about · email me · subscribe
Spurious correlation #1,071 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the first name Marisa and the second variable is Robberies in Minnesota.  The chart goes from 1985 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Fewer Marisas meant fewer Marisa-tas, and without those delicious pastries, the temptation for theft just crumbled away. It was a dough-lightful win for law enforcement in Minnesota!

Model: dalle-3
Prompt: Generate an image that captures the lively streets of Minnesota, with Marisa's name prominently displayed on marquee boards in bright lights. Show bustling activity, with people excitedly talking and moving about. Additionally, depict grocery stores with bushels of tater tots being targeted by a sudden surge in robberies. Finally, include the scent of hotdish wafting through the state while locals scramble to secure their coveted tater tots. 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: Popularity of the first name Marisa and Robberies in Minnesota. 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: Cyber folk An image that looks like it is a scene from A Disney Movie Brutalism Surrealism A TIME magazine cover image
ChatGPT: A TIME magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Popularity of the first name Marisa and Robberies in Minnesota, in the following situation: Every time someone named Marisa became popular, it coincided with a spike in robberies in Minnesota. How is this possible, you ask? Well, it turns out that the mere mention of the name Marisa triggered a subconscious craving for hotdish in Minnesotans. This led to a statewide shortage of tater tots, which in turn, fueled a series of hangry robberies at local grocery stores. It seems that in Minnesota, when it comes to hotdish ingredients, desperate times call for desperate tater tots. . Keep the description simple.
ChatGPT: Picture the streets of Minnesota bustling with activity as news of the name Marisa's rising popularity spreads. Marquee boards display the name in bright lights while excited chatter fills the air. Concurrently, grocery stores with bushels of tater tots become the target of a sudden surge in robberies. Amidst the chaos, the scent of hotdish wafts through the state, as locals scramble to secure their coveted tater tots.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A TIME magazine cover image ] and depicting this scene: Picture the streets of Minnesota bustling with activity as news of the name Marisa's rising popularity spreads. Marquee boards display the name in bright lights while excited chatter fills the air. Concurrently, grocery stores with bushels of tater tots become the target of a sudden surge in robberies. Amidst the chaos, the scent of hotdish wafts through the state, as locals scramble to secure their coveted tater tots. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that captures the lively streets of Minnesota, with Marisa's name prominently displayed on marquee boards in bright lights. Show bustling activity, with people excitedly talking and moving about. Additionally, depict grocery stores with bushels of tater tots being targeted by a sudden surge in robberies. Finally, include the scent of hotdish wafting through the state while locals scramble to secure their coveted tater tots.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Popularity of the first name Marisa caused Robberies in Minnesota to decrease.

AI academic paper

(Because p < 0.01)
Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota

The Journal of Quirky Social Science

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Popularity of the first name Marisa and Robberies in Minnesota. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from US Social Security Administration and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.8870963 and p < 0.01 for 1985 to 2022.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota"

[[ABSTRACT]]
This paper explores the surprising correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota. Utilizing data from the US Social Security Administration and FBI Criminal Justice Information Services, a statistically significant correlation coefficient of 0.8870963 was identified for the period spanning 1985 to 2022, with a p-value of less than 0.01. The findings suggest that the rise and fall of Marisas may be more than just a matter of chance, as there appears to be a peculiar connection to the prevalence of robberies in the Land of 10,000 Lakes. The implications of this research open the door to questioning the influence of names on criminal behavior, prompting us to consider if the name Marisa is associated with more than just a penchant for pilfering.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Popularity of the first name Marisa and Robberies in Minnesota. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
"Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota"

[[ABSTRACT]]
This paper explores the surprising correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota. Utilizing data from the US Social Security Administration and FBI Criminal Justice Information Services, a statistically significant correlation coefficient of 0.8870963 was identified for the period spanning 1985 to 2022, with a p-value of less than 0.01. The findings suggest that the rise and fall of Marisas may be more than just a matter of chance, as there appears to be a peculiar connection to the prevalence of robberies in the Land of 10,000 Lakes. The implications of this research open the door to questioning the influence of names on criminal behavior, prompting us to consider if the name Marisa is associated with more than just a penchant for pilfering.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of statistical analysis and comedy does not come often; however, in the case of the correlation between the frequency of the name “Marisa” and instances of robberies in the state of Minnesota, a compelling case is made. This uncommon juxtaposition of seemingly unrelated phenomena has piqued the interest of researchers, statisticians, and stand-up comedians alike. In this study, we delve into the intriguing connection between the rise and fall of Marisas and the occurrence of robberies in the Land of 10,000 Lakes.

The choice of the first name Marisa, while seemingly arbitrary at first glance, lends itself well to this investigation due to its intriguing phonetic resemblance to the word “mischief.” It prompts one to wonder if there are more heists involving Marisas than one might expect. And what about the correlation with robberies in Minnesota? Is there perhaps an underground network of mischievous Marisas and their associates plotting capers throughout the state? We are here to shed light on these questions, as well as to explore whether there is more to the name "Marisa" than its popular connotations.

This study is not just a whimsical exercise in wordplay and puzzling correlations. It presents a robust statistical analysis that underscores the need to consider factors beyond traditional criminological indicators. Our findings suggest that there might indeed be a significant association between the prevalence of the name Marisa and the occurrence of robberies in Minnesota. This unexpected discovery challenges existing perceptions and expands the scope of factors considered in criminal behavior research.

In this paper, we present a comprehensive analysis of the data gathered from the US Social Security Administration and FBI Criminal Justice Information Services, spanning nearly four decades. Our statistical model yields a correlation coefficient of 0.8870963, with a p-value of less than 0.01, affirming the robustness of the observed association. While the correlation might seem humorous at first glance, the statistical rigor and significance of our findings warrant serious attention.

The implications of this research extend beyond mere statistical curiosity. Delving into the potential influence of names on criminal behavior prompts a reconsideration of the myriad factors that contribute to societal phenomena. As we wade through the mirthful mystique of Marisas and the enigma of Minnesotan robberies, we invite our readers to join us in pondering the profound questions that arise from this unlikely association.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Popularity of the first name Marisa and Robberies in Minnesota. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota"

[[ABSTRACT]]
This paper explores the surprising correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota. Utilizing data from the US Social Security Administration and FBI Criminal Justice Information Services, a statistically significant correlation coefficient of 0.8870963 was identified for the period spanning 1985 to 2022, with a p-value of less than 0.01. The findings suggest that the rise and fall of Marisas may be more than just a matter of chance, as there appears to be a peculiar connection to the prevalence of robberies in the Land of 10,000 Lakes. The implications of this research open the door to questioning the influence of names on criminal behavior, prompting us to consider if the name Marisa is associated with more than just a penchant for pilfering.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of statistical analysis and comedy does not come often; however, in the case of the correlation between the frequency of the name “Marisa” and instances of robberies in the state of Minnesota, a compelling case is made. This uncommon juxtaposition of seemingly unrelated phenomena has piqued the interest of researchers, statisticians, and stand-up comedians alike. In this study, we delve into the intriguing connection between the rise and fall of Marisas and the occurrence of robberies in the Land of 10,000 Lakes.
The choice of the first name Marisa, while seemingly arbitrary at first glance, lends itself well to this investigation due to its intriguing phonetic resemblance to the word “mischief.” It prompts one to wonder if there are more heists involving Marisas than one might expect. And what about the correlation with robberies in Minnesota? Is there perhaps an underground network of mischievous Marisas and their associates plotting capers throughout the state? We are here to shed light on these questions, as well as to explore whether there is more to the name "Marisa" than its popular connotations.
This study is not just a whimsical exercise in wordplay and puzzling correlations. It presents a robust statistical analysis that underscores the need to consider factors beyond traditional criminological indicators. Our findings suggest that there might indeed be a significant association between the prevalence of the name Marisa and the occurrence of robberies in Minnesota. This unexpected discovery challenges existing perceptions and expands the scope of factors considered in criminal behavior research.
In this paper, we present a comprehensive analysis of the data gathered from the US Social Security Administration and FBI Criminal Justice Information Services, spanning nearly four decades. Our statistical model yields a correlation coefficient of 0.8870963, with a p-value of less than 0.01, affirming the robustness of the observed association. While the correlation might seem humorous at first glance, the statistical rigor and significance of our findings warrant serious attention.
The implications of this research extend beyond mere statistical curiosity. Delving into the potential influence of names on criminal behavior prompts a reconsideration of the myriad factors that contribute to societal phenomena. As we wade through the mirthful mystique of Marisas and the enigma of Minnesotan robberies, we invite our readers to join us in pondering the profound questions that arise from this unlikely association.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The unusual correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota has prompted a plethora of research endeavors aimed at unraveling this intriguing association. Smith et al. (2015) conducted a study focusing on the cultural significance of names and their potential impact on criminal behavior, laying the groundwork for subsequent investigations into the enigmatic link between Marisas and robberies in the Land of 10,000 Lakes. Similarly, Doe (2018) postulated a theoretical framework proposing that phonetic alignment of names with certain words might subconsciously influence individuals toward behaviors associated with those words.

In "The Sociolinguistics of Names" by Jones (2009), the author delves into the complex interplay between names and societal perceptions, shedding light on the potential influence of names on behavioral patterns. This work provides valuable insights into the underlying mechanisms that could contribute to the curious correlation between the name Marisa and the prevalence of robberies in Minnesota.

On a lighter note, "The Great Marisa Caper" by Hill (2012) is a work of fiction centered around a daring heist masterminded by a wily character named Marisa, which, while not directly related to statistical analyses, paints an imaginative picture of the potential adventures that Marisas may embark upon. Additionally, "Marisa: Queen of Thieves" by Evans (2017) is a riveting tale of intrigue and cloak-and-dagger escapades, invoking elements of mystery and larceny associated with the name Marisa.

Furthermore, movies such as "Ocean's Marisa" and "Now You See Marisa, Now You Don't" offer whimsical portrayals of cunning maneuvers and heists, evoking the playful side of the correlation between Marisas and criminal activities. While these may not be direct sources of statistical evidence, they contribute to the broader cultural conversation surrounding the captivating connection between the name Marisa and the occurrence of robberies in Minnesota.

The interdisciplinary nature of this investigation necessitates the exploration of both scholarly and creative works to gain a comprehensive understanding of the complexities underlying the unexpected relationship between the name Marisa and criminal activities in the state of Minnesota. As we journey through the academic and literary landscape, the lighthearted and thought-provoking perspectives on this correlation provide a multi-faceted backdrop to our exploration of this peculiar phenomenon.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Popularity of the first name Marisa and Robberies in Minnesota. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from US Social Security Administration and FBI Criminal Justice Information Services . You used data from 1985 to 2022

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota"

[[ABSTRACT]]
This paper explores the surprising correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota. Utilizing data from the US Social Security Administration and FBI Criminal Justice Information Services, a statistically significant correlation coefficient of 0.8870963 was identified for the period spanning 1985 to 2022, with a p-value of less than 0.01. The findings suggest that the rise and fall of Marisas may be more than just a matter of chance, as there appears to be a peculiar connection to the prevalence of robberies in the Land of 10,000 Lakes. The implications of this research open the door to questioning the influence of names on criminal behavior, prompting us to consider if the name Marisa is associated with more than just a penchant for pilfering.

[[INTRODUCTION]]
The intersection of statistical analysis and comedy does not come often; however, in the case of the correlation between the frequency of the name “Marisa” and instances of robberies in the state of Minnesota, a compelling case is made. This uncommon juxtaposition of seemingly unrelated phenomena has piqued the interest of researchers, statisticians, and stand-up comedians alike. In this study, we delve into the intriguing connection between the rise and fall of Marisas and the occurrence of robberies in the Land of 10,000 Lakes.
The choice of the first name Marisa, while seemingly arbitrary at first glance, lends itself well to this investigation due to its intriguing phonetic resemblance to the word “mischief.” It prompts one to wonder if there are more heists involving Marisas than one might expect. And what about the correlation with robberies in Minnesota? Is there perhaps an underground network of mischievous Marisas and their associates plotting capers throughout the state? We are here to shed light on these questions, as well as to explore whether there is more to the name "Marisa" than its popular connotations.
This study is not just a whimsical exercise in wordplay and puzzling correlations. It presents a robust statistical analysis that underscores the need to consider factors beyond traditional criminological indicators. Our findings suggest that there might indeed be a significant association between the prevalence of the name Marisa and the occurrence of robberies in Minnesota. This unexpected discovery challenges existing perceptions and expands the scope of factors considered in criminal behavior research.
In this paper, we present a comprehensive analysis of the data gathered from the US Social Security Administration and FBI Criminal Justice Information Services, spanning nearly four decades. Our statistical model yields a correlation coefficient of 0.8870963, with a p-value of less than 0.01, affirming the robustness of the observed association. While the correlation might seem humorous at first glance, the statistical rigor and significance of our findings warrant serious attention.
The implications of this research extend beyond mere statistical curiosity. Delving into the potential influence of names on criminal behavior prompts a reconsideration of the myriad factors that contribute to societal phenomena. As we wade through the mirthful mystique of Marisas and the enigma of Minnesotan robberies, we invite our readers to join us in pondering the profound questions that arise from this unlikely association.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the curious connection between the popularity of the first name Marisa and the incidence of robberies in Minnesota, our research team embarked on a multifaceted methodological journey. The primary sources of data for this investigation were the US Social Security Administration’s records of first name occurrences and the FBI Criminal Justice Information Services’ reports on robberies in the state of Minnesota. The period under scrutiny encompassed the years 1985 to 2022, during which we meticulously examined the ebb and flow of Marisas and robberies alike.

The initial step in our methodology entailed the retrieval of the historical naming data from the US Social Security Administration, which catalogues the frequency of names given to newborns. After obtaining these records, we engaged in rigorous data processing procedures to aggregate and organize the counts of Marisas born each year. This involved meticulous attention to detail to ensure that no Marisa was inadvertently misclassified as a Maria or Mariângela, as the distinction between a Marisa and a Mariselma could be the difference between statistical significance and statistical insignificance.

Simultaneously, we delved into the labyrinth of crime statistics provided by the FBI Criminal Justice Information Services. To extract relevant information on robberies in Minnesota, we navigated through the digital repository with a Sherlockian determination, carefully selecting and tabulating data specific to the Land of 10,000 Lakes. Each reported robbery was scrutinized for any potential link to a Marisa, and any instances of Marisa-inspired larceny or capers were noted with a mix of amusement and scholarly attentiveness.

Having amassed the requisite data, we meticulously aligned the temporal sequences of Marisa prevalence and robbery occurrences, creating a bountiful dataset ripe for statistical analysis. Employing cutting-edge statistical software, we computed correlation coefficients and p-values with a fervor reminiscent of a detective cataloging clues in an Agatha Christie novel. Our statistical procedures were robust, accounting for seasonality, potential outliers, and autocorrelation to ensure the integrity of our analysis.

Furthermore, as an ancillary endeavor, we explored various demographic and socio-economic factors that could potentially confound the observed relationship. We scrutinized census data, employment statistics, and even factors such as climatic patterns in Minnesota, leaving no statistical stone unturned in our pursuit of understanding the curious confluence of Marisa and robbery.

Finally, after an exhaustive process of data collection, preparation, and analysis, we emerged with a statistically significant correlation coefficient of 0.8870963, attaining a p-value of less than 0.01. This momentous outcome, akin to discovering a hidden treasure at the end of a statistical scavenger hunt, provided compelling evidence of an unexpected association between the name Marisa and the perpetration of robberies in Minnesota. And thus, armed with data and statistical acumen, we stand ready to share our intriguing findings with the academic community and demonstrate the unanticipated humor and significance inherent in the intersection of Marisa and Minnesota robberies.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Popularity of the first name Marisa and Robberies in Minnesota. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 1985 to 2022, you found a correlation 0.8870963, r-squared of 0.7869399, 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]]
"Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota"

[[ABSTRACT]]
This paper explores the surprising correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota. Utilizing data from the US Social Security Administration and FBI Criminal Justice Information Services, a statistically significant correlation coefficient of 0.8870963 was identified for the period spanning 1985 to 2022, with a p-value of less than 0.01. The findings suggest that the rise and fall of Marisas may be more than just a matter of chance, as there appears to be a peculiar connection to the prevalence of robberies in the Land of 10,000 Lakes. The implications of this research open the door to questioning the influence of names on criminal behavior, prompting us to consider if the name Marisa is associated with more than just a penchant for pilfering.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of statistical analysis and comedy does not come often; however, in the case of the correlation between the frequency of the name “Marisa” and instances of robberies in the state of Minnesota, a compelling case is made. This uncommon juxtaposition of seemingly unrelated phenomena has piqued the interest of researchers, statisticians, and stand-up comedians alike. In this study, we delve into the intriguing connection between the rise and fall of Marisas and the occurrence of robberies in the Land of 10,000 Lakes.
The choice of the first name Marisa, while seemingly arbitrary at first glance, lends itself well to this investigation due to its intriguing phonetic resemblance to the word “mischief.” It prompts one to wonder if there are more heists involving Marisas than one might expect. And what about the correlation with robberies in Minnesota? Is there perhaps an underground network of mischievous Marisas and their associates plotting capers throughout the state? We are here to shed light on these questions, as well as to explore whether there is more to the name "Marisa" than its popular connotations.
This study is not just a whimsical exercise in wordplay and puzzling correlations. It presents a robust statistical analysis that underscores the need to consider factors beyond traditional criminological indicators. Our findings suggest that there might indeed be a significant association between the prevalence of the name Marisa and the occurrence of robberies in Minnesota. This unexpected discovery challenges existing perceptions and expands the scope of factors considered in criminal behavior research.
In this paper, we present a comprehensive analysis of the data gathered from the US Social Security Administration and FBI Criminal Justice Information Services, spanning nearly four decades. Our statistical model yields a correlation coefficient of 0.8870963, with a p-value of less than 0.01, affirming the robustness of the observed association. While the correlation might seem humorous at first glance, the statistical rigor and significance of our findings warrant serious attention.
The implications of this research extend beyond mere statistical curiosity. Delving into the potential influence of names on criminal behavior prompts a reconsideration of the myriad factors that contribute to societal phenomena. As we wade through the mirthful mystique of Marisas and the enigma of Minnesotan robberies, we invite our readers to join us in pondering the profound questions that arise from this unlikely association.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data revealed a striking correlation between the popularity of the first name Marisa and the frequency of robberies in Minnesota. Our research team rigorously examined the data collected from the US Social Security Administration and the FBI Criminal Justice Information Services, covering the period from 1985 to 2022.

The correlation coefficient of 0.8870963 indicates a strong positive relationship between the two variables, suggesting that as the prevalence of the name Marisa increased, so did the occurrence of robberies in Minnesota. The r-squared value of 0.7869399 further confirms that approximately 78.69% of the variability in robbery occurrences can be attributed to changes in the popularity of the name Marisa.

Figure 1 presents a scatterplot illustrating the pronounced correlation between the frequency of the name Marisa and the incidences of robberies in Minnesota. The tight clustering of data points provides visual evidence of the substantial association between these seemingly disparate phenomena.

The statistical significance of the correlation, with a p-value of less than 0.01, underscores the robustness of the observed relationship. Such a low p-value indicates that the likelihood of obtaining such a strong correlation by chance alone is exceedingly slim, further buttressing the validity of the findings. While the connection may seem unconventional and whimsical on the surface, the statistical analysis firmly supports the presence of a meaningful association.

These findings offer an unexpected twist in the exploration of societal phenomena, serving as a reminder that even in the realm of statistically significant correlations, there is room for surprises. The implications of this research extend beyond statistical curiosity, inviting a deeper consideration of the multifaceted influences shaping human behavior.

In conclusion, the statistical analysis of the connection between the popularity of the first name Marisa and robberies in Minnesota has unveiled a remarkable relationship, prompting further contemplation of the potential influence of names on criminal behavior. The unexpected nature of this correlation piques intellectual curiosity and underscores the need for expansive and open-minded inquiry into the complexities of human phenomena.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Popularity of the first name Marisa and Robberies in Minnesota. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota"

[[ABSTRACT]]
This paper explores the surprising correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota. Utilizing data from the US Social Security Administration and FBI Criminal Justice Information Services, a statistically significant correlation coefficient of 0.8870963 was identified for the period spanning 1985 to 2022, with a p-value of less than 0.01. The findings suggest that the rise and fall of Marisas may be more than just a matter of chance, as there appears to be a peculiar connection to the prevalence of robberies in the Land of 10,000 Lakes. The implications of this research open the door to questioning the influence of names on criminal behavior, prompting us to consider if the name Marisa is associated with more than just a penchant for pilfering.

[[LITERATURE REVIEW]]
The unusual correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota has prompted a plethora of research endeavors aimed at unraveling this intriguing association. Smith et al. (2015) conducted a study focusing on the cultural significance of names and their potential impact on criminal behavior, laying the groundwork for subsequent investigations into the enigmatic link between Marisas and robberies in the Land of 10,000 Lakes. Similarly, Doe (2018) postulated a theoretical framework proposing that phonetic alignment of names with certain words might subconsciously influence individuals toward behaviors associated with those words.
In "The Sociolinguistics of Names" by Jones (2009), the author delves into the complex interplay between names and societal perceptions, shedding light on the potential influence of names on behavioral patterns. This work provides valuable insights into the underlying mechanisms that could contribute to the curious correlation between the name Marisa and the prevalence of robberies in Minnesota.
On a lighter note, "The Great Marisa Caper" by Hill (2012) is a work of fiction centered around a daring heist masterminded by a wily character named Marisa, which, while not directly related to statistical analyses, paints an imaginative picture of the potential adventures that Marisas may embark upon. Additionally, "Marisa: Queen of Thieves" by Evans (2017) is a riveting tale of intrigue and cloak-and-dagger escapades, invoking elements of mystery and larceny associated with the name Marisa.
Furthermore, movies such as "Ocean's Marisa" and "Now You See Marisa, Now You Don't" offer whimsical portrayals of cunning maneuvers and heists, evoking the playful side of the correlation between Marisas and criminal activities. While these may not be direct sources of statistical evidence, they contribute to the broader cultural conversation surrounding the captivating connection between the name Marisa and the occurrence of robberies in Minnesota.
The interdisciplinary nature of this investigation necessitates the exploration of both scholarly and creative works to gain a comprehensive understanding of the complexities underlying the unexpected relationship between the name Marisa and criminal activities in the state of Minnesota. As we journey through the academic and literary landscape, the lighthearted and thought-provoking perspectives on this correlation provide a multi-faceted backdrop to our exploration of this peculiar phenomenon.

[[RESULTS]]
The analysis of the data revealed a striking correlation between the popularity of the first name Marisa and the frequency of robberies in Minnesota. Our research team rigorously examined the data collected from the US Social Security Administration and the FBI Criminal Justice Information Services, covering the period from 1985 to 2022.
The correlation coefficient of 0.8870963 indicates a strong positive relationship between the two variables, suggesting that as the prevalence of the name Marisa increased, so did the occurrence of robberies in Minnesota. The r-squared value of 0.7869399 further confirms that approximately 78.69% of the variability in robbery occurrences can be attributed to changes in the popularity of the name Marisa.
Figure 1 presents a scatterplot illustrating the pronounced correlation between the frequency of the name Marisa and the incidences of robberies in Minnesota. The tight clustering of data points provides visual evidence of the substantial association between these seemingly disparate phenomena.
The statistical significance of the correlation, with a p-value of less than 0.01, underscores the robustness of the observed relationship. Such a low p-value indicates that the likelihood of obtaining such a strong correlation by chance alone is exceedingly slim, further buttressing the validity of the findings. While the connection may seem unconventional and whimsical on the surface, the statistical analysis firmly supports the presence of a meaningful association.
These findings offer an unexpected twist in the exploration of societal phenomena, serving as a reminder that even in the realm of statistically significant correlations, there is room for surprises. The implications of this research extend beyond statistical curiosity, inviting a deeper consideration of the multifaceted influences shaping human behavior.
In conclusion, the statistical analysis of the connection between the popularity of the first name Marisa and robberies in Minnesota has unveiled a remarkable relationship, prompting further contemplation of the potential influence of names on criminal behavior. The unexpected nature of this correlation piques intellectual curiosity and underscores the need for expansive and open-minded inquiry into the complexities of human phenomena.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The present study has shed light on the remarkable and unexpected correlation between the prevalence of the first name Marisa and the incidence of robberies in Minnesota. These findings are in line with previous research that has delved into the cultural, phonetic, and societal significance of names, albeit with a whimsical twist that could make you rub your eyes in disbelief.

Our investigation presents a statistically significant correlation coefficient of 0.8870963, indicating a strong positive relationship between the popularity of the name Marisa and the frequency of robberies in Minnesota. These results align with the work of Smith et al. (2015), who laid the groundwork for exploring the potential impact of names on criminal behavior. Perhaps Marisas possess an inexplicable propensity for “making off” with more than just hearts.

The statistical significance of the correlation, with a p-value of less than 0.01, underscores the robustness of the observed relationship. It appears that as the number of Marisas escalates, so do the instances of criminal escapades in the Land of 10,000 Lakes. Who would have thought that names could have such an influence on criminal tendencies? It would seem that the mischievous side of the name Marisa is not just a flight of fancy, but rather a tangible statistical phenomenon.

The r-squared value of 0.7869399 further confirms that a substantial portion of the variability in robbery occurrences can be ascribed to changes in the popularity of the name Marisa. It’s no longer a mere flight of fancy; the data supports the notion that the rise and fall of Marisas is indeed associated with the ebb and flow of robbery incidents. This correlation might lead one to coin the term "Marisa Miscreant" with statistical evidence to back it up.

The exploration of the interdisciplinary landscape, from scholarly inquiries to creative works, has provided a multi-faceted backdrop to our investigation. While we may have started our journey with an air of amusement, the statistical evidence has prompted us to consider the profound influence of names on behavioral patterns, even in the realm of criminal activities. It appears that Marisa’s bras may indeed be a hilarious mess or, dare we say, a robbery success with statistical backing.

In the continuum of scholarly inquiry, unexpected statistical phenomena such as the correlation between the name Marisa and robberies in Minnesota remind us to maintain a spirit of curiosity and open-mindedness in exploring the complexities of human behavior. As we continue to unravel the enigma of names and their intriguing connections to societal phenomena, the lighthearted and thought-provoking perspectives presented by the correlation between Marisas and criminal activities offer a paean to the whimsical side of statistical analysis. The statistical evidence has indeed opened the door to a world of unexpected connections, challenging us to rethink the potential influence of names on our lives, even in the most unexpected of ways.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Popularity of the first name Marisa and Robberies in Minnesota. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota"

[[ABSTRACT]]
This paper explores the surprising correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota. Utilizing data from the US Social Security Administration and FBI Criminal Justice Information Services, a statistically significant correlation coefficient of 0.8870963 was identified for the period spanning 1985 to 2022, with a p-value of less than 0.01. The findings suggest that the rise and fall of Marisas may be more than just a matter of chance, as there appears to be a peculiar connection to the prevalence of robberies in the Land of 10,000 Lakes. The implications of this research open the door to questioning the influence of names on criminal behavior, prompting us to consider if the name Marisa is associated with more than just a penchant for pilfering.

[[INTRDUCTION]]
The intersection of statistical analysis and comedy does not come often; however, in the case of the correlation between the frequency of the name “Marisa” and instances of robberies in the state of Minnesota, a compelling case is made. This uncommon juxtaposition of seemingly unrelated phenomena has piqued the interest of researchers, statisticians, and stand-up comedians alike. In this study, we delve into the intriguing connection between the rise and fall of Marisas and the occurrence of robberies in the Land of 10,000 Lakes.
The choice of the first name Marisa, while seemingly arbitrary at first glance, lends itself well to this investigation due to its intriguing phonetic resemblance to the word “mischief.” It prompts one to wonder if there are more heists involving Marisas than one might expect. And what about the correlation with robberies in Minnesota? Is there perhaps an underground network of mischievous Marisas and their associates plotting capers throughout the state? We are here to shed light on these questions, as well as to explore whether there is more to the name "Marisa" than its popular connotations.
This study is not just a whimsical exercise in wordplay and puzzling correlations. It presents a robust statistical analysis that underscores the need to consider factors beyond traditional criminological indicators. Our findings suggest that there might indeed be a significant association between the prevalence of the name Marisa and the occurrence of robberies in Minnesota. This unexpected discovery challenges existing perceptions and expands the scope of factors considered in criminal behavior research.
In this paper, we present a comprehensive analysis of the data gathered from the US Social Security Administration and FBI Criminal Justice Information Services, spanning nearly four decades. Our statistical model yields a correlation coefficient of 0.8870963, with a p-value of less than 0.01, affirming the robustness of the observed association. While the correlation might seem humorous at first glance, the statistical rigor and significance of our findings warrant serious attention.
The implications of this research extend beyond mere statistical curiosity. Delving into the potential influence of names on criminal behavior prompts a reconsideration of the myriad factors that contribute to societal phenomena. As we wade through the mirthful mystique of Marisas and the enigma of Minnesotan robberies, we invite our readers to join us in pondering the profound questions that arise from this unlikely association.

[[RESULTS]]
The analysis of the data revealed a striking correlation between the popularity of the first name Marisa and the frequency of robberies in Minnesota. Our research team rigorously examined the data collected from the US Social Security Administration and the FBI Criminal Justice Information Services, covering the period from 1985 to 2022.
The correlation coefficient of 0.8870963 indicates a strong positive relationship between the two variables, suggesting that as the prevalence of the name Marisa increased, so did the occurrence of robberies in Minnesota. The r-squared value of 0.7869399 further confirms that approximately 78.69% of the variability in robbery occurrences can be attributed to changes in the popularity of the name Marisa.
Figure 1 presents a scatterplot illustrating the pronounced correlation between the frequency of the name Marisa and the incidences of robberies in Minnesota. The tight clustering of data points provides visual evidence of the substantial association between these seemingly disparate phenomena.
The statistical significance of the correlation, with a p-value of less than 0.01, underscores the robustness of the observed relationship. Such a low p-value indicates that the likelihood of obtaining such a strong correlation by chance alone is exceedingly slim, further buttressing the validity of the findings. While the connection may seem unconventional and whimsical on the surface, the statistical analysis firmly supports the presence of a meaningful association.
These findings offer an unexpected twist in the exploration of societal phenomena, serving as a reminder that even in the realm of statistically significant correlations, there is room for surprises. The implications of this research extend beyond statistical curiosity, inviting a deeper consideration of the multifaceted influences shaping human behavior.
In conclusion, the statistical analysis of the connection between the popularity of the first name Marisa and robberies in Minnesota has unveiled a remarkable relationship, prompting further contemplation of the potential influence of names on criminal behavior. The unexpected nature of this correlation piques intellectual curiosity and underscores the need for expansive and open-minded inquiry into the complexities of human phenomena.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In light of our statistical analysis, it is clear that the name "Marisa" carries more weight than meets the eye. The correlation between the frequency of this moniker and the frequency of robberies in Minnesota is nothing short of eyebrow-raising, to say the least. It seems the misadventures of Marisas and the misdeeds of Minnesota have more in common than the initial consonant.

While the findings may raise a few giggles, the statistical rigor and significance of this connection cannot be dismissed. The p-value of less than 0.01 firmly suggests that the likelihood of this correlation occurring by pure chance is as rare as finding a solitary M&M in a bag of Skittles.

The implications of this research are as intriguing as an unsolved riddle - prompting us to ponder the tantalizing question: Is the gravitational pull of trouble just stronger when surrounded by Marisas? Indeed, the allure of statistical patterns in human behavior has never been more tantalizing.

It's time to draw the curtain on this peculiar correlation and declare with utmost statistical confidence that further research in this area is not needed. The link between the popularity of the name Marisa and robberies in Minnesota has been firmly established, and it's time to embrace the whimsy of this unexpected connection. After all, who knew that statistical analysis could harbor such mirth and mischief?


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 Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Social Science


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 Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota. Respond only with the name of a fictional organization.

ChatGPT:

The Association for Whimsical Research and Statistics


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 Marisa's Bras: A Hilarious Mess or Robbery Success? A Statistical Analysis of the Marisa Name Popularity and Robberies in Minnesota with an abstract of This paper explores the surprising correlation between the popularity of the first name Marisa and the occurrence of robberies in Minnesota. Utilizing data from the US Social Security Administration and FBI Criminal Justice Information Services, a statistically significant correlation coefficient of 0.8870963 was identified for the period spanning 1985 to 2022, with a p-value of less than 0.01. The findings suggest that the rise and fall of Marisas may be more than just a matter of chance, as there appears to be a peculiar connection to the prevalence of robberies in the Land of 10,000 Lakes. The implications of this research open the door to questioning the influence of names on criminal behavior, prompting us to consider if the name Marisa is associated with more than just a penchant for pilfering.

ChatGPT:

Marisa, robbery, correlation, statistical analysis, name popularity, Minnesota, US Social Security Administration, FBI Criminal Justice Information Services, correlation coefficient, p-value, criminal behavior

*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

Popularity of the first name Marisa
Detailed data title: Babies of all sexes born in the US named Marisa
Source: US Social Security Administration
See what else correlates with Popularity of the first name Marisa

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

Correlation r = 0.8870963 (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 = 0.7869399 (Coefficient of determination)
This means 78.7% of the change in the one variable (i.e., Robberies in Minnesota) is predictable based on the change in the other (i.e., Popularity of the first name Marisa) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.2E-13. 0.0000000000001210031343720205
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.89 in 1.2E-11% of random cases. Said differently, if you correlated 8,264,248,733,636 random variables You don't actually need 8 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 37 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 37 because we have two variables measured over a period of 38 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.79, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Popularity of the first name Marisa (Babies born)9781054989107210441111115312861730218721981857147714331110105298293394595380061161247841132930825817217510898885462683937
Robberies in Minnesota (Robbery rate)85.8102102.594.794.892.798109.5112.7117.6123.7115.6114.792.58275.575.478.477.179.992.1105.391.880.168.763.863.364.667.867.668.867.565.152.555.968.57057




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([978,1054,989,1072,1044,1111,1153,1286,1730,2187,2198,1857,1477,1433,1110,1052,982,933,945,953,800,611,612,478,411,329,308,258,172,175,108,98,88,54,62,68,39,37,])
array_2 = np.array([85.8,102,102.5,94.7,94.8,92.7,98,109.5,112.7,117.6,123.7,115.6,114.7,92.5,82,75.5,75.4,78.4,77.1,79.9,92.1,105.3,91.8,80.1,68.7,63.8,63.3,64.6,67.8,67.6,68.8,67.5,65.1,52.5,55.9,68.5,70,57,])
array_1_name = "Popularity of the first name Marisa"
array_2_name = "Robberies in Minnesota"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!


Correlation ID: 1071 · Black Variable ID: 2320 · Red Variable ID: 20197
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0