balanced thorough data collection and analysis with a touch of humor, as we navigated through the intricacies of Biomass power generation and the enigmatic patterns of online search behavior.

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 Biomass power generated in Serbia and Google searches for 'i am dizzy'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy'"

[[ABSTRACT]]
This paper investigates the unexpected relationship between Biomass power generation in Serbia and the frequency of Google searches for the phrase "I am dizzy." Leveraging data from the Energy Information Administration and Google Trends, our research team sought to shed light on this quirky connection. Unearthing a correlation coefficient of 0.9878804 and p < 0.01 during the time span from 2012 to 2021, our findings suggest an intriguing association that warrants further investigation and perhaps a little dizziness of our own as we contemplate the mysteries of biomass energy and human perception.

[[LITERATURE REVIEW]]
The authors find that the examination of the interplay between Biomass power generation in Serbia and Google searches for "I am dizzy" has not been extensively addressed in the academic literature. However, several studies have explored the influence of environmental factors on human behavior, providing a suitable foundation for our investigation.
Smith et al. (2015) delve into the psychological impact of renewable energy sources, highlighting the potential for cognitive dissonance when individuals encounter novel forms of sustainable power. Doe and Jones (2018) investigate the physiological effects of exposure to biomass-related activities, offering insights into the potential connections between environmental stimuli and sensory perception.
Turning to the realm of non-fiction literature, "Energy Transitions: Global and National Perspectives" by Brown and Green (2017) and "The Biomass Revolution" by Wood (2016) offer comprehensive analyses of biomass energy production and its implications for the environment and society. These works serve as valuable references for contextualizing the peculiar relationship between Biomass power and dizziness.
On the fictional front, "The Dizzying Heights" by Summit (2019) and "A Spinning Adventure" by Turner (2020) evoke themes of disorientation and surprise, mirroring the unexpected nature of the Biomass-Google search association. While strictly works of fiction, these books inadvertently offer a metaphorical lens through which to approach our investigation.
In a slightly less conventional approach, the researchers also consulted an array of unconventional sources, including the backs of shampoo bottles found in various laboratory bathrooms. Though not scholarly in nature, these texts demonstrate the vast reach of our literature review and serve as a lighthearted reminder of the unexpected places where inspiration can be found.

[[RESULTS]]
The statistical analysis of the data revealed a strong positive correlation between Biomass power generated in Serbia and Google searches for the phrase "I am dizzy." The correlation coefficient of 0.9878804 indicates a remarkably robust relationship between these two seemingly disparate variables. Further bolstering the strength of this association, the coefficient of determination (r-squared) was calculated to be 0.9759077, revealing that approximately 97.5% of the variability in Google searches for "I am dizzy" can be explained by the variability in Biomass power generation in Serbia. The obtained p-value of < 0.01 indicates that the observed correlation is statistically significant, dismissing the possibility that this correlation is due to mere chance or random fluctuations.
The strength and significance of the relationship between Biomass power generation in Serbia and Google searches for "I am dizzy" are graphically depicted in Figure 1. The scatterplot exhibits a tight clustering of data points, illustrating the compelling alignment between the two variables. The figure provides a visual testimony to the dizzying intertwine between biomass power and human sensation, sure to set one's head spinning with contemplation.
The unexpected nature of this correlation invites further speculation and inquiry. While the precise mechanisms underlying this connection remain shrouded in ambiguity, the findings prompt speculation on how environmental factors, such as the production of renewable energy, may sway the public's proclivity to seek answers to their equilibrium-related dilemmas through the digital realm. This association may be spinning a tale of its own, giving new meaning to the phrase "power of biomass" and leaving us all a little dizzy with curiosity.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The revelation of a significant correlation between Biomass power generation in Serbia and searches for "I am dizzy" on Google presents a dizzying array of intriguing questions for further investigation. These findings substantiate earlier research that has explored the influence of environmental stimuli on human perception. Smith et al. (2015) pointed to the potential for cognitive dissonance when individuals encounter novel forms of sustainable power, mirroring the disorientation expressed through Google searches for dizziness. Similarly, Doe and Jones (2018) shed light on the physiological effects of exposure to biomass-related activities, providing a tangible link to the sensory perception reflected in these digital queries.

Delving into less traditional sources, our notably unconventional investigation drew inspiration from the lighthearted musings found on the backs of shampoo bottles, hinting at the unexpected places where scholarly insight can be found. This multidisciplinary approach, albeit with a wry smile, underlines the breadth of perspectives that enrich our exploration of the Biomass-Google connection.

The remarkably robust correlation coefficient of 0.9878804 and the coefficient of determination (r-squared) of 0.9759077 reinforce the strength and explanatory power of the relationship between Biomass power and Google searches for dizziness. The p-value of < 0.01 consolidates this association, dismissing the notion that the dizzying alignment of these variables is a product of happenstance.

The compelling scatterplot in Figure 1 encapsulates the tight clustering of data points, visually attesting to the captivating interplay between biomass power and human sensation. The juxtaposition of these seemingly incongruous factors serves as a poignant reminder of the unexpected twists and turns that research can take, leaving even seasoned scholars a little dizzy with the sheer complexity of the world around us. This unexpected correlation, veiled in ambiguity, invites a degree of speculation and encourages further investigation into the mechanisms underlying this peculiar connection.

The enigmatic dance between Biomass power in Serbia and Google searches for "I am dizzy" may well be indicative of a rich narrative woven by environmental influences and human behavior, spinning a tale that captures the essence of the phrase "power of biomass" in an entirely new light. These findings prompt a spirited curiosity, reminding us that within the seemingly mundane lies a world of intrigue and unexpected connections, leaving us all a little dizzy with the thrill of discovery.

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 Biomass power generated in Serbia and Google searches for 'i am dizzy'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy'"

[[ABSTRACT]]
This paper investigates the unexpected relationship between Biomass power generation in Serbia and the frequency of Google searches for the phrase "I am dizzy." Leveraging data from the Energy Information Administration and Google Trends, our research team sought to shed light on this quirky connection. Unearthing a correlation coefficient of 0.9878804 and p < 0.01 during the time span from 2012 to 2021, our findings suggest an intriguing association that warrants further investigation and perhaps a little dizziness of our own as we contemplate the mysteries of biomass energy and human perception.

[[INTRDUCTION]]
The link between environmental factors and human behavior has long been a subject of fascination and inquiry. This study delves into the curious relationship between the production of Biomass power in Serbia and the curious phenomenon of Google searches for the phrase "I am dizzy." While seemingly disparate at first glance, there exists a peculiar association between these two seemingly unrelated variables. Perhaps it's a sign that even in the most unexpected places, a twirl of correlation can be found.
Biomass power, derived from organic materials such as wood, crops, and waste, has gained increasing attention as a renewable energy source in recent years. Serbia, with its dedication to sustainable energy technologies, has been a focal point for biomass power generation. Meanwhile, the phrase "I am dizzy" has cropped up sporadically in Google searches, prompting our curiosity to spin in the direction of this unexpected query.
The aim of this study is to unravel the dizzying conundrum that connects the production of Biomass power in Serbia with the sensation of dizziness that prompts individuals to seek solace in the arms of the Google search bar. As we twirl our way through the findings of this investigation, we shall attempt to navigate the labyrinth of associations and counterintuitive relationships with the grace of a synchronized dancer. In doing so, we hope to shed light on the intricate interplay between renewable energy and the quirks of human cognition.

[[RESULTS]]
The statistical analysis of the data revealed a strong positive correlation between Biomass power generated in Serbia and Google searches for the phrase "I am dizzy." The correlation coefficient of 0.9878804 indicates a remarkably robust relationship between these two seemingly disparate variables. Further bolstering the strength of this association, the coefficient of determination (r-squared) was calculated to be 0.9759077, revealing that approximately 97.5% of the variability in Google searches for "I am dizzy" can be explained by the variability in Biomass power generation in Serbia. The obtained p-value of < 0.01 indicates that the observed correlation is statistically significant, dismissing the possibility that this correlation is due to mere chance or random fluctuations.
The strength and significance of the relationship between Biomass power generation in Serbia and Google searches for "I am dizzy" are graphically depicted in Figure 1. The scatterplot exhibits a tight clustering of data points, illustrating the compelling alignment between the two variables. The figure provides a visual testimony to the dizzying intertwine between biomass power and human sensation, sure to set one's head spinning with contemplation.
The unexpected nature of this correlation invites further speculation and inquiry. While the precise mechanisms underlying this connection remain shrouded in ambiguity, the findings prompt speculation on how environmental factors, such as the production of renewable energy, may sway the public's proclivity to seek answers to their equilibrium-related dilemmas through the digital realm. This association may be spinning a tale of its own, giving new meaning to the phrase "power of biomass" and leaving us all a little dizzy with curiosity.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation has brought to light the surprising association between Biomass power generation in Serbia and the frequency of Google searches for the phrase "I am dizzy." The remarkable correlation coefficient of 0.9878804, coupled with a p-value of < 0.01, underscores the strength and statistical significance of this connection. The findings of this study not only unveil an unexpected link between renewable energy and human sensory experiences but also prompt wry smiles and a few bemused headshakes as we contemplate the intricacies of the world around us.

The interplay between biomass power and the human sensation of dizziness opens the door to a myriad of speculative avenues. Perhaps the burgeoning enthusiasm for renewable energy sources in Serbia has inadvertently set heads spinning, leading individuals to seek solace in the virtual embrace of the Google search bar. The visual depiction of the robust correlation in Figure 1 serves as a palpable reminder that in the realm of scientific inquiry, one can often find oneself on a dizzying dance floor of unexpected connections.

While our findings shed light on this peculiar correlation, the underlying mechanisms and causal pathways remain enigmatic, inviting further research and scholarly conjecture. Nevertheless, the inherently whimsical nature of this association serves as a lighthearted reminder that even in the realm of scientific inquiry, there is always room for playful contemplation and a touch of amusement.

In light of the undeniable correlation and the enigmatic allure of this interconnection, we must assert that no further research is needed in this area, as the results of this study decisively demystify the dizzying relationship between Biomass power generation in Serbia and the curious phrase "I am dizzy." However, we encourage future researchers to approach their inquiries with a twirl of curiosity and an appetite for unexpected connections, for who knows what else may be waiting to be discovered in the whimsical dance of scientific investigation.

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 The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy'. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Neurological 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 The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy'. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Sustainable Bioenergy Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy' with an abstract of This paper investigates the unexpected relationship between Biomass power generation in Serbia and the frequency of Google searches for the phrase "I am dizzy." Leveraging data from the Energy Information Administration and Google Trends, our research team sought to shed light on this quirky connection. Unearthing a correlation coefficient of 0.9878804 and p < 0.01 during the time span from 2012 to 2021, our findings suggest an intriguing association that warrants further investigation and perhaps a little dizziness of our own as we contemplate the mysteries of biomass energy and human perception.

ChatGPT:

Biomass power generation, Serbia, Google searches, "I am dizzy", correlation coefficient, Energy Information Administration, Google Trends, association, human perception, Biomass energy, Serbia, power generation, Google, correlation analysis, renewable energy, dizzy, dizziness, search frequency, internet searches

*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

Biomass power generated in Serbia
Detailed data title: Total biomass power generated in Serbia in billion kWh
Source: Energy Information Administration
See what else correlates with Biomass power generated in Serbia

Google searches for 'i am dizzy'
Detailed data title: Relative volume of Google searches for 'i am dizzy' (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 'i am dizzy'

Correlation r = 0.9878804 (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 = 0.9759077 (Coefficient of determination)
This means 97.6% of the change in the one variable (i.e., Google searches for 'i am dizzy') is predictable based on the change in the other (i.e., Biomass power generated in Serbia) over the 10 years from 2012 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 9.3E-8.^Show 0.0000000930250612141917600000
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 0.99 in 9.3E-6% of random cases. Said differently, if you correlated 10,749,791 random variables^Note You don't actually need 10 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 9 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 9 because we have two variables measured over a period of 10 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.

[ 0.95, 1 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Biomass power generated in Serbia (Billion kWh)	0.007	0.021	0.025	0.027	0.038	0.079	0.107	0.144	0.183	0.224337
Google searches for 'i am dizzy' (Rel. search volume)	38.4167	40.4167	41.9167	43.1667	43.0833	48.9167	52.8333	61.5	75.3333	80.5

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.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.007,0.021,0.025,0.027,0.038,0.079,0.107,0.144,0.183,0.224337,])
array_2 = np.array([38.4167,40.4167,41.9167,43.1667,43.0833,48.9167,52.8333,61.5,75.3333,80.5,])
array_1_name = "Biomass power generated in Serbia"
array_2_name = "Google searches for 'i am dizzy'"

# 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 Biomass power generated in Serbia
Line chart for only Google searches for 'i am dizzy'
AI-generated correlation image
The spurious research paper: The Power of Biomass: A Spin on Google Searches for 'I Am Dizzy'

View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!

Correlation ID: 1601 · Black Variable ID: 23957 · Red Variable ID: 1401


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