about · email me · subscribe
Spurious correlation #1,698 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of chemists in Alaska and the second variable is Total runs scored in the World Series.  The chart goes from 2003 to 2013, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the number of chemists in Alaska increased, so did the total runs scored in the World Series. This is because the chemists discovered a new compound that, when applied to baseballs, made them mysteriously bouncier. It was a true case of Alaskan chemists adding a little extra *chemistry* to the game!

Model: dalle-3
Prompt: Generate an image of a steampunk-style laboratory in the snowy Alaskan wilderness. Within the laboratory, a team of chemists is seen working diligently on various experiments, all while keeping one eye on a television screen showing the World Series. The tension in the room is evident as the runs scored in the game correlate to elements on the periodic table. The chemists cheer and scribble down notes as the total runs scored in the series rises, showcasing their integration of a love for science and baseball in this remote outpost. 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 number of chemists in Alaska and Total runs scored in the World Series. 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: Pop art Psychedelic Steampunk Psychedelic Parallax art
ChatGPT: Steampunk

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 number of chemists in Alaska and Total runs scored in the World Series together. Keep the description simple.
ChatGPT: In a small laboratory nestled in the snowy Alaskan wilderness, a team of dedicated chemists work diligently on experiments as they keep one eye on a television screen. The World Series is on, and the tension in the room is palpable as the runs scored in the game correlate to the elements on their periodic table. The chemists cheer and scribble down notes as the total runs scored in the series rises, integrating their love for both science and baseball in this remote outpost.

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: [ Steampunk ] and depicting this scene: In a small laboratory nestled in the snowy Alaskan wilderness, a team of dedicated chemists work diligently on experiments as they keep one eye on a television screen. The World Series is on, and the tension in the room is palpable as the runs scored in the game correlate to the elements on their periodic table. The chemists cheer and scribble down notes as the total runs scored in the series rises, integrating their love for both science and baseball in this remote outpost. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a steampunk-style laboratory in the snowy Alaskan wilderness. Within the laboratory, a team of chemists is seen working diligently on various experiments, all while keeping one eye on a television screen showing the World Series. The tension in the room is evident as the runs scored in the game correlate to elements on the periodic table. The chemists cheer and scribble down notes as the total runs scored in the series rises, showcasing their integration of a love for science and baseball in this remote outpost.

*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 increases in The number of chemists in Alaska positively influenced Total runs scored in the World Series. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores

The Journal of Unconventional Connections

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between The number of chemists in Alaska and Total runs scored in the World Series. Make lots of jokes, goofy observations, and puns.

Make the title seem clever.

Your research team used data from Bureau of Larbor Statistics and Wikipedia to assess this nagging question. You found a correlation coefficient of 0.8613510 and p < 0.01 for 2003 to 2013.

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]]
"Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores"

[[ABSTRACT]]
While it may seem as whimsical as a heat-of-the-moment steal in the bottom of the ninth, our research delves into the ostensibly ludicrous connection between the number of chemists in Alaska and the total runs scored in the World Series. Utilizing data from the Bureau of Labor Statistics and Wikipedia, our team embarked on a jovial journey to uncover any potential correlation between these seemingly unrelated phenomena. Surprisingly, our analysis unveiled a robust correlation coefficient of 0.8613510, with a p-value less than 0.01, spanning the years 2003 to 2013. This unlikely association between the number of scientists concocting concoctions and the number of runs plated on the diamond may prompt further inquiries into the whimsical wonders of statistical serendipity. Our findings titrate the delicate balance between scientific curiosity and statistical amusement, serving as a testament to the unforeseen connections that permeate our statistical landscape.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between The number of chemists in Alaska and Total runs scored in the World Series. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
"Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores"

[[ABSTRACT]]
While it may seem as whimsical as a heat-of-the-moment steal in the bottom of the ninth, our research delves into the ostensibly ludicrous connection between the number of chemists in Alaska and the total runs scored in the World Series. Utilizing data from the Bureau of Labor Statistics and Wikipedia, our team embarked on a jovial journey to uncover any potential correlation between these seemingly unrelated phenomena. Surprisingly, our analysis unveiled a robust correlation coefficient of 0.8613510, with a p-value less than 0.01, spanning the years 2003 to 2013. This unlikely association between the number of scientists concocting concoctions and the number of runs plated on the diamond may prompt further inquiries into the whimsical wonders of statistical serendipity. Our findings titrate the delicate balance between scientific curiosity and statistical amusement, serving as a testament to the unforeseen connections that permeate our statistical landscape.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

What do chemists in Alaska and World Series run scores have in common, you might wonder? Well, as perplexing as it may seem, our team of intrepid researchers set out to investigate just that. While it might sound as improbable as a polar bear taking up figure skating, our study delves into the surprising correlation between these seemingly disparate entities.

In the realm of statistical oddities, the unlikely relationship between the number of chemists in Alaska and the total runs scored in the World Series caught our attention like a knuckleball in a sea of fastballs. The thought of these two apparently unrelated factors being interconnected was as bizarre as a walrus playing a trumpet – but our analysis revealed some eyebrow-raising results.

The scientific community continually seeks unexpected connections and peculiar patterns, much like a detective on the trail of a particularly confounding mystery. As such, our investigation into this whimsical relationship between Alaskan chemists and World Series run scores serves as a lighthearted yet intriguing exploration into the capricious world of statistical inquiry.

Fueled by curiosity and armed with a plethora of data from the Bureau of Labor Statistics and the hallowed pages of Wikipedia, our research team embarked on this peculiar pursuit of statistical serendipity. What we uncovered transcended our initial skepticism and led us into the lively realm of statistical amusement – serving as a testament to the whimsical wonders that await those who delve into the rich tapestry of numerical connections.

So, grab your lab coat and don your baseball cap, for we are about to embark on a journey that may leave you scratching your head with the same bemusement as a pitcher contemplating the mysteries of a knuckleball. This is the tale of scientific shenanigans, where the paths of Alaskan chemists and World Series run scores intersect in a statistical pas de deux that defies the conventional wisdom of causal relationships.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of chemists in Alaska and Total runs scored in the World Series. 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
"Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores"

[[ABSTRACT]]
While it may seem as whimsical as a heat-of-the-moment steal in the bottom of the ninth, our research delves into the ostensibly ludicrous connection between the number of chemists in Alaska and the total runs scored in the World Series. Utilizing data from the Bureau of Labor Statistics and Wikipedia, our team embarked on a jovial journey to uncover any potential correlation between these seemingly unrelated phenomena. Surprisingly, our analysis unveiled a robust correlation coefficient of 0.8613510, with a p-value less than 0.01, spanning the years 2003 to 2013. This unlikely association between the number of scientists concocting concoctions and the number of runs plated on the diamond may prompt further inquiries into the whimsical wonders of statistical serendipity. Our findings titrate the delicate balance between scientific curiosity and statistical amusement, serving as a testament to the unforeseen connections that permeate our statistical landscape.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
What do chemists in Alaska and World Series run scores have in common, you might wonder? Well, as perplexing as it may seem, our team of intrepid researchers set out to investigate just that. While it might sound as improbable as a polar bear taking up figure skating, our study delves into the surprising correlation between these seemingly disparate entities.
In the realm of statistical oddities, the unlikely relationship between the number of chemists in Alaska and the total runs scored in the World Series caught our attention like a knuckleball in a sea of fastballs. The thought of these two apparently unrelated factors being interconnected was as bizarre as a walrus playing a trumpet – but our analysis revealed some eyebrow-raising results.
The scientific community continually seeks unexpected connections and peculiar patterns, much like a detective on the trail of a particularly confounding mystery. As such, our investigation into this whimsical relationship between Alaskan chemists and World Series run scores serves as a lighthearted yet intriguing exploration into the capricious world of statistical inquiry.
Fueled by curiosity and armed with a plethora of data from the Bureau of Labor Statistics and the hallowed pages of Wikipedia, our research team embarked on this peculiar pursuit of statistical serendipity. What we uncovered transcended our initial skepticism and led us into the lively realm of statistical amusement – serving as a testament to the whimsical wonders that await those who delve into the rich tapestry of numerical connections.
So, grab your lab coat and don your baseball cap, for we are about to embark on a journey that may leave you scratching your head with the same bemusement as a pitcher contemplating the mysteries of a knuckleball. This is the tale of scientific shenanigans, where the paths of Alaskan chemists and World Series run scores intersect in a statistical pas de deux that defies the conventional wisdom of causal relationships.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith and Doe's Study of Unlikely Correlations," the authors find themselves embarking on an expedition akin to Lewis and Clark's, albeit in the realm of statistical endeavor. The study, while ostensibly serious in its pursuit of uncovering unforeseen connections, delves into the whimsical world of statistical oddities with the same fervor as a group of penguin researchers stumbling upon a disco party in the Antarctic. The authors uncover a myriad of unexpected relationships between seemingly unrelated variables, sending shockwaves through the staid world of statistical analysis.

Furthermore, in "Jones' Statistical Anomalies: A Collection of Statistical Peculiarities," the authors delve into numerous instances of unconventional numerical interplay, akin to stumbling upon a parade of dancing flamingos in the midst of a mundane statistical landscape. The study highlights the importance of remaining open to the possibility of serendipitous statistical associations, much like stumbling upon a treasure map in the middle of conducting a routine data analysis.

Moving beyond the hallowed halls of academic research, the literature on whimsical connections extends to non-fiction works such as "The Signal and the Noise" by Nate Silver and "Freakonomics" by Steven D. Levitt and Stephen J. Dubner, which elucidate the entertaining and often surprising world of statistical anomalies that lurk beneath the seemingly ordinary surface of data.

In the realm of fiction, books such as "The Curious Incident of the Dog in the Night-Time" by Mark Haddon and "The Hitchhiker's Guide to the Galaxy" by Douglas Adams, while not directly related to statistical oddities, nonetheless capture the sense of bewildering discovery and whimsical phenomena that permeate our study of unexpected connections.

Exploring the world of unexpected correlations requires a keen eye, an open mind, and a willingness to embrace the delightfully absurd. In this vein, the researchers turned to extracurricular sources of inspiration, including cartoons such as "Scooby-Doo" and children's shows like "Sesame Street," in a bid to infuse their exploration with a touch of light-hearted whimsy and unanticipated discoveries. These sources, while seemingly unrelated to the rigorous pursuit of statistical inquiry, served as a source of creative stimulation and a reminder of the playful nature of scientific exploration.

Overall, the literature on unlikely correlations and statistical serendipity underscores the importance of maintaining a sense of curiosity and humor in the sometimes austere world of research, as we tread lightly through the forest of data, mindful of the potential surprises that await us like a mischievous leprechaun at the end of a rainbow.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of chemists in Alaska and Total runs scored in the World Series. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Wikipedia . You used data from 2003 to 2013

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]]
"Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores"

[[ABSTRACT]]
While it may seem as whimsical as a heat-of-the-moment steal in the bottom of the ninth, our research delves into the ostensibly ludicrous connection between the number of chemists in Alaska and the total runs scored in the World Series. Utilizing data from the Bureau of Labor Statistics and Wikipedia, our team embarked on a jovial journey to uncover any potential correlation between these seemingly unrelated phenomena. Surprisingly, our analysis unveiled a robust correlation coefficient of 0.8613510, with a p-value less than 0.01, spanning the years 2003 to 2013. This unlikely association between the number of scientists concocting concoctions and the number of runs plated on the diamond may prompt further inquiries into the whimsical wonders of statistical serendipity. Our findings titrate the delicate balance between scientific curiosity and statistical amusement, serving as a testament to the unforeseen connections that permeate our statistical landscape.

[[INTRODUCTION]]
What do chemists in Alaska and World Series run scores have in common, you might wonder? Well, as perplexing as it may seem, our team of intrepid researchers set out to investigate just that. While it might sound as improbable as a polar bear taking up figure skating, our study delves into the surprising correlation between these seemingly disparate entities.
In the realm of statistical oddities, the unlikely relationship between the number of chemists in Alaska and the total runs scored in the World Series caught our attention like a knuckleball in a sea of fastballs. The thought of these two apparently unrelated factors being interconnected was as bizarre as a walrus playing a trumpet – but our analysis revealed some eyebrow-raising results.
The scientific community continually seeks unexpected connections and peculiar patterns, much like a detective on the trail of a particularly confounding mystery. As such, our investigation into this whimsical relationship between Alaskan chemists and World Series run scores serves as a lighthearted yet intriguing exploration into the capricious world of statistical inquiry.
Fueled by curiosity and armed with a plethora of data from the Bureau of Labor Statistics and the hallowed pages of Wikipedia, our research team embarked on this peculiar pursuit of statistical serendipity. What we uncovered transcended our initial skepticism and led us into the lively realm of statistical amusement – serving as a testament to the whimsical wonders that await those who delve into the rich tapestry of numerical connections.
So, grab your lab coat and don your baseball cap, for we are about to embark on a journey that may leave you scratching your head with the same bemusement as a pitcher contemplating the mysteries of a knuckleball. This is the tale of scientific shenanigans, where the paths of Alaskan chemists and World Series run scores intersect in a statistical pas de deux that defies the conventional wisdom of causal relationships.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unearth the enigmatic connection between the number of chemists in the frosty domain of Alaska and the total runs scored in the prestigious World Series, we navigated a winding path through the labyrinth of statistical inquiry. Our pursuit of statistical serendipity began with the procurement of data from reliable sources, primarily the Bureau of Labor Statistics and the illustrious citadel of knowledge, Wikipedia. The years 2003 to 2013 provided the temporal boundaries within which we sought to unravel this whimsical riddle, ensuring a comprehensive coverage of phenomena that spanned a decade of scientific and sporting evolution.

Armed with information that traversed both the scientific realm and the world of sports, our intrepid research team embarked on the Herculean task of data collection. Our investigative journey saw us meticulously scouring through online databases, academic publications, and uncharted statistical seas to ascertain the number of chemists employed in the picturesque expanse of Alaska. This hunt for laborious alchemists culminated in the acquisition of precise numerical figures that encapsulated the delightful diversity of talent positioned amidst the northern lights.

In parallel, our quest delved into the spirited domain of baseball, where we harvested copious statistics pertaining to the total runs scored in the World Series across the aforementioned decade. These numerical gems were sought, not unlike a valiant outfielder pursuing a soaring fly ball, to provide a robust depiction of the scoring dynamics that unfolded within the majestic confines of the diamond.

With both sets of data securely ensconced within the annals of our research repository, we conducted a rigorous statistical analysis that was as intricate as the stitching on a new baseball. The elucidation of any potential correlation between these seemingly unrelated phenomena involved the deployment of sophisticated statistical techniques, including but not limited to correlation analysis, regression modelling, and time series examination.

Furthermore, our methodology encompassed the employment of erstwhile statistical software that has tuned many an analytical engine to purr melodiously. Utilizing this technological marvel, we subjected our data to a battery of statistical tests, peering through the lens of empirical scrutiny to discern any significant patterns that may have lain dormant beneath the surface.

The integration of these methodological components allowed us to not only uncover the high-spirited correlation coefficient of 0.8613510 that tied together the number of chemists in Alaska and the total runs scored in the World Series but also to affirm the statistical robustness of this surprising relationship. The acquisition of such outcomes served as a testament to the wit and whimsy that permeate the realms of scientific exploration and statistical inquiry, proving that even the most improbable connections can emerge from the crucible of empirical investigation.


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

Please make up the results section of an academic research paper presenting the findings of the connection between The number of chemists in Alaska and Total runs scored in the World Series. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Wikipedia .

For the time period 2003 to 2013, you found a correlation 0.8613510, r-squared of 0.7419255, 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]]
"Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores"

[[ABSTRACT]]
While it may seem as whimsical as a heat-of-the-moment steal in the bottom of the ninth, our research delves into the ostensibly ludicrous connection between the number of chemists in Alaska and the total runs scored in the World Series. Utilizing data from the Bureau of Labor Statistics and Wikipedia, our team embarked on a jovial journey to uncover any potential correlation between these seemingly unrelated phenomena. Surprisingly, our analysis unveiled a robust correlation coefficient of 0.8613510, with a p-value less than 0.01, spanning the years 2003 to 2013. This unlikely association between the number of scientists concocting concoctions and the number of runs plated on the diamond may prompt further inquiries into the whimsical wonders of statistical serendipity. Our findings titrate the delicate balance between scientific curiosity and statistical amusement, serving as a testament to the unforeseen connections that permeate our statistical landscape.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
What do chemists in Alaska and World Series run scores have in common, you might wonder? Well, as perplexing as it may seem, our team of intrepid researchers set out to investigate just that. While it might sound as improbable as a polar bear taking up figure skating, our study delves into the surprising correlation between these seemingly disparate entities.
In the realm of statistical oddities, the unlikely relationship between the number of chemists in Alaska and the total runs scored in the World Series caught our attention like a knuckleball in a sea of fastballs. The thought of these two apparently unrelated factors being interconnected was as bizarre as a walrus playing a trumpet – but our analysis revealed some eyebrow-raising results.
The scientific community continually seeks unexpected connections and peculiar patterns, much like a detective on the trail of a particularly confounding mystery. As such, our investigation into this whimsical relationship between Alaskan chemists and World Series run scores serves as a lighthearted yet intriguing exploration into the capricious world of statistical inquiry.
Fueled by curiosity and armed with a plethora of data from the Bureau of Labor Statistics and the hallowed pages of Wikipedia, our research team embarked on this peculiar pursuit of statistical serendipity. What we uncovered transcended our initial skepticism and led us into the lively realm of statistical amusement – serving as a testament to the whimsical wonders that await those who delve into the rich tapestry of numerical connections.
So, grab your lab coat and don your baseball cap, for we are about to embark on a journey that may leave you scratching your head with the same bemusement as a pitcher contemplating the mysteries of a knuckleball. This is the tale of scientific shenanigans, where the paths of Alaskan chemists and World Series run scores intersect in a statistical pas de deux that defies the conventional wisdom of causal relationships.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Astonishingly, our investigation into the correlation between the number of chemists in Alaska and the total runs scored in the World Series yielded a robust and unforeseen relationship. Spanning the years 2003 to 2013, our study unveiled a striking correlation coefficient of 0.8613510, accompanied by an r-squared value of 0.7419255 and a p-value less than 0.01. These statistical findings defy the expectation that these two variables are as unrelated as a snowflake in the desert.

The inference of a strong positive correlation provides a basis for further exploration into the whimsical world of statistical serendipity. The unexpected connection between the number of chemists in the northern wilds of Alaska and the number of runs on the baseball diamond raises questions as perplexing as the trajectory of a knuckleball.

The scatterplot (Fig. 1) visually portrays the surprising relationship between the number of chemists in Alaska and the total runs scored in the World Series, offering a playful yet thought-provoking depiction of this unlikely interconnection.

This unexpected association of scientific pursuits and sporting feats accentuates the unexplored territories in correlational studies and motivates further investigations into the colorful and unconventional intersections within the fabric of statistical inquiry.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of chemists in Alaska and Total runs scored in the World Series. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores"

[[ABSTRACT]]
While it may seem as whimsical as a heat-of-the-moment steal in the bottom of the ninth, our research delves into the ostensibly ludicrous connection between the number of chemists in Alaska and the total runs scored in the World Series. Utilizing data from the Bureau of Labor Statistics and Wikipedia, our team embarked on a jovial journey to uncover any potential correlation between these seemingly unrelated phenomena. Surprisingly, our analysis unveiled a robust correlation coefficient of 0.8613510, with a p-value less than 0.01, spanning the years 2003 to 2013. This unlikely association between the number of scientists concocting concoctions and the number of runs plated on the diamond may prompt further inquiries into the whimsical wonders of statistical serendipity. Our findings titrate the delicate balance between scientific curiosity and statistical amusement, serving as a testament to the unforeseen connections that permeate our statistical landscape.

[[LITERATURE REVIEW]]
In "Smith and Doe's Study of Unlikely Correlations," the authors find themselves embarking on an expedition akin to Lewis and Clark's, albeit in the realm of statistical endeavor. The study, while ostensibly serious in its pursuit of uncovering unforeseen connections, delves into the whimsical world of statistical oddities with the same fervor as a group of penguin researchers stumbling upon a disco party in the Antarctic. The authors uncover a myriad of unexpected relationships between seemingly unrelated variables, sending shockwaves through the staid world of statistical analysis.
Furthermore, in "Jones' Statistical Anomalies: A Collection of Statistical Peculiarities," the authors delve into numerous instances of unconventional numerical interplay, akin to stumbling upon a parade of dancing flamingos in the midst of a mundane statistical landscape. The study highlights the importance of remaining open to the possibility of serendipitous statistical associations, much like stumbling upon a treasure map in the middle of conducting a routine data analysis.
Moving beyond the hallowed halls of academic research, the literature on whimsical connections extends to non-fiction works such as "The Signal and the Noise" by Nate Silver and "Freakonomics" by Steven D. Levitt and Stephen J. Dubner, which elucidate the entertaining and often surprising world of statistical anomalies that lurk beneath the seemingly ordinary surface of data.
In the realm of fiction, books such as "The Curious Incident of the Dog in the Night-Time" by Mark Haddon and "The Hitchhiker's Guide to the Galaxy" by Douglas Adams, while not directly related to statistical oddities, nonetheless capture the sense of bewildering discovery and whimsical phenomena that permeate our study of unexpected connections.
Exploring the world of unexpected correlations requires a keen eye, an open mind, and a willingness to embrace the delightfully absurd. In this vein, the researchers turned to extracurricular sources of inspiration, including cartoons such as "Scooby-Doo" and children's shows like "Sesame Street," in a bid to infuse their exploration with a touch of light-hearted whimsy and unanticipated discoveries. These sources, while seemingly unrelated to the rigorous pursuit of statistical inquiry, served as a source of creative stimulation and a reminder of the playful nature of scientific exploration.
Overall, the literature on unlikely correlations and statistical serendipity underscores the importance of maintaining a sense of curiosity and humor in the sometimes austere world of research, as we tread lightly through the forest of data, mindful of the potential surprises that await us like a mischievous leprechaun at the end of a rainbow.

[[RESULTS]]
Astonishingly, our investigation into the correlation between the number of chemists in Alaska and the total runs scored in the World Series yielded a robust and unforeseen relationship. Spanning the years 2003 to 2013, our study unveiled a striking correlation coefficient of 0.8613510, accompanied by an r-squared value of 0.7419255 and a p-value less than 0.01. These statistical findings defy the expectation that these two variables are as unrelated as a snowflake in the desert.
The inference of a strong positive correlation provides a basis for further exploration into the whimsical world of statistical serendipity. The unexpected connection between the number of chemists in the northern wilds of Alaska and the number of runs on the baseball diamond raises questions as perplexing as the trajectory of a knuckleball.
The scatterplot (Fig. 1) visually portrays the surprising relationship between the number of chemists in Alaska and the total runs scored in the World Series, offering a playful yet thought-provoking depiction of this unlikely interconnection.
This unexpected association of scientific pursuits and sporting feats accentuates the unexplored territories in correlational studies and motivates further investigations into the colorful and unconventional intersections within the fabric of statistical inquiry.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our analysis of the unlikely connection between the number of chemists in Alaska and the total runs scored in the World Series has unveiled a peculiarly robust correlation, akin to stumbling upon a hidden treasure chest in the midst of a vast statistical ocean. The seemingly whimsical pursuit embarked upon in this study aligns with the spirit of prior research that has embraced the untamed landscape of statistical anomalies with the same fervor as a team of researchers stumbling upon a pack of playful penguins.

Intriguingly, our findings are in line with previous studies that have dared to explore the unpredictable and often delightful connections that lie beneath the surface of seemingly unrelated data. Much like the unlikely relationships uncovered by Smith and Doe in their expedition into uncharted statistical territories, our investigation has illuminated a surprising harmony between the number of chemists in the frosty climes of Alaska and the total runs tallied on the baseball diamond.

Drawing from the colorful tapestry of prior literature, our study serves as a testament to the unexpected correlations that dart like mischievous leprechauns through the forest of data analysis. The statistical significance of our results, with a p-value less than 0.01, highlights the credibility of this enchanting bond between scientific pursuits and sporting triumphs, akin to stumbling upon a vibrant parade of dancing flamingos in the midst of a staid statistical landscape.

Moreover, the r-squared value of 0.7419255 fortifies the weight of this association, transcending the boundaries of statistical whimsy to signal the presence of a substantive relationship that warrants further exploration. The robust correlation coefficient of 0.8613510 mirrors the astonishing revelations of Jones' collection of statistical oddities, underscoring the profound impact of this delightful interconnection and the essence of statistical amusement that permeates our inquiry.

The unexpected kinship between the number of chemists laboring in the wintry wonderland of Alaska and the total runs woven into the fabric of the World Series prompts us to approach the realm of statistical exploration with a blend of inquiry and humor, akin to the tender balance between the serious and the whimsical that illuminates our quest for knowledge. Our findings, much like a whimsical treasure map discovered amidst routine data analysis, encourage further investigations into the enchanting territory of statistical serendipity, captivating our curiosity and affirming the uncharted vistas that beckon within the colorful tapestry of statistical fascination.

In conclusion, our study bears testament to the enchanting landscape of unexpected correlations and the delightful amalgamation of statistical inquiry and whimsy. The revelations unveiled within our analysis serve as a testament to the entertaining and often surprising world of statistical anomalies, underscoring the profound impact of statistical serendipity on our pursuit of knowledge.

(500 words)


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of chemists in Alaska and Total runs scored in the World Series. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores"

[[ABSTRACT]]
While it may seem as whimsical as a heat-of-the-moment steal in the bottom of the ninth, our research delves into the ostensibly ludicrous connection between the number of chemists in Alaska and the total runs scored in the World Series. Utilizing data from the Bureau of Labor Statistics and Wikipedia, our team embarked on a jovial journey to uncover any potential correlation between these seemingly unrelated phenomena. Surprisingly, our analysis unveiled a robust correlation coefficient of 0.8613510, with a p-value less than 0.01, spanning the years 2003 to 2013. This unlikely association between the number of scientists concocting concoctions and the number of runs plated on the diamond may prompt further inquiries into the whimsical wonders of statistical serendipity. Our findings titrate the delicate balance between scientific curiosity and statistical amusement, serving as a testament to the unforeseen connections that permeate our statistical landscape.

[[INTRDUCTION]]
What do chemists in Alaska and World Series run scores have in common, you might wonder? Well, as perplexing as it may seem, our team of intrepid researchers set out to investigate just that. While it might sound as improbable as a polar bear taking up figure skating, our study delves into the surprising correlation between these seemingly disparate entities.
In the realm of statistical oddities, the unlikely relationship between the number of chemists in Alaska and the total runs scored in the World Series caught our attention like a knuckleball in a sea of fastballs. The thought of these two apparently unrelated factors being interconnected was as bizarre as a walrus playing a trumpet – but our analysis revealed some eyebrow-raising results.
The scientific community continually seeks unexpected connections and peculiar patterns, much like a detective on the trail of a particularly confounding mystery. As such, our investigation into this whimsical relationship between Alaskan chemists and World Series run scores serves as a lighthearted yet intriguing exploration into the capricious world of statistical inquiry.
Fueled by curiosity and armed with a plethora of data from the Bureau of Labor Statistics and the hallowed pages of Wikipedia, our research team embarked on this peculiar pursuit of statistical serendipity. What we uncovered transcended our initial skepticism and led us into the lively realm of statistical amusement – serving as a testament to the whimsical wonders that await those who delve into the rich tapestry of numerical connections.
So, grab your lab coat and don your baseball cap, for we are about to embark on a journey that may leave you scratching your head with the same bemusement as a pitcher contemplating the mysteries of a knuckleball. This is the tale of scientific shenanigans, where the paths of Alaskan chemists and World Series run scores intersect in a statistical pas de deux that defies the conventional wisdom of causal relationships.

[[RESULTS]]
Astonishingly, our investigation into the correlation between the number of chemists in Alaska and the total runs scored in the World Series yielded a robust and unforeseen relationship. Spanning the years 2003 to 2013, our study unveiled a striking correlation coefficient of 0.8613510, accompanied by an r-squared value of 0.7419255 and a p-value less than 0.01. These statistical findings defy the expectation that these two variables are as unrelated as a snowflake in the desert.
The inference of a strong positive correlation provides a basis for further exploration into the whimsical world of statistical serendipity. The unexpected connection between the number of chemists in the northern wilds of Alaska and the number of runs on the baseball diamond raises questions as perplexing as the trajectory of a knuckleball.
The scatterplot (Fig. 1) visually portrays the surprising relationship between the number of chemists in Alaska and the total runs scored in the World Series, offering a playful yet thought-provoking depiction of this unlikely interconnection.
This unexpected association of scientific pursuits and sporting feats accentuates the unexplored territories in correlational studies and motivates further investigations into the colorful and unconventional intersections within the fabric of statistical inquiry.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In summary, our research has unearthed an unexpected and seemingly whimsical connection between the number of chemists in Alaska and the total runs scored in the World Series. This peculiar correlation has left us as perplexed as a player facing a knuckleball on a windy day. The robust correlation coefficient of 0.8613510, akin to a pitcher's fastball, along with the r-squared value of 0.7419255, emphatically attests to the striking relationship between these ostensibly unrelated variables.

One might question the causality behind this statistical harmony, much like the eternal debate of whether the chicken or the egg came first. Could it be that the chemists in Alaska, with their concoctions and compounds, brew a potent elixir of statistical fortune that permeates the world of baseball? Or perhaps the spirited performance on the diamond propels chemists to greater scientific heights, akin to the momentum of a late-inning rally?

As tempting as it may be to delve deeper into the mysteries of Alaskan chemistry and baseball runs, we must acknowledge the bounds of statistical probability and resist the urge to concoct elaborate narratives akin to a tall tale spun around a campfire. Therefore, we assert with unwavering certainty that no further research is needed in this area. Our findings stand as a testament to the capricious dance of statistical serendipity, a charming reminder that even the most peculiar connections can find their place in the annals of empirical inquiry.


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unconventional Connections


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 Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Absurd Science Research


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Scientific Shenanigans: Exploring the Unlikely Link Between Alaskan Chemists and World Series Run Scores with an abstract of While it may seem as whimsical as a heat-of-the-moment steal in the bottom of the ninth, our research delves into the ostensibly ludicrous connection between the number of chemists in Alaska and the total runs scored in the World Series. Utilizing data from the Bureau of Labor Statistics and Wikipedia, our team embarked on a jovial journey to uncover any potential correlation between these seemingly unrelated phenomena. Surprisingly, our analysis unveiled a robust correlation coefficient of 0.8613510, with a p-value less than 0.01, spanning the years 2003 to 2013. This unlikely association between the number of scientists concocting concoctions and the number of runs plated on the diamond may prompt further inquiries into the whimsical wonders of statistical serendipity. Our findings titrate the delicate balance between scientific curiosity and statistical amusement, serving as a testament to the unforeseen connections that permeate our statistical landscape.

ChatGPT:

Alaskan chemists, World Series run scores, correlation analysis, data analysis, statistics, scientific research, Bureau of Labor Statistics, whimsical connections, statistical serendipity, unlikely correlation, scientific curiosity, statistical amusement, unexpected connections.

*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 number of chemists in Alaska
Detailed data title: BLS estimate of chemists in Alaska
Source: Bureau of Larbor Statistics
See what else correlates with The number of chemists in Alaska

Total runs scored in the World Series
Source: Wikipedia
See what else correlates with Total runs scored in the World Series

Correlation r = 0.8613510 (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 = 0.7419255 (Coefficient of determination)
This means 74.2% of the change in the one variable (i.e., Total runs scored in the World Series) is predictable based on the change in the other (i.e., The number of chemists in Alaska) over the 11 years from 2003 through 2013.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00066. 0.0006569295915970067000000000
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 0.86 in 0.066% of random cases. Said differently, if you correlated 1,522 random variables Which I absolutely did.
with the same 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 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.

[ 0.54, 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.
20032004200520062007200820092010201120122013
The number of chemists in Alaska (Chemists)90706070609016016019060100
Total runs scored in the World Series (Runs scored)3836343339395941682241




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([90,70,60,70,60,90,160,160,190,60,100,])
array_2 = np.array([38,36,34,33,39,39,59,41,68,22,41,])
array_1_name = "The number of chemists in Alaska"
array_2_name = "Total runs scored in the World Series"

# 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 dedication to rating warms my heart!


Correlation ID: 1698 · Black Variable ID: 4713 · Red Variable ID: 536
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0