Spurious correlation #2,278 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Global Rice Consumption and the second variable is Cheniere Energy's stock price (LNG). The chart goes from 2009 to 2022, 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 Global Rice Consumption and the second variable is Cheniere Energy's stock price (LNG). The chart goes from 2009 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

More rice dishes led to more gas production. As rice consumption rose, so did the demand for natural gas, giving Cheniere Energy a firm foothold in the market. It's clear that when it comes to LNG stocks, the secret ingredient is rice! Remember, that's just a grain of truth in the stock market stir-fry!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a vibrant cyberpunk street market in an Asian metropolis where aromatic steam rises from street food stalls offering enticing bowls of rice dishes. In the backdrop, a towering digital screen displays the stock market ticker, featuring the dynamic stock price of Cheniere Energy amidst the bustling and futuristic cityscape. 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: Global Rice Consumption and Cheniere Energy's stock price. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Brutalism A photo-realistic image Vaporwave Realistic Cyberpunk
ChatGPT: Cyberpunk

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 Global Rice Consumption and Cheniere Energy's stock price together. Keep the description simple.
ChatGPT: Picture a bustling street food market in a busy Asian city, with vendors selling fragrant steaming bowls of rice dishes to a long line of customers. In the background, a large screen displays the stock market ticker, showing the fluctuating stock price of Cheniere Energy.

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: [ Cyberpunk ] and depicting this scene: Picture a bustling street food market in a busy Asian city, with vendors selling fragrant steaming bowls of rice dishes to a long line of customers. In the background, a large screen displays the stock market ticker, showing the fluctuating stock price of Cheniere Energy. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a vibrant cyberpunk street market in an Asian metropolis where aromatic steam rises from street food stalls offering enticing bowls of rice dishes. In the backdrop, a towering digital screen displays the stock market ticker, featuring the dynamic stock price of Cheniere Energy amidst the bustling and futuristic cityscape.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Global Rice Consumption caused Cheniere Energy's stock price (LNG) to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

Grains & Gains: A Quantitative Analysis of the Rice-LNG Correlation

The Journal of Culinary Economics and Nutrition

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Global Rice Consumption and Cheniere Energy's stock price (LNG). Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. 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]]
"Grains & Gains: A Quantitative Analysis of the Rice-LNG Correlation"

[[ABSTRACT]]
In this paper, the connections between global rice consumption and Cheniere Energy's stock price (LNG) are closely examined and quantified. While the topic may seem as mismatched as pineapple on pizza, we delved into the data to explore the potential relationship between the world's most consumed staple food and an energy company's stock performance.

Utilizing data from Statista and LSEG Analytics (Refinitiv), we diligently crunched the numbers for the period of 2009 to 2022, uncovering a correlation coefficient of 0.9282046, indicating a substantial positive association between global rice consumption and LNG stock prices. The p-value, humorously exceeding its expiration date at less than 0.01, provides strong evidence against the null hypothesis of no relationship.

So, while it may seem odd that a bowl of rice could impact stock market performance, our findings suggest there may be a rice grain of truth to this unexpected connection. This paper not only sheds light on an intriguing correlation but also serves as a reminder that sometimes, in the world of statistical analysis, the most unlikely pairings can yield surprising results.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Rice, the humble grain that accompanies many a meal, may seem an unlikely candidate to influence the stock market. However, as we delve into the world of quantitative analysis, we may find ourselves in a bit of a financial stir-fry. The seemingly disparate fields of agricultural consumption and energy sector investments have collided in our investigation, leading to the tantalizing question: could there be a deeper connection between global rice consumption and the stock price of Cheniere Energy (LNG) than meets the eye?
Much like a chef carefully selecting the ingredients for a delectable dish, we have sifted through the data from Statista and LSEG Analytics (Refinitiv) to concoct a savory statistical stew. Our goal is to uncover any potential relationship between the consumption of the world's most beloved staple food and the stock performance of a leading energy company.
In this paper, we aim to collide the seemingly unrelated universes of rice paddies and stock exchanges, peeling back the layers of this financial onion to reveal any underlying correlations. Our findings may not only enrich our understanding of market dynamics but also add a dash of flavor to the often bland landscape of economic research.
So, dear reader, buckle up and grab your chopsticks, for we are about to embark on a journey of data-driven discovery that may just prove that rice and riches are more interconnected than we ever dared to imagine.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

As we dive into the world of finance and food, it is imperative to survey existing literature to ascertain any prior investigations into the enigmatic relationship between global rice consumption and Cheniere Energy's stock price (LNG). Gird your loins, esteemed reader, for we are about to embark on a scholarly journey filled with numbers, charts, and perhaps a sprinkle of whimsy.

Smith et al. (2018) brought forth a comprehensive analysis of agricultural commodity consumption and its impact on financial markets, primarily focusing on the staple grain of rice. Their study delved into the intricate web of supply and demand forces, but alas, it did not venture into the tumultuous seas of stock price correlations. A missed opportunity, one might say, as they overlooked the potential for a risotto-revenue relationship.

Doe and Jones (2015) examined energy sector stock performances in relation to global dietary patterns, tracing the effects of dietary shifts on the stock prices of leading companies. While their findings were rather illuminating, they failed to zoom in on the specific interplay between rice consumption and LNG stock prices. A bit like skimming through the ingredients list without savoring the aromatic flavors of the dish.

Turning to other sources of knowledge, "The Rice Diet Solution" by Kitty Gurkin Rosati and Robert Rosati presents an in-depth exploration of rice consumption and its impact on human health. While the book may not directly refer to stock prices, one cannot help but wonder if a healthy diet could lead to heightened stock market acumen. After all, a well-fed mind is a savvy mind, or so the saying goes.

In the realm of fiction, "Rice, Noodle, Fish" by Matt Goulding traverses the culinary landscape of Japan, intertwining tales of gastronomic delights with the soul-stirring beauty of the country. While the tangential relevance to rice and energy stocks may seem tenuous at best, one cannot discount the potential inspirational impact of a good foodie read on financial acumen. Who's to say a well-prepared bowl of rice cannot serve as the catalyst for an investment epiphany?

Venturing into the whimsical and deviating from traditional scholarly sources, our research team took an unorthodox approach by scrutinizing the inscriptions on random CVS receipts. Although the receipts did not explicitly divulge any secrets regarding the rice-LNG correlation, they did reveal an alarming prevalence of impulse candy purchases - a phenomenon that may have tangential implications for stock market behavior but, regrettably, little relevance to our current study.

In closing, our literature review meanders through the established and the imaginative, painting a tapestry of potential influences on our investigation. As we forge ahead, let us remember that the pursuit of knowledge often leads us down unexpected and occasionally amusing paths.

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 Global Rice Consumption and Cheniere Energy's stock price (LNG). Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
"Grains & Gains: A Quantitative Analysis of the Rice-LNG Correlation"

[[ABSTRACT]]
In this paper, the connections between global rice consumption and Cheniere Energy's stock price (LNG) are closely examined and quantified. While the topic may seem as mismatched as pineapple on pizza, we delved into the data to explore the potential relationship between the world's most consumed staple food and an energy company's stock performance.

Utilizing data from Statista and LSEG Analytics (Refinitiv), we diligently crunched the numbers for the period of 2009 to 2022, uncovering a correlation coefficient of 0.9282046, indicating a substantial positive association between global rice consumption and LNG stock prices. The p-value, humorously exceeding its expiration date at less than 0.01, provides strong evidence against the null hypothesis of no relationship.

So, while it may seem odd that a bowl of rice could impact stock market performance, our findings suggest there may be a rice grain of truth to this unexpected connection. This paper not only sheds light on an intriguing correlation but also serves as a reminder that sometimes, in the world of statistical analysis, the most unlikely pairings can yield surprising results.

[[LITERATURE REVIEW]]
As we dive into the world of finance and food, it is imperative to survey existing literature to ascertain any prior investigations into the enigmatic relationship between global rice consumption and Cheniere Energy's stock price (LNG). Gird your loins, esteemed reader, for we are about to embark on a scholarly journey filled with numbers, charts, and perhaps a sprinkle of whimsy.
Smith et al. (2018) brought forth a comprehensive analysis of agricultural commodity consumption and its impact on financial markets, primarily focusing on the staple grain of rice. Their study delved into the intricate web of supply and demand forces, but alas, it did not venture into the tumultuous seas of stock price correlations. A missed opportunity, one might say, as they overlooked the potential for a risotto-revenue relationship.
Doe and Jones (2015) examined energy sector stock performances in relation to global dietary patterns, tracing the effects of dietary shifts on the stock prices of leading companies. While their findings were rather illuminating, they failed to zoom in on the specific interplay between rice consumption and LNG stock prices. A bit like skimming through the ingredients list without savoring the aromatic flavors of the dish.
Turning to other sources of knowledge, "The Rice Diet Solution" by Kitty Gurkin Rosati and Robert Rosati presents an in-depth exploration of rice consumption and its impact on human health. While the book may not directly refer to stock prices, one cannot help but wonder if a healthy diet could lead to heightened stock market acumen. After all, a well-fed mind is a savvy mind, or so the saying goes.
In the realm of fiction, "Rice, Noodle, Fish" by Matt Goulding traverses the culinary landscape of Japan, intertwining tales of gastronomic delights with the soul-stirring beauty of the country. While the tangential relevance to rice and energy stocks may seem tenuous at best, one cannot discount the potential inspirational impact of a good foodie read on financial acumen. Who's to say a well-prepared bowl of rice cannot serve as the catalyst for an investment epiphany?
Venturing into the whimsical and deviating from traditional scholarly sources, our research team took an unorthodox approach by scrutinizing the inscriptions on random CVS receipts. Although the receipts did not explicitly divulge any secrets regarding the rice-LNG correlation, they did reveal an alarming prevalence of impulse candy purchases - a phenomenon that may have tangential implications for stock market behavior but, regrettably, little relevance to our current study.
In closing, our literature review meanders through the established and the imaginative, painting a tapestry of potential influences on our investigation. As we forge ahead, let us remember that the pursuit of knowledge often leads us down unexpected and occasionally amusing paths.

[[RESULTS]]
The results of our analysis revealed a substantial positive correlation between global rice consumption and the stock price of Cheniere Energy (LNG) for the time period 2009 to 2022. Our findings uncovered a correlation coefficient of 0.9282046, with an r-squared value of 0.8615637, and a p-value of less than 0.01. This p-value was so low, it may need a booster seat to reach the significance table.
In simpler terms, our data suggests that as global rice consumption increased, so did the stock price of Cheniere Energy. It seems that the world's love for rice is not just limited to dinner plates but also has a bit of a ripple effect on the stock market. Who knew rice could serve up such gains?
To visually illustrate this noteworthy correlation, we present in Fig. 1 a scatterplot showcasing the clear relationship between global rice consumption and Cheniere Energy's stock price. It's almost as if the stock price is riding on the back of a rice grain, surfing the waves of global consumption. Quite the unconventional surfing partner!
These findings not only provide an intriguing insight into the interplay of seemingly unrelated markets but also offer a reminder that in the world of data analysis, there's always the potential for unexpected connections to emerge. It's as if statistical analysis has its own secret recipe, and sometimes, it serves up a dish that surprises even the most seasoned researchers.
In conclusion, our results contribute to the growing body of research exploring the unanticipated interconnections within the world of global markets. This study not only highlights the importance of considering diverse influencers on stock prices but also adds a sprinkle of amusement to the often serious realm of economic analysis. Who knew crunching numbers could lead us to contemplate the curious relationship between the rice bowl and the stock exchange?

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our research has unearthed a surprisingly strong positive correlation between global rice consumption and Cheniere Energy's stock price. It seems that our initial suspicion of a connection between a food staple and an energy company was not just a half-baked idea after all! Our findings align with prior research by Smith et al. and Doe and Jones, implicitly supporting the idea that dietary patterns and agricultural commodities can indeed exert influence on financial markets. It's almost as if the stock market has a voracious appetite for correlation, and our analysis serves up a satisfying helping of evidence to this effect.

Just as "The Rice Diet Solution" hinted at the potential impact of a healthy diet on cognitive function, our findings suggest that the collective appetite for rice may have a more significant influence on market dynamics than previously envisioned. Perhaps a well-fed populace is not only a boon for individual health but also a catalyst for stock market vitality. Who would have thought that a steaming bowl of rice could power not only our bodies but also a corporation's stock performance?

Our literature review, while cheekily exploring eclectic sources from culinary travelogues to whimsical forays into anonymous receipts, ultimately substantiates the notion that unconventional influences can shape stock price dynamics. It's a bit like discovering an unexpected ingredient that unexpectedly elevates the flavor profile of a dish - in this case, the surprising addition of global rice consumption heightening the savor of LNG stock prices.

As we navigate the somewhat unconventional landscape of exploring the rice-LNG correlation, it's clear that our results serve as a tasty addition to the broader conversation surrounding market influences. While financial analysis is often perceived as dry and serious, our findings remind us that the universe of data holds unforeseen connections and, occasionally, a side dish of humor. It's as if statistical analysis sometimes sprinkles a dash of whimsy into its recipe, serving up amusing revelations alongside the more expected outcomes.

In this vein, our study adds a spoonful of levity to the often serious discourse on market influences, proving that even the most unlikely pairings can yield delectable results. And who knows, maybe our next research venture will uncover the enigmatic connection between kale consumption and cryptocurrency prices. Until then, let's savor the unexpected correlations we've uncovered and toast to the intriguing interplay of global markets and our daily dining habits.

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 Global Rice Consumption and Cheniere Energy's stock price (LNG). Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Grains & Gains: A Quantitative Analysis of the Rice-LNG Correlation"

[[ABSTRACT]]
In this paper, the connections between global rice consumption and Cheniere Energy's stock price (LNG) are closely examined and quantified. While the topic may seem as mismatched as pineapple on pizza, we delved into the data to explore the potential relationship between the world's most consumed staple food and an energy company's stock performance.

Utilizing data from Statista and LSEG Analytics (Refinitiv), we diligently crunched the numbers for the period of 2009 to 2022, uncovering a correlation coefficient of 0.9282046, indicating a substantial positive association between global rice consumption and LNG stock prices. The p-value, humorously exceeding its expiration date at less than 0.01, provides strong evidence against the null hypothesis of no relationship.

So, while it may seem odd that a bowl of rice could impact stock market performance, our findings suggest there may be a rice grain of truth to this unexpected connection. This paper not only sheds light on an intriguing correlation but also serves as a reminder that sometimes, in the world of statistical analysis, the most unlikely pairings can yield surprising results.

[[INTRDUCTION]]
Rice, the humble grain that accompanies many a meal, may seem an unlikely candidate to influence the stock market. However, as we delve into the world of quantitative analysis, we may find ourselves in a bit of a financial stir-fry. The seemingly disparate fields of agricultural consumption and energy sector investments have collided in our investigation, leading to the tantalizing question: could there be a deeper connection between global rice consumption and the stock price of Cheniere Energy (LNG) than meets the eye?
Much like a chef carefully selecting the ingredients for a delectable dish, we have sifted through the data from Statista and LSEG Analytics (Refinitiv) to concoct a savory statistical stew. Our goal is to uncover any potential relationship between the consumption of the world's most beloved staple food and the stock performance of a leading energy company.
In this paper, we aim to collide the seemingly unrelated universes of rice paddies and stock exchanges, peeling back the layers of this financial onion to reveal any underlying correlations. Our findings may not only enrich our understanding of market dynamics but also add a dash of flavor to the often bland landscape of economic research.
So, dear reader, buckle up and grab your chopsticks, for we are about to embark on a journey of data-driven discovery that may just prove that rice and riches are more interconnected than we ever dared to imagine.

[[RESULTS]]
The results of our analysis revealed a substantial positive correlation between global rice consumption and the stock price of Cheniere Energy (LNG) for the time period 2009 to 2022. Our findings uncovered a correlation coefficient of 0.9282046, with an r-squared value of 0.8615637, and a p-value of less than 0.01. This p-value was so low, it may need a booster seat to reach the significance table.
In simpler terms, our data suggests that as global rice consumption increased, so did the stock price of Cheniere Energy. It seems that the world's love for rice is not just limited to dinner plates but also has a bit of a ripple effect on the stock market. Who knew rice could serve up such gains?
To visually illustrate this noteworthy correlation, we present in Fig. 1 a scatterplot showcasing the clear relationship between global rice consumption and Cheniere Energy's stock price. It's almost as if the stock price is riding on the back of a rice grain, surfing the waves of global consumption. Quite the unconventional surfing partner!
These findings not only provide an intriguing insight into the interplay of seemingly unrelated markets but also offer a reminder that in the world of data analysis, there's always the potential for unexpected connections to emerge. It's as if statistical analysis has its own secret recipe, and sometimes, it serves up a dish that surprises even the most seasoned researchers.
In conclusion, our results contribute to the growing body of research exploring the unanticipated interconnections within the world of global markets. This study not only highlights the importance of considering diverse influencers on stock prices but also adds a sprinkle of amusement to the often serious realm of economic analysis. Who knew crunching numbers could lead us to contemplate the curious relationship between the rice bowl and the stock exchange?

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has uncovered a surprising positive correlation between global rice consumption and Cheniere Energy's stock price, lending credence to the hypothesis that rice isn't just a staple food but a potential market mover. It seems that when it comes to financial gains, rice is n-ice to have around! Our findings not only highlight the interconnectedness of seemingly unrelated sectors but also add a touch of flavor to the somewhat bland landscape of economic research. It's as if the stock market's been taking some culinary inspiration from the rice paddies!

The significance of this correlation cannot be overstated, as it challenges traditional notions about the dynamics of market influences. While some may dismiss our findings as straight out of left field, we stand by our statistically sound discovery. It's a reminder that in the world of data analysis, even the seemingly mismatched pairs can dance to the same beat. In the grand symphony of global markets, rice and stock prices may be strange bedfellows, but isn't it the unexpected pairings that often lead to the most compelling stories?

However, as tempting as it may be to further delve into the rice-LNG correlation, we must assert that no more research is needed in this area. It's time to stir the pot elsewhere and let this tasty discovery simmer in the annals of economic analysis. After all, we wouldn't want to overcook this rice and spoil the market stew!

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 Grains & Gains: A Quantitative Analysis of the Rice-LNG Correlation. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Culinary Economics and Nutrition

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 Grains & Gains: A Quantitative Analysis of the Rice-LNG Correlation. Respond only with the name of a fictional organization.

ChatGPT:

The International Association for Cereal Economics and Nutrition (IACEN)

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 Grains & Gains: A Quantitative Analysis of the Rice-LNG Correlation with an abstract of In this paper, the connections between global rice consumption and Cheniere Energy's stock price (LNG) are closely examined and quantified. While the topic may seem as mismatched as pineapple on pizza, we delved into the data to explore the potential relationship between the world's most consumed staple food and an energy company's stock performance.
Utilizing data from Statista and LSEG Analytics (Refinitiv), we diligently crunched the numbers for the period of 2009 to 2022, uncovering a correlation coefficient of 0.9282046, indicating a substantial positive association between global rice consumption and LNG stock prices. The p-value, humorously exceeding its expiration date at less than 0.01, provides strong evidence against the null hypothesis of no relationship.
So, while it may seem odd that a bowl of rice could impact stock market performance, our findings suggest there may be a rice grain of truth to this unexpected connection. This paper not only sheds light on an intriguing correlation but also serves as a reminder that sometimes, in the world of statistical analysis, the most unlikely pairings can yield surprising results.

ChatGPT:

Rice consumption, LNG stock price, correlation analysis, global rice consumption, Cheniere Energy, stock performance, Statista, LSEG Analytics, Refinitiv, correlation coefficient, p-value, association, rice impact on stock market, statistical analysis, unexpected correlation, surprising results

*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

Global Rice Consumption
Source: Statista
See what else correlates with Global Rice Consumption

Cheniere Energy's stock price (LNG)
Detailed data title: Opening price of Cheniere Energy (LNG) 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 Cheniere Energy's stock price (LNG)

Correlation r = 0.9282046 (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 = 0.8615637 (Coefficient of determination)
This means 86.2% of the change in the one variable (i.e., Cheniere Energy's stock price (LNG)) is predictable based on the change in the other (i.e., Global Rice Consumption) over the 14 years from 2009 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.7E-6.^Show 0.0000016916073482526452000000
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 0.93 in 0.00017% of random cases. Said differently, if you correlated 591,154 random variables^Note You don't actually need 591 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 13 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 13 because we have two variables measured over a period of 14 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.

[ 0.78, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Global Rice Consumption (Thousand Metric Tons)	437179	438338	445084	460825	462623	473878	474845	468882	483817	481678	485064	493953	503437	519895
Cheniere Energy's stock price (LNG) (Stock price)	2.84	2.5	5.62	8.89	19	42.67	69.81	37.01	41.46	53.96	57.7	61.12	60.99	101.93

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([437179,438338,445084,460825,462623,473878,474845,468882,483817,481678,485064,493953,503437,519895,])
array_2 = np.array([2.84,2.5,5.62,8.89,19,42.67,69.81,37.01,41.46,53.96,57.7,61.12,60.99,101.93,])
array_1_name = "Global Rice Consumption"
array_2_name = "Cheniere Energy's stock price (LNG)"

# 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 Global Rice Consumption
Line chart for only Cheniere Energy's stock price (LNG)
AI-generated correlation image
The spurious research paper: Grains & Gains: A Quantitative Analysis of the Rice-LNG Correlation

View another random correlation

How fun was this correlation?

Thanks for being the explorer we needed!

Correlation ID: 2278 · Black Variable ID: 437 · Red Variable ID: 1779


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