about · email me · subscribe
Spurious correlation #2,631 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Total revenue generated by the National Hockey League and the second variable is Patents granted in the US.  The chart goes from 2006 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the NHL's total revenue goes up, so does their ability to "ice"-olate and invest in new technologies and equipment. With more funds available, teams can afford top-notch research and development, leading to a "slapshot" of innovative ideas. This, in turn, leads to a "power play" in the patent game, as the NHL's success "sticks" it to the competition, prompting a "puk-a" new wave of patents granted in the US.

Model: dalle-3
Prompt: Generate an image of an ice hockey rink illuminated by vibrant, multicolored spotlights. Show players gliding gracefully across the glistening ice, emphasizing their skill and agility. The scoreboard should prominently feature the growing total revenue of the National Hockey League. In the stands, depict a group of players animatedly discussing game strategies and equipment improvements. In the background, include a large banner proudly displaying the increasing number of patents granted in the US, symbolizing the surge in new ideas and inventions sparked by the players' innovative approach to the game. The style should take inspiration from pop art, with bold and contrasting colors, along with exaggerated and stylized forms to lend a dynamic and eye-catching quality to the overall visual. 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: Total revenue generated by the National Hockey League and Patents granted in the US. 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: An image that looks like it is a scene from A Disney Movie Pop art Brutalism A scene from Skyrim Charcoal
ChatGPT: Pop art

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 Total revenue generated by the National Hockey League and Patents granted in the US, in the following situation: As the NHL’s revenue grew, players became more innovative in their game strategies and equipment, leading to a surge in new ideas and inventions. Apparently, there’s a direct correlation between slap shots and patent applications!. Keep the description simple.
ChatGPT: In the scene, an ice hockey rink is bathed in the glow of spotlights as players skillfully glide across the ice. The scoreboard prominently displays the steadily increasing total revenue generated by the National Hockey League. Meanwhile, in the stands, a group of players huddle together, eagerly discussing game strategies and equipment improvements. In the background, a large banner proudly displays the increasing number of patents granted in the US, symbolizing the surge in new ideas and inventions sparked by the players' innovative approach to the game.

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: [ Pop art ] and depicting this scene: In the scene, an ice hockey rink is bathed in the glow of spotlights as players skillfully glide across the ice. The scoreboard prominently displays the steadily increasing total revenue generated by the National Hockey League. Meanwhile, in the stands, a group of players huddle together, eagerly discussing game strategies and equipment improvements. In the background, a large banner proudly displays the increasing number of patents granted in the US, symbolizing the surge in new ideas and inventions sparked by the players' innovative approach to the game. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of an ice hockey rink illuminated by vibrant, multicolored spotlights. Show players gliding gracefully across the glistening ice, emphasizing their skill and agility. The scoreboard should prominently feature the growing total revenue of the National Hockey League. In the stands, depict a group of players animatedly discussing game strategies and equipment improvements. In the background, include a large banner proudly displaying the increasing number of patents granted in the US, symbolizing the surge in new ideas and inventions sparked by the players' innovative approach to the game. The style should take inspiration from pop art, with bold and contrasting colors, along with exaggerated and stylized forms to lend a dynamic and eye-catching quality to the overall visual.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Total revenue generated by the National Hockey League caused Patents granted in the US to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted

The Journal of Sports Finance and Innovation

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Total revenue generated by the National Hockey League and Patents granted in the US. Make lots of jokes, goofy observations, and puns.

Make the title seem clever.

Your research team used data from Statista and USPTO to assess this nagging question. You found a correlation coefficient of 0.8880719 and p < 0.01 for 2006 to 2020.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted

[[ABSTRACT]]
This study explores the surprising relationship between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States. By deploying rigorous statistical analysis using data from Statista and the United States Patent and Trademark Office (USPTO), we unearthed a correlation coefficient of 0.8880719 and a p-value less than 0.01 for the years 2006 to 2020. The findings suggest a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. Our analysis sheds light on the puckuliar interplay between hockey economics and patent activity, pointing to potential avenues for future research at the intersection of sports and innovation.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Total revenue generated by the National Hockey League and Patents granted in the US. Make lots of jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted

[[ABSTRACT]]
This study explores the surprising relationship between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States. By deploying rigorous statistical analysis using data from Statista and the United States Patent and Trademark Office (USPTO), we unearthed a correlation coefficient of 0.8880719 and a p-value less than 0.01 for the years 2006 to 2020. The findings suggest a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. Our analysis sheds light on the puckuliar interplay between hockey economics and patent activity, pointing to potential avenues for future research at the intersection of sports and innovation.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As the saying goes, "There's no business like snow business," and the National Hockey League (NHL) is no exception. With its fast-paced action, bone-jarring hits, and soaring ticket sales, the NHL has long been a focal point of economic and sporting interest. However, what if we told you that the success of the NHL may extend beyond the rink and into the world of innovation and patents? Yes, you heard that right – we're delving into the icy depths of the connection between the NHL's total revenue and the number of patents granted in the United States. It's a tale that may seem as outlandish as a zamboni performing figure eights, but the evidence we present will have you shouting "goal" in no time.

In the grand tradition of unexpected pairings, such as peanut butter and jelly or Bert and Ernie, this study aims to uncover the hidden link between the financial prowess of the NHL and the inventive spirit behind patented creations. While one may initially assume these two realms to be as compatible as a hockey puck on a golf course, our analysis paints a different picture altogether. Strap on your skates, because we're about to glide through a puckuliar narrative of sports, money, and intellectual property that may just leave you shouting, "Lord Stanley, what a discovery!"



Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft 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 Total revenue generated by the National Hockey League and Patents granted in the US. 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 the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted

[[ABSTRACT]]
This study explores the surprising relationship between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States. By deploying rigorous statistical analysis using data from Statista and the United States Patent and Trademark Office (USPTO), we unearthed a correlation coefficient of 0.8880719 and a p-value less than 0.01 for the years 2006 to 2020. The findings suggest a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. Our analysis sheds light on the puckuliar interplay between hockey economics and patent activity, pointing to potential avenues for future research at the intersection of sports and innovation.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the saying goes, "There's no business like snow business," and the National Hockey League (NHL) is no exception. With its fast-paced action, bone-jarring hits, and soaring ticket sales, the NHL has long been a focal point of economic and sporting interest. However, what if we told you that the success of the NHL may extend beyond the rink and into the world of innovation and patents? Yes, you heard that right – we're delving into the icy depths of the connection between the NHL's total revenue and the number of patents granted in the United States. It's a tale that may seem as outlandish as a zamboni performing figure eights, but the evidence we present will have you shouting "goal" in no time.
In the grand tradition of unexpected pairings, such as peanut butter and jelly or Bert and Ernie, this study aims to uncover the hidden link between the financial prowess of the NHL and the inventive spirit behind patented creations. While one may initially assume these two realms to be as compatible as a hockey puck on a golf course, our analysis paints a different picture altogether. Strap on your skates, because we're about to glide through a puckuliar narrative of sports, money, and intellectual property that may just leave you shouting, "Lord Stanley, what a discovery!"


-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.," the authors find a statistically significant positive correlation between sporting events and economic activity. In "Doe's study," the researchers examine the economic impact of professional sports leagues, finding evidence of substantial financial influence within local and national economies. Similarly, "Jones et al." investigate the relationship between innovation and economic growth, illustrating the pivotal role of patents in driving technological advancement and prosperity.

Delving deeper into the economic and sporting spheres, "Moneyball" by Michael Lewis presents a compelling narrative of the Oakland Athletics' unconventional approach to baseball, highlighting the intersection of sports and financial strategy. In "The Art of Innovation" by Tom Kelley, the author explores the dynamics of creativity and invention within organizations, shedding light on the process of ideation and development of new products and technologies.

Drawing inspiration from a different realm, the fictional works of "The Mighty Ducks" series and "Beartown" by Fredrik Backman provide a glimpse into the fictionalized world of ice hockey and its broader societal impact, emphasizing the emotive and communal aspects of sports culture.

Expanding the scope of literature review through unconventional sources, the researchers conducted an extensive analysis of labels and descriptions on household products and daily necessities, including the intriguing insights garnered from the backs of shampoo bottles. Although not traditionally recognized as scholarly material, these unconventional sources surprisingly yielded unexpected and enlightening revelations underpinning the quirky relationship between the National Hockey League's financial performance and the issuance of patents in the United States.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Total revenue generated by the National Hockey League and Patents granted in the US. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Statista and USPTO . You used data from 2006 to 2020

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]]
Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted

[[ABSTRACT]]
This study explores the surprising relationship between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States. By deploying rigorous statistical analysis using data from Statista and the United States Patent and Trademark Office (USPTO), we unearthed a correlation coefficient of 0.8880719 and a p-value less than 0.01 for the years 2006 to 2020. The findings suggest a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. Our analysis sheds light on the puckuliar interplay between hockey economics and patent activity, pointing to potential avenues for future research at the intersection of sports and innovation.

[[INTRODUCTION]]
As the saying goes, "There's no business like snow business," and the National Hockey League (NHL) is no exception. With its fast-paced action, bone-jarring hits, and soaring ticket sales, the NHL has long been a focal point of economic and sporting interest. However, what if we told you that the success of the NHL may extend beyond the rink and into the world of innovation and patents? Yes, you heard that right – we're delving into the icy depths of the connection between the NHL's total revenue and the number of patents granted in the United States. It's a tale that may seem as outlandish as a zamboni performing figure eights, but the evidence we present will have you shouting "goal" in no time.
In the grand tradition of unexpected pairings, such as peanut butter and jelly or Bert and Ernie, this study aims to uncover the hidden link between the financial prowess of the NHL and the inventive spirit behind patented creations. While one may initially assume these two realms to be as compatible as a hockey puck on a golf course, our analysis paints a different picture altogether. Strap on your skates, because we're about to glide through a puckuliar narrative of sports, money, and intellectual property that may just leave you shouting, "Lord Stanley, what a discovery!"


-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

The methodology employed in this study aimed to dissect the seemingly incongruous relationship between the total revenue of the National Hockey League (NHL) and the number of patents granted in the United States. Data for the NHL's total revenue was sourced from Statista, while the number of patents granted in the U.S. was collected from the United States Patent and Trademark Office (USPTO), through a process that was as meticulous as analyzing the stitches on a hockey puck.

To begin, the research team performed a thorough review of existing academic literature and data sources to identify potential variables that could influence both NHL's total revenue and the number of patents granted. Upon identifying these variables, a series of convoluted statistical analyses were concocted to wrangle the data into submission.

The NHL's total revenue was plotted over time, resembling the trajectory of a puck hurtling towards a goalie's net. Similarly, the number of patents granted in the U.S. was graphed, creating a visual representation as compelling as a top-shelf slapshot. The relationship between these two variables was then examined using the most sophisticated statistical methods available - or failing that, the ones that had the most entertaining acronyms.

In order to establish a concrete connection, correlation analysis was performed, resembling the synchronized movements of a well-coordinated power play. Furthermore, a regression analysis was executed to disentangle the nuanced interplay between the revenue of the NHL and the patent activity in the U.S., akin to a referee untangling a scrum in the corner of the rink.

The data from 2006 to 2020 was as carefully tended to as the ice in between periods, ensuring a comprehensive understanding of the relationship between these two seemingly unrelated domains. Finally, a series of sensitivity analyses were conducted to test the robustness of the findings, as we made sure our results were as solid as the boards surrounding the rink.

In conclusion, the methodology used in this study was as rigorous as a coach's game plan, serving as the foundation for uncovering the puckuliar connection between the financial success of the NHL and the level of innovation represented by patents granted.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the 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 Total revenue generated by the National Hockey League and Patents granted in the US. Make lots of jokes, goofy observations, and puns.

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

For the time period 2006 to 2020, you found a correlation 0.8880719, r-squared of 0.7886717, 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]]
Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted

[[ABSTRACT]]
This study explores the surprising relationship between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States. By deploying rigorous statistical analysis using data from Statista and the United States Patent and Trademark Office (USPTO), we unearthed a correlation coefficient of 0.8880719 and a p-value less than 0.01 for the years 2006 to 2020. The findings suggest a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. Our analysis sheds light on the puckuliar interplay between hockey economics and patent activity, pointing to potential avenues for future research at the intersection of sports and innovation.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As the saying goes, "There's no business like snow business," and the National Hockey League (NHL) is no exception. With its fast-paced action, bone-jarring hits, and soaring ticket sales, the NHL has long been a focal point of economic and sporting interest. However, what if we told you that the success of the NHL may extend beyond the rink and into the world of innovation and patents? Yes, you heard that right – we're delving into the icy depths of the connection between the NHL's total revenue and the number of patents granted in the United States. It's a tale that may seem as outlandish as a zamboni performing figure eights, but the evidence we present will have you shouting "goal" in no time.
In the grand tradition of unexpected pairings, such as peanut butter and jelly or Bert and Ernie, this study aims to uncover the hidden link between the financial prowess of the NHL and the inventive spirit behind patented creations. While one may initially assume these two realms to be as compatible as a hockey puck on a golf course, our analysis paints a different picture altogether. Strap on your skates, because we're about to glide through a puckuliar narrative of sports, money, and intellectual property that may just leave you shouting, "Lord Stanley, what a discovery!"


-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Astonishingly, our analysis revealed a striking correlation coefficient of 0.8880719 between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States from 2006 to 2020. This puckuliar correlation suggests a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. The r-squared value of 0.7886717 indicates that approximately 78.87% of the variability in patents granted can be explained by the variability in NHL total revenue. It seems the NHL's triumphs on the ice may be mirrored by a surge in patent-based triumphs off the ice – it's a real hat trick of economic and innovative activity!

Moreover, the p-value being less than 0.01 provides clear evidence against the null hypothesis, supporting the assertion that there is indeed a significant relationship between NHL total revenue and patents granted in the United States. This finding suggests that as the NHL's financial fortunes soar, so too does the level of innovative activity represented by patents granted. It's as if the zamboni of success is resurfacing the ice of invention, creating a favorable environment for patent activities to thrive.

In Figure 1, the scatterplot visually emphasizes the strong correlation we uncovered, showcasing how the NHL's financial performance seems to skate hand in hand with the number of patents granted in the United States. It's almost as if the NHL's booming revenue is firing shots on goal, and the USPTO is busy making saves in the form of patents granted. This unexpected synergy between professional hockey and intellectual property sure puts a new spin on the term "power play."

Overall, our findings highlight the unexpected synergy between the financial success of the NHL and the innovative output represented by patents, opening the door to further investigations into the fascinating interplay between sports economics and intellectual property.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Total revenue generated by the National Hockey League and Patents granted in the US. Make lots of jokes, goofy observations, and puns.

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]]
Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted

[[ABSTRACT]]
This study explores the surprising relationship between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States. By deploying rigorous statistical analysis using data from Statista and the United States Patent and Trademark Office (USPTO), we unearthed a correlation coefficient of 0.8880719 and a p-value less than 0.01 for the years 2006 to 2020. The findings suggest a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. Our analysis sheds light on the puckuliar interplay between hockey economics and patent activity, pointing to potential avenues for future research at the intersection of sports and innovation.

[[LITERATURE REVIEW]]
In "Smith et al.," the authors find a statistically significant positive correlation between sporting events and economic activity. In "Doe's study," the researchers examine the economic impact of professional sports leagues, finding evidence of substantial financial influence within local and national economies. Similarly, "Jones et al." investigate the relationship between innovation and economic growth, illustrating the pivotal role of patents in driving technological advancement and prosperity.
Delving deeper into the economic and sporting spheres, "Moneyball" by Michael Lewis presents a compelling narrative of the Oakland Athletics' unconventional approach to baseball, highlighting the intersection of sports and financial strategy. In "The Art of Innovation" by Tom Kelley, the author explores the dynamics of creativity and invention within organizations, shedding light on the process of ideation and development of new products and technologies.
Drawing inspiration from a different realm, the fictional works of "The Mighty Ducks" series and "Beartown" by Fredrik Backman provide a glimpse into the fictionalized world of ice hockey and its broader societal impact, emphasizing the emotive and communal aspects of sports culture.
Expanding the scope of literature review through unconventional sources, the researchers conducted an extensive analysis of labels and descriptions on household products and daily necessities, including the intriguing insights garnered from the backs of shampoo bottles. Although not traditionally recognized as scholarly material, these unconventional sources surprisingly yielded unexpected and enlightening revelations underpinning the quirky relationship between the National Hockey League's financial performance and the issuance of patents in the United States.

[[RESULTS]]
Astonishingly, our analysis revealed a striking correlation coefficient of 0.8880719 between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States from 2006 to 2020. This puckuliar correlation suggests a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. The r-squared value of 0.7886717 indicates that approximately 78.87% of the variability in patents granted can be explained by the variability in NHL total revenue. It seems the NHL's triumphs on the ice may be mirrored by a surge in patent-based triumphs off the ice – it's a real hat trick of economic and innovative activity!
Moreover, the p-value being less than 0.01 provides clear evidence against the null hypothesis, supporting the assertion that there is indeed a significant relationship between NHL total revenue and patents granted in the United States. This finding suggests that as the NHL's financial fortunes soar, so too does the level of innovative activity represented by patents granted. It's as if the zamboni of success is resurfacing the ice of invention, creating a favorable environment for patent activities to thrive.
In Figure 1, the scatterplot visually emphasizes the strong correlation we uncovered, showcasing how the NHL's financial performance seems to skate hand in hand with the number of patents granted in the United States. It's almost as if the NHL's booming revenue is firing shots on goal, and the USPTO is busy making saves in the form of patents granted. This unexpected synergy between professional hockey and intellectual property sure puts a new spin on the term "power play."
Overall, our findings highlight the unexpected synergy between the financial success of the NHL and the innovative output represented by patents, opening the door to further investigations into the fascinating interplay between sports economics and intellectual property.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our study have undoubtedly uncovered a puckuliar relationship between the National Hockey League's (NHL) total revenue and the number of patents granted in the United States. Our findings align with prior research that has illustrated the influential role of sporting events in economic activity and the significant impact of professional sports leagues on local and national economies. Somehow, the financial victories of the NHL seem to be mirrored by an upswing in patent-based triumphs, as though a well-executed power play on the ice leads to a surge of innovative activity off the ice.

Our results are in line with prior studies that have demonstrated a positive relationship between innovation and economic growth, underscoring the essential role of patents in driving technological advancement and prosperity. In a way, it's as if the NHL's prosperity acts as a catalyst for a flurry of inventive endeavors, inspiring individuals and organizations to pursue creative solutions and technical breakthroughs – perhaps the hockey stick’s curve is influencing the shape of innovation, creating unexpected ripples in the market.

The unexpected synergy we have uncovered between professional hockey and intellectual property is reminiscent of the unorthodox approach to baseball chronicled in Michael Lewis's "Moneyball." Much like the Oakland Athletics' unconventional strategy, the intertwining of hockey economics and patent activity constitutes a fascinating intersection of sports and financial strategy, reinforcing the notion that success in one domain can catalyze innovation in another – almost like a well-executed slapshot setting off a chain reaction of inventive ideas.

Moreover, the unintentional insights we gleaned from unconventional sources, such as the fictionalized world of ice hockey in "The Mighty Ducks" series and "Beartown" by Fredrik Backman, underscore the emotive and communal aspects of sports culture that weave into the fabric of economic and innovative activity. It's as if the emotional highs and lows of the sporting world send shockwaves into the sphere of intellectual property, influencing the ebbs and flows of inventive output in unforeseen ways.

The unexpected correlation we have unearthed emphasizes the potential for further investigations into the fascinating interplay between sports economics and intellectual property. Our findings open the door to a deeper exploration of the mechanisms through which sporting successes catalyze inventive activity, launching a line of inquiry that promises to score its fair share of academic and practical goals.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Total revenue generated by the National Hockey League and Patents granted in the US. Make lots of jokes, goofy observations, and puns.

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]]
Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted

[[ABSTRACT]]
This study explores the surprising relationship between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States. By deploying rigorous statistical analysis using data from Statista and the United States Patent and Trademark Office (USPTO), we unearthed a correlation coefficient of 0.8880719 and a p-value less than 0.01 for the years 2006 to 2020. The findings suggest a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. Our analysis sheds light on the puckuliar interplay between hockey economics and patent activity, pointing to potential avenues for future research at the intersection of sports and innovation.

[[INTRDUCTION]]
As the saying goes, "There's no business like snow business," and the National Hockey League (NHL) is no exception. With its fast-paced action, bone-jarring hits, and soaring ticket sales, the NHL has long been a focal point of economic and sporting interest. However, what if we told you that the success of the NHL may extend beyond the rink and into the world of innovation and patents? Yes, you heard that right – we're delving into the icy depths of the connection between the NHL's total revenue and the number of patents granted in the United States. It's a tale that may seem as outlandish as a zamboni performing figure eights, but the evidence we present will have you shouting "goal" in no time.
In the grand tradition of unexpected pairings, such as peanut butter and jelly or Bert and Ernie, this study aims to uncover the hidden link between the financial prowess of the NHL and the inventive spirit behind patented creations. While one may initially assume these two realms to be as compatible as a hockey puck on a golf course, our analysis paints a different picture altogether. Strap on your skates, because we're about to glide through a puckuliar narrative of sports, money, and intellectual property that may just leave you shouting, "Lord Stanley, what a discovery!"


[[RESULTS]]
Astonishingly, our analysis revealed a striking correlation coefficient of 0.8880719 between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States from 2006 to 2020. This puckuliar correlation suggests a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. The r-squared value of 0.7886717 indicates that approximately 78.87% of the variability in patents granted can be explained by the variability in NHL total revenue. It seems the NHL's triumphs on the ice may be mirrored by a surge in patent-based triumphs off the ice – it's a real hat trick of economic and innovative activity!
Moreover, the p-value being less than 0.01 provides clear evidence against the null hypothesis, supporting the assertion that there is indeed a significant relationship between NHL total revenue and patents granted in the United States. This finding suggests that as the NHL's financial fortunes soar, so too does the level of innovative activity represented by patents granted. It's as if the zamboni of success is resurfacing the ice of invention, creating a favorable environment for patent activities to thrive.
In Figure 1, the scatterplot visually emphasizes the strong correlation we uncovered, showcasing how the NHL's financial performance seems to skate hand in hand with the number of patents granted in the United States. It's almost as if the NHL's booming revenue is firing shots on goal, and the USPTO is busy making saves in the form of patents granted. This unexpected synergy between professional hockey and intellectual property sure puts a new spin on the term "power play."
Overall, our findings highlight the unexpected synergy between the financial success of the NHL and the innovative output represented by patents, opening the door to further investigations into the fascinating interplay between sports economics and intellectual property.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has revealed a puckuliar and compelling relationship between NHL total revenue and patents granted in the United States. The evidence suggests that the financial success of the NHL may indeed be a catalyst for stimulating inventive activities, much like a well-placed slapshot can energize a team. It's as if the NHL's economic victories are inspiring a flurry of creative breakthroughs across the nation, akin to a sudden power play leading to a surge in patent activity.

The unexpected connection we've uncovered between the seemingly distinct realms of sports economics and intellectual property is nothing short of a hat trick in the world of scholarly discoveries. This revelation is akin to finding out that hockey sticks have a secret ability to unlock the mysteries of innovation – a real plot twist worthy of a Stanley Cup finals game.

With a correlation coefficient of 0.8880719 and a p-value less than 0.01, the statistical support for this association is as solid as the ice beneath a skilled skater. It's as if the NHL's financial prowess reignites the flames of innovation, driving forward a game-changing synergy between sports and patent activities.

In light of these findings, it seems, dare we say, that no more research is needed in this area. The study's results certainly pack a punch, delivering an unexpected and entertaining twist to the age-old debate on the intersection of sports and innovation. With our study, we can confidently say that the question of whether the NHL's success is linked to patent activity has been convincingly answered – and the verdict is as clear as a freshly cleaned rink: it certainly is.


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 Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Sports Finance and Innovation


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 Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Interdisciplinary Ice Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Stick Handling Success: A Puckuliar Connection Between National Hockey League Total Revenue and US Patents Granted with an abstract of This study explores the surprising relationship between the total revenue generated by the National Hockey League (NHL) and the number of patents granted in the United States. By deploying rigorous statistical analysis using data from Statista and the United States Patent and Trademark Office (USPTO), we unearthed a correlation coefficient of 0.8880719 and a p-value less than 0.01 for the years 2006 to 2020. The findings suggest a strong positive association between the financial success of the NHL and the level of innovation represented by patents granted. Our analysis sheds light on the puckuliar interplay between hockey economics and patent activity, pointing to potential avenues for future research at the intersection of sports and innovation.

ChatGPT:

National Hockey League revenue, US patents granted, NHL financial success, patent activity correlation, NHL revenue trend, USPTO granted patents, sports innovation, hockey economics, innovation correlation, NHL financial impact, patent statistics, NHL revenue analysis

*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

Total revenue generated by the National Hockey League
Source: Statista
See what else correlates with Total revenue generated by the National Hockey League

Patents granted in the US
Detailed data title: Total number of patents granted in the US
Source: USPTO
See what else correlates with Patents granted in the US

Correlation r = 0.8880719 (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 = 0.7886717 (Coefficient of determination)
This means 78.9% of the change in the one variable (i.e., Patents granted in the US) is predictable based on the change in the other (i.e., Total revenue generated by the National Hockey League) over the 15 years from 2006 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 9.8E-6. 0.0000098383472958837230000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.89 in 0.00098% of random cases. Said differently, if you correlated 101,643 random variables You don't actually need 101 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 14 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 14 because we have two variables measured over a period of 15 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.

[ 0.69, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200620072008200920102011201220132014201520162017201820192020
Total revenue generated by the National Hockey League (Billion US Dollars)22.442.752.822.933.093.372.633.73.984.14.434.865.094.37
Patents granted in the US (Patents granted)196405182899185224191927244341247713276788302948326032325980333583351403339992391103388900




Why this works

  1. 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.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([2,2.44,2.75,2.82,2.93,3.09,3.37,2.63,3.7,3.98,4.1,4.43,4.86,5.09,4.37,])
array_2 = np.array([196405,182899,185224,191927,244341,247713,276788,302948,326032,325980,333583,351403,339992,391103,388900,])
array_1_name = "Total revenue generated by the National Hockey League"
array_2_name = "Patents granted in the US"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating skills are top-notch!


Correlation ID: 2631 · Black Variable ID: 436 · Red Variable ID: 848
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0