about · email me · subscribe
Spurious correlation #5,690 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air quality in Scranton, Pennsylvania and the second variable is Google searches for 'flights to Antarctica'.  The chart goes from 2004 to 2023, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Well, you see, as the air quality in Scranton improved, it created a ripple effect in the atmosphere. This led to a localized air current enhancement, affectionately known as the "Dunder Mifflin Draft," which just so happened to facilitate more efficient flight paths to Antarctica. Looks like the penguins might have some new tourists waddling their way!

Model: dalle-3
Prompt: Prompt: Generate an image of a cityscape resembling Whiterun in Skyrim, with clear skies and a refreshing breeze. Show an icy continent in the distance, with a group of people excitedly browsing flights. Portray penguins waddling around the city, as if it were natural for them to be there. 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: Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica'. 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: Vaporwave A scene from Skyrim A photo-realistic image Magic realism Woodblock painting
ChatGPT: A scene from Skyrim

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 Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica', in the following situation: Well, you see, as the air quality in Scranton improved, it created a ripple effect in the atmosphere. This led to a localized air current enhancement, affectionately known as the "Dunder Mifflin Draft," which just so happened to facilitate more efficient flight paths to Antarctica. Looks like the penguins might have some new tourists waddling their way!. Keep the description simple.
ChatGPT: The air quality in Scranton, Pennsylvania has significantly improved, and the skies above are clear and bright. A refreshing breeze, known as the "Dunder Mifflin Draft," sweeps through the city. Meanwhile, Google searches for "flights to Antarctica" have spiked, and a group of eager travelers excitedly browse through their options, dreaming of visiting the icy continent. The improved air quality has created a perfect environment for more efficient flight paths, setting the stage for an influx of tourists making their way to Antarctica to meet the penguins.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A scene from Skyrim ] and depicting this scene: The air quality in Scranton, Pennsylvania has significantly improved, and the skies above are clear and bright. A refreshing breeze, known as the "Dunder Mifflin Draft," sweeps through the city. Meanwhile, Google searches for "flights to Antarctica" have spiked, and a group of eager travelers excitedly browse through their options, dreaming of visiting the icy continent. The improved air quality has created a perfect environment for more efficient flight paths, setting the stage for an influx of tourists making their way to Antarctica to meet the penguins. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image of a cityscape resembling Whiterun in Skyrim, with clear skies and a refreshing breeze. Show an icy continent in the distance, with a group of people excitedly browsing flights. Portray penguins waddling around the city, as if it were natural for them to be there.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Air quality in Scranton, Pennsylvania caused flights to Antarctica (Google searches for 'flights to Antarctica') to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)
Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'

The Journal of Zany Atmospheric Research

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title seem clever.

Your research team used data from Environmental Protection Agency and Google Trends to assess this nagging question. You found a correlation coefficient of 0.8437795 and p < 0.01 for 2004 to 2023.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'

[[ABSTRACT]]
In this study, we set out to unravel the peculiar connection between air quality in Scranton, Pennsylvania, and the Google searches for 'flights to Antarctica'. Using data from the Environmental Protection Agency to gauge air quality and Google Trends for search data, our research team dove into the unexpected correlation between these seemingly unrelated phenomena. Our analysis revealed a striking correlation coefficient of 0.8437795 and p < 0.01 over the period from 2004 to 2023.

It turns out that the residents of Scranton, known for their love of "The Office" and a good dad joke, could not resist a chance to seek out a breath of fresh air - quite literally. The findings suggest that as air quality in Scranton deteriorates, interest in seeking alternative, fresher air in Antarctica grows. It appears that the city's residents aren't just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler.

This unexpected connection sheds light on the curious ways in which environmental factors can influence our online behavior and travel aspirations. Our research serves as a gentle reminder that sometimes, the whimsical patterns in data hold equally whimsical truths – and that a flight to Antarctica may just be the breath of fresh air we all need.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'

[[ABSTRACT]]
In this study, we set out to unravel the peculiar connection between air quality in Scranton, Pennsylvania, and the Google searches for 'flights to Antarctica'. Using data from the Environmental Protection Agency to gauge air quality and Google Trends for search data, our research team dove into the unexpected correlation between these seemingly unrelated phenomena. Our analysis revealed a striking correlation coefficient of 0.8437795 and p < 0.01 over the period from 2004 to 2023.

It turns out that the residents of Scranton, known for their love of "The Office" and a good dad joke, could not resist a chance to seek out a breath of fresh air - quite literally. The findings suggest that as air quality in Scranton deteriorates, interest in seeking alternative, fresher air in Antarctica grows. It appears that the city's residents aren't just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler.

This unexpected connection sheds light on the curious ways in which environmental factors can influence our online behavior and travel aspirations. Our research serves as a gentle reminder that sometimes, the whimsical patterns in data hold equally whimsical truths – and that a flight to Antarctica may just be the breath of fresh air we all need.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Air quality has long been a subject of concern for environmental researchers and policymakers, as it has significant implications for human health and well-being. In recent years, the influence of air quality on various aspects of human behavior has garnered increasing attention. Along these lines, our study uncovers a surprising relationship between air quality in Scranton, Pennsylvania, and the frequency of Google searches for 'flights to Antarctica'.

*Dad Joke Alert* Why did the air quality researcher bring a map to the bar? Because he heard the drinks were on the house!

Our investigation stems from the curiosity sparked by the juxtaposition of these seemingly unrelated phenomena. Scranton, recognized for its industrial history and vibrant community, is not typically associated with aspirations of traveling to the icy landscapes of Antarctica. Yet, as we delved into the data, a connection emerged that left us, much like the residents of Scranton, pleasantly surprised.

*Dad Joke Alert* Why do statisticians love Scranton? Because it always keeps them on their toes -- no, seriously, have you seen those correlation coefficients?

The relationship between air quality and the desire to book a flight to Antarctica may seem as unexpected as finding a polar bear in Pennsylvania. However, our rigorous analysis has revealed a remarkably robust correlation, challenging preconceived notions and prompting further inquiry into the underlying factors at play.

*Dad Joke Alert* What do penguins have to do with air quality in Scranton? Well, it turns out they're both flightless birds – of course, one prefers to keep its feet on the ground while the other is busy searching for flights to Antarctica!

In this paper, we present our findings, which illuminate the intricate interplay between environmental conditions and human behavior. Our research not only provides a glimpse into the idiosyncrasies of how air quality influences online search patterns but also underscores the need to consider unconventional connections when studying the impact of environmental factors on human decision-making.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'

[[ABSTRACT]]
In this study, we set out to unravel the peculiar connection between air quality in Scranton, Pennsylvania, and the Google searches for 'flights to Antarctica'. Using data from the Environmental Protection Agency to gauge air quality and Google Trends for search data, our research team dove into the unexpected correlation between these seemingly unrelated phenomena. Our analysis revealed a striking correlation coefficient of 0.8437795 and p < 0.01 over the period from 2004 to 2023.

It turns out that the residents of Scranton, known for their love of "The Office" and a good dad joke, could not resist a chance to seek out a breath of fresh air - quite literally. The findings suggest that as air quality in Scranton deteriorates, interest in seeking alternative, fresher air in Antarctica grows. It appears that the city's residents aren't just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler.

This unexpected connection sheds light on the curious ways in which environmental factors can influence our online behavior and travel aspirations. Our research serves as a gentle reminder that sometimes, the whimsical patterns in data hold equally whimsical truths – and that a flight to Antarctica may just be the breath of fresh air we all need.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Air quality has long been a subject of concern for environmental researchers and policymakers, as it has significant implications for human health and well-being. In recent years, the influence of air quality on various aspects of human behavior has garnered increasing attention. Along these lines, our study uncovers a surprising relationship between air quality in Scranton, Pennsylvania, and the frequency of Google searches for 'flights to Antarctica'.
*Dad Joke Alert* Why did the air quality researcher bring a map to the bar? Because he heard the drinks were on the house!
Our investigation stems from the curiosity sparked by the juxtaposition of these seemingly unrelated phenomena. Scranton, recognized for its industrial history and vibrant community, is not typically associated with aspirations of traveling to the icy landscapes of Antarctica. Yet, as we delved into the data, a connection emerged that left us, much like the residents of Scranton, pleasantly surprised.
*Dad Joke Alert* Why do statisticians love Scranton? Because it always keeps them on their toes -- no, seriously, have you seen those correlation coefficients?
The relationship between air quality and the desire to book a flight to Antarctica may seem as unexpected as finding a polar bear in Pennsylvania. However, our rigorous analysis has revealed a remarkably robust correlation, challenging preconceived notions and prompting further inquiry into the underlying factors at play.
*Dad Joke Alert* What do penguins have to do with air quality in Scranton? Well, it turns out they're both flightless birds – of course, one prefers to keep its feet on the ground while the other is busy searching for flights to Antarctica!
In this paper, we present our findings, which illuminate the intricate interplay between environmental conditions and human behavior. Our research not only provides a glimpse into the idiosyncrasies of how air quality influences online search patterns but also underscores the need to consider unconventional connections when studying the impact of environmental factors on human decision-making.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith et al. shed light on the complex relationship between air quality and human behavior, laying the groundwork for understanding the influence of environmental factors on societal trends. Building on this foundation, Doe and Jones expounded upon the role of air quality in shaping online search patterns, elucidating the subtle yet significant impact of environmental conditions on internet users' interests and aspirations.

In "Air Quality and Online Behavior," the authors find lorem and ipsum.

Turning to the world of non-fiction literature, "The Air We Breathe: A Comprehensive Analysis" and "Antarctica: A Chilling Exploration" provide invaluable insights into the dynamics of air quality and the allure of Antarctica, respectively. These comprehensive works offer a wealth of knowledge, often overlooked by traditional academic circles, yet essential for understanding the quirks of human behavior.

On a more fictional note, "Ice Bound: A Thrilling Adventure" and "Airborne: High-Flying Tales" offer captivating narratives that, while featuring plotlines disconnected from our research focus, evoke the spirit of exploration and the allure of distant, pristine landscapes. These works, while not grounded in empirical evidence, capture the essence of the yearning for unspoiled air and remote destinations, thereby contributing to the broader context of our investigation.

In an unconventional approach to literature review, the researchers took inspiration from a range of sources, including the whimsical musings on old library cards, serendipitously relevant fortune cookie messages, and, yes, even the arcane wisdom hidden within the labyrinthine CVS receipts. Drawing parallels between air quality in Scranton and the inclination to seek flights to Antarctica demanded an open-minded exploration of diverse literature, ensuring a holistic understanding that transcends conventional boundaries.

In "A Study of Antarctic Transportation and Scrantonian Aspirations," the authors find an abundance of levity and an unexpected chuckle.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 Environmental Protection Agency and Google Trends . You used data from 2004 to 2023

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'

[[ABSTRACT]]
In this study, we set out to unravel the peculiar connection between air quality in Scranton, Pennsylvania, and the Google searches for 'flights to Antarctica'. Using data from the Environmental Protection Agency to gauge air quality and Google Trends for search data, our research team dove into the unexpected correlation between these seemingly unrelated phenomena. Our analysis revealed a striking correlation coefficient of 0.8437795 and p < 0.01 over the period from 2004 to 2023.

It turns out that the residents of Scranton, known for their love of "The Office" and a good dad joke, could not resist a chance to seek out a breath of fresh air - quite literally. The findings suggest that as air quality in Scranton deteriorates, interest in seeking alternative, fresher air in Antarctica grows. It appears that the city's residents aren't just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler.

This unexpected connection sheds light on the curious ways in which environmental factors can influence our online behavior and travel aspirations. Our research serves as a gentle reminder that sometimes, the whimsical patterns in data hold equally whimsical truths – and that a flight to Antarctica may just be the breath of fresh air we all need.

[[INTRODUCTION]]
Air quality has long been a subject of concern for environmental researchers and policymakers, as it has significant implications for human health and well-being. In recent years, the influence of air quality on various aspects of human behavior has garnered increasing attention. Along these lines, our study uncovers a surprising relationship between air quality in Scranton, Pennsylvania, and the frequency of Google searches for 'flights to Antarctica'.
*Dad Joke Alert* Why did the air quality researcher bring a map to the bar? Because he heard the drinks were on the house!
Our investigation stems from the curiosity sparked by the juxtaposition of these seemingly unrelated phenomena. Scranton, recognized for its industrial history and vibrant community, is not typically associated with aspirations of traveling to the icy landscapes of Antarctica. Yet, as we delved into the data, a connection emerged that left us, much like the residents of Scranton, pleasantly surprised.
*Dad Joke Alert* Why do statisticians love Scranton? Because it always keeps them on their toes -- no, seriously, have you seen those correlation coefficients?
The relationship between air quality and the desire to book a flight to Antarctica may seem as unexpected as finding a polar bear in Pennsylvania. However, our rigorous analysis has revealed a remarkably robust correlation, challenging preconceived notions and prompting further inquiry into the underlying factors at play.
*Dad Joke Alert* What do penguins have to do with air quality in Scranton? Well, it turns out they're both flightless birds – of course, one prefers to keep its feet on the ground while the other is busy searching for flights to Antarctica!
In this paper, we present our findings, which illuminate the intricate interplay between environmental conditions and human behavior. Our research not only provides a glimpse into the idiosyncrasies of how air quality influences online search patterns but also underscores the need to consider unconventional connections when studying the impact of environmental factors on human decision-making.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Our methodology for investigating the connection between air quality in Scranton, Pennsylvania, and Google searches for 'flights to Antarctica' was as robust and eclectic as the phenomena under study. We drew data on air quality from the Environmental Protection Agency's Air Quality System, encompassing measurements of pollutants such as carbon monoxide, ozone, and particulate matter, spanning the years 2004 to 2023. Google search data for 'flights to Antarctica' was obtained from Google Trends, capturing search interest over the same period.

To ensure the statistical integrity of our analysis, we employed a mix of quantitative and qualitative methods that could rival the diverse personalities of "The Office" characters. We conducted a time series analysis to examine the temporal trends in air quality and search interest, incorporating autoregressive integrated moving average (ARIMA) modeling to account for any potential seasonality or trend effects lurking in the data. This approach allowed us to capture the nuances of both the air quality fluctuations in Scranton and the ebb and flow of the populace's yearning for a frosty escape to Antarctica.

As with any good statistical escapade, the data underwent rigorous preprocessing. We applied data cleaning methods with the fervor of Michael Scott trying to clear the air after a practical joke gone awry, ensuring the removal of any outliers or irregularities that could sway our results like a gust of Antarctic wind.

To assess the relationship between air quality and search interest, we calculated correlation coefficients and conducted Granger causality tests. The former provided insight into the strength and direction of the association, akin to determining if Dwight Schrute and Jim Halpert's antics were positively or negatively correlated in a given episode, while the latter helped untangle the temporal dynamics, indicating whether changes in air quality Granger-cause changes in search interest or vice versa.

Given the unconventional nature of our research inquiry, we also delved into textual analysis of online forums and social media platforms to grasp the sentiments and motivations underlying the residents' fascination with Antarctic getaways. This qualitative exploration added depth to our findings, akin to the nuanced character developments over nine seasons of "The Office" that kept viewers as captivated as a peculiar statistical anomaly.

To ensure the robustness and generalizability of our results, we performed sensitivity analyses and cross-validated our models, likening this meticulous process to Phyllis' unwavering dedication to ensuring that every Scranton White Pages order was delivered flawlessly.

In the spirit of data transparency and reproducibility, our methodology and code for the statistical analyses are made publicly available, inviting others to join in the quirky quest of understanding the interplay between air quality and unconventional travel aspirations.

*Dad Joke Alert* Why did the statistician bring a fan to the data analysis party? He wanted to blow the results away!


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

Please make up the results section of an academic research paper presenting the findings of the connection between Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 Environmental Protection Agency and Google Trends .

For the time period 2004 to 2023, you found a correlation 0.8437795, r-squared of 0.7119638, 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]]
Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'

[[ABSTRACT]]
In this study, we set out to unravel the peculiar connection between air quality in Scranton, Pennsylvania, and the Google searches for 'flights to Antarctica'. Using data from the Environmental Protection Agency to gauge air quality and Google Trends for search data, our research team dove into the unexpected correlation between these seemingly unrelated phenomena. Our analysis revealed a striking correlation coefficient of 0.8437795 and p < 0.01 over the period from 2004 to 2023.

It turns out that the residents of Scranton, known for their love of "The Office" and a good dad joke, could not resist a chance to seek out a breath of fresh air - quite literally. The findings suggest that as air quality in Scranton deteriorates, interest in seeking alternative, fresher air in Antarctica grows. It appears that the city's residents aren't just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler.

This unexpected connection sheds light on the curious ways in which environmental factors can influence our online behavior and travel aspirations. Our research serves as a gentle reminder that sometimes, the whimsical patterns in data hold equally whimsical truths – and that a flight to Antarctica may just be the breath of fresh air we all need.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Air quality has long been a subject of concern for environmental researchers and policymakers, as it has significant implications for human health and well-being. In recent years, the influence of air quality on various aspects of human behavior has garnered increasing attention. Along these lines, our study uncovers a surprising relationship between air quality in Scranton, Pennsylvania, and the frequency of Google searches for 'flights to Antarctica'.
*Dad Joke Alert* Why did the air quality researcher bring a map to the bar? Because he heard the drinks were on the house!
Our investigation stems from the curiosity sparked by the juxtaposition of these seemingly unrelated phenomena. Scranton, recognized for its industrial history and vibrant community, is not typically associated with aspirations of traveling to the icy landscapes of Antarctica. Yet, as we delved into the data, a connection emerged that left us, much like the residents of Scranton, pleasantly surprised.
*Dad Joke Alert* Why do statisticians love Scranton? Because it always keeps them on their toes -- no, seriously, have you seen those correlation coefficients?
The relationship between air quality and the desire to book a flight to Antarctica may seem as unexpected as finding a polar bear in Pennsylvania. However, our rigorous analysis has revealed a remarkably robust correlation, challenging preconceived notions and prompting further inquiry into the underlying factors at play.
*Dad Joke Alert* What do penguins have to do with air quality in Scranton? Well, it turns out they're both flightless birds – of course, one prefers to keep its feet on the ground while the other is busy searching for flights to Antarctica!
In this paper, we present our findings, which illuminate the intricate interplay between environmental conditions and human behavior. Our research not only provides a glimpse into the idiosyncrasies of how air quality influences online search patterns but also underscores the need to consider unconventional connections when studying the impact of environmental factors on human decision-making.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our investigation into the relationship between air quality in Scranton, Pennsylvania, and Google searches for 'flights to Antarctica' yielded captivating results. The statistical analysis revealed a significant correlation coefficient of 0.8437795, indicating a strong positive relationship between these variables. Furthermore, the r-squared value of 0.7119638 suggests that approximately 71.2% of the variability in the frequency of Google searches for flights to Antarctica can be explained by the fluctuations in air quality in Scranton. The observed p-value of less than 0.01 signifies a high level of statistical significance, providing robust evidence for the established correlation.

The striking findings of this study can be visually appreciated in Fig. 1, which portrays a scatterplot depicting the pronounced correlation between air quality in Scranton, Pennsylvania, and Google searches for 'flights to Antarctica'. This compelling visualization further underscores the strength of the identified relationship and emphasizes its statistical significance.

It seems that the residents of Scranton are not just fans of "The Office"; they also appear to possess a keen affinity for clean air and perhaps a penchant for polar adventures. This unexpected connection between air quality and aspirations for distant travel sheds an amusing light on the idiosyncrasies of human behavior in response to environmental factors.

Our research provides a lighthearted yet thought-provoking perspective on the interplay between air quality and online search patterns, offering a gentle reminder of the whimsical truths that can be revealed through statistical analysis. After all, who would have thought that a flight to Antarctica could be the breath of fresh air that many seek?


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'

[[ABSTRACT]]
In this study, we set out to unravel the peculiar connection between air quality in Scranton, Pennsylvania, and the Google searches for 'flights to Antarctica'. Using data from the Environmental Protection Agency to gauge air quality and Google Trends for search data, our research team dove into the unexpected correlation between these seemingly unrelated phenomena. Our analysis revealed a striking correlation coefficient of 0.8437795 and p < 0.01 over the period from 2004 to 2023.

It turns out that the residents of Scranton, known for their love of "The Office" and a good dad joke, could not resist a chance to seek out a breath of fresh air - quite literally. The findings suggest that as air quality in Scranton deteriorates, interest in seeking alternative, fresher air in Antarctica grows. It appears that the city's residents aren't just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler.

This unexpected connection sheds light on the curious ways in which environmental factors can influence our online behavior and travel aspirations. Our research serves as a gentle reminder that sometimes, the whimsical patterns in data hold equally whimsical truths – and that a flight to Antarctica may just be the breath of fresh air we all need.

[[LITERATURE REVIEW]]
In their seminal work, Smith et al. shed light on the complex relationship between air quality and human behavior, laying the groundwork for understanding the influence of environmental factors on societal trends. Building on this foundation, Doe and Jones expounded upon the role of air quality in shaping online search patterns, elucidating the subtle yet significant impact of environmental conditions on internet users' interests and aspirations.
In "Air Quality and Online Behavior," the authors find lorem and ipsum.
Turning to the world of non-fiction literature, "The Air We Breathe: A Comprehensive Analysis" and "Antarctica: A Chilling Exploration" provide invaluable insights into the dynamics of air quality and the allure of Antarctica, respectively. These comprehensive works offer a wealth of knowledge, often overlooked by traditional academic circles, yet essential for understanding the quirks of human behavior.
On a more fictional note, "Ice Bound: A Thrilling Adventure" and "Airborne: High-Flying Tales" offer captivating narratives that, while featuring plotlines disconnected from our research focus, evoke the spirit of exploration and the allure of distant, pristine landscapes. These works, while not grounded in empirical evidence, capture the essence of the yearning for unspoiled air and remote destinations, thereby contributing to the broader context of our investigation.
In an unconventional approach to literature review, the researchers took inspiration from a range of sources, including the whimsical musings on old library cards, serendipitously relevant fortune cookie messages, and, yes, even the arcane wisdom hidden within the labyrinthine CVS receipts. Drawing parallels between air quality in Scranton and the inclination to seek flights to Antarctica demanded an open-minded exploration of diverse literature, ensuring a holistic understanding that transcends conventional boundaries.
In "A Study of Antarctic Transportation and Scrantonian Aspirations," the authors find an abundance of levity and an unexpected chuckle.

[[RESULTS]]
Our investigation into the relationship between air quality in Scranton, Pennsylvania, and Google searches for 'flights to Antarctica' yielded captivating results. The statistical analysis revealed a significant correlation coefficient of 0.8437795, indicating a strong positive relationship between these variables. Furthermore, the r-squared value of 0.7119638 suggests that approximately 71.2% of the variability in the frequency of Google searches for flights to Antarctica can be explained by the fluctuations in air quality in Scranton. The observed p-value of less than 0.01 signifies a high level of statistical significance, providing robust evidence for the established correlation.
The striking findings of this study can be visually appreciated in Fig. 1, which portrays a scatterplot depicting the pronounced correlation between air quality in Scranton, Pennsylvania, and Google searches for 'flights to Antarctica'. This compelling visualization further underscores the strength of the identified relationship and emphasizes its statistical significance.
It seems that the residents of Scranton are not just fans of "The Office"; they also appear to possess a keen affinity for clean air and perhaps a penchant for polar adventures. This unexpected connection between air quality and aspirations for distant travel sheds an amusing light on the idiosyncrasies of human behavior in response to environmental factors.
Our research provides a lighthearted yet thought-provoking perspective on the interplay between air quality and online search patterns, offering a gentle reminder of the whimsical truths that can be revealed through statistical analysis. After all, who would have thought that a flight to Antarctica could be the breath of fresh air that many seek?

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our research indicate a surprisingly strong and statistically significant correlation between air quality in Scranton, Pennsylvania, and Google searches for 'flights to Antarctica'. This peculiar relationship may have raised a few eyebrows, much like a dad joke at a serious academic conference, yet the robust statistical evidence supports the hypothesis that as air quality in Scranton deteriorates, the interest in seeking fresher air in Antarctica increases.

The findings of this study echo the work of Smith et al. and Doe and Jones, who laid the groundwork for understanding the influence of environmental factors, such as air quality, on human behavior. It appears that the residents of Scranton, known for their love of "The Office", are not just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler. It's almost as if they're saying, "I'd rather be cool with penguins than wheezy with air pollution," much to the delight of this, truly unique, statistician.

Our findings also complement the insights from the non-fiction literature "The Air We Breathe: A Comprehensive Analysis" and "Antarctica: A Chilling Exploration", highlighting the unconventional connection between air quality and the allure of pristine landscapes. The statistical analyses poignantly encapsulate the whimsical realities revealed by our data, much like the unexpected chuckle you get when you crack open a fortune cookie finding a relevant dad joke inside.

The strong correlation coefficient and r-squared value support the notion that approximately 71.2% of the variability in Google searches for 'flights to Antarctica' can be explained by the fluctuations in air quality in Scranton. It seems that the quirky musings on old library cards and the unexpected chuckles buried within the literature have brought us to a statistically significant insight - a bit like finding a dad joke in the most unexpected of places.

In conclusion, this study emphasizes the value of taking an open-minded approach to exploring diverse literature, inspiring a lighthearted yet thought-provoking perspective on the interplay between environmental factors and human behavior. After all, who would have thought that a flight to Antarctica could be the breath of fresh air that many seek? It appears that the statistical evidence has spoken, much like a well-timed dad joke - unexpected, yet undeniably amusing.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air quality in Scranton, Pennsylvania and Google searches for 'flights to Antarctica'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'

[[ABSTRACT]]
In this study, we set out to unravel the peculiar connection between air quality in Scranton, Pennsylvania, and the Google searches for 'flights to Antarctica'. Using data from the Environmental Protection Agency to gauge air quality and Google Trends for search data, our research team dove into the unexpected correlation between these seemingly unrelated phenomena. Our analysis revealed a striking correlation coefficient of 0.8437795 and p < 0.01 over the period from 2004 to 2023.

It turns out that the residents of Scranton, known for their love of "The Office" and a good dad joke, could not resist a chance to seek out a breath of fresh air - quite literally. The findings suggest that as air quality in Scranton deteriorates, interest in seeking alternative, fresher air in Antarctica grows. It appears that the city's residents aren't just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler.

This unexpected connection sheds light on the curious ways in which environmental factors can influence our online behavior and travel aspirations. Our research serves as a gentle reminder that sometimes, the whimsical patterns in data hold equally whimsical truths – and that a flight to Antarctica may just be the breath of fresh air we all need.

[[INTRDUCTION]]
Air quality has long been a subject of concern for environmental researchers and policymakers, as it has significant implications for human health and well-being. In recent years, the influence of air quality on various aspects of human behavior has garnered increasing attention. Along these lines, our study uncovers a surprising relationship between air quality in Scranton, Pennsylvania, and the frequency of Google searches for 'flights to Antarctica'.
*Dad Joke Alert* Why did the air quality researcher bring a map to the bar? Because he heard the drinks were on the house!
Our investigation stems from the curiosity sparked by the juxtaposition of these seemingly unrelated phenomena. Scranton, recognized for its industrial history and vibrant community, is not typically associated with aspirations of traveling to the icy landscapes of Antarctica. Yet, as we delved into the data, a connection emerged that left us, much like the residents of Scranton, pleasantly surprised.
*Dad Joke Alert* Why do statisticians love Scranton? Because it always keeps them on their toes -- no, seriously, have you seen those correlation coefficients?
The relationship between air quality and the desire to book a flight to Antarctica may seem as unexpected as finding a polar bear in Pennsylvania. However, our rigorous analysis has revealed a remarkably robust correlation, challenging preconceived notions and prompting further inquiry into the underlying factors at play.
*Dad Joke Alert* What do penguins have to do with air quality in Scranton? Well, it turns out they're both flightless birds – of course, one prefers to keep its feet on the ground while the other is busy searching for flights to Antarctica!
In this paper, we present our findings, which illuminate the intricate interplay between environmental conditions and human behavior. Our research not only provides a glimpse into the idiosyncrasies of how air quality influences online search patterns but also underscores the need to consider unconventional connections when studying the impact of environmental factors on human decision-making.

[[RESULTS]]
Our investigation into the relationship between air quality in Scranton, Pennsylvania, and Google searches for 'flights to Antarctica' yielded captivating results. The statistical analysis revealed a significant correlation coefficient of 0.8437795, indicating a strong positive relationship between these variables. Furthermore, the r-squared value of 0.7119638 suggests that approximately 71.2% of the variability in the frequency of Google searches for flights to Antarctica can be explained by the fluctuations in air quality in Scranton. The observed p-value of less than 0.01 signifies a high level of statistical significance, providing robust evidence for the established correlation.
The striking findings of this study can be visually appreciated in Fig. 1, which portrays a scatterplot depicting the pronounced correlation between air quality in Scranton, Pennsylvania, and Google searches for 'flights to Antarctica'. This compelling visualization further underscores the strength of the identified relationship and emphasizes its statistical significance.
It seems that the residents of Scranton are not just fans of "The Office"; they also appear to possess a keen affinity for clean air and perhaps a penchant for polar adventures. This unexpected connection between air quality and aspirations for distant travel sheds an amusing light on the idiosyncrasies of human behavior in response to environmental factors.
Our research provides a lighthearted yet thought-provoking perspective on the interplay between air quality and online search patterns, offering a gentle reminder of the whimsical truths that can be revealed through statistical analysis. After all, who would have thought that a flight to Antarctica could be the breath of fresh air that many seek?

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study unravels the extraordinary correlation between air quality in Scranton, Pennsylvania, and the frequency of Google searches for 'flights to Antarctica', shedding light on the delightful whims of human behavior in response to environmental conditions. The findings of our research not only emphasize the unexpected connection between these seemingly unrelated phenomena but also underscore the need to approach data analysis with an open mind, ready to embrace the quirky truths it reveals.

*Did you hear about the statistician who went on a flight to Antarctica? He wanted to see if the penguin population correlated with passenger numbers -- talk about a flight of fancy!*

The robust correlation coefficient of 0.8437795, coupled with a remarkable r-squared value of 0.7119638, signifies a substantial relationship between air quality and the desire to embark on an Antarctic adventure. Our findings, depicted eloquently in Fig. 1, also serve as a whimsical reminder that sometimes, the most enchanting patterns emerge from the most unexpected pairings.

*Why was the statistical model cold during the flight to Antarctica? It couldn't handle the chilling effect of the correlation!*

As the residents of Scranton display a keen proclivity for not only clean air but also remote polar escapades, our research suggests a charming tale of human curiosity and the pursuit of pristine environments. It appears that a breath of fresh air is not only sought after in Scranton but also in the remote landscape of Antarctica, highlighting the intriguing ways in which environmental conditions shape our aspirations and online search patterns.

*Why don't penguins like talking to statisticians? They always try to calculate the odds of a flightless bird finding a flight to Antarctica!*

With these compelling findings in mind, our investigation presents a memorable case of the captivating discoveries that arise from embracing the unexpected connections within our data. Additionally, our light-hearted analysis serves as a gentle yet poignant nudge to the broader research community, highlighting the serendipitous insights waiting to be uncovered in the quirks of human behavior and environmental influences.

In light of these resonant revelations, it is safe to assert that no further research is needed in this area. As our study has gracefully demonstrated, sometimes the most astonishing truths emerge when we dare to explore the whimsical and unforeseen avenues of statistical inquiry.


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 Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Zany Atmospheric 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 Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica'. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Atmospheric Research


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 Flying South for Clean Air: The Quirky Relationship Between Air Quality in Scranton, Pennsylvania and Google Searches for 'Flights to Antarctica' with an abstract of In this study, we set out to unravel the peculiar connection between air quality in Scranton, Pennsylvania, and the Google searches for 'flights to Antarctica'. Using data from the Environmental Protection Agency to gauge air quality and Google Trends for search data, our research team dove into the unexpected correlation between these seemingly unrelated phenomena. Our analysis revealed a striking correlation coefficient of 0.8437795 and p < 0.01 over the period from 2004 to 2023.
It turns out that the residents of Scranton, known for their love of "The Office" and a good dad joke, could not resist a chance to seek out a breath of fresh air - quite literally. The findings suggest that as air quality in Scranton deteriorates, interest in seeking alternative, fresher air in Antarctica grows. It appears that the city's residents aren't just in pursuit of penguins and chill vibes; they also have a keen eye for clean air, much like any responsible air-traveler.
This unexpected connection sheds light on the curious ways in which environmental factors can influence our online behavior and travel aspirations. Our research serves as a gentle reminder that sometimes, the whimsical patterns in data hold equally whimsical truths – and that a flight to Antarctica may just be the breath of fresh air we all need.

ChatGPT:

air quality, Scranton Pennsylvania, Google searches, flights to Antarctica, correlation, environmental factors, online behavior, travel aspirations

*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

Air quality in Scranton, Pennsylvania
Detailed data title: Percentage of days with good air quality in Scranton--Wilkes-Barre--Hazleton, PA
Source: Environmental Protection Agency
See what else correlates with Air quality in Scranton, Pennsylvania

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

See what else correlates with Google searches for 'flights to Antarctica'

Correlation r = 0.8437795 (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 = 0.7119638 (Coefficient of determination)
This means 71.2% of the change in the one variable (i.e., Google searches for 'flights to Antarctica') is predictable based on the change in the other (i.e., Air quality in Scranton, Pennsylvania) over the 20 years from 2004 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.9E-6. 0.0000029420582121130960000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.84 in 0.00029% of random cases. Said differently, if you correlated 339,898 random variables You don't actually need 339 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 19 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.64, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
20042005200620072008200920102011201220132014201520162017201820192020202120222023
Air quality in Scranton, Pennsylvania (Good air quality)55.464547.397362.739763.287765.84770.684967.945272.602771.311574.246671.232965.479579.23578.082282.191890.13789.617583.146186.027480.7377
Google searches for 'flights to Antarctica' (Rel. search volume)11.16677.8333319.916713.083316.083313.7517.416715.583318.2518.666717.833322.2525.166731.535.416734.2528.416721.333329.416728.7




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([55.4645,47.3973,62.7397,63.2877,65.847,70.6849,67.9452,72.6027,71.3115,74.2466,71.2329,65.4795,79.235,78.0822,82.1918,90.137,89.6175,83.1461,86.0274,80.7377,])
array_2 = np.array([11.1667,7.83333,19.9167,13.0833,16.0833,13.75,17.4167,15.5833,18.25,18.6667,17.8333,22.25,25.1667,31.5,35.4167,34.25,28.4167,21.3333,29.4167,28.7,])
array_1_name = "Air quality in Scranton, Pennsylvania"
array_2_name = "Google searches for 'flights to Antarctica'"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating is stellar!


Correlation ID: 5690 · Black Variable ID: 21247 · Red Variable ID: 1373
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0