about · email me · subscribe
Spurious correlation #3,794 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Robberies in Kansas and the second variable is Remaining Forest Cover in the Brazilian Amazon.  The chart goes from 1987 to 2022, and the two variables track closely in value over that time. Small Image

AI explanation

As robberies in Kansas decreased, there was a surplus of ski masks in the global market. This led to an unexpected surge in demand for camouflage fashion, prompting people to clear the Amazonian forests for trendy tree-print clothing. Remember, only you can prevent forest cover loss by not wearing forest-inspired attire!

Model: dalle-3
Prompt: Generate an image in the style of a TIME magazine cover depicting a dramatic scene in the Brazilian Amazon rainforest. A group of fleeing criminals from Kansas is hurriedly building makeshift shelters amidst the dense forest. The sound of chainsaws resonates through the air as the remaining forest cover diminishes, while the robbers convert their stolen goods into currency to support their activities. Capture the intense atmosphere of the scene, portraying the tension of the criminals' actions against the backdrop of the vanishing rainforest. 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: Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon. 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: Art nouveau An image that looks like it is a scene from A Disney Movie Concept art A TIME magazine cover image Celtic art
ChatGPT: A TIME magazine cover image

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 Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon, in the following situation: Because as robberies increased in Kansas, more criminals hid out in the Amazon, causing deforestation. They needed to build hideouts, so they chopped down more trees.. Keep the description simple.
ChatGPT: In a clearing in the dense Brazilian Amazon rainforest, a group of fleeing criminals from Kansas are seen hastily constructing makeshift shelters out of chopped down trees. The sound of chainsaws echoes through the forest as the remaining forest cover dwindles, while the robbers convert the stolen goods into currency to fund their activities.

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 TIME magazine cover image ] and depicting this scene: In a clearing in the dense Brazilian Amazon rainforest, a group of fleeing criminals from Kansas are seen hastily constructing makeshift shelters out of chopped down trees. The sound of chainsaws echoes through the forest as the remaining forest cover dwindles, while the robbers convert the stolen goods into currency to fund their activities. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image in the style of a TIME magazine cover depicting a dramatic scene in the Brazilian Amazon rainforest. A group of fleeing criminals from Kansas is hurriedly building makeshift shelters amidst the dense forest. The sound of chainsaws resonates through the air as the remaining forest cover diminishes, while the robbers convert their stolen goods into currency to support their activities. Capture the intense atmosphere of the scene, portraying the tension of the criminals' actions against the backdrop of the vanishing rainforest.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Robberies in Kansas caused Remaining Forest Cover in the Brazilian Amazon to decrease. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed

The Journal of Ecological Criminology

Jan 2024
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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from FBI Criminal Justice Information Services and Mongabay to assess this nagging question. You found a correlation coefficient of 0.8873229 and p < 0.01 for 1987 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]]
Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed

[[ABSTRACT]]
This paper presents the shocking link between robberies in Kansas and remaining forest cover in the Brazilian Amazon. It is a robber's paradox of sorts, unraveling a connection that has eluded researchers for too long. Our intrepid research team embarked on an investigation using data from FBI Criminal Justice Information Services and Mongabay to address this perplexing conundrum. To our surprise, we uncovered a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022, leaving us with little room for doubt. The implications of this unlikely association are far-reaching and simply tree-mendous. In this paper, we delve into the unusual connection and offer some leafy insights that may change the way we perceive crime and environmental conservation.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed

[[ABSTRACT]]
This paper presents the shocking link between robberies in Kansas and remaining forest cover in the Brazilian Amazon. It is a robber's paradox of sorts, unraveling a connection that has eluded researchers for too long. Our intrepid research team embarked on an investigation using data from FBI Criminal Justice Information Services and Mongabay to address this perplexing conundrum. To our surprise, we uncovered a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022, leaving us with little room for doubt. The implications of this unlikely association are far-reaching and simply tree-mendous. In this paper, we delve into the unusual connection and offer some leafy insights that may change the way we perceive crime and environmental conservation.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The world of research often leads us down unexpected paths, uncovering connections that seem, at first glance, utterly improbable. As renowned physicist Niels Bohr once said, "Prediction is very difficult, especially if it's about the future." And indeed, our foray into the relationship between robberies in Kansas and the remaining forest cover in the Brazilian Amazon embodies the spirit of Bohr's words – for what could be more surprising than the nexus of criminal activity in the American Midwest with the verdant expanses of the South American rainforest?

It is far from an ordinary day when one contemplates the possible correlation between theft and trees, between bandits and biodiversity. However, as scholars committed to the pursuit of knowledge, we are duty-bound to explore even the most unconventional of hypotheses. While one might initially dismiss such an investigation as some kind of environmental "folly," our findings hint at an intricate web of interconnections that challenge our preconceptions and set the stage for a most intriguing intellectual caper.

This study takes root in the recognition that the impacts of human activity reach far beyond the geographic and cultural boundaries we traditionally recognize. The intricate dance of cause and effect in our increasingly interconnected world demands that we cast our net wider in search of understanding. In this spirit, we set out to uncover the curious associations between criminal activity and ecological preservation, fully prepared for surprises of wilderness proportions.

Little did we know, as we delved into the FBI Criminal Justice Information Services and the vast treasure trove of environmental data sourced from Mongabay, that we would stumble upon a statistical revelation that challenges even the most seasoned minds. The statistical correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022 left us bemused, astounded, and thoroughly dumbfounded. The evidence was compelling, bordering on absurdity, and it left us with but one option – to confront this abnormality head-on and to excavate the roots of this enigmatic linkage.

In the ensuing sections of this paper, we aim to unravel this enigma and offer a branch of explanations that, dare I say, may leaf you pondering the complex interplay between crime and conservation. It is our hope that this research will not only pique the interest of the scholarly community but also inject a much-needed dose of "tree-humor" into the often-serious discourse of academic inquiry. After all, who said academic papers can't be both informative and forest-ful of fun?


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon. Make lots of 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed

[[ABSTRACT]]
This paper presents the shocking link between robberies in Kansas and remaining forest cover in the Brazilian Amazon. It is a robber's paradox of sorts, unraveling a connection that has eluded researchers for too long. Our intrepid research team embarked on an investigation using data from FBI Criminal Justice Information Services and Mongabay to address this perplexing conundrum. To our surprise, we uncovered a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022, leaving us with little room for doubt. The implications of this unlikely association are far-reaching and simply tree-mendous. In this paper, we delve into the unusual connection and offer some leafy insights that may change the way we perceive crime and environmental conservation.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of research often leads us down unexpected paths, uncovering connections that seem, at first glance, utterly improbable. As renowned physicist Niels Bohr once said, "Prediction is very difficult, especially if it's about the future." And indeed, our foray into the relationship between robberies in Kansas and the remaining forest cover in the Brazilian Amazon embodies the spirit of Bohr's words – for what could be more surprising than the nexus of criminal activity in the American Midwest with the verdant expanses of the South American rainforest?
It is far from an ordinary day when one contemplates the possible correlation between theft and trees, between bandits and biodiversity. However, as scholars committed to the pursuit of knowledge, we are duty-bound to explore even the most unconventional of hypotheses. While one might initially dismiss such an investigation as some kind of environmental "folly," our findings hint at an intricate web of interconnections that challenge our preconceptions and set the stage for a most intriguing intellectual caper.
This study takes root in the recognition that the impacts of human activity reach far beyond the geographic and cultural boundaries we traditionally recognize. The intricate dance of cause and effect in our increasingly interconnected world demands that we cast our net wider in search of understanding. In this spirit, we set out to uncover the curious associations between criminal activity and ecological preservation, fully prepared for surprises of wilderness proportions.
Little did we know, as we delved into the FBI Criminal Justice Information Services and the vast treasure trove of environmental data sourced from Mongabay, that we would stumble upon a statistical revelation that challenges even the most seasoned minds. The statistical correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022 left us bemused, astounded, and thoroughly dumbfounded. The evidence was compelling, bordering on absurdity, and it left us with but one option – to confront this abnormality head-on and to excavate the roots of this enigmatic linkage.
In the ensuing sections of this paper, we aim to unravel this enigma and offer a branch of explanations that, dare I say, may leaf you pondering the complex interplay between crime and conservation. It is our hope that this research will not only pique the interest of the scholarly community but also inject a much-needed dose of "tree-humor" into the often-serious discourse of academic inquiry. After all, who said academic papers can't be both informative and forest-ful of fun?

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The association between robberies in Kansas and remaining forest cover in the Brazilian Amazon may seem outlandish at first glance, prompting many to pine for a more conventional correlation. Yet, an exhaustive review of the literature showcases the diverse perspectives and unexpected connections that underpin this improbable nexus.

In "Crime in the Heartland: A Study of Robbery Trends in Kansas," Smith et al. meticulously document the ebb and flow of criminal activity in the Midwestern state, detailing the modi operandi of brazen bandits and cunning cat burglars alike. Their work offers a sobering portrayal of criminal behavior, punctuated by the occasional corny pun.

Meanwhile, Doe's seminal paper "Deforestation in the Amazon: A Looming Crisis" paints a vivid picture of the encroaching threat to the world's largest tropical rainforest. With impassioned prose, Doe underscores the urgent need for conservation efforts and leaves readers with a profound sense of arboreal urgency.

Jones' influential study "A Statistical Analysis of Environmental Factors and Criminal Behavior" takes a broader view, seeking to uncover hidden patterns in seemingly disparate phenomena. While Jones' work may not directly address the specific link between robberies in Kansas and forest cover in the Amazon, it lays the groundwork for understanding the interconnectedness of seemingly unrelated variables—much like the unexpected pairing of detectives and deforestation in our current investigation.

Turning our attention to non-fiction books, "The Environmental Bandit: Chronicles of a Robber Turned Tree Planter" presents a compelling account of one man's journey from a life of crime to a mission of reforestation. This gripping narrative challenges conventional wisdom and highlights the redemptive potential of even the most unlikely protagonists.

In a delightful departure from the standard academic fare, works of fiction also offer intriguing insights. "The Jungle Heist Chronicles" by A. Novel explores the exploits of a group of eco-conscious bandits whose daring escapades in the Brazilian Amazon are fueled by a desire to save the endangered rainforest. While the events may be purely fictional, the underlying theme of environmental stewardship coupled with criminal activities beckons us to ponder the possibilities of fact imitating fiction.

As we dive deeper into the heart of our investigation, we uncover unexpected sources of inspiration. Cartoons like "The Wild Adventures of Woody the Woodpecker" and children's shows such as "Captain Planet and the Planeteers" provide a whimsical yet surprisingly insightful lens through which to examine the intersection of crime and conservation. Who would have thought that Saturday morning cartoons could offer such "tree-mendous" wisdom?

In the pages that follow, we aim to glean insights from this diverse array of sources to shed light on the peculiar connection between robberies in Kansas and remaining forest cover in the Brazilian Amazon. Prepare to be simultaneously entertained and enlightened, for what lies ahead is a scholarly escapade like no other.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Mongabay . You used data from 1987 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]]
Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed

[[ABSTRACT]]
This paper presents the shocking link between robberies in Kansas and remaining forest cover in the Brazilian Amazon. It is a robber's paradox of sorts, unraveling a connection that has eluded researchers for too long. Our intrepid research team embarked on an investigation using data from FBI Criminal Justice Information Services and Mongabay to address this perplexing conundrum. To our surprise, we uncovered a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022, leaving us with little room for doubt. The implications of this unlikely association are far-reaching and simply tree-mendous. In this paper, we delve into the unusual connection and offer some leafy insights that may change the way we perceive crime and environmental conservation.

[[INTRODUCTION]]
The world of research often leads us down unexpected paths, uncovering connections that seem, at first glance, utterly improbable. As renowned physicist Niels Bohr once said, "Prediction is very difficult, especially if it's about the future." And indeed, our foray into the relationship between robberies in Kansas and the remaining forest cover in the Brazilian Amazon embodies the spirit of Bohr's words – for what could be more surprising than the nexus of criminal activity in the American Midwest with the verdant expanses of the South American rainforest?
It is far from an ordinary day when one contemplates the possible correlation between theft and trees, between bandits and biodiversity. However, as scholars committed to the pursuit of knowledge, we are duty-bound to explore even the most unconventional of hypotheses. While one might initially dismiss such an investigation as some kind of environmental "folly," our findings hint at an intricate web of interconnections that challenge our preconceptions and set the stage for a most intriguing intellectual caper.
This study takes root in the recognition that the impacts of human activity reach far beyond the geographic and cultural boundaries we traditionally recognize. The intricate dance of cause and effect in our increasingly interconnected world demands that we cast our net wider in search of understanding. In this spirit, we set out to uncover the curious associations between criminal activity and ecological preservation, fully prepared for surprises of wilderness proportions.
Little did we know, as we delved into the FBI Criminal Justice Information Services and the vast treasure trove of environmental data sourced from Mongabay, that we would stumble upon a statistical revelation that challenges even the most seasoned minds. The statistical correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022 left us bemused, astounded, and thoroughly dumbfounded. The evidence was compelling, bordering on absurdity, and it left us with but one option – to confront this abnormality head-on and to excavate the roots of this enigmatic linkage.
In the ensuing sections of this paper, we aim to unravel this enigma and offer a branch of explanations that, dare I say, may leaf you pondering the complex interplay between crime and conservation. It is our hope that this research will not only pique the interest of the scholarly community but also inject a much-needed dose of "tree-humor" into the often-serious discourse of academic inquiry. After all, who said academic papers can't be both informative and forest-ful of fun?

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unearth the perplexing link between robberies in Kansas and the remaining forest cover in the Brazilian Amazon, a mix of rigorous data collection and, dare I say, forest gumping was employed. As a first step, our research team sourced robbery data from the FBI Criminal Justice Information Services. Armed with this data, we proceeded to assess the annual number of reported robberies in Kansas from 1987 to 2022. It is worth noting that the research team resisted the temptation to don trench coats and fedoras while conducting this data collection, despite the allure of an investigative aesthetic.

Simultaneously, we delved into the tangled underbrush of the Brazilian Amazon's environmental landscape using data provided by Mongabay. This invaluable resource offered insights into the remaining forest cover in the region, allowing us to scrutinize the annual changes in canopy area. The research team refrained from swinging from vines or wrestling anacondas while browsing this data, opting instead for a more sedate approach to forest exploration.

Once we had gathered this wealth of information, statistical analyses were conducted to weigh the correlation between these seemingly disparate variables. Utilizing the time-honored techniques of correlation analysis, we scrutinized the relationship between the annual number of robberies in Kansas and the remaining forest cover in the Brazilian Amazon. Careful attention was paid to avoid the pitfalls of a statistical wild goose chase, as the research team aimed to approach the analysis with a cool head and an un-clouded forest view.

In accordance with established research practices, the statistical significance of the correlation was assessed through hypothesis testing, ultimately yielding a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022. This statistical revelation sent ripples through the academic community, prompting reflections on the profound ways in which criminal activity and ecological preservation are intertwined. As the dust settled on our data analysis, we were left to ponder the unexpected synergy between crime in the heartland of the United States and the evergreen expanse of the Amazon rainforest.

In summary, our methodology blended conventional statistical analyses with a whimsical spirit of exploration, akin to wandering through a forest in search of buried treasure. This approach allowed us to uncover compelling evidence of the connection between robberies in Kansas and remaining forest cover in the Brazilian Amazon, leaving us with a revelation as wild as finding a hidden grove in the midst of an urban jungle.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Mongabay .

For the time period 1987 to 2022, you found a correlation 0.8873229, r-squared of 0.7873419, 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]]
Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed

[[ABSTRACT]]
This paper presents the shocking link between robberies in Kansas and remaining forest cover in the Brazilian Amazon. It is a robber's paradox of sorts, unraveling a connection that has eluded researchers for too long. Our intrepid research team embarked on an investigation using data from FBI Criminal Justice Information Services and Mongabay to address this perplexing conundrum. To our surprise, we uncovered a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022, leaving us with little room for doubt. The implications of this unlikely association are far-reaching and simply tree-mendous. In this paper, we delve into the unusual connection and offer some leafy insights that may change the way we perceive crime and environmental conservation.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The world of research often leads us down unexpected paths, uncovering connections that seem, at first glance, utterly improbable. As renowned physicist Niels Bohr once said, "Prediction is very difficult, especially if it's about the future." And indeed, our foray into the relationship between robberies in Kansas and the remaining forest cover in the Brazilian Amazon embodies the spirit of Bohr's words – for what could be more surprising than the nexus of criminal activity in the American Midwest with the verdant expanses of the South American rainforest?
It is far from an ordinary day when one contemplates the possible correlation between theft and trees, between bandits and biodiversity. However, as scholars committed to the pursuit of knowledge, we are duty-bound to explore even the most unconventional of hypotheses. While one might initially dismiss such an investigation as some kind of environmental "folly," our findings hint at an intricate web of interconnections that challenge our preconceptions and set the stage for a most intriguing intellectual caper.
This study takes root in the recognition that the impacts of human activity reach far beyond the geographic and cultural boundaries we traditionally recognize. The intricate dance of cause and effect in our increasingly interconnected world demands that we cast our net wider in search of understanding. In this spirit, we set out to uncover the curious associations between criminal activity and ecological preservation, fully prepared for surprises of wilderness proportions.
Little did we know, as we delved into the FBI Criminal Justice Information Services and the vast treasure trove of environmental data sourced from Mongabay, that we would stumble upon a statistical revelation that challenges even the most seasoned minds. The statistical correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022 left us bemused, astounded, and thoroughly dumbfounded. The evidence was compelling, bordering on absurdity, and it left us with but one option – to confront this abnormality head-on and to excavate the roots of this enigmatic linkage.
In the ensuing sections of this paper, we aim to unravel this enigma and offer a branch of explanations that, dare I say, may leaf you pondering the complex interplay between crime and conservation. It is our hope that this research will not only pique the interest of the scholarly community but also inject a much-needed dose of "tree-humor" into the often-serious discourse of academic inquiry. After all, who said academic papers can't be both informative and forest-ful of fun?

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis of the relationship between robberies in Kansas and the remaining forest cover in the Brazilian Amazon yielded quite the unexpected, dare I say, "tree-mendous" revelation. Our analysis uncovered a striking correlation coefficient of 0.8873229, indicating a strong positive association, and an r-square value of 0.7873419 for the time period spanning 1987 to 2022. The p-value of less than 0.01 further emphasizes the robustness of this correlation, leaving us with little room for doubt and a whole lot of room for fascination.

In one fell swoop, this finding uproots any lingering doubts about the link between criminal activities in the American heartland and the sprawling greenery of the Amazon rainforest. Fig. 1 succinctly depicts the scatterplot, portraying the undeniably strong correlation between these seemingly disparate variables. It's a sight to behold, capturing the essence of this unlikely yet compelling association.

The implications of this revelation are as far-reaching as the branches of the Amazon trees. Our findings prompt a reevaluation of the interconnectivity of seemingly unrelated phenomena. We were initially leaf-tless in our attempt to comprehend this conundrum, but now we find ourselves on the cusp of a new understanding – could the preservation of nature hold unforeseen consequences for the prevalence of criminal activities in distant lands? This unexpected correlation may hold the key to unlocking a realm of inquiry that extends far beyond the scope of conventional environmental research.

However, this discovery also leaves us with a trunk-load of unanswered questions. What mechanisms underlie this surprising relationship? Is there a link between societal attitudes towards theft and the perception and conservation of natural spaces? These are tantalizing branches of inquiry that this study opens up, and we are motivated to delve deeper into this uncharted territory – both figuratively and literally.

In a world where the unexpected often takes root in the most unlikely places, our findings serve as a reminder that the tendrils of cause and effect can stretch across continents and manifest in ways that challenge our long-held beliefs. This unlikely nexus of forest cover and criminal activity opens a door to a forest of questions, and we excitedly embark on the journey to explore each and every one of them.

In the words of Henry David Thoreau, "I frequently tramped eight or ten miles through the deepest snow to keep an appointment with a beech-tree, or a yellow birch, or an old acquaintance among the pines." Indeed, our research has led us through unexpected terrain, and we now find ourselves forging new friendships among the lofty canopies of curiosity and discovery.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed

[[ABSTRACT]]
This paper presents the shocking link between robberies in Kansas and remaining forest cover in the Brazilian Amazon. It is a robber's paradox of sorts, unraveling a connection that has eluded researchers for too long. Our intrepid research team embarked on an investigation using data from FBI Criminal Justice Information Services and Mongabay to address this perplexing conundrum. To our surprise, we uncovered a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022, leaving us with little room for doubt. The implications of this unlikely association are far-reaching and simply tree-mendous. In this paper, we delve into the unusual connection and offer some leafy insights that may change the way we perceive crime and environmental conservation.

[[LITERATURE REVIEW]]
The association between robberies in Kansas and remaining forest cover in the Brazilian Amazon may seem outlandish at first glance, prompting many to pine for a more conventional correlation. Yet, an exhaustive review of the literature showcases the diverse perspectives and unexpected connections that underpin this improbable nexus.
In "Crime in the Heartland: A Study of Robbery Trends in Kansas," Smith et al. meticulously document the ebb and flow of criminal activity in the Midwestern state, detailing the modi operandi of brazen bandits and cunning cat burglars alike. Their work offers a sobering portrayal of criminal behavior, punctuated by the occasional corny pun.
Meanwhile, Doe's seminal paper "Deforestation in the Amazon: A Looming Crisis" paints a vivid picture of the encroaching threat to the world's largest tropical rainforest. With impassioned prose, Doe underscores the urgent need for conservation efforts and leaves readers with a profound sense of arboreal urgency.
Jones' influential study "A Statistical Analysis of Environmental Factors and Criminal Behavior" takes a broader view, seeking to uncover hidden patterns in seemingly disparate phenomena. While Jones' work may not directly address the specific link between robberies in Kansas and forest cover in the Amazon, it lays the groundwork for understanding the interconnectedness of seemingly unrelated variables—much like the unexpected pairing of detectives and deforestation in our current investigation.
Turning our attention to non-fiction books, "The Environmental Bandit: Chronicles of a Robber Turned Tree Planter" presents a compelling account of one man's journey from a life of crime to a mission of reforestation. This gripping narrative challenges conventional wisdom and highlights the redemptive potential of even the most unlikely protagonists.
In a delightful departure from the standard academic fare, works of fiction also offer intriguing insights. "The Jungle Heist Chronicles" by A. Novel explores the exploits of a group of eco-conscious bandits whose daring escapades in the Brazilian Amazon are fueled by a desire to save the endangered rainforest. While the events may be purely fictional, the underlying theme of environmental stewardship coupled with criminal activities beckons us to ponder the possibilities of fact imitating fiction.
As we dive deeper into the heart of our investigation, we uncover unexpected sources of inspiration. Cartoons like "The Wild Adventures of Woody the Woodpecker" and children's shows such as "Captain Planet and the Planeteers" provide a whimsical yet surprisingly insightful lens through which to examine the intersection of crime and conservation. Who would have thought that Saturday morning cartoons could offer such "tree-mendous" wisdom?
In the pages that follow, we aim to glean insights from this diverse array of sources to shed light on the peculiar connection between robberies in Kansas and remaining forest cover in the Brazilian Amazon. Prepare to be simultaneously entertained and enlightened, for what lies ahead is a scholarly escapade like no other.

[[RESULTS]]
The statistical analysis of the relationship between robberies in Kansas and the remaining forest cover in the Brazilian Amazon yielded quite the unexpected, dare I say, "tree-mendous" revelation. Our analysis uncovered a striking correlation coefficient of 0.8873229, indicating a strong positive association, and an r-square value of 0.7873419 for the time period spanning 1987 to 2022. The p-value of less than 0.01 further emphasizes the robustness of this correlation, leaving us with little room for doubt and a whole lot of room for fascination.
In one fell swoop, this finding uproots any lingering doubts about the link between criminal activities in the American heartland and the sprawling greenery of the Amazon rainforest. Fig. 1 succinctly depicts the scatterplot, portraying the undeniably strong correlation between these seemingly disparate variables. It's a sight to behold, capturing the essence of this unlikely yet compelling association.
The implications of this revelation are as far-reaching as the branches of the Amazon trees. Our findings prompt a reevaluation of the interconnectivity of seemingly unrelated phenomena. We were initially leaf-tless in our attempt to comprehend this conundrum, but now we find ourselves on the cusp of a new understanding – could the preservation of nature hold unforeseen consequences for the prevalence of criminal activities in distant lands? This unexpected correlation may hold the key to unlocking a realm of inquiry that extends far beyond the scope of conventional environmental research.
However, this discovery also leaves us with a trunk-load of unanswered questions. What mechanisms underlie this surprising relationship? Is there a link between societal attitudes towards theft and the perception and conservation of natural spaces? These are tantalizing branches of inquiry that this study opens up, and we are motivated to delve deeper into this uncharted territory – both figuratively and literally.
In a world where the unexpected often takes root in the most unlikely places, our findings serve as a reminder that the tendrils of cause and effect can stretch across continents and manifest in ways that challenge our long-held beliefs. This unlikely nexus of forest cover and criminal activity opens a door to a forest of questions, and we excitedly embark on the journey to explore each and every one of them.
In the words of Henry David Thoreau, "I frequently tramped eight or ten miles through the deepest snow to keep an appointment with a beech-tree, or a yellow birch, or an old acquaintance among the pines." Indeed, our research has led us through unexpected terrain, and we now find ourselves forging new friendships among the lofty canopies of curiosity and discovery.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The unexpected correlation between robberies in Kansas and remaining forest cover in the Brazilian Amazon has uprooted conventional assumptions and planted the seeds of a new understanding. Our investigation not only confirmed the unlikely association proposed in the literature review but also provided robust empirical evidence to support this puzzling connection.

The correlation coefficient of 0.8873229 and p-value less than 0.01 found in our analysis corroborate the nonpareil link between these seemingly unrelated variables. It is evident that as the remaining forest cover in the Brazilian Amazon decreases, the number of robberies in Kansas increases – a revelation that is both astoundingly novel and undeniably branch-tastic.

Our findings are not merely a leaf in the wind but hold profound implications for understanding the interconnectedness of socio-environmental phenomena. The robustness of this unexpected correlation hints at a deeper interplay between criminal activities and environmental conservation efforts, challenging traditional paradigms and branching out into uncharted territories of inquiry. The tree-mendous implications of this discovery compel us to delve deeper into the roots of this association and explore its implications for policy and practice.

Through this study, we have come to appreciate the oak-celerating interconnections between seemingly disparate spheres of human activity and natural ecosystems. The unexpected correlation between robberies in Kansas and forest cover in the Brazilian Amazon serves as a poignant reminder that the tendrils of cause and effect can stretch across continents, intertwining in ways we had hardly twigged before.

While our study sheds light on this surprising association, it also leaves a fertile bed of questions yet to be explored. What are the underlying mechanisms driving this correlation? Could societal attitudes towards theft and environmental conservation be intertwined in unexpected ways? These questions beckon us to branch out into new avenues of research, rooting out the underlying factors that sustain this connection.

In conclusion, our findings underscore the need to embrace unexpected associations and to explore the uncharted territories of interdisciplinary research. This study not only offers leafy insights into the curious connection between robberies in Kansas and remaining forest cover in the Brazilian Amazon but also provides a sturdy trunk for future inquiries into the unexpected intersections of human behavior and environmental dynamics. As we emerge from this scholarly escapade, we find ourselves branching out into new frontiers of understanding, leaving behind the comforting shade of conventional wisdom and venturing into the verdant unknown of unexpected connections.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Robberies in Kansas and Remaining Forest Cover in the Brazilian Amazon. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed

[[ABSTRACT]]
This paper presents the shocking link between robberies in Kansas and remaining forest cover in the Brazilian Amazon. It is a robber's paradox of sorts, unraveling a connection that has eluded researchers for too long. Our intrepid research team embarked on an investigation using data from FBI Criminal Justice Information Services and Mongabay to address this perplexing conundrum. To our surprise, we uncovered a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022, leaving us with little room for doubt. The implications of this unlikely association are far-reaching and simply tree-mendous. In this paper, we delve into the unusual connection and offer some leafy insights that may change the way we perceive crime and environmental conservation.

[[INTRDUCTION]]
The world of research often leads us down unexpected paths, uncovering connections that seem, at first glance, utterly improbable. As renowned physicist Niels Bohr once said, "Prediction is very difficult, especially if it's about the future." And indeed, our foray into the relationship between robberies in Kansas and the remaining forest cover in the Brazilian Amazon embodies the spirit of Bohr's words – for what could be more surprising than the nexus of criminal activity in the American Midwest with the verdant expanses of the South American rainforest?
It is far from an ordinary day when one contemplates the possible correlation between theft and trees, between bandits and biodiversity. However, as scholars committed to the pursuit of knowledge, we are duty-bound to explore even the most unconventional of hypotheses. While one might initially dismiss such an investigation as some kind of environmental "folly," our findings hint at an intricate web of interconnections that challenge our preconceptions and set the stage for a most intriguing intellectual caper.
This study takes root in the recognition that the impacts of human activity reach far beyond the geographic and cultural boundaries we traditionally recognize. The intricate dance of cause and effect in our increasingly interconnected world demands that we cast our net wider in search of understanding. In this spirit, we set out to uncover the curious associations between criminal activity and ecological preservation, fully prepared for surprises of wilderness proportions.
Little did we know, as we delved into the FBI Criminal Justice Information Services and the vast treasure trove of environmental data sourced from Mongabay, that we would stumble upon a statistical revelation that challenges even the most seasoned minds. The statistical correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022 left us bemused, astounded, and thoroughly dumbfounded. The evidence was compelling, bordering on absurdity, and it left us with but one option – to confront this abnormality head-on and to excavate the roots of this enigmatic linkage.
In the ensuing sections of this paper, we aim to unravel this enigma and offer a branch of explanations that, dare I say, may leaf you pondering the complex interplay between crime and conservation. It is our hope that this research will not only pique the interest of the scholarly community but also inject a much-needed dose of "tree-humor" into the often-serious discourse of academic inquiry. After all, who said academic papers can't be both informative and forest-ful of fun?

[[RESULTS]]
The statistical analysis of the relationship between robberies in Kansas and the remaining forest cover in the Brazilian Amazon yielded quite the unexpected, dare I say, "tree-mendous" revelation. Our analysis uncovered a striking correlation coefficient of 0.8873229, indicating a strong positive association, and an r-square value of 0.7873419 for the time period spanning 1987 to 2022. The p-value of less than 0.01 further emphasizes the robustness of this correlation, leaving us with little room for doubt and a whole lot of room for fascination.
In one fell swoop, this finding uproots any lingering doubts about the link between criminal activities in the American heartland and the sprawling greenery of the Amazon rainforest. Fig. 1 succinctly depicts the scatterplot, portraying the undeniably strong correlation between these seemingly disparate variables. It's a sight to behold, capturing the essence of this unlikely yet compelling association.
The implications of this revelation are as far-reaching as the branches of the Amazon trees. Our findings prompt a reevaluation of the interconnectivity of seemingly unrelated phenomena. We were initially leaf-tless in our attempt to comprehend this conundrum, but now we find ourselves on the cusp of a new understanding – could the preservation of nature hold unforeseen consequences for the prevalence of criminal activities in distant lands? This unexpected correlation may hold the key to unlocking a realm of inquiry that extends far beyond the scope of conventional environmental research.
However, this discovery also leaves us with a trunk-load of unanswered questions. What mechanisms underlie this surprising relationship? Is there a link between societal attitudes towards theft and the perception and conservation of natural spaces? These are tantalizing branches of inquiry that this study opens up, and we are motivated to delve deeper into this uncharted territory – both figuratively and literally.
In a world where the unexpected often takes root in the most unlikely places, our findings serve as a reminder that the tendrils of cause and effect can stretch across continents and manifest in ways that challenge our long-held beliefs. This unlikely nexus of forest cover and criminal activity opens a door to a forest of questions, and we excitedly embark on the journey to explore each and every one of them.
In the words of Henry David Thoreau, "I frequently tramped eight or ten miles through the deepest snow to keep an appointment with a beech-tree, or a yellow birch, or an old acquaintance among the pines." Indeed, our research has led us through unexpected terrain, and we now find ourselves forging new friendships among the lofty canopies of curiosity and discovery.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has unearthed a correlation between robberies in Kansas and remaining forest cover in the Brazilian Amazon so strong, it's almost as if the thieves were leaf-ing behind a trail of evidence. The statistically significant connection has uprooted our preconceptions and branched out into a tangled web of potential implications.

This unlikely alliance between crime and conservation challenges the conventional wisdom in a way that could make even the most hardened researcher break out in tree-mbling excitement. From the depths of the American Midwest to the lush expanses of the Amazon, this unexpected correlation highlights the intricate dance of cause and effect in our interconnected world.

Our findings lead us to ponder many tantalizing branches of inquiry. Could societal attitudes toward theft be intertwined with perceptions of and attitudes toward nature? Could the preservation of the Amazon rainforest have unforeseen consequences for criminal activities in distant lands? These questions are ripe for further exploration, and we are eager to leaf no stone unturned in our pursuit of answers.

As we stand on the cusp of a new understanding, it's clear that this research invites us to venture into uncharted territory, much like explorers in the verdant Amazon. It offers a forest of questions to explore, and we're ready to delve into this enigmatic linkage with the enthusiasm of a tree-hugger in springtime.

With that said, it is undeniable - our findings have laid down roots in unexpected terrain, presenting a trunk-load of intriguing possibilities and prospects for future research. However, as much as we'd love to continue this wild and tree-mendous adventure, it's time to branch out and leave this research in the capable hands of future scholars. After all, when it comes to the unlikely link between robberies in Kansas and remaining forest cover in the Brazilian Amazon, it appears that no more research is needed.


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 Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Ecological Criminology


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 Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Midwestern Ecology and Crime Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Robberies in Kansas and Remaining Forest Canvases: A Surprising Link Revealed with an abstract of This paper presents the shocking link between robberies in Kansas and remaining forest cover in the Brazilian Amazon. It is a robber's paradox of sorts, unraveling a connection that has eluded researchers for too long. Our intrepid research team embarked on an investigation using data from FBI Criminal Justice Information Services and Mongabay to address this perplexing conundrum. To our surprise, we uncovered a correlation coefficient of 0.8873229 and p < 0.01 for the years 1987 to 2022, leaving us with little room for doubt. The implications of this unlikely association are far-reaching and simply tree-mendous. In this paper, we delve into the unusual connection and offer some leafy insights that may change the way we perceive crime and environmental conservation.

ChatGPT:

robberies, Kansas, forest cover, Brazilian Amazon, correlation, FBI Criminal Justice Information Services, Mongabay, paradox, research, correlation coefficient, p-value, implications, crime, environmental conservation

*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

Robberies in Kansas
Detailed data title: The robbery rate per 100,000 residents in Kansas
Source: FBI Criminal Justice Information Services
See what else correlates with Robberies in Kansas

Remaining Forest Cover in the Brazilian Amazon
Detailed data title: Estimated Remaining Forest Cover in the Brazilian Amazon
Source: Mongabay
See what else correlates with Remaining Forest Cover in the Brazilian Amazon

Correlation r = 0.8873229 (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 = 0.7873419 (Coefficient of determination)
This means 78.7% of the change in the one variable (i.e., Remaining Forest Cover in the Brazilian Amazon) is predictable based on the change in the other (i.e., Robberies in Kansas) over the 36 years from 1987 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 5.7E-13. 0.0000000000005653476902744684
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 0.89 in 5.7E-11% of random cases. Said differently, if you correlated 1,768,823,004,326 random variables You don't actually need 1 trillion 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 35 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 35 because we have two variables measured over a period of 36 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, 0.94 ] 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.
198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Robberies in Kansas (Robbery rate)82.185.999.8117.6138.4129.9123.6115.1108.296.397.78777.176.289.779.882.566.365.367.972.86063.453.850.451.746.246.962.760.456.148.839.731.833.329.2
Remaining Forest Cover in the Brazilian Amazon (Sq. KM)374457037235203705750369202036809903667200365231036374103608350359019035769603559580354232035241003505930348428034588803431110341210033978103386160337325033657903358790335237033478003341910333690033306903322800331585033083103298550329012032796503268050




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.
  5. Outlandish outliers: There are "outliers" in this data. In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

    For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

    (This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
    They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.




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([82.1,85.9,99.8,117.6,138.4,129.9,123.6,115.1,108.2,96.3,97.7,87,77.1,76.2,89.7,79.8,82.5,66.3,65.3,67.9,72.8,60,63.4,53.8,50.4,51.7,46.2,46.9,62.7,60.4,56.1,48.8,39.7,31.8,33.3,29.2,])
array_2 = np.array([3744570,3723520,3705750,3692020,3680990,3667200,3652310,3637410,3608350,3590190,3576960,3559580,3542320,3524100,3505930,3484280,3458880,3431110,3412100,3397810,3386160,3373250,3365790,3358790,3352370,3347800,3341910,3336900,3330690,3322800,3315850,3308310,3298550,3290120,3279650,3268050,])
array_1_name = "Robberies in Kansas"
array_2_name = "Remaining Forest Cover in the Brazilian Amazon"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your correlation inspection deserves a standing ovation!


Correlation ID: 3794 · Black Variable ID: 20189 · Red Variable ID: 372
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0