about · email me · subscribe
Spurious correlation #1,249 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Movie ticket sales in the U.S. and Canada by year and the second variable is The number of first-line retail sales supervisors in New Mexico.  The chart goes from 2010 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As movie ticket sales dropped, fewer people experienced the magic of cinema. This led to a decline in demand for popcorn and snacks at the theaters. With less need for snack-related supervision, first-line retail sales supervisor positions in New Mexico were no longer as butterly competitive, causing a decrease in the number of supervisors.

Model: dalle-3
Prompt: Generate an image of a street scene from an aerial perspective. The streets are depicted with intricate details of old cobblestones and vintage lampposts, reminiscent of classic newspaper illustrations. The theater, with its grand marquee, stands out as the focal point with a few people lingering by the entrance. However, the lines are visibly shorter and there's a noticeable decrease in foot traffic. In contrast, adjacent to the theater are rows of dimly lit living room windows showcasing figures cozily seated with popcorn bowls, casting a warm glow into the night. The surrounding streets appear quieter, with only a few solitary figures strolling, while the storefronts reveal vacant aisles and unoccupied retail sales supervisors. The image captures the transition of people from outdoor activities to indoor comfort, emphasizing the changing cultural landscape. 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: Because as movie ticket sales decreased, people had less reason to go out, leading to more time spent at home. With more time at home, there was an increase in online shopping, reducing the need for retail sales supervisors. . 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: Concept art Charcoal Pop art A Discovery magazine cover image A black-and-white newspaper illustration
ChatGPT: A black-and-white newspaper illustration

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. Because as movie ticket sales decreased, people had less reason to go out, leading to more time spent at home. With more time at home, there was an increase in online shopping, reducing the need for retail sales supervisors.
ChatGPT: As movie ticket sales decreased, the bustling lines at the theater started to dwindle. People stayed in more, cozying up on their sofas with popcorn in hand. As a result, the streets became emptier as more folks stayed home. Meanwhile, the glow of computer screens illuminated living rooms, with more and more online shopping happening. With the decline in foot traffic at retail stores, the once busy aisles grew quieter, and retail sales supervisors found themselves with fewer customers to attend to.

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: [ A black-and-white newspaper illustration ] and depicting this scene: As movie ticket sales decreased, the bustling lines at the theater started to dwindle. People stayed in more, cozying up on their sofas with popcorn in hand. As a result, the streets became emptier as more folks stayed home. Meanwhile, the glow of computer screens illuminated living rooms, with more and more online shopping happening. With the decline in foot traffic at retail stores, the once busy aisles grew quieter, and retail sales supervisors found themselves with fewer customers to attend to. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a street scene from an aerial perspective. The streets are depicted with intricate details of old cobblestones and vintage lampposts, reminiscent of classic newspaper illustrations. The theater, with its grand marquee, stands out as the focal point with a few people lingering by the entrance. However, the lines are visibly shorter and there's a noticeable decrease in foot traffic. In contrast, adjacent to the theater are rows of dimly lit living room windows showcasing figures cozily seated with popcorn bowls, casting a warm glow into the night. The surrounding streets appear quieter, with only a few solitary figures strolling, while the storefronts reveal vacant aisles and unoccupied retail sales supervisors. The image captures the transition of people from outdoor activities to indoor comfort, emphasizing the changing cultural landscape.

*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 a decrease in Movie ticket sales in the U.S. and Canada by year caused The number of first-line retail sales supervisors in New Mexico to decrease.

AI academic paper

(Because p < 0.01)
Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico

The Journal of Irreverent Research and Quirky Findings

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Movie ticket sales in the U.S. and Canada by year and The number of first-line retail sales supervisors in New Mexico. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title a clever pun.

Your research team used data from Statista and Bureau of Larbor Statistics to assess this nagging question. You found a correlation coefficient of 0.9240050 and p < 0.01 for 2010 to 2022.

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]]
Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico

[[ABSTRACT]]
This study presents an unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. Using data from Statista and the Bureau of Labor Statistics, we examined the relationship between these two seemingly unrelated variables from 2010 to 2022. The results revealed a strong positive correlation, with a correlation coefficient of 0.9240050 and a significance level of p < 0.01.

Our findings suggest a surprising connection between the entertainment industry and retail management in the Land of Enchantment. This correlation could spark some lively discussions among economists and movie buffs alike. It seems that as movie ticket sales soar, so do the ranks of retail supervisors in New Mexico - perhaps they're needed to deal with the inevitable surge of customers seeking movie snacks. This unexpected link certainly adds a new dimension to the phrase "retail therapy." Further research is warranted to explore the underlying mechanisms driving this correlation and to unravel the common threads between moviegoers and retail management in New Mexico.



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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Movie ticket sales in the U.S. and Canada by year and The number of first-line retail sales supervisors in New Mexico. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico

[[ABSTRACT]]
This study presents an unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. Using data from Statista and the Bureau of Labor Statistics, we examined the relationship between these two seemingly unrelated variables from 2010 to 2022. The results revealed a strong positive correlation, with a correlation coefficient of 0.9240050 and a significance level of p < 0.01.

Our findings suggest a surprising connection between the entertainment industry and retail management in the Land of Enchantment. This correlation could spark some lively discussions among economists and movie buffs alike. It seems that as movie ticket sales soar, so do the ranks of retail supervisors in New Mexico - perhaps they're needed to deal with the inevitable surge of customers seeking movie snacks. This unexpected link certainly adds a new dimension to the phrase "retail therapy." Further research is warranted to explore the underlying mechanisms driving this correlation and to unravel the common threads between moviegoers and retail management in New Mexico.


-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The field of economics often uncovers surprising associations between seemingly unrelated variables. In this study, we delve into the unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in the state of New Mexico. One might say this correlation is a reel eye-opener! The analysis of this peculiar relationship sheds light on the intricate interplay between the entertainment industry and retail management.

Given the seemingly disparate nature of the variables under investigation, one might initially assume that any link between the two would be as elusive as a good parking spot at a popular movie premiere. However, our study challenges these assumptions and uncovers a statistically significant connection that cannot be dismissed as mere coincidence.

As the popcorn pops and the candy bars stack up, the number of retail sales supervisors in New Mexico seems to follow suit. It appears that the demand for movie tickets goes hand in hand with the demand for retail supervisors in the Land of Enchantment. One wonders if there's a certain "scent-sational" allure to working in retail during blockbuster movie releases. This unexpected association alludes to a deeper, more nuanced relationship between consumer behavior in the entertainment industry and supervisory roles in the retail sector.

Our findings not only defy conventional wisdom but also raise a plethora of questions. What underlying factors drive this intriguing correlation? Is there a shared behavioral underpinning to the choices of moviegoers and retail workers in New Mexico? The data hints at a link that is as riveting as a thrilling plot twist, and just as deserving of further exploration.

In light of these compelling results, it becomes apparent that the implications of this correlation extend beyond the realms of pure economics. As we embark on this journey to unravel the unexpected relationship between movie ticket sales and retail supervisors in New Mexico, we are poised to uncover a connection as captivating as a box office hit and as perplexing as a critically acclaimed mystery.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Movie ticket sales in the U.S. and Canada by year and The number of first-line retail sales supervisors in New Mexico. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico

[[ABSTRACT]]
This study presents an unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. Using data from Statista and the Bureau of Labor Statistics, we examined the relationship between these two seemingly unrelated variables from 2010 to 2022. The results revealed a strong positive correlation, with a correlation coefficient of 0.9240050 and a significance level of p < 0.01.

Our findings suggest a surprising connection between the entertainment industry and retail management in the Land of Enchantment. This correlation could spark some lively discussions among economists and movie buffs alike. It seems that as movie ticket sales soar, so do the ranks of retail supervisors in New Mexico - perhaps they're needed to deal with the inevitable surge of customers seeking movie snacks. This unexpected link certainly adds a new dimension to the phrase "retail therapy." Further research is warranted to explore the underlying mechanisms driving this correlation and to unravel the common threads between moviegoers and retail management in New Mexico.


-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The field of economics often uncovers surprising associations between seemingly unrelated variables. In this study, we delve into the unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in the state of New Mexico. One might say this correlation is a reel eye-opener! The analysis of this peculiar relationship sheds light on the intricate interplay between the entertainment industry and retail management.
Given the seemingly disparate nature of the variables under investigation, one might initially assume that any link between the two would be as elusive as a good parking spot at a popular movie premiere. However, our study challenges these assumptions and uncovers a statistically significant connection that cannot be dismissed as mere coincidence.
As the popcorn pops and the candy bars stack up, the number of retail sales supervisors in New Mexico seems to follow suit. It appears that the demand for movie tickets goes hand in hand with the demand for retail supervisors in the Land of Enchantment. One wonders if there's a certain "scent-sational" allure to working in retail during blockbuster movie releases. This unexpected association alludes to a deeper, more nuanced relationship between consumer behavior in the entertainment industry and supervisory roles in the retail sector.
Our findings not only defy conventional wisdom but also raise a plethora of questions. What underlying factors drive this intriguing correlation? Is there a shared behavioral underpinning to the choices of moviegoers and retail workers in New Mexico? The data hints at a link that is as riveting as a thrilling plot twist, and just as deserving of further exploration.
In light of these compelling results, it becomes apparent that the implications of this correlation extend beyond the realms of pure economics. As we embark on this journey to unravel the unexpected relationship between movie ticket sales and retail supervisors in New Mexico, we are poised to uncover a connection as captivating as a box office hit and as perplexing as a critically acclaimed mystery.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

A number of scholars have previously delved into the intricate world of movie ticket sales and its correlations with various economic and social factors. Smith and Doe (2015) explored the impact of movie genres on ticket sales, while Jones (2018) investigated the influence of celebrity endorsements on movie attendance. However, none of these studies have ventured into the uncharted territory of connecting movie ticket sales with the number of retail supervisors in a specific state, such as New Mexico.

In "The Economics of Entertainment" by Adams, a comprehensive analysis of the economic dynamics of the entertainment industry is presented, offering valuable insights into the factors influencing movie ticket sales. Taking a more imaginative approach, "The Movies as History" by Film Historian delves into the sociocultural aspects of moviegoing, examining how historical events and societal trends shape audience preferences.

Moving from non-fiction to fiction, "Moneyball" by Michael Lewis, though about baseball, provides a fascinating exploration of statistical correlations in an unexpected context. In a similar vein, "The Da Vinci Code" by Dan Brown, while a work of fiction, challenges readers to uncover hidden connections and unexpected truths, much like our study.

Drawing from unconventional sources, the animated series "SpongeBob SquarePants" portrays the wacky adventures of a sponge living in a pineapple under the sea, inadvertently providing a comedic yet thought-provoking lens through which to view unexpected correlations. Additionally, "Dora the Explorer" introduces preschoolers to the concept of exploration and problem-solving, perhaps serving as a metaphor for our research journey into deciphering the link between movie ticket sales and retail supervisors in New Mexico.

As we navigate through this eclectic mix of literature and media, we prepare to unveil the unexpected connection between movie ticket sales and retail supervisors in New Mexico, culminating in a revelation that may rival even the most surprising plot twist.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Movie ticket sales in the U.S. and Canada by year and The number of first-line retail sales supervisors in New Mexico. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 Statista and Bureau of Larbor Statistics . You used data from 2010 to 2022

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]]
Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico

[[ABSTRACT]]
This study presents an unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. Using data from Statista and the Bureau of Labor Statistics, we examined the relationship between these two seemingly unrelated variables from 2010 to 2022. The results revealed a strong positive correlation, with a correlation coefficient of 0.9240050 and a significance level of p < 0.01.

Our findings suggest a surprising connection between the entertainment industry and retail management in the Land of Enchantment. This correlation could spark some lively discussions among economists and movie buffs alike. It seems that as movie ticket sales soar, so do the ranks of retail supervisors in New Mexico - perhaps they're needed to deal with the inevitable surge of customers seeking movie snacks. This unexpected link certainly adds a new dimension to the phrase "retail therapy." Further research is warranted to explore the underlying mechanisms driving this correlation and to unravel the common threads between moviegoers and retail management in New Mexico.


[[INTRODUCTION]]
The field of economics often uncovers surprising associations between seemingly unrelated variables. In this study, we delve into the unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in the state of New Mexico. One might say this correlation is a reel eye-opener! The analysis of this peculiar relationship sheds light on the intricate interplay between the entertainment industry and retail management.
Given the seemingly disparate nature of the variables under investigation, one might initially assume that any link between the two would be as elusive as a good parking spot at a popular movie premiere. However, our study challenges these assumptions and uncovers a statistically significant connection that cannot be dismissed as mere coincidence.
As the popcorn pops and the candy bars stack up, the number of retail sales supervisors in New Mexico seems to follow suit. It appears that the demand for movie tickets goes hand in hand with the demand for retail supervisors in the Land of Enchantment. One wonders if there's a certain "scent-sational" allure to working in retail during blockbuster movie releases. This unexpected association alludes to a deeper, more nuanced relationship between consumer behavior in the entertainment industry and supervisory roles in the retail sector.
Our findings not only defy conventional wisdom but also raise a plethora of questions. What underlying factors drive this intriguing correlation? Is there a shared behavioral underpinning to the choices of moviegoers and retail workers in New Mexico? The data hints at a link that is as riveting as a thrilling plot twist, and just as deserving of further exploration.
In light of these compelling results, it becomes apparent that the implications of this correlation extend beyond the realms of pure economics. As we embark on this journey to unravel the unexpected relationship between movie ticket sales and retail supervisors in New Mexico, we are poised to uncover a connection as captivating as a box office hit and as perplexing as a critically acclaimed mystery.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data for this study was sourced primarily from Statista and the Bureau of Labor Statistics, covering the period from 2010 to 2022. Movie ticket sales from both the United States and Canada were obtained from industry reports and box office performance analyses. The number of first-line retail sales supervisors in New Mexico was extracted from employment data and industry surveys. It was important to ensure that the data selected for analysis was as robust as a well-constructed plot and as reliable as a seasoned movie reviewer.

Data Analysis:
To explore the association between movie ticket sales and the number of retail sales supervisors in New Mexico, a series of statistical analyses were employed. Initially, a correlation analysis was conducted to ascertain the strength and direction of the relationship between the two variables. The correlation coefficient derived was akin to a protagonist – it revealed the magnitude of the relationship, while the significance level acted as the twist in the tale – indicating whether the observed association was mere happenstance or a meaningful connection.

Furthermore, a time-series analysis was utilized to discern any temporal patterns or fluctuations in the variables over the study period. This approach enabled us to gauge whether the correlation between movie ticket sales and retail supervisors in New Mexico bore the same mark as a recurring cinematic theme.

Additionally, a regression analysis was executed to determine the extent to which movie ticket sales could predict the number of retail sales supervisors in New Mexico. This method allowed us to ascertain whether the observed correlation was as predictable as a Hollywood cliché or as surprising as an unexpected plot twist.

Oh, and speaking of plot twists, did you hear about the mathematician who’s afraid of negative numbers? He’ll stop at nothing to avoid them.

Control Variables:
Several control variables were incorporated into the analysis to mitigate the potential influence of extraneous factors. These included economic indicators such as unemployment rates, consumer spending patterns, and retail industry performance. By accounting for these variables, we aimed to ensure that any observed correlation between movie ticket sales and retail supervisors was not confounded by external factors, much like how an unsolved mystery can hinge on the smallest of details.

Model Validation:
To validate the robustness of the findings, sensitivity analyses were conducted utilizing different data sources and alternate model specifications. This approach provided a sense of reassurance that the observed correlation was not a whimsical artifact of the data but rather a tangible connection worthy of further scrutiny.

In summary, the methodology employed in this study sought to uncover the unexpected correlation between movie ticket sales in the U.S. and Canada and the number of first-line retail sales supervisors in New Mexico. By employing a combination of statistical techniques and data validation measures, we endeavored to untangle this unlikely relationship, much like peeling back the layers of a complex storyline to reveal its underlying coherence.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Movie ticket sales in the U.S. and Canada by year and The number of first-line retail sales supervisors in New Mexico. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 Statista and Bureau of Larbor Statistics .

For the time period 2010 to 2022, you found a correlation 0.9240050, r-squared of 0.8537853, 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]]
Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico

[[ABSTRACT]]
This study presents an unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. Using data from Statista and the Bureau of Labor Statistics, we examined the relationship between these two seemingly unrelated variables from 2010 to 2022. The results revealed a strong positive correlation, with a correlation coefficient of 0.9240050 and a significance level of p < 0.01.

Our findings suggest a surprising connection between the entertainment industry and retail management in the Land of Enchantment. This correlation could spark some lively discussions among economists and movie buffs alike. It seems that as movie ticket sales soar, so do the ranks of retail supervisors in New Mexico - perhaps they're needed to deal with the inevitable surge of customers seeking movie snacks. This unexpected link certainly adds a new dimension to the phrase "retail therapy." Further research is warranted to explore the underlying mechanisms driving this correlation and to unravel the common threads between moviegoers and retail management in New Mexico.


-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The field of economics often uncovers surprising associations between seemingly unrelated variables. In this study, we delve into the unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in the state of New Mexico. One might say this correlation is a reel eye-opener! The analysis of this peculiar relationship sheds light on the intricate interplay between the entertainment industry and retail management.
Given the seemingly disparate nature of the variables under investigation, one might initially assume that any link between the two would be as elusive as a good parking spot at a popular movie premiere. However, our study challenges these assumptions and uncovers a statistically significant connection that cannot be dismissed as mere coincidence.
As the popcorn pops and the candy bars stack up, the number of retail sales supervisors in New Mexico seems to follow suit. It appears that the demand for movie tickets goes hand in hand with the demand for retail supervisors in the Land of Enchantment. One wonders if there's a certain "scent-sational" allure to working in retail during blockbuster movie releases. This unexpected association alludes to a deeper, more nuanced relationship between consumer behavior in the entertainment industry and supervisory roles in the retail sector.
Our findings not only defy conventional wisdom but also raise a plethora of questions. What underlying factors drive this intriguing correlation? Is there a shared behavioral underpinning to the choices of moviegoers and retail workers in New Mexico? The data hints at a link that is as riveting as a thrilling plot twist, and just as deserving of further exploration.
In light of these compelling results, it becomes apparent that the implications of this correlation extend beyond the realms of pure economics. As we embark on this journey to unravel the unexpected relationship between movie ticket sales and retail supervisors in New Mexico, we are poised to uncover a connection as captivating as a box office hit and as perplexing as a critically acclaimed mystery.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the relationship between annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico yielded a correlation coefficient of 0.9240050, indicative of a strong positive correlation. In essence, as movie ticket sales increased, so did the number of retail sales supervisors in the Land of Enchantment. One might say that this unexpected correlation is a box office smash in the world of economic research.

The coefficient of determination (r-squared) of 0.8537853 highlighted the robustness of this correlation, indicating that approximately 85.4% of the variation in the number of retail sales supervisors can be explained by the variation in movie ticket sales. This finding suggests that the link between these two variables is not merely a flash in the pan, but rather a substantial and enduring relationship.

Furthermore, the significance level of p < 0.01 provides strong evidence to reject the null hypothesis of no correlation. It seems that this correlation is about as statistically significant as a well-executed plot twist in a blockbuster film.

The scatterplot (Fig. 1) visually depicts the striking positive correlation between movie ticket sales and the number of retail sales supervisors in New Mexico. The points tightly cluster around a trend line, resembling the orderly formation of moviegoers queuing up for their favorite films. This unexpected connection between movie ticket sales and retail supervision in New Mexico certainly adds an element of surprise to the usually mundane world of economic data analysis.

In summary, the results of this study reveal a notable and statistically significant positive correlation between movie ticket sales and the number of first-line retail sales supervisors in New Mexico. This unexpected relationship opens the door to further exploration and paves the way for new avenues of research in the fields of economics and consumer behavior. The unexpected correlation between movie ticket sales and retail supervisors in New Mexico is undoubtedly a reel eye-opener, and it beckons for deeper investigation into the nuanced dynamics at play.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Movie ticket sales in the U.S. and Canada by year and The number of first-line retail sales supervisors in New Mexico. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico

[[ABSTRACT]]
This study presents an unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. Using data from Statista and the Bureau of Labor Statistics, we examined the relationship between these two seemingly unrelated variables from 2010 to 2022. The results revealed a strong positive correlation, with a correlation coefficient of 0.9240050 and a significance level of p < 0.01.

Our findings suggest a surprising connection between the entertainment industry and retail management in the Land of Enchantment. This correlation could spark some lively discussions among economists and movie buffs alike. It seems that as movie ticket sales soar, so do the ranks of retail supervisors in New Mexico - perhaps they're needed to deal with the inevitable surge of customers seeking movie snacks. This unexpected link certainly adds a new dimension to the phrase "retail therapy." Further research is warranted to explore the underlying mechanisms driving this correlation and to unravel the common threads between moviegoers and retail management in New Mexico.


[[LITERATURE REVIEW]]
A number of scholars have previously delved into the intricate world of movie ticket sales and its correlations with various economic and social factors. Smith and Doe (2015) explored the impact of movie genres on ticket sales, while Jones (2018) investigated the influence of celebrity endorsements on movie attendance. However, none of these studies have ventured into the uncharted territory of connecting movie ticket sales with the number of retail supervisors in a specific state, such as New Mexico.
In "The Economics of Entertainment" by Adams, a comprehensive analysis of the economic dynamics of the entertainment industry is presented, offering valuable insights into the factors influencing movie ticket sales. Taking a more imaginative approach, "The Movies as History" by Film Historian delves into the sociocultural aspects of moviegoing, examining how historical events and societal trends shape audience preferences.
Moving from non-fiction to fiction, "Moneyball" by Michael Lewis, though about baseball, provides a fascinating exploration of statistical correlations in an unexpected context. In a similar vein, "The Da Vinci Code" by Dan Brown, while a work of fiction, challenges readers to uncover hidden connections and unexpected truths, much like our study.
Drawing from unconventional sources, the animated series "SpongeBob SquarePants" portrays the wacky adventures of a sponge living in a pineapple under the sea, inadvertently providing a comedic yet thought-provoking lens through which to view unexpected correlations. Additionally, "Dora the Explorer" introduces preschoolers to the concept of exploration and problem-solving, perhaps serving as a metaphor for our research journey into deciphering the link between movie ticket sales and retail supervisors in New Mexico.
As we navigate through this eclectic mix of literature and media, we prepare to unveil the unexpected connection between movie ticket sales and retail supervisors in New Mexico, culminating in a revelation that may rival even the most surprising plot twist.

[[RESULTS]]
The analysis of the relationship between annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico yielded a correlation coefficient of 0.9240050, indicative of a strong positive correlation. In essence, as movie ticket sales increased, so did the number of retail sales supervisors in the Land of Enchantment. One might say that this unexpected correlation is a box office smash in the world of economic research.
The coefficient of determination (r-squared) of 0.8537853 highlighted the robustness of this correlation, indicating that approximately 85.4% of the variation in the number of retail sales supervisors can be explained by the variation in movie ticket sales. This finding suggests that the link between these two variables is not merely a flash in the pan, but rather a substantial and enduring relationship.
Furthermore, the significance level of p < 0.01 provides strong evidence to reject the null hypothesis of no correlation. It seems that this correlation is about as statistically significant as a well-executed plot twist in a blockbuster film.
The scatterplot (Fig. 1) visually depicts the striking positive correlation between movie ticket sales and the number of retail sales supervisors in New Mexico. The points tightly cluster around a trend line, resembling the orderly formation of moviegoers queuing up for their favorite films. This unexpected connection between movie ticket sales and retail supervision in New Mexico certainly adds an element of surprise to the usually mundane world of economic data analysis.
In summary, the results of this study reveal a notable and statistically significant positive correlation between movie ticket sales and the number of first-line retail sales supervisors in New Mexico. This unexpected relationship opens the door to further exploration and paves the way for new avenues of research in the fields of economics and consumer behavior. The unexpected correlation between movie ticket sales and retail supervisors in New Mexico is undoubtedly a reel eye-opener, and it beckons for deeper investigation into the nuanced dynamics at play.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study provide compelling evidence of a strong positive correlation between annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. This unexpected connection not only confirms but extends prior research in the area of peculiar correlations. It seems that the link between movie ticket sales and retail supervision in New Mexico is no mere mirage in the desert of economic anomalies.

Building upon existing literature, which, to our surprise, did not previously explore this specific correlation, our study unravels a thread that ties together the world of entertainment and retail management in the Land of Enchantment. As Adams elucidated the economic dynamics of the entertainment industry and Film Historian delved into the sociocultural aspects of moviegoing, it becomes clear that our study's unexpected correlation adds a new dimension to the scholarly understanding of the influence of movies on seemingly unrelated economic factors. It appears that this study's revelation is not just another twist in the plot; it is the unexpected climax that captivates and challenges traditional economic thinking.

The robust correlation coefficient of 0.9240050 and its associated significance level of p < 0.01 lend credence to the veracity of this unanticipated relationship. The statistical strength of this correlation resembles a well-crafted punchline in a big-budget comedy, eliciting amusement and incredulity in equal measure. Who knew that movie ticket sales and retail supervision in New Mexico would make for such an unexpected duo?

Moreover, the coefficient of determination (r-squared) of 0.8537853 suggests that approximately 85.4% of the variation in the number of retail sales supervisors can be elucidated by the variation in movie ticket sales. This robust proportion indicates that the influence of movie ticket sales on the demand for retail supervisors in New Mexico is not a flimsy subplot but rather a compelling narrative in the economic landscape. Perhaps we should start calling it "retail supervi-cinema"!

Our study firmly establishes the presence of an unexpected correlation between two seemingly disparate variables. The scatterplot visually depicts the strong positive relationship between movie ticket sales and the number of retail sales supervisors in New Mexico, rendering it as clear as a high-definition movie screen. This unexpected correlation challenges the very fabric of conventional economic theory, injecting a sense of excitement into the traditionally staid realm of economic research. It seems that this unexpected correlation is not just a passing fad but rather a main feature in the theater of economic phenomena.

As we consider the broader implications of this unexpected correlation, it becomes evident that further research is warranted to uncover the underlying mechanisms driving this phenomenon. What unseen forces are at play in the demand for retail supervisors in New Mexico that are so intimately linked with the ups and downs of movie ticket sales? The unexpected correlation between movie ticket sales and retail supervisors not only bewitches us with its intrigue but also beckons us to delve deeper into the enigma of consumer behavior and economic interconnections.

In conclusion, the unexpected correlation between movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico provides a captivating twist in the scholarly understanding of economic relationships. This unanticipated connection challenges traditional economic thinking and paves the way for future research endeavors that may uncover the mysterious forces at play in the world of moviegoers and retail management. It seems that the only thing more surprising than this unexpected correlation is perhaps the unexpected twists and turns of a classic dad joke. After all, sometimes the most unexpected correlations occur in the realm of humor!


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Movie ticket sales in the U.S. and Canada by year and The number of first-line retail sales supervisors in New Mexico. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico

[[ABSTRACT]]
This study presents an unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. Using data from Statista and the Bureau of Labor Statistics, we examined the relationship between these two seemingly unrelated variables from 2010 to 2022. The results revealed a strong positive correlation, with a correlation coefficient of 0.9240050 and a significance level of p < 0.01.

Our findings suggest a surprising connection between the entertainment industry and retail management in the Land of Enchantment. This correlation could spark some lively discussions among economists and movie buffs alike. It seems that as movie ticket sales soar, so do the ranks of retail supervisors in New Mexico - perhaps they're needed to deal with the inevitable surge of customers seeking movie snacks. This unexpected link certainly adds a new dimension to the phrase "retail therapy." Further research is warranted to explore the underlying mechanisms driving this correlation and to unravel the common threads between moviegoers and retail management in New Mexico.


[[INTRDUCTION]]
The field of economics often uncovers surprising associations between seemingly unrelated variables. In this study, we delve into the unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in the state of New Mexico. One might say this correlation is a reel eye-opener! The analysis of this peculiar relationship sheds light on the intricate interplay between the entertainment industry and retail management.
Given the seemingly disparate nature of the variables under investigation, one might initially assume that any link between the two would be as elusive as a good parking spot at a popular movie premiere. However, our study challenges these assumptions and uncovers a statistically significant connection that cannot be dismissed as mere coincidence.
As the popcorn pops and the candy bars stack up, the number of retail sales supervisors in New Mexico seems to follow suit. It appears that the demand for movie tickets goes hand in hand with the demand for retail supervisors in the Land of Enchantment. One wonders if there's a certain "scent-sational" allure to working in retail during blockbuster movie releases. This unexpected association alludes to a deeper, more nuanced relationship between consumer behavior in the entertainment industry and supervisory roles in the retail sector.
Our findings not only defy conventional wisdom but also raise a plethora of questions. What underlying factors drive this intriguing correlation? Is there a shared behavioral underpinning to the choices of moviegoers and retail workers in New Mexico? The data hints at a link that is as riveting as a thrilling plot twist, and just as deserving of further exploration.
In light of these compelling results, it becomes apparent that the implications of this correlation extend beyond the realms of pure economics. As we embark on this journey to unravel the unexpected relationship between movie ticket sales and retail supervisors in New Mexico, we are poised to uncover a connection as captivating as a box office hit and as perplexing as a critically acclaimed mystery.

[[RESULTS]]
The analysis of the relationship between annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico yielded a correlation coefficient of 0.9240050, indicative of a strong positive correlation. In essence, as movie ticket sales increased, so did the number of retail sales supervisors in the Land of Enchantment. One might say that this unexpected correlation is a box office smash in the world of economic research.
The coefficient of determination (r-squared) of 0.8537853 highlighted the robustness of this correlation, indicating that approximately 85.4% of the variation in the number of retail sales supervisors can be explained by the variation in movie ticket sales. This finding suggests that the link between these two variables is not merely a flash in the pan, but rather a substantial and enduring relationship.
Furthermore, the significance level of p < 0.01 provides strong evidence to reject the null hypothesis of no correlation. It seems that this correlation is about as statistically significant as a well-executed plot twist in a blockbuster film.
The scatterplot (Fig. 1) visually depicts the striking positive correlation between movie ticket sales and the number of retail sales supervisors in New Mexico. The points tightly cluster around a trend line, resembling the orderly formation of moviegoers queuing up for their favorite films. This unexpected connection between movie ticket sales and retail supervision in New Mexico certainly adds an element of surprise to the usually mundane world of economic data analysis.
In summary, the results of this study reveal a notable and statistically significant positive correlation between movie ticket sales and the number of first-line retail sales supervisors in New Mexico. This unexpected relationship opens the door to further exploration and paves the way for new avenues of research in the fields of economics and consumer behavior. The unexpected correlation between movie ticket sales and retail supervisors in New Mexico is undoubtedly a reel eye-opener, and it beckons for deeper investigation into the nuanced dynamics at play.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]
In conclusion, our study has unveiled an unexpected and statistically significant correlation between annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. The robust correlation coefficient and the high level of statistical significance support the legitimacy of this peculiar relationship. One might say this correlation is the best thing since sliced bread - or in this case, since the invention of the popcorn machine!

The link between movie ticket sales and retail supervisors in New Mexico, though surprising, hints at a deeper intertwining of entertainment consumption and retail management. It seems that as moviegoers flock to theaters, retail supervisors in New Mexico stand ready to meet their merchandise needs, perhaps armed with ticket-shaped name tags for the occasion. This correlation introduces a whole new meaning to "retail therapy" – it seems that the movie theater is not the only place for a blockbusting roster of supervisory responsibilities!

The visually striking scatterplot, akin to the orderly formation of moviegoers queuing up for their favorite films, adds an element of whimsy to the otherwise serious field of economic data analysis. It seems that even statistical relationships can have a sense of humor – one might even say they have a particular "punny" disposition!

Overall, our findings have broader implications for the fields of economics and consumer behavior. The unexpected correlation we have uncovered is as intriguing as a good plot twist and as deserving of further exploration as a tantalizing mystery. However, it seems that the punchline of this investigation is clear: no more research is needed on the connection between movie ticket sales and retail supervisors in New Mexico. This correlation is as rock-solid as a superhero's box office performance!


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 Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Irreverent Research and Quirky Findings


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 Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Cinematic Sociology


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 Flicks and Fits: An Unexpected Correlation Between Movie Ticket Sales and Retail Supervisors in New Mexico with an abstract of This study presents an unexpected correlation between the annual movie ticket sales in the United States and Canada and the number of first-line retail sales supervisors in New Mexico. Using data from Statista and the Bureau of Labor Statistics, we examined the relationship between these two seemingly unrelated variables from 2010 to 2022. The results revealed a strong positive correlation, with a correlation coefficient of 0.9240050 and a significance level of p < 0.01.
Our findings suggest a surprising connection between the entertainment industry and retail management in the Land of Enchantment. This correlation could spark some lively discussions among economists and movie buffs alike. It seems that as movie ticket sales soar, so do the ranks of retail supervisors in New Mexico - perhaps they're needed to deal with the inevitable surge of customers seeking movie snacks. This unexpected link certainly adds a new dimension to the phrase "retail therapy." Further research is warranted to explore the underlying mechanisms driving this correlation and to unravel the common threads between moviegoers and retail management in New Mexico.

ChatGPT:

movie ticket sales, United States, Canada, retail supervisors, New Mexico, correlation, Statista, Bureau of Labor Statistics, 2010-2022, entertainment industry, retail management, economists, movie buffs, customer surge, retail therapy, underlying mechanisms

*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

Movie ticket sales in the U.S. and Canada by year
Source: Statista
See what else correlates with Movie ticket sales in the U.S. and Canada by year

The number of first-line retail sales supervisors in New Mexico
Detailed data title: BLS estimate of first-line supervisors of retail sales workers in New Mexico
Source: Bureau of Larbor Statistics
See what else correlates with The number of first-line retail sales supervisors in New Mexico

Correlation r = 0.9240050 (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 = 0.8537853 (Coefficient of determination)
This means 85.4% of the change in the one variable (i.e., The number of first-line retail sales supervisors in New Mexico) is predictable based on the change in the other (i.e., Movie ticket sales in the U.S. and Canada by year) over the 13 years from 2010 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.4E-6. 0.0000064208658900504580000000
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 0.92 in 0.00064% of random cases. Said differently, if you correlated 155,742 random variables You don't actually need 155 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 12 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 12 because we have two variables measured over a period of 13 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.

[ 0.76, 0.98 ] 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.
2010201120122013201420152016201720182019202020212022
Movie ticket sales in the U.S. and Canada by year (Millions)1339100000000128292000000013809200000001329170000000225722000000013231700000001302560000000122564000000013113000000001228760000000221760000000492340000000812790000000
The number of first-line retail sales supervisors in New Mexico (Laborers)9080855084908490922087008640852085608170718075207970




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. Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
  5. 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([1339100000000,1282920000000,1380920000000,1329170000000,2257220000000,1323170000000,1302560000000,1225640000000,1311300000000,1228760000000,221760000000,492340000000,812790000000,])
array_2 = np.array([9080,8550,8490,8490,9220,8700,8640,8520,8560,8170,7180,7520,7970,])
array_1_name = "Movie ticket sales in the U.S. and Canada by year"
array_2_name = "The number of first-line retail sales supervisors in New Mexico"

# 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?

Hats off to you for rating!


Correlation ID: 1249 · Black Variable ID: 286 · Red Variable ID: 18408
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0