Spurious correlation #1,546 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The price of gold and the second variable is Global shipwrecks . The chart goes from 1975 to 2014, 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 The price of gold and the second variable is Global shipwrecks . The chart goes from 1975 to 2014, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the price of gold rose, more people invested in jewelry and bullion. This led to an unprecedented demand for extravagant treasure chests, causing a shortage in the shipping industry. Ships, loaded with precious cargo, began to sink under the weight of this gilded opportunity. The allure of striking it rich with sunken riches also led to a surge in risky maritime ventures, further contributing to the rise in global shipwrecks. It was a perfect storm of wealth, greed, and maritime mishaps.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a vast ocean with several sunken ships lying on the seabed. Their treasures glint in the golden light of the setting sun. The shimmering treasure represents the price of gold, while the multitude of sunken ships portrays the number of shipwrecks. Use symbolism to visually capture the essence of riches and loss beneath the waves. 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: The price of gold and Number of shipwrecks. 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: Sci-fi fantacy Symbolism Sci-fi fantacy Charcoal Woodblock painting
ChatGPT: Symbolism

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 The price of gold and Number of shipwrecks together. Keep the description simple.
ChatGPT: A vast ocean with several sunken ships lying on the seabed, their treasures glinting in the golden light of the setting sun. The price of gold is represented by the shimmering treasure, while the number of shipwrecks is shown by the multitude of sunken ships.

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: [ Symbolism ] and depicting this scene: A vast ocean with several sunken ships lying on the seabed, their treasures glinting in the golden light of the setting sun. The price of gold is represented by the shimmering treasure, while the number of shipwrecks is shown by the multitude of sunken ships. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a vast ocean with several sunken ships lying on the seabed. Their treasures glint in the golden light of the setting sun. The shimmering treasure represents the price of gold, while the multitude of sunken ships portrays the number of shipwrecks. Use symbolism to visually capture the essence of riches and loss beneath the waves.

*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 The price of gold caused Global shipwrecks to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks

Journal of Nautical Economics and Maritime Archaeology

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 The price of gold and Global shipwrecks . 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks"

[[ABSTRACT]]
In this paper, we delve into the intriguing association between the price of gold and the occurrence of global shipwrecks over the period from 1975 to 2014. Using data from Kitco and Wikipedia, we conducted a rigorous analysis to unravel the connection. Our findings reveal a striking correlation coefficient of 0.8788749 and p < 0.01, demonstrating a strong relationship between the two variables. As we navigate through the waves of statistics and dive into the depths of economic and maritime history, we present both serious and whimsical interpretations of this unexpected link. Our study not only sheds light on the financial implications of underwater treasure, but also highlights the shipwrecking tales that may have been "golden" opportunities for some and "sunk costs" for others. Join us on this research voyage to uncover the buried treasure of economic insights and seafaring humor.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Welcome aboard, fellow researchers, as we embark on a nautical adventure to explore the captivating correlation between the price of gold and the occurrence of global shipwrecks. Just like a mischievous pirate searching for buried treasure, we are on a quest to uncover the hidden connection between these two seemingly unrelated phenomena. So grab your compass and telescope, because we are about to set sail on the high seas of statistical analysis and economic oceanography!
As we navigate through the treacherous waters of economic data, we cannot help but marvel at the enigmatic allure of gold. With its shimmering luster and enduring value, gold has captivated humanity for centuries, driving explorers to the ends of the earth in pursuit of this precious metal. But could the price of gold hold more secrets than meets the eye? Could it be intricately entwined with the legendary tales of maritime disasters and sunken treasure?
In our pursuit of knowledge, we scoured the vast seas of historical records and academic literature, casting our net far and wide to reel in data on global shipwrecks. We then hoisted the sails of statistical analysis and charted a course to examine the relationship between the price of gold and the occurrence of these maritime catastrophes. Our compass of curiosity pointed us toward the years 1975 to 2014, a period teeming with economic fluctuations and seafaring escapades.
Armed with an arsenal of statistical tools and a keen sense of scientific curiosity, we embarked on a journey akin to that of intrepid explorers, undeterred by the siren calls of conventional wisdom. Our investigation led us to uncover a striking correlation coefficient of 0.8788749, signaling a significant association between the price of gold and global shipwrecks. In the language of statistical significance, our findings left us so exhilarated that we could practically hear the triumphant strains of a sea shanty reverberating through the halls of academia.
Now, as we prepare to dive into the depths of our analysis, let us not forget to approach our findings with a sense of wonder and whimsy. While we may be swashbuckling through the realms of economic analysis, it is crucial to anchor our scholarly pursuits in a spirit of scholarly mirth and intellectual adventure. Therefore, as we chart our course through the choppy waters of this research, we invite you to don your scholarly snorkel and plunge into the depths of economic insight and maritime merriment.
Join us as we hoist the anchor of conventional thinking and embark on a voyage of discovery, unraveling the mysteries of underwater treasure and unearthing the buried gems of economic wisdom. For in the waves of statistics and the currents of economic history, there lies a treasure trove of knowledge waiting to be uncovered. Prepare to set sail on this scholarly journey, where the winds of research and the tides of humor converge to reveal the hidden riches of economic analysis and maritime lore.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "The Economic Anchors of Gold Prices" by Smith et al., the authors find that the price of gold experiences fluctuations in response to various macroeconomic factors such as inflation rates, interest rates, and geopolitical tensions. Meanwhile, in "Shipwrecks: A Maritime Mystery" by Doe and Jones, the authors delve into the historical records of maritime disasters, exploring the causes and consequences of these nautical calamities. As we embark on our own investigation into the intriguing association between the price of gold and global shipwrecks, we are reminded of the vast sea of academic literature and its capacity to both enlighten and entertain.

Turning to non-fiction works, "Gold: The Definitive Visual Guide" by Thomas and "Shipwrecks: Disasters of the Deep Sea" by Brown offer invaluable insights into the allure of gold and the perils of shipwrecks. However, as we navigate through the literary currents, we stumble upon a selection of fiction works that, while not scholarly in nature, mirror the thematic undercurrents of our study. "Treasure Island" by Robert Louis Stevenson and "The Deep Blue Good-By" by John D. MacDonald beckon readers with tales of hidden treasures and maritime exploits, serving as both a riveting read and a delightful reminder of the maritime mysteries we seek to uncover.

In our pursuit of comedic relief amidst the waves of scholarly literature, we must not forget the cinematic treasures that pay homage to the maritime realm. "Pirates of the Caribbean: The Curse of the Black Pearl" and "Fool's Gold" provide a whimsical portrayal of treasure hunting and seafaring adventures, offering a lighthearted respite from the rigid rigors of academic inquiry.

As we chart our course through the realms of literature, both academic and imaginative, we are reminded of the multifaceted tapestry of human fascination with gold and maritime escapades. The rich tapestry of literature surrounding these topics serves as both a source of knowledge and a beacon of amusement as we navigate the turbulent seas of economic analysis and maritime lore. Join us as we navigate this scholarly sea, where the crosscurrents of research and the tides of humor converge to shed light on the hidden riches of economic insight and maritime merriment.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between The price of gold and Global shipwrecks . Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Kitco and Wikipedia . You used data from 1975 to 2014

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]]
"Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks"

[[ABSTRACT]]
In this paper, we delve into the intriguing association between the price of gold and the occurrence of global shipwrecks over the period from 1975 to 2014. Using data from Kitco and Wikipedia, we conducted a rigorous analysis to unravel the connection. Our findings reveal a striking correlation coefficient of 0.8788749 and p < 0.01, demonstrating a strong relationship between the two variables. As we navigate through the waves of statistics and dive into the depths of economic and maritime history, we present both serious and whimsical interpretations of this unexpected link. Our study not only sheds light on the financial implications of underwater treasure, but also highlights the shipwrecking tales that may have been "golden" opportunities for some and "sunk costs" for others. Join us on this research voyage to uncover the buried treasure of economic insights and seafaring humor.

[[INTRODUCTION]]
Welcome aboard, fellow researchers, as we embark on a nautical adventure to explore the captivating correlation between the price of gold and the occurrence of global shipwrecks. Just like a mischievous pirate searching for buried treasure, we are on a quest to uncover the hidden connection between these two seemingly unrelated phenomena. So grab your compass and telescope, because we are about to set sail on the high seas of statistical analysis and economic oceanography!
As we navigate through the treacherous waters of economic data, we cannot help but marvel at the enigmatic allure of gold. With its shimmering luster and enduring value, gold has captivated humanity for centuries, driving explorers to the ends of the earth in pursuit of this precious metal. But could the price of gold hold more secrets than meets the eye? Could it be intricately entwined with the legendary tales of maritime disasters and sunken treasure?
In our pursuit of knowledge, we scoured the vast seas of historical records and academic literature, casting our net far and wide to reel in data on global shipwrecks. We then hoisted the sails of statistical analysis and charted a course to examine the relationship between the price of gold and the occurrence of these maritime catastrophes. Our compass of curiosity pointed us toward the years 1975 to 2014, a period teeming with economic fluctuations and seafaring escapades.
Armed with an arsenal of statistical tools and a keen sense of scientific curiosity, we embarked on a journey akin to that of intrepid explorers, undeterred by the siren calls of conventional wisdom. Our investigation led us to uncover a striking correlation coefficient of 0.8788749, signaling a significant association between the price of gold and global shipwrecks. In the language of statistical significance, our findings left us so exhilarated that we could practically hear the triumphant strains of a sea shanty reverberating through the halls of academia.
Now, as we prepare to dive into the depths of our analysis, let us not forget to approach our findings with a sense of wonder and whimsy. While we may be swashbuckling through the realms of economic analysis, it is crucial to anchor our scholarly pursuits in a spirit of scholarly mirth and intellectual adventure. Therefore, as we chart our course through the choppy waters of this research, we invite you to don your scholarly snorkel and plunge into the depths of economic insight and maritime merriment.
Join us as we hoist the anchor of conventional thinking and embark on a voyage of discovery, unraveling the mysteries of underwater treasure and unearthing the buried gems of economic wisdom. For in the waves of statistics and the currents of economic history, there lies a treasure trove of knowledge waiting to be uncovered. Prepare to set sail on this scholarly journey, where the winds of research and the tides of humor converge to reveal the hidden riches of economic analysis and maritime lore.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Ahoy, mateys! Now that we've set the stage for our daring quest, it's time to unveil the secret map of our methodology, which guided us through the tempestuous seas of research. Our journey of discovery was not for the faint of heart, as we faced the daunting task of untangling the relationship between the price of gold and global shipwrecks. So batten down the hatches, dear readers, as we illuminate the path we charted to uncover this hidden treasure trove of data and insights.

Data Collection:

First, we commandeered our virtual ship and set sail across the vast expanse of the internet, navigating the digital currents in search of reliable sources to bolster our study. While we cast a wide net, our main sources of data were the illustrious Kitco and the encyclopedic expanse of Wikipedia. We plundered their databases, seizing historical gold prices and plundering information on global shipwrecks from the years 1975 to 2014.

Analytical Approach:

Armed with our trusty sextant of statistical analysis, we ventured forth to unpack the mysteries hiding within our data. We plotted the course of correlation analysis to unveil the extent of association between the price of gold and the occurrence of global shipwrecks. Employing the techniques of bivariate analysis, we clambered through the tangled web of numbers to discern the strength and direction of this unlikely connection.

To navigate the treacherous waters of significance testing, we hoisted the flag of hypothesis testing and braved the tempest of p-values. With our statistical compass in hand, we determined the veracity of our findings, ensuring that the bond between gold prices and shipwrecks was not merely a trick of the light.

Statistical Rigor:

In our pursuit of scholarly excellence, we spared no expense in ensuring the rigor of our analysis. Our statistical models were as sturdy as a galleon in a storm, scrutinizing every data point for outliers and anomalies. We engaged in rigorous sensitivity analyses, testing the robustness of our findings to ensure that they stood firm against the onslaught of skepticism.

Limitations and Caveats:

As any seasoned navigator knows, even the most well-crafted maps have their limitations. We acknowledge that our study is not without its choppy seas and looming shadows. The data from sources such as Wikipedia may carry the whispers of uncertainty, while the complexity of economic phenomena could conceal unforeseen currents amidst our correlations.

Nevertheless, with our compass set firmly on scientific integrity and our sails billowing with scholarly enthusiasm, we forged ahead undeterred, leveraging our analytical tools to provide a clear-eyed narrative of our findings.

And thus, with the wind in our research sails and the spirit of intellectual discovery as our guiding star, we present our methodologies as a testament to the unyielding pursuit of knowledge and the thrill of scholarly adventure. Onward, dear readers, to the depths of our findings, where the hidden treasures of statistical endeavor and oceanic wonder await their reckoning.

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

Please make up the results section of an academic research paper presenting the findings of the connection between The price of gold and Global shipwrecks . Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Kitco and Wikipedia .

For the time period 1975 to 2014, you found a correlation 0.8788749, r-squared of 0.7724210, 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]]
"Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks"

[[ABSTRACT]]
In this paper, we delve into the intriguing association between the price of gold and the occurrence of global shipwrecks over the period from 1975 to 2014. Using data from Kitco and Wikipedia, we conducted a rigorous analysis to unravel the connection. Our findings reveal a striking correlation coefficient of 0.8788749 and p < 0.01, demonstrating a strong relationship between the two variables. As we navigate through the waves of statistics and dive into the depths of economic and maritime history, we present both serious and whimsical interpretations of this unexpected link. Our study not only sheds light on the financial implications of underwater treasure, but also highlights the shipwrecking tales that may have been "golden" opportunities for some and "sunk costs" for others. Join us on this research voyage to uncover the buried treasure of economic insights and seafaring humor.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Welcome aboard, fellow researchers, as we embark on a nautical adventure to explore the captivating correlation between the price of gold and the occurrence of global shipwrecks. Just like a mischievous pirate searching for buried treasure, we are on a quest to uncover the hidden connection between these two seemingly unrelated phenomena. So grab your compass and telescope, because we are about to set sail on the high seas of statistical analysis and economic oceanography!
As we navigate through the treacherous waters of economic data, we cannot help but marvel at the enigmatic allure of gold. With its shimmering luster and enduring value, gold has captivated humanity for centuries, driving explorers to the ends of the earth in pursuit of this precious metal. But could the price of gold hold more secrets than meets the eye? Could it be intricately entwined with the legendary tales of maritime disasters and sunken treasure?
In our pursuit of knowledge, we scoured the vast seas of historical records and academic literature, casting our net far and wide to reel in data on global shipwrecks. We then hoisted the sails of statistical analysis and charted a course to examine the relationship between the price of gold and the occurrence of these maritime catastrophes. Our compass of curiosity pointed us toward the years 1975 to 2014, a period teeming with economic fluctuations and seafaring escapades.
Armed with an arsenal of statistical tools and a keen sense of scientific curiosity, we embarked on a journey akin to that of intrepid explorers, undeterred by the siren calls of conventional wisdom. Our investigation led us to uncover a striking correlation coefficient of 0.8788749, signaling a significant association between the price of gold and global shipwrecks. In the language of statistical significance, our findings left us so exhilarated that we could practically hear the triumphant strains of a sea shanty reverberating through the halls of academia.
Now, as we prepare to dive into the depths of our analysis, let us not forget to approach our findings with a sense of wonder and whimsy. While we may be swashbuckling through the realms of economic analysis, it is crucial to anchor our scholarly pursuits in a spirit of scholarly mirth and intellectual adventure. Therefore, as we chart our course through the choppy waters of this research, we invite you to don your scholarly snorkel and plunge into the depths of economic insight and maritime merriment.
Join us as we hoist the anchor of conventional thinking and embark on a voyage of discovery, unraveling the mysteries of underwater treasure and unearthing the buried gems of economic wisdom. For in the waves of statistics and the currents of economic history, there lies a treasure trove of knowledge waiting to be uncovered. Prepare to set sail on this scholarly journey, where the winds of research and the tides of humor converge to reveal the hidden riches of economic analysis and maritime lore.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the connection between the price of gold and global shipwrecks yielded intriguing results that navigated us through the stormy seas of statistical analysis and economic curiosities. Our data revealed a correlation coefficient of 0.8788749, a r-squared of 0.7724210, and a p-value of less than 0.01, indicating a robust and statistically significant relationship between these seemingly disparate phenomena. This correlation is as strong as the hull of a well-built ship, with the price of gold and global shipwrecks sailing in the same direction, much like a synchronized dance between a treasure chest and an intrepid explorer.

Behold, the scatterplot in Fig. 1 depicts this captivating relationship with all the finesse of a seasoned captain steering his ship through turbulent waters. The data points are as abundant as seashells on a sandy shore, forming a clear and compelling pattern that links the price of gold and global shipwrecks in a manner that would make even the most seasoned maritime historian raise an admiring eyebrow.

Our findings shed light on a connection that may seem as improbable as a pirate parrot reciting statistical formulas. The allure of gold, with its inherent value and universal appeal, intertwines with the tales of maritime misfortune to weave a narrative as captivating as a swashbuckling adventure on the high seas. It's as if economics and maritime history have conspired to create a captivating tale of financial intrigue and nautical misadventure. The relationship between these variables not only resembles a treasure map leading to buried riches but also uncovers the untold stories of shipwrecks that may have been pivotal moments in the annals of economic history.

In conclusion, our study unfurls the sails of economic insight and the mast of maritime merriment, showcasing the unexpected harmony between the price of gold and global shipwrecks. As researchers, we are buoyed by the discovery of this correlation that spans across the oceans of time and economic fluctuations. We invite our fellow scholars to join us in reveling in the whimsy and wonder of these findings and to set their course for future explorations into the uncharted waters of interdisciplinary research.

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 The price of gold and Global shipwrecks . Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks"

[[ABSTRACT]]
In this paper, we delve into the intriguing association between the price of gold and the occurrence of global shipwrecks over the period from 1975 to 2014. Using data from Kitco and Wikipedia, we conducted a rigorous analysis to unravel the connection. Our findings reveal a striking correlation coefficient of 0.8788749 and p < 0.01, demonstrating a strong relationship between the two variables. As we navigate through the waves of statistics and dive into the depths of economic and maritime history, we present both serious and whimsical interpretations of this unexpected link. Our study not only sheds light on the financial implications of underwater treasure, but also highlights the shipwrecking tales that may have been "golden" opportunities for some and "sunk costs" for others. Join us on this research voyage to uncover the buried treasure of economic insights and seafaring humor.

[[LITERATURE REVIEW]]
In "The Economic Anchors of Gold Prices" by Smith et al., the authors find that the price of gold experiences fluctuations in response to various macroeconomic factors such as inflation rates, interest rates, and geopolitical tensions. Meanwhile, in "Shipwrecks: A Maritime Mystery" by Doe and Jones, the authors delve into the historical records of maritime disasters, exploring the causes and consequences of these nautical calamities. As we embark on our own investigation into the intriguing association between the price of gold and global shipwrecks, we are reminded of the vast sea of academic literature and its capacity to both enlighten and entertain.
Turning to non-fiction works, "Gold: The Definitive Visual Guide" by Thomas and "Shipwrecks: Disasters of the Deep Sea" by Brown offer invaluable insights into the allure of gold and the perils of shipwrecks. However, as we navigate through the literary currents, we stumble upon a selection of fiction works that, while not scholarly in nature, mirror the thematic undercurrents of our study. "Treasure Island" by Robert Louis Stevenson and "The Deep Blue Good-By" by John D. MacDonald beckon readers with tales of hidden treasures and maritime exploits, serving as both a riveting read and a delightful reminder of the maritime mysteries we seek to uncover.
In our pursuit of comedic relief amidst the waves of scholarly literature, we must not forget the cinematic treasures that pay homage to the maritime realm. "Pirates of the Caribbean: The Curse of the Black Pearl" and "Fool's Gold" provide a whimsical portrayal of treasure hunting and seafaring adventures, offering a lighthearted respite from the rigid rigors of academic inquiry.
As we chart our course through the realms of literature, both academic and imaginative, we are reminded of the multifaceted tapestry of human fascination with gold and maritime escapades. The rich tapestry of literature surrounding these topics serves as both a source of knowledge and a beacon of amusement as we navigate the turbulent seas of economic analysis and maritime lore. Join us as we navigate this scholarly sea, where the crosscurrents of research and the tides of humor converge to shed light on the hidden riches of economic insight and maritime merriment.

[[RESULTS]]
The analysis of the connection between the price of gold and global shipwrecks yielded intriguing results that navigated us through the stormy seas of statistical analysis and economic curiosities. Our data revealed a correlation coefficient of 0.8788749, a r-squared of 0.7724210, and a p-value of less than 0.01, indicating a robust and statistically significant relationship between these seemingly disparate phenomena. This correlation is as strong as the hull of a well-built ship, with the price of gold and global shipwrecks sailing in the same direction, much like a synchronized dance between a treasure chest and an intrepid explorer.
Behold, the scatterplot in Fig. 1 depicts this captivating relationship with all the finesse of a seasoned captain steering his ship through turbulent waters. The data points are as abundant as seashells on a sandy shore, forming a clear and compelling pattern that links the price of gold and global shipwrecks in a manner that would make even the most seasoned maritime historian raise an admiring eyebrow.
Our findings shed light on a connection that may seem as improbable as a pirate parrot reciting statistical formulas. The allure of gold, with its inherent value and universal appeal, intertwines with the tales of maritime misfortune to weave a narrative as captivating as a swashbuckling adventure on the high seas. It's as if economics and maritime history have conspired to create a captivating tale of financial intrigue and nautical misadventure. The relationship between these variables not only resembles a treasure map leading to buried riches but also uncovers the untold stories of shipwrecks that may have been pivotal moments in the annals of economic history.
In conclusion, our study unfurls the sails of economic insight and the mast of maritime merriment, showcasing the unexpected harmony between the price of gold and global shipwrecks. As researchers, we are buoyed by the discovery of this correlation that spans across the oceans of time and economic fluctuations. We invite our fellow scholars to join us in reveling in the whimsy and wonder of these findings and to set their course for future explorations into the uncharted waters of interdisciplinary research.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

As we reflect on the findings of our study, we are met with an ocean of possibilities and a boatload of insights. Our results not only support the existing literature but also add a layer of depth to the discourse on the enigmatic relationship between the price of gold and global shipwrecks.

The correlation coefficient of 0.8788749 we observed is as strong as an anchor hoisting up a sunken treasure chest. It holds firm in the face of statistical tides, guiding us to the conclusion that the price of gold and global shipwrecks are more intertwined than a pair of unraveled ship rigging. Our r-squared of 0.7724210 further buoyed our confidence in the robustness of this relationship, as it explained a significant portion of the variation in the occurrence of shipwrecks based on gold prices.

Our p-value of less than 0.01 had us feeling like we stumbled upon a chest of statistical gold, signaling that the observed relationship is not merely a fluke but a genuine discovery worthy of further exploration. This statistical significance is as striking as a lighthouse beacon on a dark, stormy night, guiding us with unwavering certainty.

Turning to the literature, we recall the subtle yet significant pointers from our literature review, such as the thematic undercurrents of nautical exploits in works of fiction like "Treasure Island," which now seem eerily prescient in light of our findings. Similarly, the cinematic portrayal of treasure hunting in "Pirates of the Caribbean" takes on a whole new dimension of realism in the wake of our statistically supported insights. Who would have thought that Hollywood could be steering us toward academic truth?

In our voyage through the sea of scholarly literature, we stumbled upon unexpected comedic relief that now seems surprisingly pertinent. The lighthearted portrayal of maritime adventures in "Fool's Gold" seems oddly apropos, given our serious research findings about the financial implications of shipwrecks and underwater treasures. It's as if the waves of academic inquiry and the tides of humor have collided to illuminate the wealth of knowledge hidden beneath the surface of popular culture.

In closing, our findings not only uphold the existing academic discourse but also reaffirm the power of interdisciplinary research to unearth unexpected connections. Like intrepid sailors navigating uncharted waters, we have uncovered a treasure trove of economic and maritime insights that will undoubtedly chart new courses for future research endeavors. So, batten down the hatches and prepare to embark on further scholarly expeditions into the depths of economic and maritime mysteries. The winds of statistical discovery and the currents of historical revelation await our bold exploration.

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 The price of gold and Global shipwrecks . Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks"

[[ABSTRACT]]
In this paper, we delve into the intriguing association between the price of gold and the occurrence of global shipwrecks over the period from 1975 to 2014. Using data from Kitco and Wikipedia, we conducted a rigorous analysis to unravel the connection. Our findings reveal a striking correlation coefficient of 0.8788749 and p < 0.01, demonstrating a strong relationship between the two variables. As we navigate through the waves of statistics and dive into the depths of economic and maritime history, we present both serious and whimsical interpretations of this unexpected link. Our study not only sheds light on the financial implications of underwater treasure, but also highlights the shipwrecking tales that may have been "golden" opportunities for some and "sunk costs" for others. Join us on this research voyage to uncover the buried treasure of economic insights and seafaring humor.

[[INTRDUCTION]]
Welcome aboard, fellow researchers, as we embark on a nautical adventure to explore the captivating correlation between the price of gold and the occurrence of global shipwrecks. Just like a mischievous pirate searching for buried treasure, we are on a quest to uncover the hidden connection between these two seemingly unrelated phenomena. So grab your compass and telescope, because we are about to set sail on the high seas of statistical analysis and economic oceanography!
As we navigate through the treacherous waters of economic data, we cannot help but marvel at the enigmatic allure of gold. With its shimmering luster and enduring value, gold has captivated humanity for centuries, driving explorers to the ends of the earth in pursuit of this precious metal. But could the price of gold hold more secrets than meets the eye? Could it be intricately entwined with the legendary tales of maritime disasters and sunken treasure?
In our pursuit of knowledge, we scoured the vast seas of historical records and academic literature, casting our net far and wide to reel in data on global shipwrecks. We then hoisted the sails of statistical analysis and charted a course to examine the relationship between the price of gold and the occurrence of these maritime catastrophes. Our compass of curiosity pointed us toward the years 1975 to 2014, a period teeming with economic fluctuations and seafaring escapades.
Armed with an arsenal of statistical tools and a keen sense of scientific curiosity, we embarked on a journey akin to that of intrepid explorers, undeterred by the siren calls of conventional wisdom. Our investigation led us to uncover a striking correlation coefficient of 0.8788749, signaling a significant association between the price of gold and global shipwrecks. In the language of statistical significance, our findings left us so exhilarated that we could practically hear the triumphant strains of a sea shanty reverberating through the halls of academia.
Now, as we prepare to dive into the depths of our analysis, let us not forget to approach our findings with a sense of wonder and whimsy. While we may be swashbuckling through the realms of economic analysis, it is crucial to anchor our scholarly pursuits in a spirit of scholarly mirth and intellectual adventure. Therefore, as we chart our course through the choppy waters of this research, we invite you to don your scholarly snorkel and plunge into the depths of economic insight and maritime merriment.
Join us as we hoist the anchor of conventional thinking and embark on a voyage of discovery, unraveling the mysteries of underwater treasure and unearthing the buried gems of economic wisdom. For in the waves of statistics and the currents of economic history, there lies a treasure trove of knowledge waiting to be uncovered. Prepare to set sail on this scholarly journey, where the winds of research and the tides of humor converge to reveal the hidden riches of economic analysis and maritime lore.

[[RESULTS]]
The analysis of the connection between the price of gold and global shipwrecks yielded intriguing results that navigated us through the stormy seas of statistical analysis and economic curiosities. Our data revealed a correlation coefficient of 0.8788749, a r-squared of 0.7724210, and a p-value of less than 0.01, indicating a robust and statistically significant relationship between these seemingly disparate phenomena. This correlation is as strong as the hull of a well-built ship, with the price of gold and global shipwrecks sailing in the same direction, much like a synchronized dance between a treasure chest and an intrepid explorer.
Behold, the scatterplot in Fig. 1 depicts this captivating relationship with all the finesse of a seasoned captain steering his ship through turbulent waters. The data points are as abundant as seashells on a sandy shore, forming a clear and compelling pattern that links the price of gold and global shipwrecks in a manner that would make even the most seasoned maritime historian raise an admiring eyebrow.
Our findings shed light on a connection that may seem as improbable as a pirate parrot reciting statistical formulas. The allure of gold, with its inherent value and universal appeal, intertwines with the tales of maritime misfortune to weave a narrative as captivating as a swashbuckling adventure on the high seas. It's as if economics and maritime history have conspired to create a captivating tale of financial intrigue and nautical misadventure. The relationship between these variables not only resembles a treasure map leading to buried riches but also uncovers the untold stories of shipwrecks that may have been pivotal moments in the annals of economic history.
In conclusion, our study unfurls the sails of economic insight and the mast of maritime merriment, showcasing the unexpected harmony between the price of gold and global shipwrecks. As researchers, we are buoyed by the discovery of this correlation that spans across the oceans of time and economic fluctuations. We invite our fellow scholars to join us in reveling in the whimsy and wonder of these findings and to set their course for future explorations into the uncharted waters of interdisciplinary research.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

Ahoy, landlubbers and fellow researchers! As we conclude our swashbuckling adventure through the treacherous waters of economic analysis, we emerge with a treasure trove of insights into the connection between the price of gold and global shipwrecks. Our findings have uncovered a correlation coefficient so strong, it could practically lift the anchor of a massive galleon. With a robust correlation coefficient of 0.8788749 and a p-value lower than a sunken chest of Spanish doubloons, the association between these two variables is as clear as a pirate's eye patch.

When we plotted the data on a scatterplot, the relationship between the price of gold and global shipwrecks shimmered like a pile of freshly unearthed doubloons. It was as if the data points were performing a synchronized dance, a tango of economic fluctuations and maritime misfortune that would make even the most seasoned sailor do a double take.

Our research has not only uncovered a link between these two phenomena but has also unveiled a tale as rich and captivating as the legends of old. It's as if the price of gold and global shipwrecks have been in cahoots throughout history, weaving a narrative so intriguing it could rival the most dramatic of high-seas adventures.

In the spirit of scholarly mirth and intellectual adventure, we invite you to bask in the glow of this discovery and to set sail for new horizons of interdisciplinary research. However, in the grand tradition of academic wit, we proclaim that no more research is needed in this area. For we have not only struck gold but also unearthed the buried treasures of economic insight and maritime merriment. May your future endeavors be as rewarding as stumbling upon a chest of long-lost gold coins at the bottom of the sea!

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 Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Nautical Economics and Maritime Archaeology

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 Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks. Respond only with the name of a fictional organization.

ChatGPT:

The International Institute for Maritime Economics and Archaeology

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 Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks with an abstract of In this paper, we delve into the intriguing association between the price of gold and the occurrence of global shipwrecks over the period from 1975 to 2014. Using data from Kitco and Wikipedia, we conducted a rigorous analysis to unravel the connection. Our findings reveal a striking correlation coefficient of 0.8788749 and p < 0.01, demonstrating a strong relationship between the two variables. As we navigate through the waves of statistics and dive into the depths of economic and maritime history, we present both serious and whimsical interpretations of this unexpected link. Our study not only sheds light on the financial implications of underwater treasure, but also highlights the shipwrecking tales that may have been "golden" opportunities for some and "sunk costs" for others. Join us on this research voyage to uncover the buried treasure of economic insights and seafaring humor.

ChatGPT:

Gold prices, shipwrecks, global shipwrecks, economic history, maritime history, gold price correlation, treasure hunting, underwater treasure, financial implications, buried treasure, Kitco data, Wikipedia data

*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

The price of gold
Detailed data title: Yearly cumulative average of London PM fix gold price
Source: Kitco
See what else correlates with The price of gold

Global shipwrecks
Detailed data title: Ships sunk, foundered, grounded, or otherwise lost during the year
Source: Wikipedia
See what else correlates with Global shipwrecks

Correlation r = 0.8788749 (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 = 0.7724210 (Coefficient of determination)
This means 77.2% of the change in the one variable (i.e., Global shipwrecks ) is predictable based on the change in the other (i.e., The price of gold) over the 40 years from 1975 through 2014.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.9E-14.^Show 0.0000000000000886400527033710
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 8.9E-12% of random cases. Said differently, if you correlated 11,281,581,739,876 random variables^Note You don't actually need 11 trillion 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 39 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 39 because we have two variables measured over a period of 40 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, 0.93 ] 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.

	1975	1976	1977	1978	1979	1980	1981	1982	1983	1984	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014
The price of gold (In USD per ounce)	161.04	124.83	147.79	193.19	306.68	612.56	459.71	375.81	424.18	360.42	317.22	367.53	446.48	436.98	381.44	383.51	362.11	343.82	359.77	384	383.792	387.81	331.02	294.24	278.98	279.11	271.04	309.73	363.38	409.72	444.74	603.46	695.39	871.96	972.35	1224.53	1571.52	1668.98	1411.23	1291.88
Global shipwrecks (Wrecks)	13	36	25	29	24	34	33	32	15	33	20	23	19	29	23	13	25	13	12	16	7	15	14	10	10	14	12	16	15	18	6	13	33	31	55	71	123	111	70	52

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([161.04,124.83,147.79,193.19,306.68,612.56,459.71,375.81,424.18,360.42,317.22,367.53,446.48,436.98,381.44,383.51,362.11,343.82,359.77,384,383.792,387.81,331.02,294.24,278.98,279.11,271.04,309.73,363.38,409.72,444.74,603.46,695.39,871.96,972.35,1224.53,1571.52,1668.98,1411.23,1291.88,])
array_2 = np.array([13,36,25,29,24,34,33,32,15,33,20,23,19,29,23,13,25,13,12,16,7,15,14,10,10,14,12,16,15,18,6,13,33,31,55,71,123,111,70,52,])
array_1_name = "The price of gold"
array_2_name = "Global shipwrecks "

# 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 The price of gold
Line chart for only Global shipwrecks
AI-generated correlation image
The spurious research paper: Gold Diggers: A Ship-Shape Analysis of the Relationship Between Gold Prices and Global Shipwrecks

View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!

Correlation ID: 1546 · Black Variable ID: 346 · Red Variable ID: 504


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