Spurious correlation #1,675 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Cottage cheese consumption and the second variable is Motor vehicle thefts in Maryland. 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 Cottage cheese consumption and the second variable is Motor vehicle thefts in Maryland. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Cottage cheese consumption curdled, it led to a wheely gouda situation for car owners in Maryland. It may sound cheesy, but as people cut back on Cottage cheese, they found themselves whey less inclined to take a break from their illegal activities. It's udderly ridiculous, but it seems that the lack of Cottage cheese just didn't drive thieves to steal cars as much. The connection may seem far-feta-ched, but it's as gouda as it gets! Remember, it's all fun and games until someone steals your cheddar!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a serene scene in the world of Skyrim, where a character is shown enjoying a snack of cottage cheese while seated inside a car. Meanwhile, in the background, visualize a thief in the act of trying to break into another car parked nearby. The overall image should encapsulate the juxtaposition of calm and chaos in the fantasy universe of Skyrim. 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: Cottage cheese consumption and Motor vehicle thefts in Maryland. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Woodblock painting Steampunk A scene from Skyrim Whimsical illustration Photorealism
ChatGPT: A scene from Skyrim

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 Cottage cheese consumption and Motor vehicle thefts in Maryland together. Keep the description simple.
ChatGPT: A person enjoying a snack of cottage cheese while sitting in their car. In the background, a thief is trying to break into another car parked nearby.

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 scene from Skyrim ] and depicting this scene: A person enjoying a snack of cottage cheese while sitting in their car. In the background, a thief is trying to break into another car parked nearby. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a serene scene in the world of Skyrim, where a character is shown enjoying a snack of cottage cheese while seated inside a car. Meanwhile, in the background, visualize a thief in the act of trying to break into another car parked nearby. The overall image should encapsulate the juxtaposition of calm and chaos in the fantasy universe of Skyrim.

*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 Cottage cheese consumption caused Motor vehicle thefts in Maryland to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland

The Journal of Dairy Deviancy

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 Cottage cheese consumption and Motor vehicle thefts in Maryland. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 name some cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland

[[ABSTRACT]]
Abstract:
This study delves into the curiously whimsical connection between cottage cheese consumption and motor vehicle thefts in the state of Maryland. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, we embarked on a scholarly journey to unravel the wheyward relationship between these seemingly unrelated phenomena. Leveraging correlation analysis, we observed a surprisingly robust correlation coefficient of 0.9106428, with a statistically significant p-value of less than 0.01.

Our findings, though potentially cheesy, shed light on a striking association worthy of further investigation. We speculate that the compelling relationship may stem from the interactions of certain bioactive compounds in cottage cheese with neuronal pathways, affecting impulse control and risk-taking behavior. Furthermore, the inherently crumbly texture of cottage cheese may serve as a metaphor for the fragility of social order, provoking diversions towards vehicular misdeeds.

In conclusion, while our study provides intriguing insights into the unexplored realms of dairy delinquency, it also beckons additional scrutiny into the mechanisms underpinning this phenomenon. Remember folks, when it comes to statistical analysis and dairy products, there’s no whey around it!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The connection between dairy consumption and criminal behavior has long been a topic of fascination, and perhaps a cheesily intriguing one at that. Amidst this curdled landscape of academic inquiry, our study seeks to unravel the wheyward relationship between a most unexpected pair: cottage cheese consumption and motor vehicle thefts in the state of Maryland. It’s a research topic that might make one say, "Hey, that's gouda be interesting!"
As researchers, we often tread unexplored paths, venturing into the unknown, much like a brave soul trying a new cheese for the first time. In this study, we utilized data from the USDA and FBI Criminal Justice Information Services spanning over three decades, with the aim of enlightening the scientific community on this rather unconventional connection. One might say we delved into this study with a healthy dose of curiosity and a side of cracker-ness.
Our investigation revealed a surprisingly robust correlation coefficient of 0.9106428 between cottage cheese consumption and motor vehicle thefts in Maryland, with a statistically significant p-value of less than 0.01. One might even say it was a case of "grate minds think alike."
The findings, though perhaps a bit cheesy, raise fundamental questions about the potential influence of dairy products on criminal behavior, prompting further reflection and investigation. As we delve deeper into the enigmatic realms of cottage cheese and crime, we invite you to join us on this intellectually enriching, yet unexpectedly whimsical, journey. After all, in the immortal words of Shakespeare, "To brie or not to brie, that is the question."

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

A thorough analysis of existing literature reveals a paucity of research examining the relationship between cottage cheese consumption and motor vehicle thefts. However, Smith et al. (2010) and Doe et al. (2015) have explored the broader association between dairy consumption and criminal behavior, hinting at the potential for unexpected linkages waiting to be unraveled. Despite the serious tone of these works, one can almost hear the faint sound of a dairy cow's "moo" in the background, beckoning towards the whimsical nature of our own inquiry.

In "The Dairy Dilemma" by Jones (2018), the author delves into the societal implications of dairy consumption, offering a philosophical exploration of the moral and ethical dimensions of dairy-related choices. While the book does not explicitly delve into criminal behavior, it provokes contemplation about the hidden complexities of dairy products – a fitting precursor to our own investigation into the unforeseen connection between cottage cheese and vehicular misdeeds.

Moving into the realm of literature less conventionally related to criminology and dairy products, we encounter "The Swiss Miss Mystery" by A. Author (2005), a captivating detective novel set in the idyllic Swiss countryside. While the novel's title may suggest a more direct link to dairy products, the intricacies of solving a mystery may provide valuable insights into the nature of our own scholarly pursuit – for what is academic research if not a quest to unravel mysteries?

"Cheddar and the Case of the Missing Wheels" is a children's book by A. Nother (2012) that follows the adventures of a mischievous mouse named Cheddar as he solves comically daring crimes in a bustling city. While the book may be aimed at young readers, the clever ventures of its cheese-loving protagonist serve as a gentle reminder that the pursuit of knowledge can take delightfully unexpected forms – much like our own investigation.

The popular animated series "SpongeBob SquarePants" features an episode where SpongeBob's pet snail, Gary, develops a penchant for sneaking away with the town's fleet of miniature boats. While the show's overt absurdity may seem disconnected from scholarly endeavors, its exploration of unexpected behavior in marine creatures presents a humorous parallel to our own quest to comprehend the unlikely correlation between cottage cheese consumption and motor vehicle thefts.

In sum, the literature review showcases both the dearth of prior investigation into our research topic and the potential for unexpected insights from sources beyond the traditional realms of criminology and sociology. As we journey through the cheesy realm of cottage cheese and criminal behavior, we are reminded to embrace the unexpected and seek wisdom in the most improbable of places. Remember, in the pursuit of knowledge, there's always room for a slice of humor.

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 Cottage cheese consumption and Motor vehicle thefts in Maryland. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland

[[ABSTRACT]]
Abstract:
This study delves into the curiously whimsical connection between cottage cheese consumption and motor vehicle thefts in the state of Maryland. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, we embarked on a scholarly journey to unravel the wheyward relationship between these seemingly unrelated phenomena. Leveraging correlation analysis, we observed a surprisingly robust correlation coefficient of 0.9106428, with a statistically significant p-value of less than 0.01.

Our findings, though potentially cheesy, shed light on a striking association worthy of further investigation. We speculate that the compelling relationship may stem from the interactions of certain bioactive compounds in cottage cheese with neuronal pathways, affecting impulse control and risk-taking behavior. Furthermore, the inherently crumbly texture of cottage cheese may serve as a metaphor for the fragility of social order, provoking diversions towards vehicular misdeeds.

In conclusion, while our study provides intriguing insights into the unexplored realms of dairy delinquency, it also beckons additional scrutiny into the mechanisms underpinning this phenomenon. Remember folks, when it comes to statistical analysis and dairy products, there’s no whey around it!

[[INTRODUCTION]]
The connection between dairy consumption and criminal behavior has long been a topic of fascination, and perhaps a cheesily intriguing one at that. Amidst this curdled landscape of academic inquiry, our study seeks to unravel the wheyward relationship between a most unexpected pair: cottage cheese consumption and motor vehicle thefts in the state of Maryland. It’s a research topic that might make one say, "Hey, that's gouda be interesting!"
As researchers, we often tread unexplored paths, venturing into the unknown, much like a brave soul trying a new cheese for the first time. In this study, we utilized data from the USDA and FBI Criminal Justice Information Services spanning over three decades, with the aim of enlightening the scientific community on this rather unconventional connection. One might say we delved into this study with a healthy dose of curiosity and a side of cracker-ness.
Our investigation revealed a surprisingly robust correlation coefficient of 0.9106428 between cottage cheese consumption and motor vehicle thefts in Maryland, with a statistically significant p-value of less than 0.01. One might even say it was a case of "grate minds think alike."
The findings, though perhaps a bit cheesy, raise fundamental questions about the potential influence of dairy products on criminal behavior, prompting further reflection and investigation. As we delve deeper into the enigmatic realms of cottage cheese and crime, we invite you to join us on this intellectually enriching, yet unexpectedly whimsical, journey. After all, in the immortal words of Shakespeare, "To brie or not to brie, that is the question."

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The data collection process spanned the years 1990 to 2021 and primarily utilized information from the USDA and FBI Criminal Justice Information Services. This involved aggregating data on cottage cheese consumption, motor vehicle thefts, and relevant demographic and socioeconomic variables in Maryland. A comprehensive search of online databases and repositories was conducted to collate these disparate datasets, akin to skilled dairy farmers gathering their varied cheeses for a sumptuous spread.

To measure cottage cheese consumption, per capita consumption figures were obtained from the USDA, encompassing retail sales, foodservice usage, and institutional consumption. These figures were subsequently standardized to account for population growth and fluctuations, akin to crafting the perfect blend of cheese in a fondue. The motor vehicle theft data were sourced from the FBI Criminal Justice Information Services, capturing reported thefts in the state of Maryland. Additionally, demographic and socioeconomic variables, such as income levels, unemployment rates, and education attainment, were incorporated to control for potential confounding factors, not unlike carefully selecting the ideal accompaniments to complement the cheeseboard.

Following data collection, the statistical analyses embraced a brie-dth of methods to unravel the connection between cottage cheese consumption and motor vehicle thefts. The initial step entailed conducting correlation analysis to examine the bountiful relationship between the two variables. This involved computing Pearson correlation coefficients, accompanied by a careful consideration of the appropriate covariance structures to ensure the findings remained as unprocessed as a fresh block of Cheddar.

To further elucidate the potential mechanisms underlying this unexpected relationship, a series of multivariate regression models were fitted. These models accounted for demographic and socioeconomic variables, as well as temporal trends, in order to parse out the distinct influence of cottage cheese consumption on motor vehicle thefts. The models were then subjected to a battery of diagnostic tests and sensitivity analyses, not unlike subjecting a cheese to various taste tests to discern its subtle nuances.

Additionally, time series analysis was employed to discern temporal patterns and potential long-term trends in both cottage cheese consumption and motor vehicle thefts. This involved employing sophisticated algorithms to identify seasonality, trend, and other temporal components, akin to aging a fine cheese to perfection.

Finally, the findings were interpreted within the broader context of criminological theories and nutritional science, blending disparate disciplines much like the harmonious marriage of tasty cheeses and delectable wine. As with any rigorous scientific inquiry, the analyses were conducted with due diligence and skepticism, mindful of the adage that "the proof of the cheese is in the eating."

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 Cottage cheese consumption and Motor vehicle thefts in Maryland. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland

[[ABSTRACT]]
Abstract:
This study delves into the curiously whimsical connection between cottage cheese consumption and motor vehicle thefts in the state of Maryland. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, we embarked on a scholarly journey to unravel the wheyward relationship between these seemingly unrelated phenomena. Leveraging correlation analysis, we observed a surprisingly robust correlation coefficient of 0.9106428, with a statistically significant p-value of less than 0.01.

Our findings, though potentially cheesy, shed light on a striking association worthy of further investigation. We speculate that the compelling relationship may stem from the interactions of certain bioactive compounds in cottage cheese with neuronal pathways, affecting impulse control and risk-taking behavior. Furthermore, the inherently crumbly texture of cottage cheese may serve as a metaphor for the fragility of social order, provoking diversions towards vehicular misdeeds.

In conclusion, while our study provides intriguing insights into the unexplored realms of dairy delinquency, it also beckons additional scrutiny into the mechanisms underpinning this phenomenon. Remember folks, when it comes to statistical analysis and dairy products, there’s no whey around it!

[[LITERATURE REVIEW]]
A thorough analysis of existing literature reveals a paucity of research examining the relationship between cottage cheese consumption and motor vehicle thefts. However, Smith et al. (2010) and Doe et al. (2015) have explored the broader association between dairy consumption and criminal behavior, hinting at the potential for unexpected linkages waiting to be unraveled. Despite the serious tone of these works, one can almost hear the faint sound of a dairy cow's "moo" in the background, beckoning towards the whimsical nature of our own inquiry.
In "The Dairy Dilemma" by Jones (2018), the author delves into the societal implications of dairy consumption, offering a philosophical exploration of the moral and ethical dimensions of dairy-related choices. While the book does not explicitly delve into criminal behavior, it provokes contemplation about the hidden complexities of dairy products – a fitting precursor to our own investigation into the unforeseen connection between cottage cheese and vehicular misdeeds.
Moving into the realm of literature less conventionally related to criminology and dairy products, we encounter "The Swiss Miss Mystery" by A. Author (2005), a captivating detective novel set in the idyllic Swiss countryside. While the novel's title may suggest a more direct link to dairy products, the intricacies of solving a mystery may provide valuable insights into the nature of our own scholarly pursuit – for what is academic research if not a quest to unravel mysteries?
"Cheddar and the Case of the Missing Wheels" is a children's book by A. Nother (2012) that follows the adventures of a mischievous mouse named Cheddar as he solves comically daring crimes in a bustling city. While the book may be aimed at young readers, the clever ventures of its cheese-loving protagonist serve as a gentle reminder that the pursuit of knowledge can take delightfully unexpected forms – much like our own investigation.
The popular animated series "SpongeBob SquarePants" features an episode where SpongeBob's pet snail, Gary, develops a penchant for sneaking away with the town's fleet of miniature boats. While the show's overt absurdity may seem disconnected from scholarly endeavors, its exploration of unexpected behavior in marine creatures presents a humorous parallel to our own quest to comprehend the unlikely correlation between cottage cheese consumption and motor vehicle thefts.
In sum, the literature review showcases both the dearth of prior investigation into our research topic and the potential for unexpected insights from sources beyond the traditional realms of criminology and sociology. As we journey through the cheesy realm of cottage cheese and criminal behavior, we are reminded to embrace the unexpected and seek wisdom in the most improbable of places. Remember, in the pursuit of knowledge, there's always room for a slice of humor.

[[RESULTS]]
The analysis of the relationship between cottage cheese consumption and motor vehicle thefts in Maryland yielded a striking correlation coefficient of 0.9106428, suggesting a remarkably strong positive association between these seemingly unrelated variables. This finding might prompt one to quip, "Well, it looks like there's whey more to cottage cheese than meets the eye!"
Furthermore, the r-squared value of 0.8292703 indicates that approximately 83% of the variation in motor vehicle thefts can be explained by variations in cottage cheese consumption. One might say this relationship is as Gouda as it gets!
The p-value of less than 0.01 provides strong evidence against the null hypothesis, supporting the notion that the observed correlation is statistically significant. It seems that when it comes to cottage cheese and crime, the evidence is as solid as a block of cheddar.
The scatterplot (Fig. 1) visually depicts the unmistakable upward trend between cottage cheese consumption and motor vehicle thefts, further reinforcing the robustness of the correlation. It's safe to say that this finding is as clear as Black Diamond cheese!
In summary, the results of this study not only affirm the unexpected correlation between cottage cheese consumption and motor vehicle thefts in Maryland but also highlight the need for further investigation into the potential mechanisms underlying this dairy-driven delinquency. It appears that when it comes to this curiously whimsical connection, the "whey of the future" is ripe for exploration!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study provide resounding support for the earlier work by Smith et al. (2010) and Doe et al. (2015), who hinted at the broader association between dairy consumption and criminal behavior. It appears that the dairy-driven delinquency we have uncovered is not simply a curd of curiosity, but a robust and intriguing pattern that warrants further attention. One might say that our findings are as sharp as a mature cheddar!

Furthermore, the unexpectedly strong correlation coefficient of 0.9106428 and the high explanatory power of approximately 83% reflected in the r-squared value underscore the substantive nature of the relationship between cottage cheese consumption and motor vehicle thefts. This goes to show that there is indeed "whey more" to cottage cheese than meets the eye – a pun even the most serious scholars can appreciate!

The statistically significant p-value of less than 0.01 provides compelling evidence against the null hypothesis, indicating that the observed correlation is highly unlikely to have occurred by chance. In other words, it seems that when it comes to this cheesy association, the evidence is "gouda nuff" for serious consideration!

Our findings shed light on the compelling relationship between cottage cheese consumption and motor vehicle thefts, prompting a deeper dive into the potential mechanisms that underpin this unlikely connection. It seems that the influence of cottage cheese on criminal behavior may not be just a "curd of events," but rather a manifestation of the influence of bioactive compounds on neuronal pathways, affecting impulse control and risk-taking behavior. This may seem like a stretch, but our results suggest that the cheese may not stand alone in shaping human behavior.

Ultimately, as we unravel the wheyward relationship between cottage cheese consumption and motor vehicle thefts, we are reminded that the pursuit of knowledge can take delightfully unexpected forms – much like our investigation. It is clear that when it comes to statistical analysis and dairy products, there's "no whey" around the potential for cheesy puns!

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 Cottage cheese consumption and Motor vehicle thefts in Maryland. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland

[[ABSTRACT]]
Abstract:
This study delves into the curiously whimsical connection between cottage cheese consumption and motor vehicle thefts in the state of Maryland. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, we embarked on a scholarly journey to unravel the wheyward relationship between these seemingly unrelated phenomena. Leveraging correlation analysis, we observed a surprisingly robust correlation coefficient of 0.9106428, with a statistically significant p-value of less than 0.01.

Our findings, though potentially cheesy, shed light on a striking association worthy of further investigation. We speculate that the compelling relationship may stem from the interactions of certain bioactive compounds in cottage cheese with neuronal pathways, affecting impulse control and risk-taking behavior. Furthermore, the inherently crumbly texture of cottage cheese may serve as a metaphor for the fragility of social order, provoking diversions towards vehicular misdeeds.

In conclusion, while our study provides intriguing insights into the unexplored realms of dairy delinquency, it also beckons additional scrutiny into the mechanisms underpinning this phenomenon. Remember folks, when it comes to statistical analysis and dairy products, there’s no whey around it!

[[INTRDUCTION]]
The connection between dairy consumption and criminal behavior has long been a topic of fascination, and perhaps a cheesily intriguing one at that. Amidst this curdled landscape of academic inquiry, our study seeks to unravel the wheyward relationship between a most unexpected pair: cottage cheese consumption and motor vehicle thefts in the state of Maryland. It’s a research topic that might make one say, "Hey, that's gouda be interesting!"
As researchers, we often tread unexplored paths, venturing into the unknown, much like a brave soul trying a new cheese for the first time. In this study, we utilized data from the USDA and FBI Criminal Justice Information Services spanning over three decades, with the aim of enlightening the scientific community on this rather unconventional connection. One might say we delved into this study with a healthy dose of curiosity and a side of cracker-ness.
Our investigation revealed a surprisingly robust correlation coefficient of 0.9106428 between cottage cheese consumption and motor vehicle thefts in Maryland, with a statistically significant p-value of less than 0.01. One might even say it was a case of "grate minds think alike."
The findings, though perhaps a bit cheesy, raise fundamental questions about the potential influence of dairy products on criminal behavior, prompting further reflection and investigation. As we delve deeper into the enigmatic realms of cottage cheese and crime, we invite you to join us on this intellectually enriching, yet unexpectedly whimsical, journey. After all, in the immortal words of Shakespeare, "To brie or not to brie, that is the question."

[[RESULTS]]
The analysis of the relationship between cottage cheese consumption and motor vehicle thefts in Maryland yielded a striking correlation coefficient of 0.9106428, suggesting a remarkably strong positive association between these seemingly unrelated variables. This finding might prompt one to quip, "Well, it looks like there's whey more to cottage cheese than meets the eye!"
Furthermore, the r-squared value of 0.8292703 indicates that approximately 83% of the variation in motor vehicle thefts can be explained by variations in cottage cheese consumption. One might say this relationship is as Gouda as it gets!
The p-value of less than 0.01 provides strong evidence against the null hypothesis, supporting the notion that the observed correlation is statistically significant. It seems that when it comes to cottage cheese and crime, the evidence is as solid as a block of cheddar.
The scatterplot (Fig. 1) visually depicts the unmistakable upward trend between cottage cheese consumption and motor vehicle thefts, further reinforcing the robustness of the correlation. It's safe to say that this finding is as clear as Black Diamond cheese!
In summary, the results of this study not only affirm the unexpected correlation between cottage cheese consumption and motor vehicle thefts in Maryland but also highlight the need for further investigation into the potential mechanisms underlying this dairy-driven delinquency. It appears that when it comes to this curiously whimsical connection, the "whey of the future" is ripe for exploration!

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has uncovered a fascinating correlation between cottage cheese consumption and motor vehicle thefts in Maryland. The strikingly robust association suggests that there may be more to this dairy product than meets the eye. One could say that when it comes to crime, cottage cheese has some whey of leaving a mark!

Furthermore, the statistically significant p-value and the high r-squared value support the validity of our findings, leaving little room for doubt about the strength of this connection. It's as if the evidence is as solid as a well-aged Parmigiano-Reggiano.

Our speculation about the potential influence of certain bioactive compounds in cottage cheese on neuronal pathways sheds light on the mechanisms underpinning this unexpected link. Perhaps there's more than just calcium and protein in that curdled goodness that's influencing behavior!

Despite the whimsical tone of our findings, the study underscores the need for further investigation into the intersection of dairy consumption and criminal behavior. Nevertheless, in the spirit of a good dad joke, one might say that when it comes to exploring the "wheys" of cottage cheese and crime, we have "matured" this topic quite well.

In light of these compelling results, it is safe to say that no more research is needed in this area. After all, we've already milked this topic for all it's worth!

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 Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Dairy Deviancy

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 Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland. Respond only with the name of a fictional organization.

ChatGPT:

Society for the Advancement of Dairy-Related Criminology

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 Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland with an abstract of Abstract:
This study delves into the curiously whimsical connection between cottage cheese consumption and motor vehicle thefts in the state of Maryland. Utilizing data from the USDA and FBI Criminal Justice Information Services spanning the years 1990 to 2021, we embarked on a scholarly journey to unravel the wheyward relationship between these seemingly unrelated phenomena. Leveraging correlation analysis, we observed a surprisingly robust correlation coefficient of 0.9106428, with a statistically significant p-value of less than 0.01.
Our findings, though potentially cheesy, shed light on a striking association worthy of further investigation. We speculate that the compelling relationship may stem from the interactions of certain bioactive compounds in cottage cheese with neuronal pathways, affecting impulse control and risk-taking behavior. Furthermore, the inherently crumbly texture of cottage cheese may serve as a metaphor for the fragility of social order, provoking diversions towards vehicular misdeeds.
In conclusion, while our study provides intriguing insights into the unexplored realms of dairy delinquency, it also beckons additional scrutiny into the mechanisms underpinning this phenomenon. Remember folks, when it comes to statistical analysis and dairy products, there’s no whey around it!

ChatGPT:

cottage cheese consumption, motor vehicle thefts, Maryland, USDA data, FBI Criminal Justice Information Services, correlation analysis, bioactive compounds, impulse control, risk-taking behavior, dairy delinquency, statistical analysis

*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

Cottage cheese consumption
Detailed data title: Per capita consumption of Cottage cheese in the US
Source: USDA
See what else correlates with Cottage cheese consumption

Motor vehicle thefts in Maryland
Detailed data title: The motor vehicle theft rate per 100,000 residents in Maryland
Source: FBI Criminal Justice Information Services
See what else correlates with Motor vehicle thefts in Maryland

Correlation r = 0.9106428 (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 = 0.8292703 (Coefficient of determination)
This means 82.9% of the change in the one variable (i.e., Motor vehicle thefts in Maryland) is predictable based on the change in the other (i.e., Cottage cheese consumption) over the 32 years from 1990 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.8E-13.^Show 0.0000000000004811682425445090
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.91 in 4.8E-11% of random cases. Said differently, if you correlated 2,078,275,146,988 random variables^Note You don't actually need 2 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 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.

[ 0.82, 0.96 ] 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
Cottage cheese consumption (Pounds per person)	3.3	3.2	3.1	2.9	2.8	2.7	2.6	2.6	2.6	2.6	2.6	2.6	2.6	2.6	2.7	2.7	2.6	2.6	2.3	2.4	2.3	2.3	2.3	2.1	2.1	2.1	2.2	2.1	2.1	2.1	2	1.9
Motor vehicle thefts in Maryland (Motor Vehicle Theft rate)	708.7	730.8	726.4	683.4	763	717.6	711.4	602	549.4	492	539.5	594.6	624.2	660.4	645.2	609.5	543.5	505.4	449.7	344.2	311.6	275.2	254.1	225.9	219.5	223.8	230.5	224.4	201.3	186.3	172.9	193.5

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([3.3,3.2,3.1,2.9,2.8,2.7,2.6,2.6,2.6,2.6,2.6,2.6,2.6,2.6,2.7,2.7,2.6,2.6,2.3,2.4,2.3,2.3,2.3,2.1,2.1,2.1,2.2,2.1,2.1,2.1,2,1.9,])
array_2 = np.array([708.7,730.8,726.4,683.4,763,717.6,711.4,602,549.4,492,539.5,594.6,624.2,660.4,645.2,609.5,543.5,505.4,449.7,344.2,311.6,275.2,254.1,225.9,219.5,223.8,230.5,224.4,201.3,186.3,172.9,193.5,])
array_1_name = "Cottage cheese consumption"
array_2_name = "Motor vehicle thefts in Maryland"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Cottage cheese consumption
Line chart for only Motor vehicle thefts in Maryland
AI-generated correlation image
The spurious research paper: Curdled Crime: Examining the Wheyward Relationship between Cottage Cheese Consumption and Motor Vehicle Thefts in Maryland

View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!

Correlation ID: 1675 · Black Variable ID: 556 · Red Variable ID: 20139


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