Spurious correlation #3,610 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Columbus, Georgia and the second variable is ING Groep's stock price (ING). The chart goes from 2002 to 2023, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Columbus, Georgia and the second variable is ING Groep's stock price (ING). The chart goes from 2002 to 2023, and the two variables track closely in value over that time.

AI explanation

As air pollution in Columbus, Georgia increased, people started buying more air purifiers, leading to a surge in electricity demand. This caused a spike in the need for loans to fund power projects, benefiting ING Groep. You could say ING's stock price was truly electrifying, riding the smoggy wave to financial success!

^{Show image generation prompt} Model: dalle-3
Prompt: "Generate an image showing a cityscape in Columbus, Georgia with a hazy sky due to air pollution. People are wearing masks while going about their daily activities. A large screen displays the stock ticker for ING Groep (ING), showing a steady increase in value. The scene illustrates the juxtaposition of polluted air and rising pharmaceutical stock price." 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 pollution in Columbus, Georgia and ING Groep's stock price (ING). 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: Cybernetic art Cyber folk a funny image macro An image that looks like it is a scene from a Pixar movie Charcoal
ChatGPT: Air pollution in Columbus, Georgia

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 pollution in Columbus, Georgia and ING Groep's stock price (ING), in the following situation: Because as air pollution in Columbus, Georgia increased, respiratory health deteriorated, causing a surge in demand for pharmaceuticals, which ING Groep happened to have invested in heavily. This increased demand led to a boost in the company's stock price as sales of their medical products soared, proving that sometimes, dirty air can lead to clean profits.. Keep the description simple.
ChatGPT: In Columbus, Georgia, the sky is hazy with air pollution, and people are seen wearing masks while going about their daily activities due to the deteriorating respiratory health. Amidst this, the stock ticker for ING Groep (ING) is displayed on a large screen, steadily climbing as the demand for pharmaceuticals surges. The juxtaposition of the polluted air and the rising stock price of ING Groep illustrates how dirty air can lead to clean profits for the company.

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: [ Air pollution in Columbus, Georgia ] and depicting this scene: In Columbus, Georgia, the sky is hazy with air pollution, and people are seen wearing masks while going about their daily activities due to the deteriorating respiratory health. Amidst this, the stock ticker for ING Groep (ING) is displayed on a large screen, steadily climbing as the demand for pharmaceuticals surges. The juxtaposition of the polluted air and the rising stock price of ING Groep illustrates how dirty air can lead to clean profits for the company. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: "Generate an image showing a cityscape in Columbus, Georgia with a hazy sky due to air pollution. People are wearing masks while going about their daily activities. A large screen displays the stock ticker for ING Groep (ING), showing a steady increase in value. The scene illustrates the juxtaposition of polluted air and rising pharmaceutical stock price."

*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 increases in Air pollution in Columbus, Georgia positively influenced ING Groep's stock price (ING). Include one good pun.

AI academic paper

(Because p < 0.01)

When Air Pollution Floats, ING Groep's Stock Drowns: A Tale of Columbus, Georgia

The Journal of Environmental Economics and Humor

Jan 2024

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Columbus, Georgia and ING Groep's stock price (ING). 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
When Air Pollution Floats, ING Groep's Stock Drowns: A Tale of Columbus, Georgia

[[ABSTRACT]]
In this paper, we embark on a whimsical journey to explore the unexpected connection between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING). We took a deep dive into the data from the Environmental Protection Agency and LSEG Analytics (Refinitiv) to assess this mysterious relationship, and the findings are nothing to sneeze at.

After tirelessly crunching the numbers, we uncovered a correlation coefficient of 0.8753081 and p < 0.01 for the time period spanning from 2002 to 2023. It's like these variables are joined at the hip, or should I say, smog-filled lungs?

Our analysis revealed that as air pollution levels in Columbus, Georgia soared, the stock price of ING Groep took a nosedive. It seems like the market doesn't take too kindly to the idea of a polluted atmosphere. Perhaps investors had trouble seeing through the haze?

So, next time you're thinking of investing in ING, it might be worth keeping an eye on the air quality in Columbus. After all, a breath of fresh air could do wonders for your portfolio - both literally and figuratively.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the great bard Shakespeare once wrote, "What's in a polluted air that can affect a stock's price?" Well, dear readers, in this paper we aim to unravel the fascinating connection between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING). This unlikely duo has captured our attention, and with it, we hope to shed some light on the unexpected influence of air quality on financial markets.
Now, don't hold your breath, but we've uncovered some compelling evidence that might just take your breath away – pun intended. It turns out, as air pollution levels in Columbus, Georgia rose, the stock price of ING Groep fell faster than a leaf blower in a hurricane. It's like Mother Nature is pulling the strings of the stock market, orchestrating a drama of epic proportions, with smog as the villain.
But before we dive into the nitty-gritty of our research findings, let's take a moment to appreciate the sheer audacity of this unlikely correlation. Air pollution and stock prices – an odd couple indeed. It's almost as if the financial markets are in a tumultuous relationship with the environment, and Columbus, Georgia becomes the stage for their dirty dancing.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "The Impact of Air Pollution on Stock Prices" by Smith et al., the authors find a positive correlation between air pollution levels and negative movements in stock prices. They suggest that investors may respond negatively to news regarding increased pollution levels, leading to a decrease in stock prices. This aligns with our findings, highlighting the tangible impact of air pollution on financial markets. It's like the stock market is holding its breath, waiting for a breath of fresh air!

Doe and Jones, in "The Economics of Environmental Factors on Stock Performance," delve into the relationship between environmental factors and stock performance. Their research reveals that companies located in areas with high pollution levels may experience adverse effects on their stock prices. It's as if the smog isn't just clouding the skies, but also the financial outlook for these companies.

Turning to non-fiction sources, "Pollution and Profit: The Impact of Environmental Conditions on Financial Markets" presents an in-depth analysis of how environmental conditions, including air pollution, can affect the valuation of companies. The authors argue that investors are becoming increasingly attuned to the environmental practices of firms, and the level of pollution in their operating areas. It's almost as if the market is saying, "Clean up your act, or we'll clean out our portfolios!"

Now, let's shed some light on some fictional sources that are surprisingly relevant to our investigation. "The Polluted Portfolio" by Jackson Greene may not actually exist, but in an alternate universe, it could surely spin a tale of intrigue and suspense, where air pollution plays a central role in the ups and downs of stock prices. Maybe it's a thriller about a detective trying to solve the mystery of why ING Groep's stock price plummets every time an industrial plant in Columbus, Georgia ramps up its emissions.

In the world of board games, "Smogopoly" doesn't exist, but imagine the chaos of players trying to navigate a polluted cityscape while buying and selling stocks tied to the air quality index. It's a game of chance and lung capacity, where players wheeze their way to financial victory. Who knew air pollution could be so exhilarating?

In "Monopoly: Capitalist Edition," players engage in cutthroat competition to bankrupt their opponents and dominate the stock market. While air pollution isn't explicitly featured in this classic game, the metaphorical smog of greed and ruthless capitalism hangs heavy in the air. It's a dog-eat-dog world out there, and ING Groep's stock price might just be at the mercy of the game's invisible hand.

Next, we inject a breath of fresh air into our analysis, exploring the unexpected intersections of air pollution, financial markets, and literary whimsy.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Columbus, Georgia and ING Groep's stock price (ING). You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
When Air Pollution Floats, ING Groep's Stock Drowns: A Tale of Columbus, Georgia

[[ABSTRACT]]
In this paper, we embark on a whimsical journey to explore the unexpected connection between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING). We took a deep dive into the data from the Environmental Protection Agency and LSEG Analytics (Refinitiv) to assess this mysterious relationship, and the findings are nothing to sneeze at.

After tirelessly crunching the numbers, we uncovered a correlation coefficient of 0.8753081 and p < 0.01 for the time period spanning from 2002 to 2023. It's like these variables are joined at the hip, or should I say, smog-filled lungs?

Our analysis revealed that as air pollution levels in Columbus, Georgia soared, the stock price of ING Groep took a nosedive. It seems like the market doesn't take too kindly to the idea of a polluted atmosphere. Perhaps investors had trouble seeing through the haze?

So, next time you're thinking of investing in ING, it might be worth keeping an eye on the air quality in Columbus. After all, a breath of fresh air could do wonders for your portfolio - both literally and figuratively.

[[LITERATURE REVIEW]]
In "The Impact of Air Pollution on Stock Prices" by Smith et al., the authors find a positive correlation between air pollution levels and negative movements in stock prices. They suggest that investors may respond negatively to news regarding increased pollution levels, leading to a decrease in stock prices. This aligns with our findings, highlighting the tangible impact of air pollution on financial markets. It's like the stock market is holding its breath, waiting for a breath of fresh air!
Doe and Jones, in "The Economics of Environmental Factors on Stock Performance," delve into the relationship between environmental factors and stock performance. Their research reveals that companies located in areas with high pollution levels may experience adverse effects on their stock prices. It's as if the smog isn't just clouding the skies, but also the financial outlook for these companies.
Turning to non-fiction sources, "Pollution and Profit: The Impact of Environmental Conditions on Financial Markets" presents an in-depth analysis of how environmental conditions, including air pollution, can affect the valuation of companies. The authors argue that investors are becoming increasingly attuned to the environmental practices of firms, and the level of pollution in their operating areas. It's almost as if the market is saying, "Clean up your act, or we'll clean out our portfolios!"
Now, let's shed some light on some fictional sources that are surprisingly relevant to our investigation. "The Polluted Portfolio" by Jackson Greene may not actually exist, but in an alternate universe, it could surely spin a tale of intrigue and suspense, where air pollution plays a central role in the ups and downs of stock prices. Maybe it's a thriller about a detective trying to solve the mystery of why ING Groep's stock price plummets every time an industrial plant in Columbus, Georgia ramps up its emissions.
In the world of board games, "Smogopoly" doesn't exist, but imagine the chaos of players trying to navigate a polluted cityscape while buying and selling stocks tied to the air quality index. It's a game of chance and lung capacity, where players wheeze their way to financial victory. Who knew air pollution could be so exhilarating?
In "Monopoly: Capitalist Edition," players engage in cutthroat competition to bankrupt their opponents and dominate the stock market. While air pollution isn't explicitly featured in this classic game, the metaphorical smog of greed and ruthless capitalism hangs heavy in the air. It's a dog-eat-dog world out there, and ING Groep's stock price might just be at the mercy of the game's invisible hand.
Next, we inject a breath of fresh air into our analysis, exploring the unexpected intersections of air pollution, financial markets, and literary whimsy.

[[RESULTS]]
The results of our investigation revealed a striking correlation coefficient of 0.8753081 between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING) for the period of 2002 to 2023. This correlation was accompanied by an r-squared value of 0.7661643, indicating that a whopping 76.6% of the variation in ING's stock price can be attributed to changes in air pollution levels. It's like the stock price was gasping for clean air!
The p-value of less than 0.01 further cemented the statistical significance of this relationship, suggesting that the likelihood of observing such a strong connection by pure chance is about as rare as finding a blue-chip stock at a yard sale. Talk about a breath of fresh (statistical) significance!
Figure 1 displays the scatterplot demonstrating the robust link between air pollution in Columbus, Georgia, and the stock price of ING Groep. The points on the plot are as tightly packed as cars on a Los Angeles freeway, depicting the inseparable nature of these two variables. It's almost as if they're in an unbreakable embrace, or should I say, an unbreathable embrace?
It appears that when the air quality in Columbus took a turn for the worse, ING Groep's stock price followed suit, plummeting like a lead balloon. It's as if investors were saying, "Nope, we won't inhale this!" I guess you could say the market is quite sensitive to air pollution – it's like it has environmental allergies!
In summary, our findings provide compelling evidence of a substantial and significant correlation between air pollution levels in Columbus, Georgia, and the stock price of ING Groep. This research underscores the importance of considering environmental factors in financial analysis and highlights the potential influence of air quality on stock market performance. So, the next time you're contemplating your investment portfolio, don't forget to check the weather report for Columbus – and by weather, I mean air quality.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our findings have provided a breath of fresh air in the realm of environmental economics, unveiling a compelling relationship between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING). The robust correlation coefficient of 0.8753081 and accompanying p-value of less than 0.01 not only affirm the tangible influence of air quality on financial markets but also reinforce the relevance of prior research in this domain.

Taking a deep inhalation of this substantial correlation, it becomes evident that our results align with the work of Smith et al., who emphasized the adverse impact of air pollution on stock prices. It seems that investors are truly holding their breath in response to heightened pollution levels, leading to a palpable decrease in stock prices. It's like the market is saying, "No thanks, we'd rather not inhale this financial smog."

Moreover, our findings resonate with the insights of Doe and Jones, shedding light on the adverse effects of environmental factors on stock performance. The link between high pollution levels and negative stock movements mirrors our own observations, indicating that the smog isn't just clouding the skies but also investors' perspectives.

When we consider the fictional and whimsical sources from our literature review, the unexpected intersection of air pollution, financial markets, and literary whimsy takes on a surprising tangibility in our results. The imaginary "The Polluted Portfolio" and "Smogopoly" may have been crafted as a jest, but our findings almost breathe life into these hypothetical scenarios, demonstrating the real-world impact of air quality on stock prices.

As we navigate the uncharted territory of ambient air and stock market dynamics, it becomes increasingly clear that our research has breathed new life into the understanding of environmental influences on financial markets. Our contribution not only substantiates prior literature but also injects a fresh gust of empirical evidence, urging investors to look beyond balance sheets and keep an eye on atmospheric conditions when making investment decisions.

So, the next time you're assessing ING Groep's stock, remember that a clear sky in Columbus could translate to a brighter outlook for your portfolio. And if you find yourself in need of a dad joke to lighten the mood, just remember - air pollution may impact stock prices, but it can't hoard all the *shares*!

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Columbus, Georgia and ING Groep's stock price (ING). You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
When Air Pollution Floats, ING Groep's Stock Drowns: A Tale of Columbus, Georgia

[[ABSTRACT]]
In this paper, we embark on a whimsical journey to explore the unexpected connection between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING). We took a deep dive into the data from the Environmental Protection Agency and LSEG Analytics (Refinitiv) to assess this mysterious relationship, and the findings are nothing to sneeze at.

After tirelessly crunching the numbers, we uncovered a correlation coefficient of 0.8753081 and p < 0.01 for the time period spanning from 2002 to 2023. It's like these variables are joined at the hip, or should I say, smog-filled lungs?

Our analysis revealed that as air pollution levels in Columbus, Georgia soared, the stock price of ING Groep took a nosedive. It seems like the market doesn't take too kindly to the idea of a polluted atmosphere. Perhaps investors had trouble seeing through the haze?

So, next time you're thinking of investing in ING, it might be worth keeping an eye on the air quality in Columbus. After all, a breath of fresh air could do wonders for your portfolio - both literally and figuratively.

[[INTRDUCTION]]
As the great bard Shakespeare once wrote, "What's in a polluted air that can affect a stock's price?" Well, dear readers, in this paper we aim to unravel the fascinating connection between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING). This unlikely duo has captured our attention, and with it, we hope to shed some light on the unexpected influence of air quality on financial markets.
Now, don't hold your breath, but we've uncovered some compelling evidence that might just take your breath away – pun intended. It turns out, as air pollution levels in Columbus, Georgia rose, the stock price of ING Groep fell faster than a leaf blower in a hurricane. It's like Mother Nature is pulling the strings of the stock market, orchestrating a drama of epic proportions, with smog as the villain.
But before we dive into the nitty-gritty of our research findings, let's take a moment to appreciate the sheer audacity of this unlikely correlation. Air pollution and stock prices – an odd couple indeed. It's almost as if the financial markets are in a tumultuous relationship with the environment, and Columbus, Georgia becomes the stage for their dirty dancing.

[[RESULTS]]
The results of our investigation revealed a striking correlation coefficient of 0.8753081 between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING) for the period of 2002 to 2023. This correlation was accompanied by an r-squared value of 0.7661643, indicating that a whopping 76.6% of the variation in ING's stock price can be attributed to changes in air pollution levels. It's like the stock price was gasping for clean air!
The p-value of less than 0.01 further cemented the statistical significance of this relationship, suggesting that the likelihood of observing such a strong connection by pure chance is about as rare as finding a blue-chip stock at a yard sale. Talk about a breath of fresh (statistical) significance!
Figure 1 displays the scatterplot demonstrating the robust link between air pollution in Columbus, Georgia, and the stock price of ING Groep. The points on the plot are as tightly packed as cars on a Los Angeles freeway, depicting the inseparable nature of these two variables. It's almost as if they're in an unbreakable embrace, or should I say, an unbreathable embrace?
It appears that when the air quality in Columbus took a turn for the worse, ING Groep's stock price followed suit, plummeting like a lead balloon. It's as if investors were saying, "Nope, we won't inhale this!" I guess you could say the market is quite sensitive to air pollution – it's like it has environmental allergies!
In summary, our findings provide compelling evidence of a substantial and significant correlation between air pollution levels in Columbus, Georgia, and the stock price of ING Groep. This research underscores the importance of considering environmental factors in financial analysis and highlights the potential influence of air quality on stock market performance. So, the next time you're contemplating your investment portfolio, don't forget to check the weather report for Columbus – and by weather, I mean air quality.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has illuminated a fascinating and seemingly air-tight relationship between air pollution in Columbus, Georgia, and the stock price of ING Groep. It's as if the capital market is donning a pair of pollution-sniffing nose plugs! Our findings not only emphasize the substantial impact of air quality on stock market dynamics but also highlight the intricate dance between environmental variables and financial performance.

The robust correlation coefficient and r-squared value we uncovered make it clear that these two seemingly disparate factors are more intertwined than peanut butter and jelly. It's like they're performing a duet, with air pollution hitting the low notes and ING Groep's stock price reaching new lows too - talk about a symphony of smog! It seems "lungs" are not the only thing affected by air pollution – stock portfolios might need an inhaler too!

So, where do we go from here? Well, it's safe to say that further exploration of the connection between environmental factors and stock performance may yield valuable insights, but for now, it seems like we've cleared the air on this particular relationship. It's like finding a stock with a PE ratio as low as a limbo stick – pretty rare!

In summary, our research uncovers an intriguing correlation, underscoring the need to consider air quality as a potential influencer of stock price movements. It's a breath of fresh air in the world of financial analysis! And speaking of fresh air, don't forget to take a breather before delving into your next research venture.

In summary, while further exploration of the influence of air pollution on stock prices may still offer nuggets of wisdom, for now, it's safe to say we've connected the dots. It's like finding a stock with a PE ratio as low as your dad's favorite dad joke. No more research needed – we've nailed it!

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 When Air Pollution Floats, ING Groep's Stock Drowns: A Tale of Columbus, Georgia. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Environmental Economics and Humor

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 When Air Pollution Floats, ING Groep's Stock Drowns: A Tale of Columbus, Georgia. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Environmental Economics and Finance

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 When Air Pollution Floats, ING Groep's Stock Drowns: A Tale of Columbus, Georgia with an abstract of In this paper, we embark on a whimsical journey to explore the unexpected connection between air pollution in Columbus, Georgia, and the stock price of ING Groep (ING). We took a deep dive into the data from the Environmental Protection Agency and LSEG Analytics (Refinitiv) to assess this mysterious relationship, and the findings are nothing to sneeze at.
After tirelessly crunching the numbers, we uncovered a correlation coefficient of 0.8753081 and p < 0.01 for the time period spanning from 2002 to 2023. It's like these variables are joined at the hip, or should I say, smog-filled lungs?
Our analysis revealed that as air pollution levels in Columbus, Georgia soared, the stock price of ING Groep took a nosedive. It seems like the market doesn't take too kindly to the idea of a polluted atmosphere. Perhaps investors had trouble seeing through the haze?
So, next time you're thinking of investing in ING, it might be worth keeping an eye on the air quality in Columbus. After all, a breath of fresh air could do wonders for your portfolio - both literally and figuratively.

ChatGPT:

air pollution, Columbus Georgia, ING Groep stock, correlation coefficient, stock price, Environmental Protection Agency data, LSEG Analytics, Refinitiv, market correlation, investment, portfolio, air quality.

*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 pollution in Columbus, Georgia
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Columbus, GA-AL
Source: Environmental Protection Agency
See what else correlates with Air pollution in Columbus, Georgia

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

See what else correlates with ING Groep's stock price (ING)

Correlation r = 0.8753081 (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 = 0.7661643 (Coefficient of determination)
This means 76.6% of the change in the one variable (i.e., ING Groep's stock price (ING)) is predictable based on the change in the other (i.e., Air pollution in Columbus, Georgia) over the 22 years from 2002 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 9.71E-8.^Show 0.0000000970731140390707700000
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 0.88 in 9.71E-6% of random cases. Said differently, if you correlated 10,301,514 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 21 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 21 because we have two variables measured over a period of 22 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.

[ 0.72, 0.95 ] 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.

	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Air pollution in Columbus, Georgia (Bad air quality days)	2.43056	1.5873	3.36391	4.10959	4.65753	6.84932	2.73224	0.547945	1.36986	1.36986	0.819672	0.273973	0.547945	0.550964	1.37363	0	0	0	0.273224	1.09589	0.547945	1.0989
ING Groep's stock price (ING) (Stock price)	25.7	17.25	23.63	30.33	35.68	45.02	38.96	10.3	10.38	9.81	7.47	9.65	13.87	13.22	13.2	14.32	18.45	10.47	12.3	9.43	14.04	12.58

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([2.43056,1.5873,3.36391,4.10959,4.65753,6.84932,2.73224,0.547945,1.36986,1.36986,0.819672,0.273973,0.547945,0.550964,1.37363,0,0,0,0.273224,1.09589,0.547945,1.0989,])
array_2 = np.array([25.7,17.25,23.63,30.33,35.68,45.02,38.96,10.3,10.38,9.81,7.47,9.65,13.87,13.22,13.2,14.32,18.45,10.47,12.3,9.43,14.04,12.58,])
array_1_name = "Air pollution in Columbus, Georgia"
array_2_name = "ING Groep's stock price (ING)"

# 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 Air pollution in Columbus, Georgia
Line chart for only ING Groep's stock price (ING)
AI-generated correlation image
The spurious research paper: When Air Pollution Floats, ING Groep's Stock Drowns: A Tale of Columbus, Georgia

View another random correlation

How fun was this correlation?

Kudos for rating!

Correlation ID: 3610 · Black Variable ID: 20491 · Red Variable ID: 1736


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