Spurious correlation #3,689 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Cleveland and the second variable is Viewership count for Days of Our Lives. The chart goes from 1980 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Cleveland and the second variable is Viewership count for Days of Our Lives. The chart goes from 1980 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the air cleared, residents were able to go outside and find more fulfilling ways to spend their time than watching daytime soap operas, like taking up competitive pigeon racing.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image showing the smog-filled skyline of Cleveland transforming into a blend of hazy, abstract forms, with the silhouettes of people inside their homes visible through the thick air. Amidst this landscape, the scene shifts to an intense and dramatic television portrayal of "Days of Our Lives," with the buildings and cityscape fading into the background as the gripping soap opera seizes the attention of the viewers. 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: Air pollution in Cleveland and Viewership count for Days of Our Lives. 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: Celtic art a Polaroid photo Brutalism Photorealism Steampunk
ChatGPT: Brutalism

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 Air pollution in Cleveland and Viewership count for Days of Our Lives, in the following situation: As air pollution in Cleveland increased, viewership for Days of Our Lives skyrocketed. People simply couldn't breathe with the suspense and drama, so they stayed indoors to watch the show! The smog-choked air made everyone crave the clean drama of daytime television.. Keep the description simple.
ChatGPT: The smog-filled skyline of Cleveland created a hazy backdrop as people gathered inside their homes, glued to their TV screens. The increasing air pollution seemed to fuel the climb in viewership for Days of Our Lives, as the cityscape faded into the background and the gripping drama took center stage.

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: [ Brutalism ] and depicting this scene: The smog-filled skyline of Cleveland created a hazy backdrop as people gathered inside their homes, glued to their TV screens. The increasing air pollution seemed to fuel the climb in viewership for Days of Our Lives, as the cityscape faded into the background and the gripping drama took center stage. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image showing the smog-filled skyline of Cleveland transforming into a blend of hazy, abstract forms, with the silhouettes of people inside their homes visible through the thick air. Amidst this landscape, the scene shifts to an intense and dramatic television portrayal of "Days of Our Lives," with the buildings and cityscape fading into the background as the gripping soap opera seizes the attention of the viewers.

*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.
^{Show prompt for explanation} 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 Air pollution in Cleveland caused Viewership count for Days of Our Lives to decrease. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)

Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership

The Journal of Pop Culture and Environmental Studies

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} 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 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 Air pollution in Cleveland and Viewership count for Days of Our Lives. 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership

[[ABSTRACT]]
This study assesses the potential link between air pollution levels in Cleveland and the viewership count for the long-running soap opera "Days of Our Lives." Utilizing data from the Environmental Protection Agency and Wikipedia, a correlation coefficient of 0.7073964 and p < 0.01 for the years 1980 to 2021 was identified. The findings suggest a statistically significant relationship between the two variables, raising intriguing questions about the impact of environmental factors on television preferences. The implications of these results are beyond soap-operatic, providing a breath of fresh air for interdisciplinary research and prompting further investigation into the curious interconnection between atmospheric conditions and daily drama indulgence.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The gust of interest in the relationship between environmental factors and human behavior has been blowing through the academic community in recent years. As we all know, air pollution has long been associated with a host of negative impacts on human health and well-being, from respiratory problems to cardiovascular diseases. However, the wisp of a new question has wafted into the air: could poor air quality also influence our choices in entertainment?
This study aims to untangle the threads of this puzzling question by focusing on a particularly intriguing case: the correlation between air pollution levels in Cleveland and the viewership count for the enduring daytime drama "Days of Our Lives." While it may seem like a plot twist straight out of a soap opera itself, the notion that atmospheric conditions could influence our television habits has not been given much screen time in the research world. Nevertheless, with the aid of statistical analysis and a dash of curiosity, we sought to shed light on this shadowy connection.
Our investigation into this uncharted territory involved collecting data from the Environmental Protection Agency to measure levels of air pollutants in Cleveland, while tapping into the treasure trove of Wikipedia to track the viewership count for "Days of Our Lives" over the years. The results of our analysis have brought a breath of fresh air to the literature, revealing a statistically significant correlation between air pollution and viewership count, with a correlation coefficient of 0.7073964 and p < 0.01 for the years 1980 to 2021. This discovery leapt out at us like a dramatic twist in a soap opera, prompting us to delve deeper into the implications of this unlikely link.
In delving into this seemingly whimsical connection, we are stirred by more than mere curiosity. The implications of our findings stretch beyond the world of soap operas, reaching into the realms of environmental and behavioral research. These findings are more than just a flash in the pan; they offer a tantalizing glimpse into the potential influence of atmospheric conditions on our everyday choices. As we mull over these unexpected results, we are reminded that the web of connections in the world around us is more intricate and mysterious than we often realize.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The examination of the potential relationship between air pollution and television viewership leads us to consider a range of studies and sources that shed light on this curious connection. Smith et al. (2015) investigated the impact of environmental factors on daily activities, including leisure pursuits such as television watching, in a comprehensive review of behavioral economics. They found a surprising correlation between air quality and recreational choices, hinting at the possibility that individuals may be swayed in their entertainment preferences by the atmospheric conditions around them. Building on this foundation, Doe (2018) delved into the realm of environmental psychology, uncovering subtle influences of air pollution on human behavior, which could extend to the realm of media consumption patterns.

Jones et al. (2020) brought a fresh perspective to the table, examining the interplay between urban environments and cultural consumption. Their work highlighted the nuanced ways in which external factors, such as air pollution, can subtly shape individuals' engagement with cultural products, including television programs. This line of inquiry prompts us to consider the potential reverberations of air quality on the viewership of specific television shows, such as the long-standing and beloved "Days of Our Lives."

Turning to non-fiction works, "The Air Pollution Crisis" by Johnson (2019) and "Environmental Influences on Human Behavior" by Brown (2021) offer comprehensive insights into the impacts of air pollution on various facets of human life. While these works may not explicitly address television viewership, they lay the groundwork for understanding the far-reaching effects of environmental factors on human behavior, opening the door to the possibility of unexpected connections with seemingly unrelated phenomena.

In the realm of fiction, the popular novel "The Smog of Suspicion" by Green (2017) presents a tongue-in-cheek exploration of a world where air pollution takes on a life of its own, affecting everything from interpersonal relationships to societal trends. While clearly a work of fiction, the novel provides a whimsical backdrop against which to contemplate the potential influence of air quality on the escapism of soap opera consumption.

In a more casual and contemporary vein, social media posts have also hinted at the intersection of air pollution and entertainment choices. Anecdotal accounts on platforms such as Twitter and Reddit have occasionally alluded to the effects of air quality on individuals' desire to engage with specific television content. While these accounts are by no means scientific evidence, they nonetheless hint at the broader cultural consciousness of the potential impact of environmental conditions on media consumption habits.

These diverse sources form the backdrop against which we approach the investigation of the connection between air pollution levels in Cleveland and the viewership count for "Days of Our Lives." As we navigate this unusual terrain, we are reminded of the often unexpected and convoluted ways in which external forces can shape our everyday choices – a theme that seems to play out with dramatic flair in both the world of soap operas and in the unexpected linkages of environmental and behavioral research.

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 Air pollution in Cleveland and Viewership count for Days of Our Lives. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Wikipedia . You used data from 1980 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]]
Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership

[[ABSTRACT]]
This study assesses the potential link between air pollution levels in Cleveland and the viewership count for the long-running soap opera "Days of Our Lives." Utilizing data from the Environmental Protection Agency and Wikipedia, a correlation coefficient of 0.7073964 and p < 0.01 for the years 1980 to 2021 was identified. The findings suggest a statistically significant relationship between the two variables, raising intriguing questions about the impact of environmental factors on television preferences. The implications of these results are beyond soap-operatic, providing a breath of fresh air for interdisciplinary research and prompting further investigation into the curious interconnection between atmospheric conditions and daily drama indulgence.

[[INTRODUCTION]]
The gust of interest in the relationship between environmental factors and human behavior has been blowing through the academic community in recent years. As we all know, air pollution has long been associated with a host of negative impacts on human health and well-being, from respiratory problems to cardiovascular diseases. However, the wisp of a new question has wafted into the air: could poor air quality also influence our choices in entertainment?
This study aims to untangle the threads of this puzzling question by focusing on a particularly intriguing case: the correlation between air pollution levels in Cleveland and the viewership count for the enduring daytime drama "Days of Our Lives." While it may seem like a plot twist straight out of a soap opera itself, the notion that atmospheric conditions could influence our television habits has not been given much screen time in the research world. Nevertheless, with the aid of statistical analysis and a dash of curiosity, we sought to shed light on this shadowy connection.
Our investigation into this uncharted territory involved collecting data from the Environmental Protection Agency to measure levels of air pollutants in Cleveland, while tapping into the treasure trove of Wikipedia to track the viewership count for "Days of Our Lives" over the years. The results of our analysis have brought a breath of fresh air to the literature, revealing a statistically significant correlation between air pollution and viewership count, with a correlation coefficient of 0.7073964 and p < 0.01 for the years 1980 to 2021. This discovery leapt out at us like a dramatic twist in a soap opera, prompting us to delve deeper into the implications of this unlikely link.
In delving into this seemingly whimsical connection, we are stirred by more than mere curiosity. The implications of our findings stretch beyond the world of soap operas, reaching into the realms of environmental and behavioral research. These findings are more than just a flash in the pan; they offer a tantalizing glimpse into the potential influence of atmospheric conditions on our everyday choices. As we mull over these unexpected results, we are reminded that the web of connections in the world around us is more intricate and mysterious than we often realize.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodological approach employed in this study involved a blend of quantitative analysis and data collection from publicly available sources. To assess the potential relationship between air pollution levels in Cleveland and the viewership count for "Days of Our Lives," a series of steps were taken.

First, air pollution data was gathered from the Environmental Protection Agency's Air Quality System, capturing measurements of various pollutants including particulate matter (PM2.5 and PM10), carbon monoxide, sulfur dioxide, nitrogen dioxide, and ozone. These data were obtained for the city of Cleveland from the years 1980 to 2021, ensuring a comprehensive temporal scope for the analysis.

Simultaneously, data pertaining to the viewership count for "Days of Our Lives" was collected from Wikipedia, leveraging the platform's historical records and references to capture the show's popularity over the same time period. This approach allowed for the acquisition of longitudinal data on viewership patterns, encompassing the entire duration of the soap opera's run and enabling a thorough investigation into any potential correlations with air pollution levels.

Following the acquisition of data, statistical analyses were conducted to explore the relationship between air pollution and "Days of Our Lives" viewership count. This included the calculation of descriptive statistics for both variables, as well as the computation of correlation coefficients to assess the strength and direction of any potential associations. Additionally, regression analyses were performed to examine the predictive power of air pollution levels on viewership count, controlling for relevant covariates such as temporal trends and demographic changes in the Cleveland area.

It is important to note that while this study utilized data from reputable sources such as the Environmental Protection Agency and Wikipedia, the findings are contingent upon the accuracy and reliability of the information available. Furthermore, the choice of "Days of Our Lives" as the focal point for assessing viewership patterns was based on its longevity and widespread cultural recognition, serving as a suitable proxy for daytime soap opera viewership in Cleveland.

Overall, the methodology adopted in this research endeavors to shine a spotlight on the potential interplay between environmental factors and entertainment preferences, while also acknowledging the inherently complex and multifaceted nature of such relationships in a lighthearted and captivating way.

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 Air pollution in Cleveland and Viewership count for Days of Our Lives. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership

[[ABSTRACT]]
This study assesses the potential link between air pollution levels in Cleveland and the viewership count for the long-running soap opera "Days of Our Lives." Utilizing data from the Environmental Protection Agency and Wikipedia, a correlation coefficient of 0.7073964 and p < 0.01 for the years 1980 to 2021 was identified. The findings suggest a statistically significant relationship between the two variables, raising intriguing questions about the impact of environmental factors on television preferences. The implications of these results are beyond soap-operatic, providing a breath of fresh air for interdisciplinary research and prompting further investigation into the curious interconnection between atmospheric conditions and daily drama indulgence.

[[LITERATURE REVIEW]]
The examination of the potential relationship between air pollution and television viewership leads us to consider a range of studies and sources that shed light on this curious connection. Smith et al. (2015) investigated the impact of environmental factors on daily activities, including leisure pursuits such as television watching, in a comprehensive review of behavioral economics. They found a surprising correlation between air quality and recreational choices, hinting at the possibility that individuals may be swayed in their entertainment preferences by the atmospheric conditions around them. Building on this foundation, Doe (2018) delved into the realm of environmental psychology, uncovering subtle influences of air pollution on human behavior, which could extend to the realm of media consumption patterns.
Jones et al. (2020) brought a fresh perspective to the table, examining the interplay between urban environments and cultural consumption. Their work highlighted the nuanced ways in which external factors, such as air pollution, can subtly shape individuals' engagement with cultural products, including television programs. This line of inquiry prompts us to consider the potential reverberations of air quality on the viewership of specific television shows, such as the long-standing and beloved "Days of Our Lives."
Turning to non-fiction works, "The Air Pollution Crisis" by Johnson (2019) and "Environmental Influences on Human Behavior" by Brown (2021) offer comprehensive insights into the impacts of air pollution on various facets of human life. While these works may not explicitly address television viewership, they lay the groundwork for understanding the far-reaching effects of environmental factors on human behavior, opening the door to the possibility of unexpected connections with seemingly unrelated phenomena.
In the realm of fiction, the popular novel "The Smog of Suspicion" by Green (2017) presents a tongue-in-cheek exploration of a world where air pollution takes on a life of its own, affecting everything from interpersonal relationships to societal trends. While clearly a work of fiction, the novel provides a whimsical backdrop against which to contemplate the potential influence of air quality on the escapism of soap opera consumption.
In a more casual and contemporary vein, social media posts have also hinted at the intersection of air pollution and entertainment choices. Anecdotal accounts on platforms such as Twitter and Reddit have occasionally alluded to the effects of air quality on individuals' desire to engage with specific television content. While these accounts are by no means scientific evidence, they nonetheless hint at the broader cultural consciousness of the potential impact of environmental conditions on media consumption habits.
These diverse sources form the backdrop against which we approach the investigation of the connection between air pollution levels in Cleveland and the viewership count for "Days of Our Lives." As we navigate this unusual terrain, we are reminded of the often unexpected and convoluted ways in which external forces can shape our everyday choices – a theme that seems to play out with dramatic flair in both the world of soap operas and in the unexpected linkages of environmental and behavioral research.

[[RESULTS]]
The analysis of the data revealed a statistically significant correlation between air pollution levels in Cleveland and the viewership count for "Days of Our Lives" for the period spanning from 1980 to 2021. The correlation coefficient of 0.7073964 and the r-squared value of 0.5004096 indicate a moderate to strong positive relationship between the two variables. The p-value of less than 0.01 further supports the assertion of a significant association.
The scatterplot (Fig. 1) illustrates the robust correlation between air pollution levels and viewership count, affirming the strength of the statistical findings. The upward trend in the scatterplot mirrors the rise in viewership count with increasing air pollution levels, providing a visual representation of the positive relationship between these seemingly disparate factors.
These results not only raise eyebrows but also prompt a reflection on the potential influence of environmental factors on television preferences. The statistical rigor of the analysis lends gravitas to the seemingly whimsical connection, urging researchers to contemplate the broader implications of this unexpected correlation. This study serves as a testament to the unforeseen intersections that permeate our daily lives, emphasizing the need for interdisciplinary exploration and the willingness to entertain unconventional hypotheses.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The present study found a significant and positive correlation between air pollution levels in Cleveland and the viewership count for "Days of Our Lives," reaffirming a relationship that might initially seem like a soap opera plot twist. The statistical findings provide empirical support for the unconventional yet captivating notion that atmospheric conditions may influence individuals' choices in televised drama.

Building on the literature review, the results of this investigation align with prior research, drawing attention to the subtle but potent impact of environmental factors on human behavior. Smith et al. (2015) first hinted at the possibility of air quality shaping recreational activities, setting the stage for our exploration of the connection between air pollution and television viewership. Doe's (2018) work in environmental psychology further laid the groundwork for understanding how environmental cues could sway individuals' entertainment preferences, offering a compelling backdrop for the present findings.

Pertinently, the study also resonates with the broader themes highlighted in fiction, such as Green's (2017) whimsical portrayal of air pollution's influence on societal trends in "The Smog of Suspicion." While certainly not a scholarly work, this satire surprisingly foreshadowed the empirical evidence of the present investigation, effectively highlighting the potential impact of environmental conditions on cultural consumption patterns.

From a methodological standpoint, the robustness of the statistical associations bolsters the credibility of the findings, offering a solid platform from which to leap into further explorations of this intriguing phenomenon. While the results may elicit a chuckle at first glance, they ultimately underline the need for interdisciplinary research that embraces the unexpected, much like the plot twists in a long-running soap opera.

The statistical linkage between air pollution and "Days of Our Lives" viewership counts invites speculation about the underlying mechanisms at play. Could it be that individuals are subconsciously drawn to the melodramatic escapism of soap operas when faced with a hazy horizon? Or perhaps the atmospheric conditions act as a silent cue, nudging viewers toward indoor activities such as television watching? These questions, though lighthearted, point to the potential depth of inquiry that this unlikely correlation presents.

In conclusion, the results of this study offer a dose of levity to the academic arena while nudging scholars to look beyond traditional paradigms. This endeavor not only expands our understanding of the nuanced interplay between environmental factors and human behavior but also demonstrates the rich potential of research that dares to wander into the unexplored realms of everyday life – a realm where even air pollution and soap operas may share a curious bond.

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 Air pollution in Cleveland and Viewership count for Days of Our Lives. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership

[[ABSTRACT]]
This study assesses the potential link between air pollution levels in Cleveland and the viewership count for the long-running soap opera "Days of Our Lives." Utilizing data from the Environmental Protection Agency and Wikipedia, a correlation coefficient of 0.7073964 and p < 0.01 for the years 1980 to 2021 was identified. The findings suggest a statistically significant relationship between the two variables, raising intriguing questions about the impact of environmental factors on television preferences. The implications of these results are beyond soap-operatic, providing a breath of fresh air for interdisciplinary research and prompting further investigation into the curious interconnection between atmospheric conditions and daily drama indulgence.

[[INTRDUCTION]]
The gust of interest in the relationship between environmental factors and human behavior has been blowing through the academic community in recent years. As we all know, air pollution has long been associated with a host of negative impacts on human health and well-being, from respiratory problems to cardiovascular diseases. However, the wisp of a new question has wafted into the air: could poor air quality also influence our choices in entertainment?
This study aims to untangle the threads of this puzzling question by focusing on a particularly intriguing case: the correlation between air pollution levels in Cleveland and the viewership count for the enduring daytime drama "Days of Our Lives." While it may seem like a plot twist straight out of a soap opera itself, the notion that atmospheric conditions could influence our television habits has not been given much screen time in the research world. Nevertheless, with the aid of statistical analysis and a dash of curiosity, we sought to shed light on this shadowy connection.
Our investigation into this uncharted territory involved collecting data from the Environmental Protection Agency to measure levels of air pollutants in Cleveland, while tapping into the treasure trove of Wikipedia to track the viewership count for "Days of Our Lives" over the years. The results of our analysis have brought a breath of fresh air to the literature, revealing a statistically significant correlation between air pollution and viewership count, with a correlation coefficient of 0.7073964 and p < 0.01 for the years 1980 to 2021. This discovery leapt out at us like a dramatic twist in a soap opera, prompting us to delve deeper into the implications of this unlikely link.
In delving into this seemingly whimsical connection, we are stirred by more than mere curiosity. The implications of our findings stretch beyond the world of soap operas, reaching into the realms of environmental and behavioral research. These findings are more than just a flash in the pan; they offer a tantalizing glimpse into the potential influence of atmospheric conditions on our everyday choices. As we mull over these unexpected results, we are reminded that the web of connections in the world around us is more intricate and mysterious than we often realize.

[[RESULTS]]
The analysis of the data revealed a statistically significant correlation between air pollution levels in Cleveland and the viewership count for "Days of Our Lives" for the period spanning from 1980 to 2021. The correlation coefficient of 0.7073964 and the r-squared value of 0.5004096 indicate a moderate to strong positive relationship between the two variables. The p-value of less than 0.01 further supports the assertion of a significant association.
The scatterplot (Fig. 1) illustrates the robust correlation between air pollution levels and viewership count, affirming the strength of the statistical findings. The upward trend in the scatterplot mirrors the rise in viewership count with increasing air pollution levels, providing a visual representation of the positive relationship between these seemingly disparate factors.
These results not only raise eyebrows but also prompt a reflection on the potential influence of environmental factors on television preferences. The statistical rigor of the analysis lends gravitas to the seemingly whimsical connection, urging researchers to contemplate the broader implications of this unexpected correlation. This study serves as a testament to the unforeseen intersections that permeate our daily lives, emphasizing the need for interdisciplinary exploration and the willingness to entertain unconventional hypotheses.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the correlation between air pollution levels in Cleveland and the viewership count for "Days of Our Lives" has yielded a statistically significant relationship, much like a shocking plot twist in a daytime drama. The robust correlation coefficient and r-squared value indicate a moderate to strong positive association, leading us to ponder the potential impact of atmospheric conditions on television preferences. The scatterplot vividly portrays this unlikely bond, evoking a sense of intrigue akin to a mysterious character's sudden appearance on our screens.

These unexpected findings not only enrich the tapestry of scientific inquiry but also tickle the imagination with the whimsical notion of atmospheric whims shaping our entertainment choices. It's as if the winds of fate are playing a role in determining our viewing habits, creating a connection as unlikely as a classic soap opera plotline. The implications of our study extend beyond the realm of soap operatic indulgence, beckoning further contemplation of the subtle cues the environment may offer to our behaviors.

However, while we have reveled in this serendipitous discovery, we must acknowledge the limitations of our study, as with any first foray into uncharted territory. The directional nature of the observed relationship and the absence of causality call for cautious interpretation of our findings. Furthermore, the peculiar nature of the association between air pollution and television viewership in Cleveland begs for additional research in other locations and across different forms of entertainment. It is with a heavy heart, or perhaps a light one, that we assert no further research is needed in this area.

In closing, the surprising connection between air pollution and "Days of Our Lives" viewership leaves us with a lingering sense of wonderment, reminiscent of a cliffhanger ending that leaves us craving more. The world of academic inquiry holds no shortage of twists and turns, and we eagerly anticipate the unmasking of further unexpected relationships. The script of scientific discovery is never set in stone, and as we bid adieu to this curious investigation, we are reminded that sometimes the most captivating insights emerge from the most unlikely places.

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 Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Pop Culture and Environmental Studies

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 Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Research and Analysis

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership with an abstract of This study assesses the potential link between air pollution levels in Cleveland and the viewership count for the long-running soap opera "Days of Our Lives." Utilizing data from the Environmental Protection Agency and Wikipedia, a correlation coefficient of 0.7073964 and p < 0.01 for the years 1980 to 2021 was identified. The findings suggest a statistically significant relationship between the two variables, raising intriguing questions about the impact of environmental factors on television preferences. The implications of these results are beyond soap-operatic, providing a breath of fresh air for interdisciplinary research and prompting further investigation into the curious interconnection between atmospheric conditions and daily drama indulgence.

ChatGPT:

Cleveland, air pollution levels, Days of Our Lives viewership, correlation, EPA data, Cleveland air quality, environmental factors, television preferences, atmospheric conditions, interdisciplinary research

*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

Air pollution in Cleveland
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Cleveland-Elyria, OH
Source: Environmental Protection Agency
See what else correlates with Air pollution in Cleveland

Viewership count for Days of Our Lives
Detailed data title: Metered viewership count for Days of Our Lives
Source: Wikipedia
See what else correlates with Viewership count for Days of Our Lives

Correlation r = 0.7073964 (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 = 0.5004096 (Coefficient of determination)
This means 50% of the change in the one variable (i.e., Viewership count for Days of Our Lives) is predictable based on the change in the other (i.e., Air pollution in Cleveland) over the 42 years from 1980 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.6E-7.^Show 0.0000001625614585593530000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.71 in 1.6E-5% of random cases. Said differently, if you correlated 6,151,520 random variables^Note You don't actually need 6 million 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 41 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 41 because we have two variables measured over a period of 42 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.

[ 0.51, 0.83 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	1980	1981	1982	1983	1984	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Air pollution in Cleveland (Bad air quality days)	3.00546	4.93151	4.65753	9.31507	4.64481	3.83562	3.56164	4.38356	12.8415	4.65753	2.46575	8.21918	2.18579	4.65753	5.47945	5.75342	4.64481	3.28767	5.20548	6.0274	2.18579	6.57534	7.94521	2.46575	0.546448	4.65753	1.09589	1.36986	0.819672	0.547945	1.09589	1.09589	3.00546	0.273973	0.273973	0	0	0	0	0	0.273224	0
Viewership count for Days of Our Lives (Nielson share)	5600000	5500000	5700000	7100000	7100000	7200000	7000000	7100000	6500000	5400000	5200000	5400000	4900000	5600000	5300000	5800000	5800000	5100000	5800000	4200000	3800000	3600000	3100000	3100000	2700000	2600000	2300000	2100000	2200000	2200000	2000000	2000000	2100000	1900000	2050000	1800000	1600000	1600000	1600000	1400000	1200000	1200000

Why this works

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.
Lack of causal connection: There is probably^Note 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.
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^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} 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([3.00546,4.93151,4.65753,9.31507,4.64481,3.83562,3.56164,4.38356,12.8415,4.65753,2.46575,8.21918,2.18579,4.65753,5.47945,5.75342,4.64481,3.28767,5.20548,6.0274,2.18579,6.57534,7.94521,2.46575,0.546448,4.65753,1.09589,1.36986,0.819672,0.547945,1.09589,1.09589,3.00546,0.273973,0.273973,0,0,0,0,0,0.273224,0,])
array_2 = np.array([5600000,5500000,5700000,7100000,7100000,7200000,7000000,7100000,6500000,5400000,5200000,5400000,4900000,5600000,5300000,5800000,5800000,5100000,5800000,4200000,3800000,3600000,3100000,3100000,2700000,2600000,2300000,2100000,2200000,2200000,2000000,2000000,2100000,1900000,2050000,1800000,1600000,1600000,1600000,1400000,1200000,1200000,])
array_1_name = "Air pollution in Cleveland"
array_2_name = "Viewership count for Days of Our Lives"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Air pollution in Cleveland
Line chart for only Viewership count for Days of Our Lives
AI-generated correlation image
The spurious research paper: Clearing the Air: Correlating Cleveland's Air Pollution with Days of Our Lives Viewership

View another random correlation

How fun was this correlation?

Your rating is stellar!

Correlation ID: 3689 · Black Variable ID: 20474 · Red Variable ID: 87


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: