Spurious correlation #2,793 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Milk consumption and the second variable is Burglaries in Michigan. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Milk consumption and the second variable is Burglaries in Michigan. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

Fewer people were crying over spilled milk, so there was an udder lack of opportunity for dairy air burglars to moo-ve in and butter them up for a heist. Without milk on the rise, the thieves couldn't dairy risk getting caught, so they just couldn't lactose temptation to commit burglaries. The police were able to dairy up their resources for other crimes and it was all because the milk-tdown led to a dairy good outcome for Michigan's crime rate.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate a whimsical illustration portraying the idyllic countryside of Michigan, where cows with strong, muscular bodies stand as guardians around quaint homes. The cows, with watchful eyes and a determined presence, exude a sense of protection and security for the community. The scene should emphasize the charming rural setting, featuring lush green pastures and quaint homes nestled among rolling hills. The cows, with a touch of whimsy, should be depicted in a friendly and approachable manner, blending their strength with a sense of warmth and security. 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: Milk consumption and Burglaries in Michigan. 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: Cubism High-tech Concept art Whimsical illustration Celtic art
ChatGPT: Whimsical 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 Milk consumption and Burglaries in Michigan, in the following situation: As milk consumption decreased, cows became more vigilant, guarding Michigan homes from potential burglars with their mighty moo-scles, resulting in a decrease in burglary rates.. Keep the description simple.
ChatGPT: In the quaint countryside of Michigan, as people drank less milk, cows with their sturdy moo-scles, stood guard around homes. Their watchful eyes and strong presence led to a decline in burglary rates, ensuring the safety of the community.

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: [ Whimsical illustration ] and depicting this scene: In the quaint countryside of Michigan, as people drank less milk, cows with their sturdy moo-scles, stood guard around homes. Their watchful eyes and strong presence led to a decline in burglary rates, ensuring the safety of the community. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a whimsical illustration portraying the idyllic countryside of Michigan, where cows with strong, muscular bodies stand as guardians around quaint homes. The cows, with watchful eyes and a determined presence, exude a sense of protection and security for the community. The scene should emphasize the charming rural setting, featuring lush green pastures and quaint homes nestled among rolling hills. The cows, with a touch of whimsy, should be depicted in a friendly and approachable manner, blending their strength with a sense of warmth and security.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Milk consumption caused Burglaries in Michigan to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan

The Journal of Dairy Dynamics

Jan 2024

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

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Milk consumption and Burglaries in Michigan. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan

[[ABSTRACT]]
This research examines the curious association between milk consumption and burglary rates in the state of Michigan. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, a striking correlation coefficient of 0.9678454 and p < 0.01 was revealed. Despite the seemingly unrelated nature of these variables, our findings suggest a robust relationship that begs for further investigation. This paper presents an enlightening analysis of this unexpected phenomenon, shedding light on the unexpected ways in which milk and mischief may intertwine.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Milk consumption and burglaries are two topics that typically don't rub elbows in the scholarly arena. One conjures images of wholesome breakfasts and mustaches adorned with white droplets, while the other invokes thoughts of stealth, capers, and hooded figures skulking in the night. However, as the saying goes, truth is stranger than fiction. In the realm of statistical analysis, it is often the unexpected connections that provide the most intriguing results. This study delves into the correlation between the consumption of milk and the occurrence of burglaries in the state of Michigan, unearthing an udderly captivating relationship that defies conventional wisdom.
The initial impetus for this investigation stemmed from the arrival of a particularly sharp-eyed data analyst who quipped, "Would you believe me if I told you there might be a link between cow juice and criminal activity?" Such seemingly preposterous musings piqued our curiosity and led to an in-depth exploration of the numbers. To our amazement, preliminary analysis revealed a striking correlation coefficient of 0.9678454, accompanied by a p-value of less than 0.01. Such compelling statistical indicators left us with no choice but to embark on an academic escapade into this unforeseen nexus of dairy and delinquency.
As amusing as the notion may seem at first glance, the implications of such a relationship are not to be dismissed lightly. If substantiated, this association could have far-reaching consequences for public health, law enforcement, and dairy aficionados alike. The implications may be as far-reaching as they are unexpected, and thus warrant a diligent investigation.
The remainder of this paper is organized as follows: Section 2 provides a detailed review of the existing literature on both milk consumption and crime rates, highlighting the surprising lack of prior research on their confluence. Section 3 outlines the methodology employed in the collection and analysis of the empirical data, while Section 4 presents the results of our rigorous statistical examination. Section 5 offers a discussion of the implications of our findings and suggestions for future research. Finally, Section 6 concludes with a summary of our key insights, reflecting on the potential broader implications of these findings.
In light of the initial surprising correlation, this research endeavors to bring to light the unexpected ways in which milk may not only do a body good but may also have unforeseen ties to nocturnal mischief. While the connection between milk consumption and burglaries may remain enigmatic, our investigation strives to shed light on this bovine-ly bizarre phenomena and its potential ramifications.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Doe et al.," the authors find that milk consumption has been extensively studied in relation to dietary habits, calcium intake, and bone health, but surprisingly, little attention has been paid to its potential connection to criminal behavior. Meanwhile, "Smith and Jones" delve into the complex dynamics of burglary rates in urban environments, focusing on socioeconomic factors, policing strategies, and community engagement, with nary a mention of dairy products or lactose-related anomalies.

Turning to non-fiction works, "Got Milk? The Complexities of Milk Consumption in the 21st Century" and "Burglaries Unveiled: Examining the Underground World of Break-Ins" provide valuable insights into our topic of interest. These empirical studies offer nuanced perspectives on the multifaceted nature of milk consumption and the intricate web of motivations behind residential intrusions.

Expanding the lens to fiction literature, the works of Agatha Christie, renowned for her mysteries, and dairy-themed novels such as "The Milkman Cometh" and "The Maltese Cow" prompt a whimsical yet surprisingly relevant exploration of the potential intertwining of milk chug-a-lug and burglary huggerie.

In a departure from traditional scholarly sources, anecdotal evidence gleaned from social media platforms reveals intriguing musings such as "Got milk? More like got mischief!" and "I've never trusted a lactose enthusiast in a dark alley." While not empirically grounded, these online commentaries provide a lighthearted backdrop to the unexpectedly entangled realms of moo juice and illicit activities.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Milk consumption and Burglaries in Michigan. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from USDA and FBI Criminal Justice Information Services . You used data from 1990 to 2021

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan

[[ABSTRACT]]
This research examines the curious association between milk consumption and burglary rates in the state of Michigan. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, a striking correlation coefficient of 0.9678454 and p < 0.01 was revealed. Despite the seemingly unrelated nature of these variables, our findings suggest a robust relationship that begs for further investigation. This paper presents an enlightening analysis of this unexpected phenomenon, shedding light on the unexpected ways in which milk and mischief may intertwine.

[[INTRODUCTION]]
Milk consumption and burglaries are two topics that typically don't rub elbows in the scholarly arena. One conjures images of wholesome breakfasts and mustaches adorned with white droplets, while the other invokes thoughts of stealth, capers, and hooded figures skulking in the night. However, as the saying goes, truth is stranger than fiction. In the realm of statistical analysis, it is often the unexpected connections that provide the most intriguing results. This study delves into the correlation between the consumption of milk and the occurrence of burglaries in the state of Michigan, unearthing an udderly captivating relationship that defies conventional wisdom.
The initial impetus for this investigation stemmed from the arrival of a particularly sharp-eyed data analyst who quipped, "Would you believe me if I told you there might be a link between cow juice and criminal activity?" Such seemingly preposterous musings piqued our curiosity and led to an in-depth exploration of the numbers. To our amazement, preliminary analysis revealed a striking correlation coefficient of 0.9678454, accompanied by a p-value of less than 0.01. Such compelling statistical indicators left us with no choice but to embark on an academic escapade into this unforeseen nexus of dairy and delinquency.
As amusing as the notion may seem at first glance, the implications of such a relationship are not to be dismissed lightly. If substantiated, this association could have far-reaching consequences for public health, law enforcement, and dairy aficionados alike. The implications may be as far-reaching as they are unexpected, and thus warrant a diligent investigation.
The remainder of this paper is organized as follows: Section 2 provides a detailed review of the existing literature on both milk consumption and crime rates, highlighting the surprising lack of prior research on their confluence. Section 3 outlines the methodology employed in the collection and analysis of the empirical data, while Section 4 presents the results of our rigorous statistical examination. Section 5 offers a discussion of the implications of our findings and suggestions for future research. Finally, Section 6 concludes with a summary of our key insights, reflecting on the potential broader implications of these findings.
In light of the initial surprising correlation, this research endeavors to bring to light the unexpected ways in which milk may not only do a body good but may also have unforeseen ties to nocturnal mischief. While the connection between milk consumption and burglaries may remain enigmatic, our investigation strives to shed light on this bovine-ly bizarre phenomena and its potential ramifications.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology employed in this study involved a multidimensional approach to the collection and analysis of data pertaining to milk consumption and burglary rates in Michigan. The data utilized in this investigation was acquired primarily from the United States Department of Agriculture (USDA) and the FBI Criminal Justice Information Services. These data sources provided comprehensive and reliable information spanning the years 1990 to 2021, enabling a robust examination of the relationship between milk consumption and burglaries.

To initiate the data collection process, various parameters were established to capture the nuances of milk consumption and burglary rates. The consumption of milk was quantified in gallons per capita, encompassing a wide array of dairy products including whole milk, skim milk, and flavored milk variants. Additionally, the frequency and volume of milk purchases were considered to provide a comprehensive understanding of milk consumption patterns.

In parallel, burglary rates were delineated through the aggregation of reported incidents, categorizing them based on severity and geographical distribution across Michigan. The selection of this temporal and spatial scope aimed to encapsulate the dynamic interplay between milk consumption and burglary rates over a significant period, allowing for a thorough examination of their association.

Statistical analyses were then conducted on the amassed data, employing correlation coefficients and regression models to elucidate the nature and strength of the relationship between milk consumption and burglary rates. Furthermore, control variables such as demographic factors, economic indicators, and seasonal variations were incorporated into the analyses to mitigate potential confounding effects and enhance the robustness of the findings.

It is worth noting that the utilization of unconventional and peculiar variables in statistical analyses demands a meticulous consideration of data quality and representativeness. As such, rigorous data validation and cleansing processes were implemented to ensure the integrity of the results and minimize the impact of outliers or discrepancies.

Moreover, due to the unorthodox nature of the research subject, the methodology encompassed an exploratory phase wherein potential mechanisms underlying the observed relationship were hypothesized and evaluated. This unconventional approach necessitated a degree of creativity and open-mindedness, steering the investigation towards uncharted analytical territories in pursuit of elucidating the enigmatic connection between milk consumption and burglaries.

In summary, the methodology adopted in this study amalgamated traditional quantitative analyses with an astute recognition of the idiosyncrasies inherent in investigating the intersection of milk consumption and burglaries. The robustness of the findings relies on the careful curation and examination of data, fostering an environment conducive to uncovering the unexpected and thought-provoking interplay between these seemingly disparate variables.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the 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 Milk consumption and Burglaries in Michigan. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 1990 to 2021, you found a correlation 0.9678454, r-squared of 0.9367247, 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]]
Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan

[[ABSTRACT]]
This research examines the curious association between milk consumption and burglary rates in the state of Michigan. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, a striking correlation coefficient of 0.9678454 and p < 0.01 was revealed. Despite the seemingly unrelated nature of these variables, our findings suggest a robust relationship that begs for further investigation. This paper presents an enlightening analysis of this unexpected phenomenon, shedding light on the unexpected ways in which milk and mischief may intertwine.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Milk consumption and burglaries are two topics that typically don't rub elbows in the scholarly arena. One conjures images of wholesome breakfasts and mustaches adorned with white droplets, while the other invokes thoughts of stealth, capers, and hooded figures skulking in the night. However, as the saying goes, truth is stranger than fiction. In the realm of statistical analysis, it is often the unexpected connections that provide the most intriguing results. This study delves into the correlation between the consumption of milk and the occurrence of burglaries in the state of Michigan, unearthing an udderly captivating relationship that defies conventional wisdom.
The initial impetus for this investigation stemmed from the arrival of a particularly sharp-eyed data analyst who quipped, "Would you believe me if I told you there might be a link between cow juice and criminal activity?" Such seemingly preposterous musings piqued our curiosity and led to an in-depth exploration of the numbers. To our amazement, preliminary analysis revealed a striking correlation coefficient of 0.9678454, accompanied by a p-value of less than 0.01. Such compelling statistical indicators left us with no choice but to embark on an academic escapade into this unforeseen nexus of dairy and delinquency.
As amusing as the notion may seem at first glance, the implications of such a relationship are not to be dismissed lightly. If substantiated, this association could have far-reaching consequences for public health, law enforcement, and dairy aficionados alike. The implications may be as far-reaching as they are unexpected, and thus warrant a diligent investigation.
The remainder of this paper is organized as follows: Section 2 provides a detailed review of the existing literature on both milk consumption and crime rates, highlighting the surprising lack of prior research on their confluence. Section 3 outlines the methodology employed in the collection and analysis of the empirical data, while Section 4 presents the results of our rigorous statistical examination. Section 5 offers a discussion of the implications of our findings and suggestions for future research. Finally, Section 6 concludes with a summary of our key insights, reflecting on the potential broader implications of these findings.
In light of the initial surprising correlation, this research endeavors to bring to light the unexpected ways in which milk may not only do a body good but may also have unforeseen ties to nocturnal mischief. While the connection between milk consumption and burglaries may remain enigmatic, our investigation strives to shed light on this bovine-ly bizarre phenomena and its potential ramifications.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the data unearthed a remarkably strong correlation between milk consumption and burglary rates in the state of Michigan for the period spanning 1990 to 2021. The correlation coefficient of 0.9678454 indicates a near-perfect positive relationship, while the r-squared value of 0.9367247 underscores the robustness of this association. Additionally, the p-value of less than 0.01 further supports the significance of this relationship, leaving little room to chalk the findings up to mere happenstance.

Figure 1 illustrates the stark correlation between milk consumption and burglary rates, showcasing a pattern that is as undeniable as it is unexpected. The scatterplot leaves little room for doubt, depicting a near-linear relationship that charts the curious dance between these seemingly unrelated variables. It is as if the burglars were leaving a trail of milk droplets behind them – a criminal caboodle, if you will.

Upon further reflection, this peculiar correlation prompts one to consider whether there may be a "cereal" connection between dairy intake and nocturnal pilfering. Could it be that milk does indeed "do a body good," but perhaps not in the way previously thought? The implications of this correlation extend beyond mere statistical intrigue and beg for a deeper understanding of the potential mechanisms underlying this unexpected relationship.

In conclusion, the findings of this study reveal a striking correlation between milk consumption and burglary rates in Michigan, challenging conventional wisdom and paving the way for further investigation into the surprise interplay between these seemingly disparate domains. The implications of this connection may be as extensive as they are unanticipated, opening the door to an array of pun-tential interpretations and applications in both the realms of public health and law enforcement.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Milk consumption and Burglaries in Michigan. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan

[[ABSTRACT]]
This research examines the curious association between milk consumption and burglary rates in the state of Michigan. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, a striking correlation coefficient of 0.9678454 and p < 0.01 was revealed. Despite the seemingly unrelated nature of these variables, our findings suggest a robust relationship that begs for further investigation. This paper presents an enlightening analysis of this unexpected phenomenon, shedding light on the unexpected ways in which milk and mischief may intertwine.

[[LITERATURE REVIEW]]
In "Doe et al.," the authors find that milk consumption has been extensively studied in relation to dietary habits, calcium intake, and bone health, but surprisingly, little attention has been paid to its potential connection to criminal behavior. Meanwhile, "Smith and Jones" delve into the complex dynamics of burglary rates in urban environments, focusing on socioeconomic factors, policing strategies, and community engagement, with nary a mention of dairy products or lactose-related anomalies.
Turning to non-fiction works, "Got Milk? The Complexities of Milk Consumption in the 21st Century" and "Burglaries Unveiled: Examining the Underground World of Break-Ins" provide valuable insights into our topic of interest. These empirical studies offer nuanced perspectives on the multifaceted nature of milk consumption and the intricate web of motivations behind residential intrusions.
Expanding the lens to fiction literature, the works of Agatha Christie, renowned for her mysteries, and dairy-themed novels such as "The Milkman Cometh" and "The Maltese Cow" prompt a whimsical yet surprisingly relevant exploration of the potential intertwining of milk chug-a-lug and burglary huggerie.
In a departure from traditional scholarly sources, anecdotal evidence gleaned from social media platforms reveals intriguing musings such as "Got milk? More like got mischief!" and "I've never trusted a lactose enthusiast in a dark alley." While not empirically grounded, these online commentaries provide a lighthearted backdrop to the unexpectedly entangled realms of moo juice and illicit activities.

[[RESULTS]]
The analysis of the data unearthed a remarkably strong correlation between milk consumption and burglary rates in the state of Michigan for the period spanning 1990 to 2021. The correlation coefficient of 0.9678454 indicates a near-perfect positive relationship, while the r-squared value of 0.9367247 underscores the robustness of this association. Additionally, the p-value of less than 0.01 further supports the significance of this relationship, leaving little room to chalk the findings up to mere happenstance.
Figure 1 illustrates the stark correlation between milk consumption and burglary rates, showcasing a pattern that is as undeniable as it is unexpected. The scatterplot leaves little room for doubt, depicting a near-linear relationship that charts the curious dance between these seemingly unrelated variables. It is as if the burglars were leaving a trail of milk droplets behind them – a criminal caboodle, if you will.
Upon further reflection, this peculiar correlation prompts one to consider whether there may be a "cereal" connection between dairy intake and nocturnal pilfering. Could it be that milk does indeed "do a body good," but perhaps not in the way previously thought? The implications of this correlation extend beyond mere statistical intrigue and beg for a deeper understanding of the potential mechanisms underlying this unexpected relationship.
In conclusion, the findings of this study reveal a striking correlation between milk consumption and burglary rates in Michigan, challenging conventional wisdom and paving the way for further investigation into the surprise interplay between these seemingly disparate domains. The implications of this connection may be as extensive as they are unanticipated, opening the door to an array of pun-tential interpretations and applications in both the realms of public health and law enforcement.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study yield an intriguing revelation: there exists a substantial correlation between milk consumption and burglary rates in the state of Michigan. Despite the initial levity that may accompany the unexpected linkage of these variables, the statistical robustness of the relationship demands serious consideration. The near-perfect positive correlation coefficient of 0.9678454 lends substantive support to the notion that the udderly curious connection between milk chug-a-lug and burglary huggerie is not to be dismissed lightly.

The support provided by prior research, both scholarly and literary, is worth noting. The absence of attention to the potential relationship between milk consumption and criminal behavior in traditional dietary and criminological studies appears, in hindsight, as a glaring oversight. The unexpected synergy evidenced in this study resonates with the musings of social media commentaries, offering a playful yet relevant backdrop to the surprisingly intertwined domains of milk and mischief.

The statistical evidence presented in this investigation aligns with and reinforces the quirky yet seemingly substantive implications suggested in the unconventional literary sources highlighted in the review. The stark findings of a near-linear relationship, akin to a criminal caboodle, epitomize the unexpected interplay between these seemingly incongruent variables.

Indeed, the implications of this correlation extend beyond mere statistical intrigue. One cannot help but ponder whether there is, in fact, a "cereal" connection between dairy intake and nocturnal pilfering. Could it be that milk does indeed "do a body good," but perhaps not in the way previously endorsed by health campaigns? These findings challenge conventional wisdom and raise pressing questions about the potential mechanisms underlying this unexpected relationship.

While these findings would undoubtedly elicit a wry smile from the casual observer, they open the door to an array of pun-tential interpretations. The whimsical and unanticipated implications of this connection signal the need for further multidisciplinary investigation to untangle the moo-tivations behind this remarkable correlation.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Milk consumption and Burglaries in Michigan. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan

[[ABSTRACT]]
This research examines the curious association between milk consumption and burglary rates in the state of Michigan. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, a striking correlation coefficient of 0.9678454 and p < 0.01 was revealed. Despite the seemingly unrelated nature of these variables, our findings suggest a robust relationship that begs for further investigation. This paper presents an enlightening analysis of this unexpected phenomenon, shedding light on the unexpected ways in which milk and mischief may intertwine.

[[INTRDUCTION]]
Milk consumption and burglaries are two topics that typically don't rub elbows in the scholarly arena. One conjures images of wholesome breakfasts and mustaches adorned with white droplets, while the other invokes thoughts of stealth, capers, and hooded figures skulking in the night. However, as the saying goes, truth is stranger than fiction. In the realm of statistical analysis, it is often the unexpected connections that provide the most intriguing results. This study delves into the correlation between the consumption of milk and the occurrence of burglaries in the state of Michigan, unearthing an udderly captivating relationship that defies conventional wisdom.
The initial impetus for this investigation stemmed from the arrival of a particularly sharp-eyed data analyst who quipped, "Would you believe me if I told you there might be a link between cow juice and criminal activity?" Such seemingly preposterous musings piqued our curiosity and led to an in-depth exploration of the numbers. To our amazement, preliminary analysis revealed a striking correlation coefficient of 0.9678454, accompanied by a p-value of less than 0.01. Such compelling statistical indicators left us with no choice but to embark on an academic escapade into this unforeseen nexus of dairy and delinquency.
As amusing as the notion may seem at first glance, the implications of such a relationship are not to be dismissed lightly. If substantiated, this association could have far-reaching consequences for public health, law enforcement, and dairy aficionados alike. The implications may be as far-reaching as they are unexpected, and thus warrant a diligent investigation.
The remainder of this paper is organized as follows: Section 2 provides a detailed review of the existing literature on both milk consumption and crime rates, highlighting the surprising lack of prior research on their confluence. Section 3 outlines the methodology employed in the collection and analysis of the empirical data, while Section 4 presents the results of our rigorous statistical examination. Section 5 offers a discussion of the implications of our findings and suggestions for future research. Finally, Section 6 concludes with a summary of our key insights, reflecting on the potential broader implications of these findings.
In light of the initial surprising correlation, this research endeavors to bring to light the unexpected ways in which milk may not only do a body good but may also have unforeseen ties to nocturnal mischief. While the connection between milk consumption and burglaries may remain enigmatic, our investigation strives to shed light on this bovine-ly bizarre phenomena and its potential ramifications.

[[RESULTS]]
The analysis of the data unearthed a remarkably strong correlation between milk consumption and burglary rates in the state of Michigan for the period spanning 1990 to 2021. The correlation coefficient of 0.9678454 indicates a near-perfect positive relationship, while the r-squared value of 0.9367247 underscores the robustness of this association. Additionally, the p-value of less than 0.01 further supports the significance of this relationship, leaving little room to chalk the findings up to mere happenstance.
Figure 1 illustrates the stark correlation between milk consumption and burglary rates, showcasing a pattern that is as undeniable as it is unexpected. The scatterplot leaves little room for doubt, depicting a near-linear relationship that charts the curious dance between these seemingly unrelated variables. It is as if the burglars were leaving a trail of milk droplets behind them – a criminal caboodle, if you will.
Upon further reflection, this peculiar correlation prompts one to consider whether there may be a "cereal" connection between dairy intake and nocturnal pilfering. Could it be that milk does indeed "do a body good," but perhaps not in the way previously thought? The implications of this correlation extend beyond mere statistical intrigue and beg for a deeper understanding of the potential mechanisms underlying this unexpected relationship.
In conclusion, the findings of this study reveal a striking correlation between milk consumption and burglary rates in Michigan, challenging conventional wisdom and paving the way for further investigation into the surprise interplay between these seemingly disparate domains. The implications of this connection may be as extensive as they are unanticipated, opening the door to an array of pun-tential interpretations and applications in both the realms of public health and law enforcement.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In the words of Shakespeare, "The findings of this study may seem like much ado about milk and mischief, but the statistical constancy of the correlation between milk consumption and burglary rates suggests otherwise." Our results have revealed a compelling association, leaving us with more than just a "leg" to stand on in support of this unlikely relationship. While the practical implications may seem as slippery as spilled milk, the statistical evidence cannot be curdled.

Considering the wealth of speculation that could "spill forth" from these findings, it is tempting to embark on a whole "dairy" of further research. However, it appears that our current study has milked this correlation for all it's worth – to churn out more investigations into this astonishing nexus would be akin to crying over spilled...milk. Therefore, it is with great solemnity and a hint of lactose intolerance that we declare: no more research is needed in the exhilarating field of milk and burglary correlations.

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 Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Dairy Dynamics

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 Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Dairy Delights and Crime Correlations

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 Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan with an abstract of This research examines the curious association between milk consumption and burglary rates in the state of Michigan. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, a striking correlation coefficient of 0.9678454 and p < 0.01 was revealed. Despite the seemingly unrelated nature of these variables, our findings suggest a robust relationship that begs for further investigation. This paper presents an enlightening analysis of this unexpected phenomenon, shedding light on the unexpected ways in which milk and mischief may intertwine.

ChatGPT:

Michigan, milk consumption, burglary rates, USDA data, FBI Criminal Justice Information Services, correlation coefficient, surprising relationship, unexpected phenomenon

*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

Milk consumption
Detailed data title: Per capita consumption of Fluid beverage milk in the US
Source: USDA
See what else correlates with Milk consumption

Burglaries in Michigan
Detailed data title: The burglary rate per 100,000 residents in Michigan
Source: FBI Criminal Justice Information Services
See what else correlates with Burglaries in Michigan

Correlation r = 0.9678454 (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 = 0.9367247 (Coefficient of determination)
This means 93.7% of the change in the one variable (i.e., Burglaries in Michigan) is predictable based on the change in the other (i.e., Milk consumption) over the 32 years from 1990 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.6E-19.^Show 0.0000000000000000001554391083
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.97 in 1.6E-17% of random cases. Said differently, if you correlated 6,433,387,394,824,626,176 random variables^Note You don't actually need 6 quintillion 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 31 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 31 because we have two variables measured over a period of 32 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.

[ 0.93, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Milk consumption (Pounds per person)	220	218	215	210	208	205	205	201	198	197	196	192	191	188	185	185	185	183	181	181	177	173	169	164	158	155	153	149	145	141	141	134
Burglaries in Michigan (Burglary rate)	1143.3	1186.2	1041.2	982.7	967.2	909.7	895.4	825.9	837.8	778	702.2	719.9	706.6	677.6	635.7	698.2	755.9	747.4	747.6	762.8	752.7	706.3	663.4	568.3	447	407.1	400	359.2	318.8	286.2	233.1	205.8

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([220,218,215,210,208,205,205,201,198,197,196,192,191,188,185,185,185,183,181,181,177,173,169,164,158,155,153,149,145,141,141,134,])
array_2 = np.array([1143.3,1186.2,1041.2,982.7,967.2,909.7,895.4,825.9,837.8,778,702.2,719.9,706.6,677.6,635.7,698.2,755.9,747.4,747.6,762.8,752.7,706.3,663.4,568.3,447,407.1,400,359.2,318.8,286.2,233.1,205.8,])
array_1_name = "Milk consumption"
array_2_name = "Burglaries in Michigan"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Milk consumption
Line chart for only Burglaries in Michigan
AI-generated correlation image
The spurious research paper: Milk Chug-A-Lug and Burglary Huggerie: An Udderly Surprising Connection in Michigan

View another random correlation

How fun was this correlation?

Big thanks for reviewing!

Correlation ID: 2793 · Black Variable ID: 554 · Red Variable ID: 20099


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