Spurious correlation #5,001 · 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 Baltimore, Maryland and the second variable is The number of tool and die makers in Maryland. The chart goes from 2003 to 2022, 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 Baltimore, Maryland and the second variable is The number of tool and die makers in Maryland. The chart goes from 2003 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the air got cleaner in Baltimore, it became a grinding halt for tool and die makers in Maryland. With less pollution, there was less need for them to constantly "ventilate" the situation. It seems the industry just couldn't "screw" around anymore without the smog to "lubricate" their work.

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Generate an image of a brutalist-style industrial workshop in Baltimore, Maryland, with a stark contrast between the clean, visible skyline and the idle, smog-repelling equipment. Show the transition from a once bustling industrial scene to a moment of stillness and adaptation as the machines remain unused. The image should capture the atmosphere of change and adaptation in the tool and die making industry as a result of the cleared air and reduced smog in Maryland. 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 Baltimore, Maryland and The number of tool and die makers in Maryland. 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: Hyper-realistic Brutalism Data cyber art Cutsy graphics An image that looks like it is a scene from A Disney Movie
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 Baltimore, Maryland and The number of tool and die makers in Maryland, in the following situation: As the air got cleaner in Baltimore, it became a grinding halt for tool and die makers in Maryland. With less pollution, there was less need for them to constantly "ventilate" the situation. It seems the industry just couldn't "screw" around anymore without the smog to "lubricate" their work.. Keep the description simple.
ChatGPT: In Baltimore, Maryland, the air cleared up as the skyline became visible again. As the smog lifted, tool and die makers in Maryland found themselves at a standstill. The once constant need for ventilation and smog-repelling equipment diminished, leaving their machines idle and their workbench tools untouched. The air pollution reduction brought a halt to their constant grinding and screw-turning, as the industry struggled to find ways to lubricate their work without the smog.

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: In Baltimore, Maryland, the air cleared up as the skyline became visible again. As the smog lifted, tool and die makers in Maryland found themselves at a standstill. The once constant need for ventilation and smog-repelling equipment diminished, leaving their machines idle and their workbench tools untouched. The air pollution reduction brought a halt to their constant grinding and screw-turning, as the industry struggled to find ways to lubricate their work without the smog. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image of a brutalist-style industrial workshop in Baltimore, Maryland, with a stark contrast between the clean, visible skyline and the idle, smog-repelling equipment. Show the transition from a once bustling industrial scene to a moment of stillness and adaptation as the machines remain unused. The image should capture the atmosphere of change and adaptation in the tool and die making industry as a result of the cleared air and reduced smog in Maryland.

*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 Baltimore, Maryland caused The number of tool and die makers in Maryland to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland

Journal of Atmospheric Anthropology

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 Baltimore, Maryland and The number of tool and die makers in Maryland. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland

[[ABSTRACT]]
This study explores the potential connection between air pollution in Baltimore, Maryland and the number of tool and die makers in the state. Employing data from the Environmental Protection Agency and the Bureau of Labor Statistics spanning the years 2003 to 2022, the correlation coefficient was found to be a striking 0.9122289, with a p-value less than 0.01, indicating a robust statistical association. The findings suggest that as air pollution levels rise, the number of tool and die makers in Maryland also increases. The implications of these findings are quite profound, shedding light on the nuanced and often overlooked interplay between environmental factors and occupational choices. Our research aims to inspire further discourse on this subject and encourage a deeper examination of the hidden forces shaping our occupational landscape.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The interplay between environmental factors and occupational choices has long been a subject of intrigue and speculation. One would not necessarily expect air pollution levels to be associated with the number of tool and die makers in a given region, but as the saying goes, "the devil's in the details." The state of Maryland, with its vibrant industrial landscape and the ever-present issue of air pollution in Baltimore, provides an ideal backdrop for investigating this unexpected correlation.
The curiosity surrounding this unlikely duo of air pollution and tool and die makers led to the formulation of our research question: Could there be a hidden link between the quality of the air we breathe and the professionals tasked with fabricating precision tools and metal components? The idea may seem far-fetched at first glance, but as we delved into the data, it became increasingly evident that there might be more than meets the eye - or the nostrils, for that matter.
As we embark on this analytical journey, it is important to keep our minds open to the possibility that our findings may challenge conventional wisdom and add a new layer of complexity to the occupational and environmental dynamics at play. After all, in the realm of scientific inquiry, it is often the unanticipated relationships that yield the most intriguing insights.
So, put on your thinking caps and steel yourselves for a riveting exploration of the uncharted territory where air pollution and tool and die makers converge. The results may very well be, dare we say, groundbreaking.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The literature on the relationship between air pollution and occupational trends offers a wealth of insight into the potential connections that may exist. Smith et al. (2015) conducted a comprehensive analysis of air quality in urban industrial centers and its impact on local employment patterns, shedding light on the complex interplay between environmental conditions and workforce dynamics. Similarly, Doe (2018) explored the occupational preferences of individuals in regions with varying levels of air pollution, uncovering intriguing shifts in career choices in response to environmental factors. Jones (2020) delved into the correlation between air pollution exposure and the prevalence of skilled laborers, offering valuable perspectives on how external conditions may shape the composition of the workforce.

Moving beyond the traditional academic literature, non-fiction works such as "The Air We Breathe: A Comprehensive Analysis of Environmental Factors in Urban Centers" and "Industrial Revolution: History and Impact on Occupational Trends" provide additional context for understanding the broader implications of environmental conditions on the choice of professions. Moreover, fiction works such as "The Polluted Prospects" and "Tool and Die Mysteries: A Novel Approach to Environmental Influences on Occupational Pathways" offer imaginative interpretations of the potential connections between air pollution and occupational choices, inviting readers to consider the intersection of environmental factors and professional pursuits from a creative standpoint.

Furthermore, drawing inspiration from seemingly unrelated sources, board games such as "Pollution Pursuit" and "Tool and Die Tycoon" prompt players to navigate environmental challenges and occupational decision-making in simulated settings, offering playful yet thought-provoking reflections on the interplay between air quality and career paths.

In light of these diverse perspectives, it is clear that the examination of air pollution and its potential effects on the prevalence of tool and die makers in Maryland holds significant implications for understanding the intricate interplay between environmental factors and occupational preferences. The integration of both empirical research and imaginative explorations serves to enrich our understanding of this intriguing nexus, setting the stage for a multifaceted investigation into the breath-taking connections between air pollution and the occupational landscape.

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 Baltimore, Maryland and The number of tool and die makers in Maryland. 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 Bureau of Larbor Statistics . You used data from 2003 to 2022

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland

[[ABSTRACT]]
This study explores the potential connection between air pollution in Baltimore, Maryland and the number of tool and die makers in the state. Employing data from the Environmental Protection Agency and the Bureau of Labor Statistics spanning the years 2003 to 2022, the correlation coefficient was found to be a striking 0.9122289, with a p-value less than 0.01, indicating a robust statistical association. The findings suggest that as air pollution levels rise, the number of tool and die makers in Maryland also increases. The implications of these findings are quite profound, shedding light on the nuanced and often overlooked interplay between environmental factors and occupational choices. Our research aims to inspire further discourse on this subject and encourage a deeper examination of the hidden forces shaping our occupational landscape.

[[INTRODUCTION]]
The interplay between environmental factors and occupational choices has long been a subject of intrigue and speculation. One would not necessarily expect air pollution levels to be associated with the number of tool and die makers in a given region, but as the saying goes, "the devil's in the details." The state of Maryland, with its vibrant industrial landscape and the ever-present issue of air pollution in Baltimore, provides an ideal backdrop for investigating this unexpected correlation.
The curiosity surrounding this unlikely duo of air pollution and tool and die makers led to the formulation of our research question: Could there be a hidden link between the quality of the air we breathe and the professionals tasked with fabricating precision tools and metal components? The idea may seem far-fetched at first glance, but as we delved into the data, it became increasingly evident that there might be more than meets the eye - or the nostrils, for that matter.
As we embark on this analytical journey, it is important to keep our minds open to the possibility that our findings may challenge conventional wisdom and add a new layer of complexity to the occupational and environmental dynamics at play. After all, in the realm of scientific inquiry, it is often the unanticipated relationships that yield the most intriguing insights.
So, put on your thinking caps and steel yourselves for a riveting exploration of the uncharted territory where air pollution and tool and die makers converge. The results may very well be, dare we say, groundbreaking.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To investigate the enthralling association between air pollution in Baltimore, Maryland and the number of tool and die makers in the state, an ensemble of data wrangling and analytical techniques was employed. The data were primarily sourced from the Environmental Protection Agency (EPA) for air pollution levels and the Bureau of Labor Statistics (BLS) for the number of tool and die makers from the years 2003 to 2022. The choice of this data range was made to encompass a substantial period, allowing for a comprehensive analysis of longitudinal trends.

The air pollution data, encompassing atmospheric pollutants such as particulate matter, nitrogen dioxide, sulfur dioxide, and ozone, were meticulously collected from various monitoring stations across the city of Baltimore. Data pertaining to the number of tool and die makers in Maryland were aggregated from employment statistics, reflecting the employment dynamics within this specialized occupational cohort.

To establish the statistical relationship between these seemingly disparate variables, a series of analytical procedures were implemented. Firstly, the collected data were meticulously cleansed and harmonized to ensure compatibility and coherence. Subsequently, rigorous statistical analyses, including correlation and regression analyses, were performed to elucidate the nature and strength of the association between air pollution levels and the number of tool and die makers.

It is important to note that due consideration was given to potential confounding variables, such as changes in industrial composition, economic fluctuations, and technological advancements, which could plausibly influence the observed relationship. Sensitivity analyses and robustness checks were executed to assess the stability and validity of the findings in the presence of these confounders, thereby fortifying the credibility and reliability of the results.

Furthermore, in an attempt to unravel the underlying mechanisms driving this intriguing correlation, supplementary qualitative investigations were conducted. These involved interviews and focus group discussions with stakeholders from the environmental and manufacturing sectors, serving to contextualize the quantitative findings within the broader socio-economic landscape.

Overall, the employed methodology, though not without its complexities and intricacies, aptly facilitated the uncovering of the captivating connection between air pollution in Baltimore and the number of tool and die makers in Maryland. The exhaustive scrutiny of the data from various angles and the careful consideration of potential confounding factors enabled a robust and compelling analysis of this unexpected relationship.

Stay tuned for the results and discussion section to unveil the revelations arising from this meticulous methodological approach.

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 Baltimore, Maryland and The number of tool and die makers in Maryland. 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]]
Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland

[[ABSTRACT]]
This study explores the potential connection between air pollution in Baltimore, Maryland and the number of tool and die makers in the state. Employing data from the Environmental Protection Agency and the Bureau of Labor Statistics spanning the years 2003 to 2022, the correlation coefficient was found to be a striking 0.9122289, with a p-value less than 0.01, indicating a robust statistical association. The findings suggest that as air pollution levels rise, the number of tool and die makers in Maryland also increases. The implications of these findings are quite profound, shedding light on the nuanced and often overlooked interplay between environmental factors and occupational choices. Our research aims to inspire further discourse on this subject and encourage a deeper examination of the hidden forces shaping our occupational landscape.

[[LITERATURE REVIEW]]
The literature on the relationship between air pollution and occupational trends offers a wealth of insight into the potential connections that may exist. Smith et al. (2015) conducted a comprehensive analysis of air quality in urban industrial centers and its impact on local employment patterns, shedding light on the complex interplay between environmental conditions and workforce dynamics. Similarly, Doe (2018) explored the occupational preferences of individuals in regions with varying levels of air pollution, uncovering intriguing shifts in career choices in response to environmental factors. Jones (2020) delved into the correlation between air pollution exposure and the prevalence of skilled laborers, offering valuable perspectives on how external conditions may shape the composition of the workforce.
Moving beyond the traditional academic literature, non-fiction works such as "The Air We Breathe: A Comprehensive Analysis of Environmental Factors in Urban Centers" and "Industrial Revolution: History and Impact on Occupational Trends" provide additional context for understanding the broader implications of environmental conditions on the choice of professions. Moreover, fiction works such as "The Polluted Prospects" and "Tool and Die Mysteries: A Novel Approach to Environmental Influences on Occupational Pathways" offer imaginative interpretations of the potential connections between air pollution and occupational choices, inviting readers to consider the intersection of environmental factors and professional pursuits from a creative standpoint.
Furthermore, drawing inspiration from seemingly unrelated sources, board games such as "Pollution Pursuit" and "Tool and Die Tycoon" prompt players to navigate environmental challenges and occupational decision-making in simulated settings, offering playful yet thought-provoking reflections on the interplay between air quality and career paths.
In light of these diverse perspectives, it is clear that the examination of air pollution and its potential effects on the prevalence of tool and die makers in Maryland holds significant implications for understanding the intricate interplay between environmental factors and occupational preferences. The integration of both empirical research and imaginative explorations serves to enrich our understanding of this intriguing nexus, setting the stage for a multifaceted investigation into the breath-taking connections between air pollution and the occupational landscape.

[[RESULTS]]
The analysis of the data revealed a significant positive correlation between air pollution in Baltimore, Maryland and the number of tool and die makers in the state of Maryland. This remarkable association, with a correlation coefficient of 0.9122289 and an r-squared value of 0.8321615, defies traditional expectations and offers a paradoxical glimpse into the complex web of environmental and occupational dynamics.
The scatterplot in Fig. 1 visually depicts the striking correlation between air pollution levels and the number of tool and die makers. The upward trend captures the essence of this unlikely relationship, leaving researchers and readers alike breathless with its unexpected coherence.
The robust statistical significance of the correlation, indicated by a p-value of less than 0.01, reinforces the validity of this unorthodox connection. It appears that as the air in Baltimore becomes increasingly polluted, the labor force in Maryland responds by bolstering the ranks of tool and die makers, perhaps in an attempt to navigate the murky waters of a polluted atmosphere.
While the precise mechanisms underlying this link remain enigmatic, the findings beckon us to ponder the intricate interplay between environmental quality and the occupational choices of individuals. The implications of these results invite further exploration and contemplation, enriching the tapestry of interdisciplinary inquiry with an unexpected, albeit fascinating, thread.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study provide compelling evidence in support of prior research that has hinted at the intriguing interplay between air pollution and occupational preferences. The correlation coefficient of 0.9122289 lends substantial weight to the notion that as air pollution in Baltimore, Maryland increases, so does the number of tool and die makers in the state of Maryland. This unexpected relationship, while initially confounding, aligns with the assertions put forth by Smith et al. (2015), who discussed the impact of environmental conditions on local employment patterns. It appears that the labor force's response to environmental adversity may indeed manifest in the form of an influx of tool and die makers, as suggested by Doe (2018) and Jones (2020).

Moreover, the results of this study echo the narratives presented in non-fiction and fiction works that explore the potential connections between air pollution and occupational choices. The surprising coherence between air pollution levels and the proliferation of tool and die makers reflects the imaginative interpretations put forth in "The Polluted Prospects" and "Tool and Die Mysteries," highlighting the unforeseen ways in which environmental factors may sculpt occupational pathways.

The statistical significance of the correlation further underscores the compelling nature of this unorthodox relationship, akin to the thought-provoking reflections evoked by the board games "Pollution Pursuit" and "Tool and Die Tycoon." Much like players navigating simulated environmental challenges and occupational decision-making, the labor force in Maryland appears to navigate the murky waters of air pollution by expanding the cohort of tool and die makers. The robust statistical support provides a solid foundation for considering the intricate interplay between environmental quality and occupational choices, enriching the tapestry of interdisciplinary inquiry with an unexpected, albeit fascinating, thread, much like a hidden Easter egg waiting to be discovered in a well-worn novel.

In this light, the breath-taking connections unveiled in this study not only substantiate prior research but also ignite a spark for further discourse and exploration. The paradoxical glimpse into the complex web of environmental and occupational dynamics invites researchers and readers alike to ponder the nuanced and often surprising ways in which our professional pursuits may be shaped by the air we breathe. These findings underscore the need for continued investigation into the profound and often overlooked influence of environmental factors on the occupational landscape, adding an unexpected layer of depth to our understanding of the mechanisms driving occupational choices and the breath-taking connections that underpin them.

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 Baltimore, Maryland and The number of tool and die makers in Maryland. 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]]
Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland

[[ABSTRACT]]
This study explores the potential connection between air pollution in Baltimore, Maryland and the number of tool and die makers in the state. Employing data from the Environmental Protection Agency and the Bureau of Labor Statistics spanning the years 2003 to 2022, the correlation coefficient was found to be a striking 0.9122289, with a p-value less than 0.01, indicating a robust statistical association. The findings suggest that as air pollution levels rise, the number of tool and die makers in Maryland also increases. The implications of these findings are quite profound, shedding light on the nuanced and often overlooked interplay between environmental factors and occupational choices. Our research aims to inspire further discourse on this subject and encourage a deeper examination of the hidden forces shaping our occupational landscape.

[[INTRDUCTION]]
The interplay between environmental factors and occupational choices has long been a subject of intrigue and speculation. One would not necessarily expect air pollution levels to be associated with the number of tool and die makers in a given region, but as the saying goes, "the devil's in the details." The state of Maryland, with its vibrant industrial landscape and the ever-present issue of air pollution in Baltimore, provides an ideal backdrop for investigating this unexpected correlation.
The curiosity surrounding this unlikely duo of air pollution and tool and die makers led to the formulation of our research question: Could there be a hidden link between the quality of the air we breathe and the professionals tasked with fabricating precision tools and metal components? The idea may seem far-fetched at first glance, but as we delved into the data, it became increasingly evident that there might be more than meets the eye - or the nostrils, for that matter.
As we embark on this analytical journey, it is important to keep our minds open to the possibility that our findings may challenge conventional wisdom and add a new layer of complexity to the occupational and environmental dynamics at play. After all, in the realm of scientific inquiry, it is often the unanticipated relationships that yield the most intriguing insights.
So, put on your thinking caps and steel yourselves for a riveting exploration of the uncharted territory where air pollution and tool and die makers converge. The results may very well be, dare we say, groundbreaking.

[[RESULTS]]
The analysis of the data revealed a significant positive correlation between air pollution in Baltimore, Maryland and the number of tool and die makers in the state of Maryland. This remarkable association, with a correlation coefficient of 0.9122289 and an r-squared value of 0.8321615, defies traditional expectations and offers a paradoxical glimpse into the complex web of environmental and occupational dynamics.
The scatterplot in Fig. 1 visually depicts the striking correlation between air pollution levels and the number of tool and die makers. The upward trend captures the essence of this unlikely relationship, leaving researchers and readers alike breathless with its unexpected coherence.
The robust statistical significance of the correlation, indicated by a p-value of less than 0.01, reinforces the validity of this unorthodox connection. It appears that as the air in Baltimore becomes increasingly polluted, the labor force in Maryland responds by bolstering the ranks of tool and die makers, perhaps in an attempt to navigate the murky waters of a polluted atmosphere.
While the precise mechanisms underlying this link remain enigmatic, the findings beckon us to ponder the intricate interplay between environmental quality and the occupational choices of individuals. The implications of these results invite further exploration and contemplation, enriching the tapestry of interdisciplinary inquiry with an unexpected, albeit fascinating, thread.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the investigation into the relationship between air pollution in Baltimore, Maryland and the number of tool and die makers in the state has yielded eyebrow-raising results. The robust statistical association uncovered between these seemingly incongruous variables serves as a reminder that in the realm of social and environmental phenomena, surprises await those with the keen observational skills and the humility to embrace the unexpected.

The uncanny correlation between the rise in air pollution and the surge in tool and die makers prompts contemplation of the adaptive measures individuals may be undertaking in response to the compromised atmospheric conditions. Whether this points to a burgeoning demand for precision metal components to combat the effects of pollution or, dare we speculate, an unforeseen attraction to the metallic allure of tool and die crafting in the face of environmental adversity, remains an intriguing enigma worthy of further exploration.

In light of these findings, it is evident that the occupational landscape may be more intricately intertwined with environmental forces than previously conceived. As our research paints a picture of the unfolding drama between air quality and occupational choices, it tantalizingly beckons researchers to delve deeper into this unchartered, albeit slightly bewildering, terrain.

At this juncture, the results robustly advocate for the recognition of the unorthodox interplay between air pollution and the labor force makeup, injecting a breath of fresh air into the discourse surrounding occupational dynamics. However, it is crucial not to jump to hasty conclusions, as the precise mechanisms and underlying motivations driving this correlation continue to elude our grasp.

Thus, with a confident gait and a quizzical raise of the eyebrow, we assert that no more research is warranted in this area, leaving the whimsical dance of air pollution and tool and die makers to tantalize future scholars with its quirky charm.

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 Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Atmospheric Anthropology

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 Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Environmental Sociology and Industry Trends

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 Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland with an abstract of This study explores the potential connection between air pollution in Baltimore, Maryland and the number of tool and die makers in the state. Employing data from the Environmental Protection Agency and the Bureau of Labor Statistics spanning the years 2003 to 2022, the correlation coefficient was found to be a striking 0.9122289, with a p-value less than 0.01, indicating a robust statistical association. The findings suggest that as air pollution levels rise, the number of tool and die makers in Maryland also increases. The implications of these findings are quite profound, shedding light on the nuanced and often overlooked interplay between environmental factors and occupational choices. Our research aims to inspire further discourse on this subject and encourage a deeper examination of the hidden forces shaping our occupational landscape.

ChatGPT:

air pollution, Baltimore Maryland, tool and die makers, environmental protection agency, Bureau of Labor Statistics, correlation coefficient, p-value, occupational choices, environmental factors, occupational landscape

*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 Baltimore, Maryland
Detailed data title: Percentage of days with moderate or worse air quality in Baltimore-Columbia-Towson, MD
Source: Environmental Protection Agency
See what else correlates with Air pollution in Baltimore, Maryland

The number of tool and die makers in Maryland
Detailed data title: BLS estimate of tool and die makers in Maryland
Source: Bureau of Larbor Statistics
See what else correlates with The number of tool and die makers in Maryland

Correlation r = 0.9122289 (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 = 0.8321615 (Coefficient of determination)
This means 83.2% of the change in the one variable (i.e., The number of tool and die makers in Maryland) is predictable based on the change in the other (i.e., Air pollution in Baltimore, Maryland) over the 20 years from 2003 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.1E-8.^Show 0.0000000212769791627280350000
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 0.91 in 2.1E-6% of random cases. Said differently, if you correlated 46,999,153 random variables^Note You don't actually need 46 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 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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.

[ 0.79, 0.97 ] 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.

	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Air pollution in Baltimore, Maryland (Bad air quality days)	72.3288	71.5847	79.1781	65.2055	66.5753	58.7432	56.1644	57.2603	58.9041	57.377	46.0274	58.0822	51.5069	46.4481	38.9041	41.6438	38.9041	21.9178	31.2329	29.3151
The number of tool and die makers in Maryland (Tool And Die Makers)	490	580	450	410	340	320	340	330	290	340	370	300	330	230	200	130	120	80	80	60

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([72.3288,71.5847,79.1781,65.2055,66.5753,58.7432,56.1644,57.2603,58.9041,57.377,46.0274,58.0822,51.5069,46.4481,38.9041,41.6438,38.9041,21.9178,31.2329,29.3151,])
array_2 = np.array([490,580,450,410,340,320,340,330,290,340,370,300,330,230,200,130,120,80,80,60,])
array_1_name = "Air pollution in Baltimore, Maryland"
array_2_name = "The number of tool and die makers in Maryland"

# 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 Baltimore, Maryland
Line chart for only The number of tool and die makers in Maryland
AI-generated correlation image
The spurious research paper: Breath-taking Connections: The Relationship Between Air Pollution in Baltimore, Maryland and the Number of Tool and Die Makers in Maryland

View another random correlation

How fun was this correlation?

Kudos for rating!

Correlation ID: 5001 · Black Variable ID: 20320 · Red Variable ID: 9287


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