about · email me · subscribe
Spurious correlation #1,826 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Associates degrees awarded in Business and the second variable is Google searches for 'xkcd'.  The chart goes from 2011 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the number of Business Associates degrees awarded dropped, there was a corresponding decrease in the creation of soulless office environments. This led to a decrease in the collective need for workplace humor, including xkcd, ultimately causing a drop in Google searches for the beloved webcomic.

Model: dalle-3
Prompt: Generate an image that is reminiscent of a 'Star Wars' scene where a group of college students proudly displays their Associates degrees in Business in a cozy classroom setting. The students are seated and enthusiastically using their laptops to search for the popular webcomic 'xkcd' on Google, with a sense of camaraderie and achievement. The lighting is warm and inviting, and there are subtle nods to 'Star Wars' elements in the background to merge the two themes seamlessly. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Associates degrees awarded in Business and Google searches for 'xkcd'. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: A scene from Skyrim Concept art An image that looks like it is a scene from 'Star Wars' Photorealism Minimalism
ChatGPT: An image that looks like it is a scene from 'Star Wars'

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Associates degrees awarded in Business and Google searches for 'xkcd' together. Keep the description simple.
ChatGPT: In a cozy college classroom, a group of students proudly displays their Associates degrees in Business, while simultaneously using their laptops to search for the popular webcomic 'xkcd' on Google.

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: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: In a cozy college classroom, a group of students proudly displays their Associates degrees in Business, while simultaneously using their laptops to search for the popular webcomic 'xkcd' on Google. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that is reminiscent of a 'Star Wars' scene where a group of college students proudly displays their Associates degrees in Business in a cozy classroom setting. The students are seated and enthusiastically using their laptops to search for the popular webcomic 'xkcd' on Google, with a sense of camaraderie and achievement. The lighting is warm and inviting, and there are subtle nods to 'Star Wars' elements in the background to merge the two themes seamlessly.

*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 Associates degrees awarded in Business caused xkcd (Google searches for 'xkcd') to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)
Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches

The Journal of Business and Internet Research

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 silly researcher writing an academic paper.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 Associates degrees awarded in Business and Google searches for 'xkcd'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Include a pun in the title.

Your research team used data from National Center for Education Statistics and Google Trends to assess this nagging question. You found a correlation coefficient of 0.9503784 and p < 0.01 for 2011 to 2021.

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]]
"Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches"

[[ABSTRACT]]
This study ventures into the realm of curiosities by examining the potential linkage between the number of Associates degrees awarded in Business and the frequency of Google searches for the webcomic 'XKCD'. Through a meticulous analysis of data acquired from the National Center for Education Statistics and Google Trends, we uncovered an astonishing correlation coefficient of 0.9503784 with a significance level of p < 0.01 – a statistical relationship that cannot be dismissed as mere happenstance. The results of our research have sparked intriguing discussions around the water cooler, and we eagerly anticipate the academic community's reaction to this humorous yet surprisingly significant connection.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Associates degrees awarded in Business and Google searches for 'xkcd'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
"Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches"

[[ABSTRACT]]
This study ventures into the realm of curiosities by examining the potential linkage between the number of Associates degrees awarded in Business and the frequency of Google searches for the webcomic 'XKCD'. Through a meticulous analysis of data acquired from the National Center for Education Statistics and Google Trends, we uncovered an astonishing correlation coefficient of 0.9503784 with a significance level of p < 0.01 – a statistical relationship that cannot be dismissed as mere happenstance. The results of our research have sparked intriguing discussions around the water cooler, and we eagerly anticipate the academic community's reaction to this humorous yet surprisingly significant connection.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the realm of academic inquiry, one often encounters unexpected connections and correlations that defy conventional wisdom. The present study delves into such uncharted territory by investigating the possible association between the issuance of Associates degrees in Business and the prevalence of Google searches for the popular webcomic 'XKCD'. While the initial premise of this investigation may seem whimsical, the results have yielded meaningful insights that challenge traditional assumptions about causal relationships.

The subject of this investigation emerges from the curious juxtaposition of educational attainment and internet search behavior. On one hand, the conferral of Associates degrees in the field of Business represents a tangible milestone in the pursuit of vocational knowledge and skills. On the other hand, 'XKCD', a webcomic created by Randall Munroe, is renowned for its blend of incisive humor and astute scientific and technological references. The seemingly disparate domains of higher education and internet culture converge in the terrain of our inquiry, prompting us to unravel the mysterious interplay between these seemingly unrelated phenomena.

In conducting this study, we embarked on a rigorous exploration of publicly available data sources on the issuance of Associates degrees in Business and the corresponding trends in 'XKCD' Google searches. Our analytical journey waded through statistical measures and computational algorithms to distill the essence of this enigmatic correlation. Notably, our findings have teased apart a striking correlation coefficient of 0.9503784, suggesting a robust statistical association between these ostensibly incongruent domains.

In keeping with the spirit of academic inquiry, our investigation invokes both fascination and amusement, offering a window into the unexpected nuances of human behavior and cultural trends. As we embark on this scholarly expedition, we invite our esteemed peers to join us in this pursuit of quirky knowledge and to savor the whimsical facets of this unexpected connection. The implications of our findings extend beyond the confines of traditional research paradigms, inviting a playful conversation that unfolds at the intersection of academia and popular culture. In the words of the webcomic 'XKCD' itself, "Stand back! I'm going to try science!" Indeed, we invite our readers to stand back and witness the interplay of seemingly divergent forces in this lighthearted yet thought-provoking exploration.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Associates degrees awarded in Business and Google searches for 'xkcd'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches"

[[ABSTRACT]]
This study ventures into the realm of curiosities by examining the potential linkage between the number of Associates degrees awarded in Business and the frequency of Google searches for the webcomic 'XKCD'. Through a meticulous analysis of data acquired from the National Center for Education Statistics and Google Trends, we uncovered an astonishing correlation coefficient of 0.9503784 with a significance level of p < 0.01 – a statistical relationship that cannot be dismissed as mere happenstance. The results of our research have sparked intriguing discussions around the water cooler, and we eagerly anticipate the academic community's reaction to this humorous yet surprisingly significant connection.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the realm of academic inquiry, one often encounters unexpected connections and correlations that defy conventional wisdom. The present study delves into such uncharted territory by investigating the possible association between the issuance of Associates degrees in Business and the prevalence of Google searches for the popular webcomic 'XKCD'. While the initial premise of this investigation may seem whimsical, the results have yielded meaningful insights that challenge traditional assumptions about causal relationships.
The subject of this investigation emerges from the curious juxtaposition of educational attainment and internet search behavior. On one hand, the conferral of Associates degrees in the field of Business represents a tangible milestone in the pursuit of vocational knowledge and skills. On the other hand, 'XKCD', a webcomic created by Randall Munroe, is renowned for its blend of incisive humor and astute scientific and technological references. The seemingly disparate domains of higher education and internet culture converge in the terrain of our inquiry, prompting us to unravel the mysterious interplay between these seemingly unrelated phenomena.
In conducting this study, we embarked on a rigorous exploration of publicly available data sources on the issuance of Associates degrees in Business and the corresponding trends in 'XKCD' Google searches. Our analytical journey waded through statistical measures and computational algorithms to distill the essence of this enigmatic correlation. Notably, our findings have teased apart a striking correlation coefficient of 0.9503784, suggesting a robust statistical association between these ostensibly incongruent domains.
In keeping with the spirit of academic inquiry, our investigation invokes both fascination and amusement, offering a window into the unexpected nuances of human behavior and cultural trends. As we embark on this scholarly expedition, we invite our esteemed peers to join us in this pursuit of quirky knowledge and to savor the whimsical facets of this unexpected connection. The implications of our findings extend beyond the confines of traditional research paradigms, inviting a playful conversation that unfolds at the intersection of academia and popular culture. In the words of the webcomic 'XKCD' itself, "Stand back! I'm going to try science!" Indeed, we invite our readers to stand back and witness the interplay of seemingly divergent forces in this lighthearted yet thought-provoking exploration.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith and Doe examine the relationship between educational attainment and internet search behavior and note the surprising correlations that can emerge from seemingly unrelated domains. Their findings shed light on the intricate interplay between academic pursuits and popular culture, setting the stage for our investigation into the connection between Associates degrees awarded in Business and 'XKCD' Google searches. Upon perusing "The Economics of Information Technology" by Jones, we are compelled to consider the influence of web-based content on individual information-seeking behavior and the wider implications for the digital landscape.

Turning our attention to non-fiction literature, "The Search: How Google and Its Rivals Rewrote the Rules of Business and Transformed Our Culture" by John Battelle delves into the profound impact of internet search engines on modern society, hinting at the potential significance of our exploration into Google search trends for 'XKCD'. Furthermore, the thought-provoking work "Freakonomics: A Rogue Economist Explores the Hidden Side of Everything" by Steven D. Levitt and Stephen J. Dubner challenges us to uncover the unexpected and sometimes counterintuitive connections that underpin human behavior, providing a fascinating backdrop to our investigation.

In a twist of literary curiosity, the fictitious worlds of "Big Data, Big Dupe: Learning from a Century of Mistakes" by Stephen Few and "The Hitchhiker's Guide to the Galaxy" by Douglas Adams prompt us to consider the whimsical and unexpected linkages that may arise from our examination of the 'XKCD' Google searches and Associates degrees in Business. The blending of fiction and reality invites us to ponder the boundaries between scholarly investigation and speculative imagination, offering a lighthearted yet insightful lens through which to view our findings.

Beyond conventional scholarly sources, our pursuit of knowledge extended to unexpected sources, including perusing the purchasing patterns of CVS receipts and decoding the cryptic musings of fortune cookies. While these unconventional methods may raise an eyebrow or two, they have undeniably contributed to our holistic view of the unexplored dimensions of our research question. As we delve into the furthest reaches of the academic universe, we embrace the playful pursuit of knowledge and eagerly await the scholarly discourse that will undoubtedly arise from this investigation.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Associates degrees awarded in Business and Google searches for 'xkcd'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from National Center for Education Statistics and Google Trends . You used data from 2011 to 2021

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]]
"Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches"

[[ABSTRACT]]
This study ventures into the realm of curiosities by examining the potential linkage between the number of Associates degrees awarded in Business and the frequency of Google searches for the webcomic 'XKCD'. Through a meticulous analysis of data acquired from the National Center for Education Statistics and Google Trends, we uncovered an astonishing correlation coefficient of 0.9503784 with a significance level of p < 0.01 – a statistical relationship that cannot be dismissed as mere happenstance. The results of our research have sparked intriguing discussions around the water cooler, and we eagerly anticipate the academic community's reaction to this humorous yet surprisingly significant connection.

[[INTRODUCTION]]
In the realm of academic inquiry, one often encounters unexpected connections and correlations that defy conventional wisdom. The present study delves into such uncharted territory by investigating the possible association between the issuance of Associates degrees in Business and the prevalence of Google searches for the popular webcomic 'XKCD'. While the initial premise of this investigation may seem whimsical, the results have yielded meaningful insights that challenge traditional assumptions about causal relationships.
The subject of this investigation emerges from the curious juxtaposition of educational attainment and internet search behavior. On one hand, the conferral of Associates degrees in the field of Business represents a tangible milestone in the pursuit of vocational knowledge and skills. On the other hand, 'XKCD', a webcomic created by Randall Munroe, is renowned for its blend of incisive humor and astute scientific and technological references. The seemingly disparate domains of higher education and internet culture converge in the terrain of our inquiry, prompting us to unravel the mysterious interplay between these seemingly unrelated phenomena.
In conducting this study, we embarked on a rigorous exploration of publicly available data sources on the issuance of Associates degrees in Business and the corresponding trends in 'XKCD' Google searches. Our analytical journey waded through statistical measures and computational algorithms to distill the essence of this enigmatic correlation. Notably, our findings have teased apart a striking correlation coefficient of 0.9503784, suggesting a robust statistical association between these ostensibly incongruent domains.
In keeping with the spirit of academic inquiry, our investigation invokes both fascination and amusement, offering a window into the unexpected nuances of human behavior and cultural trends. As we embark on this scholarly expedition, we invite our esteemed peers to join us in this pursuit of quirky knowledge and to savor the whimsical facets of this unexpected connection. The implications of our findings extend beyond the confines of traditional research paradigms, inviting a playful conversation that unfolds at the intersection of academia and popular culture. In the words of the webcomic 'XKCD' itself, "Stand back! I'm going to try science!" Indeed, we invite our readers to stand back and witness the interplay of seemingly divergent forces in this lighthearted yet thought-provoking exploration.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
To embark on our quest to unravel the mysterious interplay between the conferral of Associates degrees in Business and the prevalence of Google searches for 'XKCD', we first sought to acquire the requisite data from reliable and authoritative sources. Consequently, we turned to the National Center for Education Statistics to procure the comprehensive records of associates degrees awarded in the field of Business from 2011 to 2021. The crisp, cold character of these hard data prodded our analytical sensibilities, much like a stimulating cup of espresso nudging the groggy mind to wakefulness in the early hours of a research morning. Subsequently, we turned our gaze to Google Trends, a veritable cornucopia of insights into the ebb and flow of internet search behavior, where we sought the frequency of 'XKCD' Google searches during the same period.

Data Analysis:
With our bounty of data in hand, we utilized a diverse array of analytical tools and techniques to scrutinize and dissect the entrails of numbers and trends, akin to a vivisection of statistical significance. Employing statistical measures that would make even the most numerically averse individual acknowledge their allure, we computed the correlation coefficient between the number of Associates degrees awarded in Business and the volume of 'XKCD' Google searches. In a display of computational prowess, akin to a beautifully orchestrated symphony, we carried out sophisticated analyses to determine the pertinence and significance of any observed statistical associations. Our odyssey through the labyrinth of statistical methodologies was guided by the twin beacons of academic rigor and intellectual curiosity, illuminating a path through the uncharted terrain of seemingly disparate phenomena and their potential congruence.

Control Variables and Limitations:
As we navigated the realm of empirical inquiry, we were mindful of the necessity to account for extraneous influences and confounding variables that could confound our quest for elucidation. We carefully considered potential covariates, akin to a guard protecting a vault of precious data, to ensure that our analysis remained anchored in empirical integrity. Furthermore, we acknowledged the lurking specter of limitations inherent in any human endeavor, even one as enigmatically delightful as our present pursuit. In the spirit of scholarly humility, we openly acknowledge the possible constraints and constraints that may encumber our endeavors to unravel this quirky connection. After all, every inquiry has its share of bumps in the road, much like a comical pratfall in the pursuit of truth.

Ethical Considerations:
In accordance with the ethical imperative of scholarly inquiry, we treated our data with the utmost respect and safeguarded the confidentiality of individuals involved in the awarding of associates degrees and the benign curiosity driving 'XKCD' searches. Our research team adhered to the highest standards of ethical conduct, akin to the unwavering moral compass of a fictional superhero, ensuring that our pursuit of knowledge remained unblemished by ethical transgressions.

In conclusion, our approach to this empirical venture was characterized by an unyielding devotion to methodological rigor, a dash of scholarly levity, and an abiding reverence for the peculiar beauty of unexpected connections.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Associates degrees awarded in Business and Google searches for 'xkcd'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from National Center for Education Statistics and Google Trends .

For the time period 2011 to 2021, you found a correlation 0.9503784, r-squared of 0.9032191, 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]]
"Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches"

[[ABSTRACT]]
This study ventures into the realm of curiosities by examining the potential linkage between the number of Associates degrees awarded in Business and the frequency of Google searches for the webcomic 'XKCD'. Through a meticulous analysis of data acquired from the National Center for Education Statistics and Google Trends, we uncovered an astonishing correlation coefficient of 0.9503784 with a significance level of p < 0.01 – a statistical relationship that cannot be dismissed as mere happenstance. The results of our research have sparked intriguing discussions around the water cooler, and we eagerly anticipate the academic community's reaction to this humorous yet surprisingly significant connection.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the realm of academic inquiry, one often encounters unexpected connections and correlations that defy conventional wisdom. The present study delves into such uncharted territory by investigating the possible association between the issuance of Associates degrees in Business and the prevalence of Google searches for the popular webcomic 'XKCD'. While the initial premise of this investigation may seem whimsical, the results have yielded meaningful insights that challenge traditional assumptions about causal relationships.
The subject of this investigation emerges from the curious juxtaposition of educational attainment and internet search behavior. On one hand, the conferral of Associates degrees in the field of Business represents a tangible milestone in the pursuit of vocational knowledge and skills. On the other hand, 'XKCD', a webcomic created by Randall Munroe, is renowned for its blend of incisive humor and astute scientific and technological references. The seemingly disparate domains of higher education and internet culture converge in the terrain of our inquiry, prompting us to unravel the mysterious interplay between these seemingly unrelated phenomena.
In conducting this study, we embarked on a rigorous exploration of publicly available data sources on the issuance of Associates degrees in Business and the corresponding trends in 'XKCD' Google searches. Our analytical journey waded through statistical measures and computational algorithms to distill the essence of this enigmatic correlation. Notably, our findings have teased apart a striking correlation coefficient of 0.9503784, suggesting a robust statistical association between these ostensibly incongruent domains.
In keeping with the spirit of academic inquiry, our investigation invokes both fascination and amusement, offering a window into the unexpected nuances of human behavior and cultural trends. As we embark on this scholarly expedition, we invite our esteemed peers to join us in this pursuit of quirky knowledge and to savor the whimsical facets of this unexpected connection. The implications of our findings extend beyond the confines of traditional research paradigms, inviting a playful conversation that unfolds at the intersection of academia and popular culture. In the words of the webcomic 'XKCD' itself, "Stand back! I'm going to try science!" Indeed, we invite our readers to stand back and witness the interplay of seemingly divergent forces in this lighthearted yet thought-provoking exploration.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of data pertaining to the issuance of Associates degrees in Business and the frequency of Google searches for the webcomic 'XKCD' revealed a remarkably strong correlation. For the time period from 2011 to 2021, we found a correlation coefficient of 0.9503784, indicating a highly robust statistical relationship between these seemingly disparate phenomena. Furthermore, the r-squared value of 0.9032191 underscores the degree to which variations in one variable are associated with changes in the other. The significance level of p < 0.01 solidifies the statistical relevance of this correlation, suggesting that the observed association is unlikely to have occurred by chance.

(Fig. 1) presents a scatterplot illustrating the strong positive correlation between the number of Associates degrees awarded in Business and the volume of Google searches for 'XKCD'. The data points align closely along a positive linear trend, thereby reinforcing the compelling statistical connection unveiled by our analysis. The strength and consistency of this correlation invite further inquiry into the underlying mechanisms driving this unexpected relationship.

These findings, while surprising, provide an intriguing lens through which to view the interplay of higher education and popular culture. Our research has brought to the fore an unlikely but robust association between the pursuit of business education and the proclivity for seeking out the intellectual banter and scientific tidbits encapsulated in the 'XKCD' webcomic. The implications of these findings prompt a reconsideration of the boundaries between seemingly incongruent domains and invite a playful exploration of the intersections between academia and internet culture.

This significant correlation, with its quirky underpinnings, not only inspires contemplation but also underscores the delightful idiosyncrasies present in the data-rich landscape of contemporary research. As we proceed to interpret and contextualize these results, we are reminded of the wisdom from the world of popular culture: "In science, there are no collisions, only opportunities for deep statistical analysis." Consequently, we invite our esteemed colleagues to embrace the unexpected and revel in the quirky insights that emerge from the interplay of apparently unrelated phenomena.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Associates degrees awarded in Business and Google searches for 'xkcd'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches"

[[ABSTRACT]]
This study ventures into the realm of curiosities by examining the potential linkage between the number of Associates degrees awarded in Business and the frequency of Google searches for the webcomic 'XKCD'. Through a meticulous analysis of data acquired from the National Center for Education Statistics and Google Trends, we uncovered an astonishing correlation coefficient of 0.9503784 with a significance level of p < 0.01 – a statistical relationship that cannot be dismissed as mere happenstance. The results of our research have sparked intriguing discussions around the water cooler, and we eagerly anticipate the academic community's reaction to this humorous yet surprisingly significant connection.

[[LITERATURE REVIEW]]
In their seminal work, Smith and Doe examine the relationship between educational attainment and internet search behavior and note the surprising correlations that can emerge from seemingly unrelated domains. Their findings shed light on the intricate interplay between academic pursuits and popular culture, setting the stage for our investigation into the connection between Associates degrees awarded in Business and 'XKCD' Google searches. Upon perusing "The Economics of Information Technology" by Jones, we are compelled to consider the influence of web-based content on individual information-seeking behavior and the wider implications for the digital landscape.
Turning our attention to non-fiction literature, "The Search: How Google and Its Rivals Rewrote the Rules of Business and Transformed Our Culture" by John Battelle delves into the profound impact of internet search engines on modern society, hinting at the potential significance of our exploration into Google search trends for 'XKCD'. Furthermore, the thought-provoking work "Freakonomics: A Rogue Economist Explores the Hidden Side of Everything" by Steven D. Levitt and Stephen J. Dubner challenges us to uncover the unexpected and sometimes counterintuitive connections that underpin human behavior, providing a fascinating backdrop to our investigation.
In a twist of literary curiosity, the fictitious worlds of "Big Data, Big Dupe: Learning from a Century of Mistakes" by Stephen Few and "The Hitchhiker's Guide to the Galaxy" by Douglas Adams prompt us to consider the whimsical and unexpected linkages that may arise from our examination of the 'XKCD' Google searches and Associates degrees in Business. The blending of fiction and reality invites us to ponder the boundaries between scholarly investigation and speculative imagination, offering a lighthearted yet insightful lens through which to view our findings.
Beyond conventional scholarly sources, our pursuit of knowledge extended to unexpected sources, including perusing the purchasing patterns of CVS receipts and decoding the cryptic musings of fortune cookies. While these unconventional methods may raise an eyebrow or two, they have undeniably contributed to our holistic view of the unexplored dimensions of our research question. As we delve into the furthest reaches of the academic universe, we embrace the playful pursuit of knowledge and eagerly await the scholarly discourse that will undoubtedly arise from this investigation.

[[RESULTS]]
The analysis of data pertaining to the issuance of Associates degrees in Business and the frequency of Google searches for the webcomic 'XKCD' revealed a remarkably strong correlation. For the time period from 2011 to 2021, we found a correlation coefficient of 0.9503784, indicating a highly robust statistical relationship between these seemingly disparate phenomena. Furthermore, the r-squared value of 0.9032191 underscores the degree to which variations in one variable are associated with changes in the other. The significance level of p < 0.01 solidifies the statistical relevance of this correlation, suggesting that the observed association is unlikely to have occurred by chance.
(Fig. 1) presents a scatterplot illustrating the strong positive correlation between the number of Associates degrees awarded in Business and the volume of Google searches for 'XKCD'. The data points align closely along a positive linear trend, thereby reinforcing the compelling statistical connection unveiled by our analysis. The strength and consistency of this correlation invite further inquiry into the underlying mechanisms driving this unexpected relationship.
These findings, while surprising, provide an intriguing lens through which to view the interplay of higher education and popular culture. Our research has brought to the fore an unlikely but robust association between the pursuit of business education and the proclivity for seeking out the intellectual banter and scientific tidbits encapsulated in the 'XKCD' webcomic. The implications of these findings prompt a reconsideration of the boundaries between seemingly incongruent domains and invite a playful exploration of the intersections between academia and internet culture.
This significant correlation, with its quirky underpinnings, not only inspires contemplation but also underscores the delightful idiosyncrasies present in the data-rich landscape of contemporary research. As we proceed to interpret and contextualize these results, we are reminded of the wisdom from the world of popular culture: "In science, there are no collisions, only opportunities for deep statistical analysis." Consequently, we invite our esteemed colleagues to embrace the unexpected and revel in the quirky insights that emerge from the interplay of apparently unrelated phenomena.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study offer a droll yet thought-provoking glimpse into the potential connections between Business Associates degrees and Google searches for 'XKCD'. With a correlation coefficient of 0.9503784 and a significance level of p < 0.01, our results confirm and extend the prior research by Smith and Doe, whose exploration of internet search behavior hinted at the unexpected correlations that may emerge from intersecting realms. In a similar vein, our investigation aligns with the playful notions put forth in "The Hitchhiker's Guide to the Galaxy" by Douglas Adams, inviting us to contemplate the whimsical and inexplicable linkages that underpin seemingly unrelated phenomena.

The alignment of our results with Jones' work on the influence of web-based content on individual information-seeking behaviors is striking. The significant correlation uncovered in our study underscores the profound impact of digital culture on educational pursuits and popular interests. Furthermore, our findings resonate with the spirit of intellectual curiosity and unconventional reasoning espoused by Levitt and Dubner in "Freakonomics." The unexpected link between Business Associates degrees and 'XKCD' searches challenges us to embrace the delightful idiosyncrasies present in the data-rich landscape of contemporary research—a sentiment that echoes the playful pursuit of knowledge advocated in unconventional sources such as fortune cookies and CVS receipts.

The robust correlation between the two seemingly disparate phenomena prompts a reconsideration of the boundaries between academic pursuits and internet culture. This unexpected linkage underscores the delightful idiosyncrasies present in the intersection of conventional scholarly investigation and speculative imagination. As we delve into the furthest reaches of the academic universe, we are reminded of the timeless words from "The Hitchhiker's Guide to the Galaxy": "In science, there are no collisions, only opportunities for deep statistical analysis." Just as 'XKCD' adeptly weaves scientific themes with humor, our research has unveiled the lighthearted yet insightful connections between academia and internet culture.

In conclusion, our findings highlight the quirky underpinnings that underscore the intricate interplay of educational pursuits and popular interests. We eagerly anticipate the scholarly discourse that will undoubtedly arise from this humorous yet surprisingly significant investigation. As we navigate the landscape of offbeat research inquiries, may we all remember the wise words emblazoned on elusive fortune cookie messages: "A statistical analysis a day keeps the absurdity away."


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Associates degrees awarded in Business and Google searches for 'xkcd'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches"

[[ABSTRACT]]
This study ventures into the realm of curiosities by examining the potential linkage between the number of Associates degrees awarded in Business and the frequency of Google searches for the webcomic 'XKCD'. Through a meticulous analysis of data acquired from the National Center for Education Statistics and Google Trends, we uncovered an astonishing correlation coefficient of 0.9503784 with a significance level of p < 0.01 – a statistical relationship that cannot be dismissed as mere happenstance. The results of our research have sparked intriguing discussions around the water cooler, and we eagerly anticipate the academic community's reaction to this humorous yet surprisingly significant connection.

[[INTRDUCTION]]
In the realm of academic inquiry, one often encounters unexpected connections and correlations that defy conventional wisdom. The present study delves into such uncharted territory by investigating the possible association between the issuance of Associates degrees in Business and the prevalence of Google searches for the popular webcomic 'XKCD'. While the initial premise of this investigation may seem whimsical, the results have yielded meaningful insights that challenge traditional assumptions about causal relationships.
The subject of this investigation emerges from the curious juxtaposition of educational attainment and internet search behavior. On one hand, the conferral of Associates degrees in the field of Business represents a tangible milestone in the pursuit of vocational knowledge and skills. On the other hand, 'XKCD', a webcomic created by Randall Munroe, is renowned for its blend of incisive humor and astute scientific and technological references. The seemingly disparate domains of higher education and internet culture converge in the terrain of our inquiry, prompting us to unravel the mysterious interplay between these seemingly unrelated phenomena.
In conducting this study, we embarked on a rigorous exploration of publicly available data sources on the issuance of Associates degrees in Business and the corresponding trends in 'XKCD' Google searches. Our analytical journey waded through statistical measures and computational algorithms to distill the essence of this enigmatic correlation. Notably, our findings have teased apart a striking correlation coefficient of 0.9503784, suggesting a robust statistical association between these ostensibly incongruent domains.
In keeping with the spirit of academic inquiry, our investigation invokes both fascination and amusement, offering a window into the unexpected nuances of human behavior and cultural trends. As we embark on this scholarly expedition, we invite our esteemed peers to join us in this pursuit of quirky knowledge and to savor the whimsical facets of this unexpected connection. The implications of our findings extend beyond the confines of traditional research paradigms, inviting a playful conversation that unfolds at the intersection of academia and popular culture. In the words of the webcomic 'XKCD' itself, "Stand back! I'm going to try science!" Indeed, we invite our readers to stand back and witness the interplay of seemingly divergent forces in this lighthearted yet thought-provoking exploration.

[[RESULTS]]
The analysis of data pertaining to the issuance of Associates degrees in Business and the frequency of Google searches for the webcomic 'XKCD' revealed a remarkably strong correlation. For the time period from 2011 to 2021, we found a correlation coefficient of 0.9503784, indicating a highly robust statistical relationship between these seemingly disparate phenomena. Furthermore, the r-squared value of 0.9032191 underscores the degree to which variations in one variable are associated with changes in the other. The significance level of p < 0.01 solidifies the statistical relevance of this correlation, suggesting that the observed association is unlikely to have occurred by chance.
(Fig. 1) presents a scatterplot illustrating the strong positive correlation between the number of Associates degrees awarded in Business and the volume of Google searches for 'XKCD'. The data points align closely along a positive linear trend, thereby reinforcing the compelling statistical connection unveiled by our analysis. The strength and consistency of this correlation invite further inquiry into the underlying mechanisms driving this unexpected relationship.
These findings, while surprising, provide an intriguing lens through which to view the interplay of higher education and popular culture. Our research has brought to the fore an unlikely but robust association between the pursuit of business education and the proclivity for seeking out the intellectual banter and scientific tidbits encapsulated in the 'XKCD' webcomic. The implications of these findings prompt a reconsideration of the boundaries between seemingly incongruent domains and invite a playful exploration of the intersections between academia and internet culture.
This significant correlation, with its quirky underpinnings, not only inspires contemplation but also underscores the delightful idiosyncrasies present in the data-rich landscape of contemporary research. As we proceed to interpret and contextualize these results, we are reminded of the wisdom from the world of popular culture: "In science, there are no collisions, only opportunities for deep statistical analysis." Consequently, we invite our esteemed colleagues to embrace the unexpected and revel in the quirky insights that emerge from the interplay of apparently unrelated phenomena.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has shed light on a remarkable correlation between the conferral of Associates degrees in Business and the frequency of 'XKCD' Google searches. While the juxtaposition of higher education and internet culture may initially appear incongruous, our findings have unveiled a compelling statistical relationship that defies preconceived notions. The robust correlation coefficient of 0.9503784, bolstered by a significance level of p < 0.01, underscores the substantive connection between these seemingly disparate domains. This unexpected linkage prompts an intriguing dialogue on the interplay of vocational education and whimsical internet pursuits.

The implications of our research extend beyond the realms of academia and internet culture, pointing to the quirky intricacies of human behavior and cultural trends. The striking statistical association revealed by our analysis invites a lighthearted yet thought-provoking exploration of the underlying mechanisms driving this curious correlation. As we navigate the peculiar terrain where business education meets the musings of 'XKCD', we are reminded of the whimsical unpredictability inherent in the data-rich landscape of contemporary research.

In the spirit of scholarly inquiry, our study beckons the academic community to embrace the playful convergences of seemingly unrelated phenomena and to revel in the delightful idiosyncrasies that emerge from statistical analysis. With these findings, we believe that no further investigation is warranted in this endeavor. As the old saying goes, "Some correlations are stranger than fiction, and this one takes the cake!"

In light of our significant findings, we advocate for an appreciation of the unexpected connections that enrich the tapestry of knowledge and invite a whimsical conversation at the intersection of academia and popular culture. With that, we affirm that this study marks the end of the road for exploring the connection between Associates degrees in Business and 'XKCD' Google searches. So, as we bid adieu to this unusual correlation, "May your p-values be small, and your confidence intervals be tight!"


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 Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Business and Internet Research


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 Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Business Education and Internet Search Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Degrees of Search: Exploring the Correlation Between Business Associates Degrees and 'XKCD' Google Searches with an abstract of This study ventures into the realm of curiosities by examining the potential linkage between the number of Associates degrees awarded in Business and the frequency of Google searches for the webcomic 'XKCD'. Through a meticulous analysis of data acquired from the National Center for Education Statistics and Google Trends, we uncovered an astonishing correlation coefficient of 0.9503784 with a significance level of p < 0.01 – a statistical relationship that cannot be dismissed as mere happenstance. The results of our research have sparked intriguing discussions around the water cooler, and we eagerly anticipate the academic community's reaction to this humorous yet surprisingly significant connection.

ChatGPT:

Associates degrees in Business, XKCD, Google searches, correlation coefficient, National Center for Education Statistics, Google Trends, statistics significance, academic research, webcomic.

*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

Associates degrees awarded in Business
Detailed data title: Associate's degrees conferred by postsecondary institutions with a field of study of Business
Source: National Center for Education Statistics
See what else correlates with Associates degrees awarded in Business

Google searches for 'xkcd'
Detailed data title: Relative volume of Google searches for 'xkcd' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'xkcd'

Correlation r = 0.9503784 (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 = 0.9032191 (Coefficient of determination)
This means 90.3% of the change in the one variable (i.e., Google searches for 'xkcd') is predictable based on the change in the other (i.e., Associates degrees awarded in Business) over the 11 years from 2011 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.4E-6. 0.0000073584795448980305000000
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 0.95 in 0.00074% of random cases. Said differently, if you correlated 135,898 random variables You don't actually need 135 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 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.82, 0.99 ] 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.
20112012201320142015201620172018201920202021
Associates degrees awarded in Business (Degrees awarded)139994143390134114129957132374128259122252117821116799112191116086
Google searches for 'xkcd' (Rel. search volume)82.833372.833361.549.666741.833327.166722.416716.916714.666711.757.83333




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([139994,143390,134114,129957,132374,128259,122252,117821,116799,112191,116086,])
array_2 = np.array([82.8333,72.8333,61.5,49.6667,41.8333,27.1667,22.4167,16.9167,14.6667,11.75,7.83333,])
array_1_name = "Associates degrees awarded in Business"
array_2_name = "Google searches for 'xkcd'"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your correlation inspection deserves a standing ovation!


Correlation ID: 1826 · Black Variable ID: 1212 · Red Variable ID: 1450
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0