about · email me · subscribe
Spurious correlation #1,048 · 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 statisticians in Oklahoma and the second variable is Customer satisfaction with Sprint.  The chart goes from 2004 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The statisticians in Oklahoma started crunching the data on Sprint's customer service, leading to a statistically significant improvement in their performance. Sprint was finally able to make call wait times and service quality measures that weren't just a 'best guess'. It all added up to happier customers, who were no longer feeling like they were just another outlier in the world of telecom grievances.

Model: dalle-3
Prompt: Prompt: Generate an image of a high-tech office in Oklahoma where statisticians are working diligently at their desks, surrounded by stacks of data and charts. The statisticians are carefully analyzing customer complaints and service data from Sprint. Show them adjusting the number of dropped calls and overcharged fees on their computer screens to find the "sweet spot" that keeps customers satisfied. Additionally, illustrate smiles on the faces of Sprint customers as they experience fewer dropped calls and fairer fees, leading to an unexpected increase in overall satisfaction with the service. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: The increase in the number of statisticians in Oklahoma caused customer satisfaction with Sprint to increase because statisticians calculated the optimal number of dropped calls and overcharged fees to keep customers at the perfect level of irritation, leading to a surprising increase in overall satisfaction with the service.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Oragami High-tech Futuristic Low poly A photo-realistic image
ChatGPT: High-tech

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. The increase in the number of statisticians in Oklahoma caused customer satisfaction with Sprint to increase because statisticians calculated the optimal number of dropped calls and overcharged fees to keep customers at the perfect level of irritation, leading to a surprising increase in overall satisfaction with the service.
ChatGPT: In a bustling office in Oklahoma, we see a group of statisticians diligently working at their desks, surrounded by stacks of data and charts. They are carefully analyzing customer complaints and service data from Sprint. As they work, we see them adjusting the number of dropped calls and overcharged fees on their computer screens to find the "sweet spot" that keeps customers satisfied. Meanwhile, we observe smiles on the faces of Sprint customers as they experience fewer dropped calls and fairer fees, leading to an unexpected increase in overall satisfaction with the service.

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: [ High-tech ] and depicting this scene: In a bustling office in Oklahoma, we see a group of statisticians diligently working at their desks, surrounded by stacks of data and charts. They are carefully analyzing customer complaints and service data from Sprint. As they work, we see them adjusting the number of dropped calls and overcharged fees on their computer screens to find the "sweet spot" that keeps customers satisfied. Meanwhile, we observe smiles on the faces of Sprint customers as they experience fewer dropped calls and fairer fees, leading to an unexpected increase in overall satisfaction with the service. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image of a high-tech office in Oklahoma where statisticians are working diligently at their desks, surrounded by stacks of data and charts. The statisticians are carefully analyzing customer complaints and service data from Sprint. Show them adjusting the number of dropped calls and overcharged fees on their computer screens to find the "sweet spot" that keeps customers satisfied. Additionally, illustrate smiles on the faces of Sprint customers as they experience fewer dropped calls and fairer fees, leading to an unexpected increase in overall satisfaction with the service.

*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 The number of statisticians in Oklahoma caused Customer satisfaction with Sprint to increase.

AI academic paper

(Because p < 0.01)
Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study

The Journal of Quirky Statistical Analyses

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 statisticians in Oklahoma and Customer satisfaction with Sprint. Make lots of jokes, goofy observations, and puns.

Make the title an alliteration.

Your research team used data from Bureau of Larbor Statistics and American Customer Satisfaction Index to assess this nagging question. You found a correlation coefficient of 0.7352215 and p < 0.01 for 2004 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]]
Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study

[[ABSTRACT]]
In this study, we set out to unravel the perplexing relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. While some might find this topic a bit "statistically" odd, our research aimed to determine if there is a quantifiable connection between the two. Utilizing data from the Bureau of Labor Statistics and the American Customer Satisfaction Index, we embarked on a journey that involved crunching numbers, analyzing trends, and unraveling statistical mysteries.

Surprisingly, our findings reveal a correlation coefficient of 0.7352215 and p < 0.01 for the period spanning from 2004 to 2020, leading us to conclude that there is indeed a substantial correlation between the abundance of statisticians in Oklahoma and customer satisfaction with Sprint. This statistical connection, while somewhat unexpected, may have implications that extend beyond the realm of numbers, suggesting a curious interplay between statistical expertise and customer contentment with telecommunications services. Our study not only sheds light on this quirky correlation but also adds a dash of statistical humor to the academic discourse.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 statisticians in Oklahoma and Customer satisfaction with Sprint. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study

[[ABSTRACT]]
In this study, we set out to unravel the perplexing relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. While some might find this topic a bit "statistically" odd, our research aimed to determine if there is a quantifiable connection between the two. Utilizing data from the Bureau of Labor Statistics and the American Customer Satisfaction Index, we embarked on a journey that involved crunching numbers, analyzing trends, and unraveling statistical mysteries.

Surprisingly, our findings reveal a correlation coefficient of 0.7352215 and p < 0.01 for the period spanning from 2004 to 2020, leading us to conclude that there is indeed a substantial correlation between the abundance of statisticians in Oklahoma and customer satisfaction with Sprint. This statistical connection, while somewhat unexpected, may have implications that extend beyond the realm of numbers, suggesting a curious interplay between statistical expertise and customer contentment with telecommunications services. Our study not only sheds light on this quirky correlation but also adds a dash of statistical humor to the academic discourse.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As we venture into the enigmatic world of statistics, we often find ourselves lost in a sea of numbers, trends, and the occasional outlier that just won't follow the trend. Today, we embark on a statistical escapade to unravel the unexpected and somewhat mind-boggling relationship between the number of statisticians in the great state of Oklahoma and the satisfaction of customers with the telecommunications giant, Sprint.

Now, you might be wondering what in the world prompted such a peculiar investigation. Well, curiosity got the best of us, and we just couldn't resist the urge to unravel this statistical riddle. Who knew that the abundance of statistics aficionados in the land of Oklahoma could have anything to do with how satisfied Sprint customers are with their services? But as the saying goes, "correlation does not imply causation," so we set out to investigate just what's cooking in the statistical cauldron.

We dived into the depths of data, armed with our trusty statistical tools and a healthy dose of skepticism, ready to crunch numbers and seek out hidden patterns like archeologists searching for ancient treasures. Our quest led us to the hallowed halls of the Bureau of Labor Statistics, where numbers flow like a river and percentages dance like nobody's watching. We paired this with the treasure trove of customer satisfaction data from the American Customer Satisfaction Index, and lo and behold, the adventure had begun.

As we delved deeper into the numbers, we couldn't help but muse about the irony that statisticians, those guardians of numbers, might have their own numbers correlated with something as unpredictable as customer satisfaction with a telecom provider. It's like witnessing a unicorn in the world of statistics – unlikely but oh so intriguing.

So, with our tongues firmly in cheek and our minds focused on the serious pursuit of statistical knowledge, we aimed to unravel the mysteries of this strange association. Through rigorous analysis, we sought to determine if the number of statistical gurus in Oklahoma had any quantifiable impact on the satisfaction levels of Sprint customers. The idea was to shed light on a bizarre correlation with a healthy dose of statistical humor thrown in for good measure because, let’s face it, statistics could use a bit of levity.

As we present our findings, brace yourselves for a romp through the world of numbers and human sentiment, where the unexpected takes center stage, and statistical correlations sometimes take us on the most peculiar of journeys. So, join us as we venture forth into the statistically odd and the delightfully befuddling world of statisticians in Oklahoma and customer satisfaction with Sprint.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of statisticians in Oklahoma and Customer satisfaction with Sprint. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study

[[ABSTRACT]]
In this study, we set out to unravel the perplexing relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. While some might find this topic a bit "statistically" odd, our research aimed to determine if there is a quantifiable connection between the two. Utilizing data from the Bureau of Labor Statistics and the American Customer Satisfaction Index, we embarked on a journey that involved crunching numbers, analyzing trends, and unraveling statistical mysteries.

Surprisingly, our findings reveal a correlation coefficient of 0.7352215 and p < 0.01 for the period spanning from 2004 to 2020, leading us to conclude that there is indeed a substantial correlation between the abundance of statisticians in Oklahoma and customer satisfaction with Sprint. This statistical connection, while somewhat unexpected, may have implications that extend beyond the realm of numbers, suggesting a curious interplay between statistical expertise and customer contentment with telecommunications services. Our study not only sheds light on this quirky correlation but also adds a dash of statistical humor to the academic discourse.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As we venture into the enigmatic world of statistics, we often find ourselves lost in a sea of numbers, trends, and the occasional outlier that just won't follow the trend. Today, we embark on a statistical escapade to unravel the unexpected and somewhat mind-boggling relationship between the number of statisticians in the great state of Oklahoma and the satisfaction of customers with the telecommunications giant, Sprint.
Now, you might be wondering what in the world prompted such a peculiar investigation. Well, curiosity got the best of us, and we just couldn't resist the urge to unravel this statistical riddle. Who knew that the abundance of statistics aficionados in the land of Oklahoma could have anything to do with how satisfied Sprint customers are with their services? But as the saying goes, "correlation does not imply causation," so we set out to investigate just what's cooking in the statistical cauldron.
We dived into the depths of data, armed with our trusty statistical tools and a healthy dose of skepticism, ready to crunch numbers and seek out hidden patterns like archeologists searching for ancient treasures. Our quest led us to the hallowed halls of the Bureau of Labor Statistics, where numbers flow like a river and percentages dance like nobody's watching. We paired this with the treasure trove of customer satisfaction data from the American Customer Satisfaction Index, and lo and behold, the adventure had begun.
As we delved deeper into the numbers, we couldn't help but muse about the irony that statisticians, those guardians of numbers, might have their own numbers correlated with something as unpredictable as customer satisfaction with a telecom provider. It's like witnessing a unicorn in the world of statistics – unlikely but oh so intriguing.
So, with our tongues firmly in cheek and our minds focused on the serious pursuit of statistical knowledge, we aimed to unravel the mysteries of this strange association. Through rigorous analysis, we sought to determine if the number of statistical gurus in Oklahoma had any quantifiable impact on the satisfaction levels of Sprint customers. The idea was to shed light on a bizarre correlation with a healthy dose of statistical humor thrown in for good measure because, let’s face it, statistics could use a bit of levity.
As we present our findings, brace yourselves for a romp through the world of numbers and human sentiment, where the unexpected takes center stage, and statistical correlations sometimes take us on the most peculiar of journeys. So, join us as we venture forth into the statistically odd and the delightfully befuddling world of statisticians in Oklahoma and customer satisfaction with Sprint.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Statistical Analysis of Telecommunications and Demographics in the South Central United States," Smith and Doe delve into the intricate relationship between population demographics and customer satisfaction with telecom services. While their focus is broader than our specific inquiry, their findings offer valuable insights into the potential impact of regional demographics on customer sentiment towards telecommunication companies. Amidst their analysis of various demographic factors, the authors touch upon the prevalence of statisticians in regional populations, hinting at the possibility of an unexplored correlation with customer satisfaction.

Turning our attention to "Telecom Trends: A Statistical Approach" by Jones, we encounter a comprehensive exploration of customer satisfaction trends in the telecom industry. Although the author does not directly address the influence of statisticians, the study provides a holistic view of the factors influencing customer contentment, serving as a foundational backdrop for our investigation.

Shifting gears, we consider non-fiction works such as "The Signal and the Noise: Why So Many Predictions Fail – but Some Don't" by Nate Silver and "Freakonomics: A Rogue Economist Explores the Hidden Side of Everything" by Steven D. Levitt and Stephen J. Dubner. While not directly related to our specific inquiry, these works illustrate the complexity of statistical analyses and the unexpected correlations that can emerge from seemingly unrelated variables. They also remind us that statistical relationships can defy conventional wisdom and lead to intriguing discoveries.

On a more whimsical note, let's take a brief detour into the realm of fiction with the likes of "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 these novels may not offer direct insights into statistics and telecommunication customer satisfaction, they serve as a lighthearted reminder that the pursuit of knowledge often unfolds in the most improbable and delightful ways.

Now, in a slightly more unconventional approach to our literature review, we cannot overlook the valuable insights gained from perusing the extensive body of literature found on those enigmatic, ink-stained totems known as CVS receipts. While ostensibly unrelated to our research topic, the intricate web of promotional offers, extraneous coupons, and cryptic product codes found on these elongated scrolls of paper serves as a poignant metaphor for uncovering unexpected connections in the most unassuming places. After a thorough examination of these elongated relics of consumer transactions, we were left pondering the eldritch mysteries of everyday commerce and its potential parallels to the statistical oddities in our own research.

With our literature review meandering through the serious, the whimsical, and the utterly absurd, we pave the way for a deeper exploration of the curiously captivating connection between statisticians in Oklahoma and customer satisfaction with Sprint.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of statisticians in Oklahoma and Customer satisfaction with Sprint. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and American Customer Satisfaction Index . You used data from 2004 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]]
Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study

[[ABSTRACT]]
In this study, we set out to unravel the perplexing relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. While some might find this topic a bit "statistically" odd, our research aimed to determine if there is a quantifiable connection between the two. Utilizing data from the Bureau of Labor Statistics and the American Customer Satisfaction Index, we embarked on a journey that involved crunching numbers, analyzing trends, and unraveling statistical mysteries.

Surprisingly, our findings reveal a correlation coefficient of 0.7352215 and p < 0.01 for the period spanning from 2004 to 2020, leading us to conclude that there is indeed a substantial correlation between the abundance of statisticians in Oklahoma and customer satisfaction with Sprint. This statistical connection, while somewhat unexpected, may have implications that extend beyond the realm of numbers, suggesting a curious interplay between statistical expertise and customer contentment with telecommunications services. Our study not only sheds light on this quirky correlation but also adds a dash of statistical humor to the academic discourse.

[[INTRODUCTION]]
As we venture into the enigmatic world of statistics, we often find ourselves lost in a sea of numbers, trends, and the occasional outlier that just won't follow the trend. Today, we embark on a statistical escapade to unravel the unexpected and somewhat mind-boggling relationship between the number of statisticians in the great state of Oklahoma and the satisfaction of customers with the telecommunications giant, Sprint.
Now, you might be wondering what in the world prompted such a peculiar investigation. Well, curiosity got the best of us, and we just couldn't resist the urge to unravel this statistical riddle. Who knew that the abundance of statistics aficionados in the land of Oklahoma could have anything to do with how satisfied Sprint customers are with their services? But as the saying goes, "correlation does not imply causation," so we set out to investigate just what's cooking in the statistical cauldron.
We dived into the depths of data, armed with our trusty statistical tools and a healthy dose of skepticism, ready to crunch numbers and seek out hidden patterns like archeologists searching for ancient treasures. Our quest led us to the hallowed halls of the Bureau of Labor Statistics, where numbers flow like a river and percentages dance like nobody's watching. We paired this with the treasure trove of customer satisfaction data from the American Customer Satisfaction Index, and lo and behold, the adventure had begun.
As we delved deeper into the numbers, we couldn't help but muse about the irony that statisticians, those guardians of numbers, might have their own numbers correlated with something as unpredictable as customer satisfaction with a telecom provider. It's like witnessing a unicorn in the world of statistics – unlikely but oh so intriguing.
So, with our tongues firmly in cheek and our minds focused on the serious pursuit of statistical knowledge, we aimed to unravel the mysteries of this strange association. Through rigorous analysis, we sought to determine if the number of statistical gurus in Oklahoma had any quantifiable impact on the satisfaction levels of Sprint customers. The idea was to shed light on a bizarre correlation with a healthy dose of statistical humor thrown in for good measure because, let’s face it, statistics could use a bit of levity.
As we present our findings, brace yourselves for a romp through the world of numbers and human sentiment, where the unexpected takes center stage, and statistical correlations sometimes take us on the most peculiar of journeys. So, join us as we venture forth into the statistically odd and the delightfully befuddling world of statisticians in Oklahoma and customer satisfaction with Sprint.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the mysterious link between the number of statisticians in the state of Oklahoma and customer satisfaction with Sprint, we embarked on an investigative journey that combined rigorous data analysis with a sprinkle of statistical whimsy. Our approach can be likened to a chef concocting a delightfully peculiar dish, using a blend of tried-and-true ingredients and a dash of flavorful surprises.

First and foremost, we gathered data from the Bureau of Labor Statistics, scouring their archives for information on the employment of statisticians in the vibrant landscape of Oklahoma. We meticulously sifted through years of data, treating each statistical nugget with the care and attention it deserved, much like a curator examining priceless artifacts in a museum. Harnessing the power of spreadsheets and statistical software, we meticulously calculated the number of statisticians per capita in Oklahoma, creating a robust foundation for our analysis.

Next, we delved into the abundant resource of customer satisfaction data provided by the American Customer Satisfaction Index (ACSI). Like intrepid explorers navigating uncharted territory, we charted the ebbs and flows of Sprint customer satisfaction over the years, seeking patterns and anomalies that might hint at the existence of a statistical connection with the number of statisticians in the Sooner State.

With our data in hand, we employed a series of rigorous statistical analyses, including regression modeling, correlation calculations, and time series analysis, to unravel the potential link between these two seemingly disparate variables. As we navigated through the labyrinth of statistical tests, we kept a keen eye out for any unexpected twists and turns – after all, in the world of statistics, you never know when a hidden outlier might pop up to say, "Surprise!"

To ensure the robustness of our findings, we applied a rigorous methodology that accounted for potential confounding variables, outliers, and the ever-elusive specter of statistical significance. Our approach was akin to a detective meticulously sifting through clues, searching for the elusive truth lurking beneath the surface of the data.

Finally, we employed advanced statistical software, drawing upon the technological marvels of the modern age to aid us in our quest. Armed with these digital allies, we navigated the complex landscape of statistical analysis with a blend of determination and good humor, fully aware that even the most serious of pursuits could benefit from a sprinkle of statistical levity.

In summary, our methodology combined the precision of statistical analysis with the spirited curiosity of exploration, creating a unique blend of scientific rigor and statistical whimsy. With this approach, we set out to unlock the enigmatic connection between the number of statisticians in Oklahoma and the satisfaction of Sprint customers, adding a touch of statistical humor to the journey.

Next, we'll move on to the results, but first, let's take a moment to appreciate the statistical elegance of our methodology – a blend of analytical rigor and whimsical flair that encapsulates the essence of statistical inquiry. Now, onto the results, where the unexpected correlations and statistical surprises await!


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

Please make up the results section of an academic research paper presenting the findings of the connection between The number of statisticians in Oklahoma and Customer satisfaction with Sprint. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2004 to 2020, you found a correlation 0.7352215, r-squared of 0.5405506, 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]]
Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study

[[ABSTRACT]]
In this study, we set out to unravel the perplexing relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. While some might find this topic a bit "statistically" odd, our research aimed to determine if there is a quantifiable connection between the two. Utilizing data from the Bureau of Labor Statistics and the American Customer Satisfaction Index, we embarked on a journey that involved crunching numbers, analyzing trends, and unraveling statistical mysteries.

Surprisingly, our findings reveal a correlation coefficient of 0.7352215 and p < 0.01 for the period spanning from 2004 to 2020, leading us to conclude that there is indeed a substantial correlation between the abundance of statisticians in Oklahoma and customer satisfaction with Sprint. This statistical connection, while somewhat unexpected, may have implications that extend beyond the realm of numbers, suggesting a curious interplay between statistical expertise and customer contentment with telecommunications services. Our study not only sheds light on this quirky correlation but also adds a dash of statistical humor to the academic discourse.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As we venture into the enigmatic world of statistics, we often find ourselves lost in a sea of numbers, trends, and the occasional outlier that just won't follow the trend. Today, we embark on a statistical escapade to unravel the unexpected and somewhat mind-boggling relationship between the number of statisticians in the great state of Oklahoma and the satisfaction of customers with the telecommunications giant, Sprint.
Now, you might be wondering what in the world prompted such a peculiar investigation. Well, curiosity got the best of us, and we just couldn't resist the urge to unravel this statistical riddle. Who knew that the abundance of statistics aficionados in the land of Oklahoma could have anything to do with how satisfied Sprint customers are with their services? But as the saying goes, "correlation does not imply causation," so we set out to investigate just what's cooking in the statistical cauldron.
We dived into the depths of data, armed with our trusty statistical tools and a healthy dose of skepticism, ready to crunch numbers and seek out hidden patterns like archeologists searching for ancient treasures. Our quest led us to the hallowed halls of the Bureau of Labor Statistics, where numbers flow like a river and percentages dance like nobody's watching. We paired this with the treasure trove of customer satisfaction data from the American Customer Satisfaction Index, and lo and behold, the adventure had begun.
As we delved deeper into the numbers, we couldn't help but muse about the irony that statisticians, those guardians of numbers, might have their own numbers correlated with something as unpredictable as customer satisfaction with a telecom provider. It's like witnessing a unicorn in the world of statistics – unlikely but oh so intriguing.
So, with our tongues firmly in cheek and our minds focused on the serious pursuit of statistical knowledge, we aimed to unravel the mysteries of this strange association. Through rigorous analysis, we sought to determine if the number of statistical gurus in Oklahoma had any quantifiable impact on the satisfaction levels of Sprint customers. The idea was to shed light on a bizarre correlation with a healthy dose of statistical humor thrown in for good measure because, let’s face it, statistics could use a bit of levity.
As we present our findings, brace yourselves for a romp through the world of numbers and human sentiment, where the unexpected takes center stage, and statistical correlations sometimes take us on the most peculiar of journeys. So, join us as we venture forth into the statistically odd and the delightfully befuddling world of statisticians in Oklahoma and customer satisfaction with Sprint.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Upon diving into the sea of numbers and statistical shenanigans, we emerged with some fascinating findings that shed light on the quirky relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. After donning our metaphorical detective hats and wielding our trusty statistical tools, we unearthed a correlation coefficient of 0.7352215 between these two seemingly disparate variables. It's as if the statistical stars aligned to reveal a connection that defies conventional wisdom and tickles the fancy of the empirical enthusiast.

In addition to this eyebrow-raising correlation, our analysis unveiled an r-squared value of 0.5405506, signifying that a substantial portion (approximately 54.06%) of the variance in Sprint customer satisfaction can be explained by the abundance of number-crunching aficionados in Oklahoma. This finding is no statistical fluke; it indicates a robust relationship that adds a touch of unpredictability to the otherwise predictable world of numerical analyses.

To top it all off, the p-value of less than 0.01 sent ripples of excitement through the realm of statistical significance, affirming that the correlation we uncovered is not a figment of statistical folklore, but a bona fide connection worthy of scientific scrutiny.

Now, let us not forget the pièce de résistance – our beloved Figure 1, a scatterplot that captures the essence of this captivating correlation in all its graphical glory. Behold, as the data points form a visual tapestry of statistical intrigue, showcasing the unmistakable trend that binds statisticians in Oklahoma to the ebbs and flows of Sprint customer contentment. It's a sight to behold, akin to a statistical romance blossoming amidst the data points, and it serves as a testament to the far-reaching implications of this curious correlation.

In conclusion, our study not only unravels the unexpected interplay between statisticians in Oklahoma and Sprint satisfaction but also injects a healthy dose of statistical whimsy into the academic arena. The statistical oddity that we uncovered beckons us to embrace the delightful befuddlement that comes with unraveling the curiosities of correlation, reminding us that the world of statistics is not without its surprises.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of statisticians in Oklahoma and Customer satisfaction with Sprint. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study

[[ABSTRACT]]
In this study, we set out to unravel the perplexing relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. While some might find this topic a bit "statistically" odd, our research aimed to determine if there is a quantifiable connection between the two. Utilizing data from the Bureau of Labor Statistics and the American Customer Satisfaction Index, we embarked on a journey that involved crunching numbers, analyzing trends, and unraveling statistical mysteries.

Surprisingly, our findings reveal a correlation coefficient of 0.7352215 and p < 0.01 for the period spanning from 2004 to 2020, leading us to conclude that there is indeed a substantial correlation between the abundance of statisticians in Oklahoma and customer satisfaction with Sprint. This statistical connection, while somewhat unexpected, may have implications that extend beyond the realm of numbers, suggesting a curious interplay between statistical expertise and customer contentment with telecommunications services. Our study not only sheds light on this quirky correlation but also adds a dash of statistical humor to the academic discourse.

[[LITERATURE REVIEW]]
In "Statistical Analysis of Telecommunications and Demographics in the South Central United States," Smith and Doe delve into the intricate relationship between population demographics and customer satisfaction with telecom services. While their focus is broader than our specific inquiry, their findings offer valuable insights into the potential impact of regional demographics on customer sentiment towards telecommunication companies. Amidst their analysis of various demographic factors, the authors touch upon the prevalence of statisticians in regional populations, hinting at the possibility of an unexplored correlation with customer satisfaction.
Turning our attention to "Telecom Trends: A Statistical Approach" by Jones, we encounter a comprehensive exploration of customer satisfaction trends in the telecom industry. Although the author does not directly address the influence of statisticians, the study provides a holistic view of the factors influencing customer contentment, serving as a foundational backdrop for our investigation.
Shifting gears, we consider non-fiction works such as "The Signal and the Noise: Why So Many Predictions Fail – but Some Don't" by Nate Silver and "Freakonomics: A Rogue Economist Explores the Hidden Side of Everything" by Steven D. Levitt and Stephen J. Dubner. While not directly related to our specific inquiry, these works illustrate the complexity of statistical analyses and the unexpected correlations that can emerge from seemingly unrelated variables. They also remind us that statistical relationships can defy conventional wisdom and lead to intriguing discoveries.
On a more whimsical note, let's take a brief detour into the realm of fiction with the likes of "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 these novels may not offer direct insights into statistics and telecommunication customer satisfaction, they serve as a lighthearted reminder that the pursuit of knowledge often unfolds in the most improbable and delightful ways.
Now, in a slightly more unconventional approach to our literature review, we cannot overlook the valuable insights gained from perusing the extensive body of literature found on those enigmatic, ink-stained totems known as CVS receipts. While ostensibly unrelated to our research topic, the intricate web of promotional offers, extraneous coupons, and cryptic product codes found on these elongated scrolls of paper serves as a poignant metaphor for uncovering unexpected connections in the most unassuming places. After a thorough examination of these elongated relics of consumer transactions, we were left pondering the eldritch mysteries of everyday commerce and its potential parallels to the statistical oddities in our own research.
With our literature review meandering through the serious, the whimsical, and the utterly absurd, we pave the way for a deeper exploration of the curiously captivating connection between statisticians in Oklahoma and customer satisfaction with Sprint.

[[RESULTS]]
Upon diving into the sea of numbers and statistical shenanigans, we emerged with some fascinating findings that shed light on the quirky relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. After donning our metaphorical detective hats and wielding our trusty statistical tools, we unearthed a correlation coefficient of 0.7352215 between these two seemingly disparate variables. It's as if the statistical stars aligned to reveal a connection that defies conventional wisdom and tickles the fancy of the empirical enthusiast.
In addition to this eyebrow-raising correlation, our analysis unveiled an r-squared value of 0.5405506, signifying that a substantial portion (approximately 54.06%) of the variance in Sprint customer satisfaction can be explained by the abundance of number-crunching aficionados in Oklahoma. This finding is no statistical fluke; it indicates a robust relationship that adds a touch of unpredictability to the otherwise predictable world of numerical analyses.
To top it all off, the p-value of less than 0.01 sent ripples of excitement through the realm of statistical significance, affirming that the correlation we uncovered is not a figment of statistical folklore, but a bona fide connection worthy of scientific scrutiny.
Now, let us not forget the pièce de résistance – our beloved Figure 1, a scatterplot that captures the essence of this captivating correlation in all its graphical glory. Behold, as the data points form a visual tapestry of statistical intrigue, showcasing the unmistakable trend that binds statisticians in Oklahoma to the ebbs and flows of Sprint customer contentment. It's a sight to behold, akin to a statistical romance blossoming amidst the data points, and it serves as a testament to the far-reaching implications of this curious correlation.
In conclusion, our study not only unravels the unexpected interplay between statisticians in Oklahoma and Sprint satisfaction but also injects a healthy dose of statistical whimsy into the academic arena. The statistical oddity that we uncovered beckons us to embrace the delightful befuddlement that comes with unraveling the curiosities of correlation, reminding us that the world of statistics is not without its surprises.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Ah, the whimsical world of statistical provocations and improbable correlations. Our findings, dear reader, tantalize the empirical intellect and tease the boundaries of statistical sensibility. The results of our study, which unveiled a robust correlation between the number of statisticians in Oklahoma and customer satisfaction with Sprint, not only affirm the enigmatic connection pondered in prior literature but also propel us into the realms of statistical merriment and merry.

Returning to the whimsical notations in our literature review, the aforementioned "Curious Incident of the Dog in the Night-Time" becomes a fitting allegory for our statistical escapade, where the unexpected bedfellows of statisticians and telecommunication satisfaction prance amidst the numerical narrative. Furthermore, the unrestrained wit of "The Hitchhiker's Guide to the Galaxy" serves as a gentle reminder that statistical journeys, much like intergalactic hitchhiking, often lead to the most delightfully incongruous destinations.

While the research by Smith and Doe toyed with the notion of statisticians' influence on customer satisfaction, our study has not just lent weight but fervent numerical embrace to this correlation. Similarly, Jones' telecom trends paves the analytical tarmac for our statistical flight, hinting at the possibility of statistical turbulence lurking beneath the serene skies of customer contentment. The statistical playbook, it seems, brims with whimsy and mischief, bending the rules and forging unexpected connections amidst the numerical landscapes.

Our findings solidify the concept that statisticians in Oklahoma may hold sway over the ebb and flow of Sprint customer contentment. The correlation coefficient of 0.7352215 embracing the jovial p-value of less than 0.01 illuminates this quirky pairing with statistical gusto. Furthermore, the r-squared value of 0.5405506 stands as a triumph of statistical storytelling, painting a whimsical panorama of the statistical saga that binds the number-crunching aficionados of Oklahoma to the telecommunication tides.

Figure 1, much like a grand tapestry woven with statistical yarn, epitomizes the graphical romance that unfurls between these improbable bedfellows. As we gaze upon its scatterplot splendor, the data points dance a merry statistical jig, in a celebration of the statistical oddity that we have uncovered. It is, without a doubt, a spectacle worthy of statistical applause and a testament to the artistry of numerical dalliances.

In the grand tapestry of statistical exploration, our study embroiders a playful yet robust thread, weaving together the enigmatic connection between statisticians in Oklahoma and Sprint satisfaction. This whimsical correlation, with its statistical ripples and empirical delights, invites us to revel in the statistical dance of improbable pairings, reminding us that beneath the veneer of numerical formality lies the boundless expanse of statistical whimsy.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of 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 statisticians in Oklahoma and Customer satisfaction with Sprint. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study

[[ABSTRACT]]
In this study, we set out to unravel the perplexing relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. While some might find this topic a bit "statistically" odd, our research aimed to determine if there is a quantifiable connection between the two. Utilizing data from the Bureau of Labor Statistics and the American Customer Satisfaction Index, we embarked on a journey that involved crunching numbers, analyzing trends, and unraveling statistical mysteries.

Surprisingly, our findings reveal a correlation coefficient of 0.7352215 and p < 0.01 for the period spanning from 2004 to 2020, leading us to conclude that there is indeed a substantial correlation between the abundance of statisticians in Oklahoma and customer satisfaction with Sprint. This statistical connection, while somewhat unexpected, may have implications that extend beyond the realm of numbers, suggesting a curious interplay between statistical expertise and customer contentment with telecommunications services. Our study not only sheds light on this quirky correlation but also adds a dash of statistical humor to the academic discourse.

[[INTRDUCTION]]
As we venture into the enigmatic world of statistics, we often find ourselves lost in a sea of numbers, trends, and the occasional outlier that just won't follow the trend. Today, we embark on a statistical escapade to unravel the unexpected and somewhat mind-boggling relationship between the number of statisticians in the great state of Oklahoma and the satisfaction of customers with the telecommunications giant, Sprint.
Now, you might be wondering what in the world prompted such a peculiar investigation. Well, curiosity got the best of us, and we just couldn't resist the urge to unravel this statistical riddle. Who knew that the abundance of statistics aficionados in the land of Oklahoma could have anything to do with how satisfied Sprint customers are with their services? But as the saying goes, "correlation does not imply causation," so we set out to investigate just what's cooking in the statistical cauldron.
We dived into the depths of data, armed with our trusty statistical tools and a healthy dose of skepticism, ready to crunch numbers and seek out hidden patterns like archeologists searching for ancient treasures. Our quest led us to the hallowed halls of the Bureau of Labor Statistics, where numbers flow like a river and percentages dance like nobody's watching. We paired this with the treasure trove of customer satisfaction data from the American Customer Satisfaction Index, and lo and behold, the adventure had begun.
As we delved deeper into the numbers, we couldn't help but muse about the irony that statisticians, those guardians of numbers, might have their own numbers correlated with something as unpredictable as customer satisfaction with a telecom provider. It's like witnessing a unicorn in the world of statistics – unlikely but oh so intriguing.
So, with our tongues firmly in cheek and our minds focused on the serious pursuit of statistical knowledge, we aimed to unravel the mysteries of this strange association. Through rigorous analysis, we sought to determine if the number of statistical gurus in Oklahoma had any quantifiable impact on the satisfaction levels of Sprint customers. The idea was to shed light on a bizarre correlation with a healthy dose of statistical humor thrown in for good measure because, let’s face it, statistics could use a bit of levity.
As we present our findings, brace yourselves for a romp through the world of numbers and human sentiment, where the unexpected takes center stage, and statistical correlations sometimes take us on the most peculiar of journeys. So, join us as we venture forth into the statistically odd and the delightfully befuddling world of statisticians in Oklahoma and customer satisfaction with Sprint.

[[RESULTS]]
Upon diving into the sea of numbers and statistical shenanigans, we emerged with some fascinating findings that shed light on the quirky relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. After donning our metaphorical detective hats and wielding our trusty statistical tools, we unearthed a correlation coefficient of 0.7352215 between these two seemingly disparate variables. It's as if the statistical stars aligned to reveal a connection that defies conventional wisdom and tickles the fancy of the empirical enthusiast.
In addition to this eyebrow-raising correlation, our analysis unveiled an r-squared value of 0.5405506, signifying that a substantial portion (approximately 54.06%) of the variance in Sprint customer satisfaction can be explained by the abundance of number-crunching aficionados in Oklahoma. This finding is no statistical fluke; it indicates a robust relationship that adds a touch of unpredictability to the otherwise predictable world of numerical analyses.
To top it all off, the p-value of less than 0.01 sent ripples of excitement through the realm of statistical significance, affirming that the correlation we uncovered is not a figment of statistical folklore, but a bona fide connection worthy of scientific scrutiny.
Now, let us not forget the pièce de résistance – our beloved Figure 1, a scatterplot that captures the essence of this captivating correlation in all its graphical glory. Behold, as the data points form a visual tapestry of statistical intrigue, showcasing the unmistakable trend that binds statisticians in Oklahoma to the ebbs and flows of Sprint customer contentment. It's a sight to behold, akin to a statistical romance blossoming amidst the data points, and it serves as a testament to the far-reaching implications of this curious correlation.
In conclusion, our study not only unravels the unexpected interplay between statisticians in Oklahoma and Sprint satisfaction but also injects a healthy dose of statistical whimsy into the academic arena. The statistical oddity that we uncovered beckons us to embrace the delightful befuddlement that comes with unraveling the curiosities of correlation, reminding us that the world of statistics is not without its surprises.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In the whimsical world of statistical musings, our foray into the correlation between the cadre of statisticians in Oklahoma and customer satisfaction with Sprint has yielded some delightfully peculiar findings. Who would have thought that the number-crunching aficionados of Oklahoma could have a say in the telecommunication joy of Sprint customers? It's like stumbling upon a statistical unicorn grazing in the meadows of correlation, a surreal yet undeniable sight to behold.

As we bid adieu to this curious statistical escapade, we can't help but marvel at the ripples of wonder that this correlation has stirred. With a correlation coefficient of 0.7352215 reminiscent of a symphonic statistical crescendo, and an r-squared value of 0.5405506 heralding the statistical significance of this peculiar association, our findings stand as a testament to the unexpected delights that empirical investigations can uncover.

Now, if you still had doubts about the enthralling nature of statistics, let this peculiar correlation serve as a reminder that the world of empirical inquiry is not without its surprises. It's like uncovering a hidden treasure chest of statistical wonderment, where the quest for knowledge leads us on the most unexpected of adventures.

In the grand tradition of scientific conclusions, we assert with utmost confidence that the correlation between statisticians in Oklahoma and Sprint satisfaction has been thoroughly probed and pondered. The statistical stars have aligned, the numbers have spoken, and it's time to hang the proverbial "no more research needed" sign on this statistical enigma. The curtain has fallen on this charming correlation, leaving us with a fond chuckle and a newfound appreciation for the statistical whimsy that underpins our empirical endeavors.


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 Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Statistical Analyses


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 Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Midwestern Statistical Analysis


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 Statisticians in Oklahoma and Sprint Satisfaction: A Statistical Study with an abstract of In this study, we set out to unravel the perplexing relationship between the number of statisticians in Oklahoma and customer satisfaction with Sprint. While some might find this topic a bit "statistically" odd, our research aimed to determine if there is a quantifiable connection between the two. Utilizing data from the Bureau of Labor Statistics and the American Customer Satisfaction Index, we embarked on a journey that involved crunching numbers, analyzing trends, and unraveling statistical mysteries.
Surprisingly, our findings reveal a correlation coefficient of 0.7352215 and p < 0.01 for the period spanning from 2004 to 2020, leading us to conclude that there is indeed a substantial correlation between the abundance of statisticians in Oklahoma and customer satisfaction with Sprint. This statistical connection, while somewhat unexpected, may have implications that extend beyond the realm of numbers, suggesting a curious interplay between statistical expertise and customer contentment with telecommunications services. Our study not only sheds light on this quirky correlation but also adds a dash of statistical humor to the academic discourse.

ChatGPT:

statisticians, Oklahoma, Sprint, customer satisfaction, statistical study, correlation coefficient, Bureau of Labor Statistics, American Customer Satisfaction Index, telecommunications services, statistical expertise, academic discourse

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

Customer satisfaction with Sprint
Source: American Customer Satisfaction Index
See what else correlates with Customer satisfaction with Sprint

Correlation r = 0.7352215 (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 = 0.5405506 (Coefficient of determination)
This means 54.1% of the change in the one variable (i.e., Customer satisfaction with Sprint) is predictable based on the change in the other (i.e., The number of statisticians in Oklahoma) over the 17 years from 2004 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00077. 0.0007714602936724377000000000
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 0.74 in 0.077% of random cases. Said differently, if you correlated 1,296 random variables Which I absolutely did.
with the same 16 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 16 because we have two variables measured over a period of 17 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.

[ 0.39, 0.9 ] 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.
20042005200620072008200920102011201220132014201520162017201820192020
The number of statisticians in Oklahoma (Statisticians)9080200190180110360310300160220200280330350260270
Customer satisfaction with Sprint (Consumer Satisfaction)5963636156637072717168657073706970




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.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. 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([90,80,200,190,180,110,360,310,300,160,220,200,280,330,350,260,270,])
array_2 = np.array([59,63,63,61,56,63,70,72,71,71,68,65,70,73,70,69,70,])
array_1_name = "The number of statisticians in Oklahoma"
array_2_name = "Customer satisfaction with Sprint"

# 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?

Bravo! Your evaluation rocks!


Correlation ID: 1048 · Black Variable ID: 13050 · Red Variable ID: 19884
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0