about · email me · subscribe
Spurious correlation #2,100 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Arson in Florida and the second variable is Google searches for 'n95 mask'.  The chart goes from 2005 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The surge in arson cases in Florida led to a sudden spike in the demand for N95 masks, as both firefighters and amateur fire-starters realized the importance of airway protection. As the flames kept rising, so did the interest in respiratory safety, proving once again that even in the midst of chaos, people will always remember to prioritize their lungs.

Model: dalle-3
Prompt: Prompt: Generate a black-and-white newspaper style illustration showing a person in Florida setting fire to a pile of debris in their backyard. Nearby, depict another person using their phone to search for "n95 mask" on Google, looking concerned about the smoke and air pollution resulting from the fire. The illustration should capture the contrast in actions and the potential impact on air quality. 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: Arson in Florida and Google searches for 'n95 mask'. 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: Low poly Oragami A black-and-white newspaper illustration 3D Pixar Style Photorealism
ChatGPT: A black-and-white newspaper illustration

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Arson in Florida and Google searches for 'n95 mask' together. Keep the description simple.
ChatGPT: A person in Florida sets fire to a pile of debris in their backyard, while nearby, someone uses their phone to search for "n95 mask" on Google, hoping to protect themselves from the resulting smoke and air pollution.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A black-and-white newspaper illustration ] and depicting this scene: A person in Florida sets fire to a pile of debris in their backyard, while nearby, someone uses their phone to search for "n95 mask" on Google, hoping to protect themselves from the resulting smoke and air pollution. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate a black-and-white newspaper style illustration showing a person in Florida setting fire to a pile of debris in their backyard. Nearby, depict another person using their phone to search for "n95 mask" on Google, looking concerned about the smoke and air pollution resulting from the fire. The illustration should capture the contrast in actions and the potential impact on air quality.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Arson in Florida positively influenced n95 mask (Google searches for 'n95 mask').

AI academic paper

(Because p < 0.01)
Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks

The Journal of Unusual Correlations

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Arson in Florida and Google searches for 'n95 mask'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from FBI Criminal Justice Information Services and Google Trends to assess this nagging question. You found a correlation coefficient of 0.9198934 and p < 0.01 for 2005 to 2022.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks

[[ABSTRACT]]
This paper delves into the fiery connection between arson incidents in the state of Florida and the online clamor for N95 masks. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we set out to investigate if there is a striking trend between these seemingly disparate events. Our findings reveal a significant positive correlation, with a correlation coefficient of 0.9198934 and a p-value below the conventional threshold of 0.01, spanning the period from 2005 to 2022. This study not only sheds light on the potential correlation between arson and public interest in N95 masks but also adds fuel to the ongoing discourse on the unexpected connections in societal behaviors.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Arson in Florida and Google searches for 'n95 mask'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks

[[ABSTRACT]]
This paper delves into the fiery connection between arson incidents in the state of Florida and the online clamor for N95 masks. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we set out to investigate if there is a striking trend between these seemingly disparate events. Our findings reveal a significant positive correlation, with a correlation coefficient of 0.9198934 and a p-value below the conventional threshold of 0.01, spanning the period from 2005 to 2022. This study not only sheds light on the potential correlation between arson and public interest in N95 masks but also adds fuel to the ongoing discourse on the unexpected connections in societal behaviors.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Arson, the incendiary act of intentionally setting fire to property, has long been a thorny issue in the realm of law enforcement and public safety. The Sunshine State, Florida, has unfortunately seen its fair share of fiery incidents over the years, prompting both concern and curiosity among researchers. On the other hand, the skyrocketing demand for N95 masks in recent times has been a hot topic of discussion, quite literally and figuratively. The ongoing global pandemic has certainly sparked a fervent interest in protective face masks, with individuals scrambling to procure these respiratory safeguards.

In this study, we embark on a quest to unravel the connection, or shall we say, the blaze of correlation between these seemingly unrelated phenomena. Who would have thought that the scorching issue of arson and the fervent hunt for N95 masks could be intertwined in such a fiery dance of statistical significance? With data sources ranging from the FBI Criminal Justice Information Services, diligently cataloging arson incidents, to Google Trends, the modern-day oracle of online search patterns, we aim to illuminate the sparks that fly between these two phenomena.

So, grab your metaphorical fire extinguisher and join us as we ignite the flames of inquiry into this sizzling correlation between Florida arson incidents and Google searches for N95 masks. This study not only seeks to add kindling to the understanding of societal behavior but also hopes to shed light on the unexpected connections that lurk within the ashes of statistical data.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Arson in Florida and Google searches for 'n95 mask'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks

[[ABSTRACT]]
This paper delves into the fiery connection between arson incidents in the state of Florida and the online clamor for N95 masks. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we set out to investigate if there is a striking trend between these seemingly disparate events. Our findings reveal a significant positive correlation, with a correlation coefficient of 0.9198934 and a p-value below the conventional threshold of 0.01, spanning the period from 2005 to 2022. This study not only sheds light on the potential correlation between arson and public interest in N95 masks but also adds fuel to the ongoing discourse on the unexpected connections in societal behaviors.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Arson, the incendiary act of intentionally setting fire to property, has long been a thorny issue in the realm of law enforcement and public safety. The Sunshine State, Florida, has unfortunately seen its fair share of fiery incidents over the years, prompting both concern and curiosity among researchers. On the other hand, the skyrocketing demand for N95 masks in recent times has been a hot topic of discussion, quite literally and figuratively. The ongoing global pandemic has certainly sparked a fervent interest in protective face masks, with individuals scrambling to procure these respiratory safeguards.
In this study, we embark on a quest to unravel the connection, or shall we say, the blaze of correlation between these seemingly unrelated phenomena. Who would have thought that the scorching issue of arson and the fervent hunt for N95 masks could be intertwined in such a fiery dance of statistical significance? With data sources ranging from the FBI Criminal Justice Information Services, diligently cataloging arson incidents, to Google Trends, the modern-day oracle of online search patterns, we aim to illuminate the sparks that fly between these two phenomena.
So, grab your metaphorical fire extinguisher and join us as we ignite the flames of inquiry into this sizzling correlation between Florida arson incidents and Google searches for N95 masks. This study not only seeks to add kindling to the understanding of societal behavior but also hopes to shed light on the unexpected connections that lurk within the ashes of statistical data.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In the quest to understand the blazing correlation between Florida arson incidents and Google searches for N95 masks, researchers have delved into a myriad of scholarly findings and empirical studies. Smith et al. (2015) explored the complex relationship between arson and public health crises, shedding light on the potential interplay between these seemingly disparate realms. Doe and Jones (2018) further investigated the societal repercussions of arson incidents, hinting at the possibility of unexpected correlations with public interest in respiratory protective gear.

Turning the pages to the broader literature on public interest and response to crises, notable works such as "Epidemics and Society: From the Black Death to the Present" (Cantor, 2001) and "The Great Influenza: The Story of the Deadliest Pandemic in History" (Barry, 2004) provide valuable insights into the collective behaviors during health emergencies. These works, though not directly aligned with arson incidents, offer a lens through which societal reactions to crises could potentially intersect with the demand for protective masks.

Expanding the scope of inquiry, the realm of fiction presents intriguing narratives that perhaps reflect, in a metaphorical sense, the unexpected connections that we seek to unravel. Consider the works of dystopian fiction such as "Station Eleven" (Mandel, 2014) and "The Road" (McCarthy, 2006), where the protagonists navigate through post-apocalyptic landscapes, emblematic of societal turmoil and the search for essential resources. While fictional, these narratives hint at the nuanced interplay between crises, human behaviors, and the pursuit of safety.

Venturing further into the esoteric realms of information acquisition, the authors, in a daring move, embarked on an unconventional method of literature review – perusing CVS receipts. Surprisingly, amidst the mundane grocery items and pharmaceutical purchases, insights into consumer behavior and their whimsical search for unusual items emerged, albeit in a rather illegible and unrelated manner.

The juxtaposition of scholarly endeavors, literary narratives, and the absurdity of unconventional literature review methods sparks a certain acknowledgment of the multifaceted lens through which we seek to understand the perplexing correlation between Florida arson incidents and Google searches for N95 masks. As we stride through the archives of data and literature, we aim to bring to light the unexpected correlations that lurk beneath the layers of statistical analyses, adding not only kindling to the inferno of knowledge but also a spoonful of whimsy to the scholarly pursuit.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Arson in Florida and Google searches for 'n95 mask'. 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 FBI Criminal Justice Information Services and Google Trends . You used data from 2005 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]]
Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks

[[ABSTRACT]]
This paper delves into the fiery connection between arson incidents in the state of Florida and the online clamor for N95 masks. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we set out to investigate if there is a striking trend between these seemingly disparate events. Our findings reveal a significant positive correlation, with a correlation coefficient of 0.9198934 and a p-value below the conventional threshold of 0.01, spanning the period from 2005 to 2022. This study not only sheds light on the potential correlation between arson and public interest in N95 masks but also adds fuel to the ongoing discourse on the unexpected connections in societal behaviors.

[[INTRODUCTION]]
Arson, the incendiary act of intentionally setting fire to property, has long been a thorny issue in the realm of law enforcement and public safety. The Sunshine State, Florida, has unfortunately seen its fair share of fiery incidents over the years, prompting both concern and curiosity among researchers. On the other hand, the skyrocketing demand for N95 masks in recent times has been a hot topic of discussion, quite literally and figuratively. The ongoing global pandemic has certainly sparked a fervent interest in protective face masks, with individuals scrambling to procure these respiratory safeguards.
In this study, we embark on a quest to unravel the connection, or shall we say, the blaze of correlation between these seemingly unrelated phenomena. Who would have thought that the scorching issue of arson and the fervent hunt for N95 masks could be intertwined in such a fiery dance of statistical significance? With data sources ranging from the FBI Criminal Justice Information Services, diligently cataloging arson incidents, to Google Trends, the modern-day oracle of online search patterns, we aim to illuminate the sparks that fly between these two phenomena.
So, grab your metaphorical fire extinguisher and join us as we ignite the flames of inquiry into this sizzling correlation between Florida arson incidents and Google searches for N95 masks. This study not only seeks to add kindling to the understanding of societal behavior but also hopes to shed light on the unexpected connections that lurk within the ashes of statistical data.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the mysterious link between Florida arson incidents and the public clamor for N95 masks, we employed a multifaceted approach that would make Sherlock Holmes proud. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we aimed to piece together the puzzle of this curiously smoky correlation.

Firstly, to capture the smoldering landscape of arson incidents, we delved into the comprehensive database maintained by the FBI Criminal Justice Information Services. This repository provided a treasure trove of incendiary data, allowing us to pinpoint the timing and locations of these fiery escapades across the Sunshine State.

As for the N95 mask frenzy, we turned to Google Trends, the modern-day crystal ball of online search patterns. With its finger on the pulse of public interest, Google Trends offered us a peek into the fervent quest for these protective face masks. We meticulously tracked the frequency of searches for 'N95 mask' within the confines of the state of Florida, capturing the ebb and flow of this sizzling curiosity.

The time frame for our escapade into the correlations stretched from 2005 to 2022, encompassing a significant period of smoldering data. Utilizing our trusty statistical tools, we calculated the correlation coefficient to measure the strength and direction of the relationship between arson incidents and N95 mask searches. Carefully adjusting our magnifying glass, we scrutinized the p-value to determine the significance of this fiery alliance.

Armed with an arsenal of statistical methods, including regression analysis and time series modeling, we set out to untangle this tantalizing web of association. By harnessing the power of data visualization techniques, we sought to paint a vivid portrait of the sparks that flew between these seemingly unrelated phenomena.

So, with our pipes of inquiry firmly clenched between our teeth, we ventured forth into this combustible terrain, armed with datasets and spreadsheets as our trusty sidekicks. Join us as we illuminate the shadows cast by this enigmatic correlation, and perhaps uncover a spark of insight into the mysteries that lie within the statistical kindling of Florida arson and N95 mask fervor.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Arson in Florida and Google searches for 'n95 mask'. 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 FBI Criminal Justice Information Services and Google Trends .

For the time period 2005 to 2022, you found a correlation 0.9198934, r-squared of 0.8462039, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks

[[ABSTRACT]]
This paper delves into the fiery connection between arson incidents in the state of Florida and the online clamor for N95 masks. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we set out to investigate if there is a striking trend between these seemingly disparate events. Our findings reveal a significant positive correlation, with a correlation coefficient of 0.9198934 and a p-value below the conventional threshold of 0.01, spanning the period from 2005 to 2022. This study not only sheds light on the potential correlation between arson and public interest in N95 masks but also adds fuel to the ongoing discourse on the unexpected connections in societal behaviors.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Arson, the incendiary act of intentionally setting fire to property, has long been a thorny issue in the realm of law enforcement and public safety. The Sunshine State, Florida, has unfortunately seen its fair share of fiery incidents over the years, prompting both concern and curiosity among researchers. On the other hand, the skyrocketing demand for N95 masks in recent times has been a hot topic of discussion, quite literally and figuratively. The ongoing global pandemic has certainly sparked a fervent interest in protective face masks, with individuals scrambling to procure these respiratory safeguards.
In this study, we embark on a quest to unravel the connection, or shall we say, the blaze of correlation between these seemingly unrelated phenomena. Who would have thought that the scorching issue of arson and the fervent hunt for N95 masks could be intertwined in such a fiery dance of statistical significance? With data sources ranging from the FBI Criminal Justice Information Services, diligently cataloging arson incidents, to Google Trends, the modern-day oracle of online search patterns, we aim to illuminate the sparks that fly between these two phenomena.
So, grab your metaphorical fire extinguisher and join us as we ignite the flames of inquiry into this sizzling correlation between Florida arson incidents and Google searches for N95 masks. This study not only seeks to add kindling to the understanding of societal behavior but also hopes to shed light on the unexpected connections that lurk within the ashes of statistical data.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

A scorching correlation between Florida arson incidents and Google searches for N95 masks was illuminated through our statistical analysis. The correlation coefficient of 0.9198934 indicates a strong positive relationship, suggesting that as arson incidents flare up, so too does public interest in acquiring N95 masks. The coefficient of determination (r-squared) of 0.8462039 further bolsters the idea that these two phenomena are not simply fanning the flames of coincidence. The p-value below the conventional threshold of 0.01 provides convincing evidence that this scorching correlation is not simply a result of random chance.

Fig. 1 presents a compelling scatterplot that visually captures the close relationship between the number of arson incidents in Florida and the intensity of Google searches for N95 masks. The data points form a trail of sparks, tracing the upward trajectory of N95 mask searches as the flames of arson incidents flicker and ignite. The linear relationship displayed in the scatterplot provides a fiery portrayal of the statistical link between these seemingly disparate events.

These findings not only add fuel to the discussion on the unexpected interconnectedness of societal behaviors but also serve as a reminder that in the realm of statistical analysis, sometimes the most unlikely pairs can set the data ablaze with significance.



Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Arson in Florida and Google searches for 'n95 mask'. 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]]
Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks

[[ABSTRACT]]
This paper delves into the fiery connection between arson incidents in the state of Florida and the online clamor for N95 masks. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we set out to investigate if there is a striking trend between these seemingly disparate events. Our findings reveal a significant positive correlation, with a correlation coefficient of 0.9198934 and a p-value below the conventional threshold of 0.01, spanning the period from 2005 to 2022. This study not only sheds light on the potential correlation between arson and public interest in N95 masks but also adds fuel to the ongoing discourse on the unexpected connections in societal behaviors.

[[LITERATURE REVIEW]]
In the quest to understand the blazing correlation between Florida arson incidents and Google searches for N95 masks, researchers have delved into a myriad of scholarly findings and empirical studies. Smith et al. (2015) explored the complex relationship between arson and public health crises, shedding light on the potential interplay between these seemingly disparate realms. Doe and Jones (2018) further investigated the societal repercussions of arson incidents, hinting at the possibility of unexpected correlations with public interest in respiratory protective gear.
Turning the pages to the broader literature on public interest and response to crises, notable works such as "Epidemics and Society: From the Black Death to the Present" (Cantor, 2001) and "The Great Influenza: The Story of the Deadliest Pandemic in History" (Barry, 2004) provide valuable insights into the collective behaviors during health emergencies. These works, though not directly aligned with arson incidents, offer a lens through which societal reactions to crises could potentially intersect with the demand for protective masks.
Expanding the scope of inquiry, the realm of fiction presents intriguing narratives that perhaps reflect, in a metaphorical sense, the unexpected connections that we seek to unravel. Consider the works of dystopian fiction such as "Station Eleven" (Mandel, 2014) and "The Road" (McCarthy, 2006), where the protagonists navigate through post-apocalyptic landscapes, emblematic of societal turmoil and the search for essential resources. While fictional, these narratives hint at the nuanced interplay between crises, human behaviors, and the pursuit of safety.
Venturing further into the esoteric realms of information acquisition, the authors, in a daring move, embarked on an unconventional method of literature review – perusing CVS receipts. Surprisingly, amidst the mundane grocery items and pharmaceutical purchases, insights into consumer behavior and their whimsical search for unusual items emerged, albeit in a rather illegible and unrelated manner.
The juxtaposition of scholarly endeavors, literary narratives, and the absurdity of unconventional literature review methods sparks a certain acknowledgment of the multifaceted lens through which we seek to understand the perplexing correlation between Florida arson incidents and Google searches for N95 masks. As we stride through the archives of data and literature, we aim to bring to light the unexpected correlations that lurk beneath the layers of statistical analyses, adding not only kindling to the inferno of knowledge but also a spoonful of whimsy to the scholarly pursuit.

[[RESULTS]]
A scorching correlation between Florida arson incidents and Google searches for N95 masks was illuminated through our statistical analysis. The correlation coefficient of 0.9198934 indicates a strong positive relationship, suggesting that as arson incidents flare up, so too does public interest in acquiring N95 masks. The coefficient of determination (r-squared) of 0.8462039 further bolsters the idea that these two phenomena are not simply fanning the flames of coincidence. The p-value below the conventional threshold of 0.01 provides convincing evidence that this scorching correlation is not simply a result of random chance.
Fig. 1 presents a compelling scatterplot that visually captures the close relationship between the number of arson incidents in Florida and the intensity of Google searches for N95 masks. The data points form a trail of sparks, tracing the upward trajectory of N95 mask searches as the flames of arson incidents flicker and ignite. The linear relationship displayed in the scatterplot provides a fiery portrayal of the statistical link between these seemingly disparate events.
These findings not only add fuel to the discussion on the unexpected interconnectedness of societal behaviors but also serve as a reminder that in the realm of statistical analysis, sometimes the most unlikely pairs can set the data ablaze with significance.


-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our study provide compelling evidence to support the existence of a fiery relationship between Florida arson incidents and the public interest in N95 masks. The significant positive correlation coefficient of 0.9198934 lends strong support to the notion that as arson incidents light up the Sunshine State, there is a simultaneous surge in online searches for respiratory protective gear. This finding aligns with the work of Smith et al. (2015), who hinted at the potential interplay between arson and public health crises, illustrating that the connection between fire and respiratory protection may not be a mere smokescreen.

The literature review, while touching on conventional studies and scholarly works, also dabbled in the peculiar, with an ode to unconventional literature review methods such as perusing CVS receipts. In a surprising turn, the whimsical search for unusual items among grocery and pharmaceutical purchases may have provided a subtle foreshadowing of the unexpected correlation between arson incidents and the quest for N95 masks. This unorthodox approach, though discussed in jest, beckons us to consider the unpredictability and serendipity that often characterize academia and scholarly pursuits.

The juxtaposition of fiction with scholarly inquiry, such as the works of dystopian fiction that metaphorically reflect societal turmoil and the pursuit of essential resources, urges us to acknowledge the nuanced interplay between crises, human behaviors, and the quest for safety. While these works may have been discussed with a hint of joviality, they offer poignant reflections on the unexpected connections lurking beneath the surface of seemingly unrelated phenomena. The multifaceted lens through which we aim to understand this perplexing correlation underscores the richness of scholarly inquiry, with each layer adding not only kindling to the inferno of knowledge but also a spoonful of whimsy to the scholarly pursuit.

Our findings may sound unconventional, likening disparate events such as arson and the clamor for N95 masks to an unexpected pair, but as statistics have shown, sometimes the most unlikely combinations can set the data ablaze with significance. This study invites further exploration into understanding the underlying mechanisms driving this connection and raises questions for future research to spark inquiries into the broader implications of societal behaviors in the face of crises.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Arson in Florida and Google searches for 'n95 mask'. 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]]
Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks

[[ABSTRACT]]
This paper delves into the fiery connection between arson incidents in the state of Florida and the online clamor for N95 masks. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we set out to investigate if there is a striking trend between these seemingly disparate events. Our findings reveal a significant positive correlation, with a correlation coefficient of 0.9198934 and a p-value below the conventional threshold of 0.01, spanning the period from 2005 to 2022. This study not only sheds light on the potential correlation between arson and public interest in N95 masks but also adds fuel to the ongoing discourse on the unexpected connections in societal behaviors.

[[INTRDUCTION]]
Arson, the incendiary act of intentionally setting fire to property, has long been a thorny issue in the realm of law enforcement and public safety. The Sunshine State, Florida, has unfortunately seen its fair share of fiery incidents over the years, prompting both concern and curiosity among researchers. On the other hand, the skyrocketing demand for N95 masks in recent times has been a hot topic of discussion, quite literally and figuratively. The ongoing global pandemic has certainly sparked a fervent interest in protective face masks, with individuals scrambling to procure these respiratory safeguards.
In this study, we embark on a quest to unravel the connection, or shall we say, the blaze of correlation between these seemingly unrelated phenomena. Who would have thought that the scorching issue of arson and the fervent hunt for N95 masks could be intertwined in such a fiery dance of statistical significance? With data sources ranging from the FBI Criminal Justice Information Services, diligently cataloging arson incidents, to Google Trends, the modern-day oracle of online search patterns, we aim to illuminate the sparks that fly between these two phenomena.
So, grab your metaphorical fire extinguisher and join us as we ignite the flames of inquiry into this sizzling correlation between Florida arson incidents and Google searches for N95 masks. This study not only seeks to add kindling to the understanding of societal behavior but also hopes to shed light on the unexpected connections that lurk within the ashes of statistical data.

[[RESULTS]]
A scorching correlation between Florida arson incidents and Google searches for N95 masks was illuminated through our statistical analysis. The correlation coefficient of 0.9198934 indicates a strong positive relationship, suggesting that as arson incidents flare up, so too does public interest in acquiring N95 masks. The coefficient of determination (r-squared) of 0.8462039 further bolsters the idea that these two phenomena are not simply fanning the flames of coincidence. The p-value below the conventional threshold of 0.01 provides convincing evidence that this scorching correlation is not simply a result of random chance.
Fig. 1 presents a compelling scatterplot that visually captures the close relationship between the number of arson incidents in Florida and the intensity of Google searches for N95 masks. The data points form a trail of sparks, tracing the upward trajectory of N95 mask searches as the flames of arson incidents flicker and ignite. The linear relationship displayed in the scatterplot provides a fiery portrayal of the statistical link between these seemingly disparate events.
These findings not only add fuel to the discussion on the unexpected interconnectedness of societal behaviors but also serve as a reminder that in the realm of statistical analysis, sometimes the most unlikely pairs can set the data ablaze with significance.


-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has sparked illuminating findings regarding the remarkable correlation between Florida arson incidents and Google searches for N95 masks, igniting a new understanding of the intertwined nature of these seemingly disassociated phenomena. The scorching correlation coefficient and the persuasive p-value have heatedly revealed a strong positive relationship, leaving no room for the cold embrace of random chance.
Our scintillating scatterplot serves as an incandescent visual testament to the close connection between arson incidents and the fervent fervor for N95 masks, painting a vivid picture of the fiery dance between these two seemingly unrelated elements. We must admit, the unexpected nature of these findings certainly adds a fiery flair to the discourse on societal behaviors.
In the grand scheme of things, our findings signal that in the realm of statistical analysis, the most unexpected pairs can indeed illuminate the data with a blaze of significance. As we extinguish the flames of our study, we are confident that no further research is needed in this area. The findings of this study stand as a glowing testament to the surprising connections that can be unearthed within the embers of statistical data.


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 Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unusual Correlations


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 Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Eccentric Research Endeavors (SERE)


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 Sparking Arson in the Sunshine State: An Examination of the Relationship between Florida Arson Incidents and Google Searches for N95 Masks with an abstract of This paper delves into the fiery connection between arson incidents in the state of Florida and the online clamor for N95 masks. Leveraging data from the FBI Criminal Justice Information Services and Google Trends, we set out to investigate if there is a striking trend between these seemingly disparate events. Our findings reveal a significant positive correlation, with a correlation coefficient of 0.9198934 and a p-value below the conventional threshold of 0.01, spanning the period from 2005 to 2022. This study not only sheds light on the potential correlation between arson and public interest in N95 masks but also adds fuel to the ongoing discourse on the unexpected connections in societal behaviors.

ChatGPT:

Florida arson incidents, arson trends, N95 mask searches, Google Trends, correlation between arson incidents and N95 mask searches, societal behaviors, FBI Criminal Justice Information Services, unexpected connections, Florida crime trends

*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

Arson in Florida
Detailed data title: The arson rate per 100,000 residents in Florida
Source: FBI Criminal Justice Information Services
See what else correlates with Arson in Florida

Google searches for 'n95 mask'
Detailed data title: Relative volume of Google searches for 'n95 mask' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'n95 mask'

Correlation r = 0.9198934 (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 = 0.8462039 (Coefficient of determination)
This means 84.6% of the change in the one variable (i.e., Google searches for 'n95 mask') is predictable based on the change in the other (i.e., Arson in Florida) over the 18 years from 2005 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.6E-8. 0.0000000661657597240847800000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.92 in 6.6E-6% of random cases. Said differently, if you correlated 15,113,557 random variables You don't actually need 15 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 17 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 17 because we have two variables measured over a period of 18 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)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!


All values for the years included above: If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200520062007200820092010201120122013201420152016201720182019202020212022
Arson in Florida (Arson rate)1414.414.7141210.19.498.57.77.47.16.55.35132.412.5
Google searches for 'n95 mask' (Rel. search volume)0.6666671001.66667000511111.666671.1428634.758.583336.33333




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."


# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([14,14.4,14.7,14,12,10.1,9.4,9,8.5,7.7,7.4,7.1,6.5,5.3,5,132.4,1,2.5,])
array_2 = np.array([0.666667,1,0,0,1.66667,0,0,0,5,1,1,1,1,1.66667,1.14286,34.75,8.58333,6.33333,])
array_1_name = "Arson in Florida"
array_2_name = "Google searches for 'n95 mask'"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating skills are top-notch!


Correlation ID: 2100 · Black Variable ID: 20080 · Red Variable ID: 1496
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0