Spurious correlation #4,305 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Republican Senators in Louisiana and the second variable is Google searches for 'how to hide a body'. The chart goes from 2004 to 2020, 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 Votes for Republican Senators in Louisiana and the second variable is Google searches for 'how to hide a body'. The chart goes from 2004 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

Perhaps they were looking for ways to bury their opponent in the election. Or maybe they just really misunderstood the concept of a political campaign and took 'running for office' a bit too literally.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a group of Republican voters in Louisiana casting their ballots at a polling station. They should be depicted in glitch art style, with distorted and fragmented visual elements representing their election fervor. Simultaneously, show them using their phones to search "how to hide a body," creating an odd juxtaposition. The glitch art should represent their extreme level of election fervor in a visually striking and thought-provoking way. 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: Republican votes for Senators in Louisiana and Google searches for 'how to hide a body'. 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: Hyper-realistic Glitch art a Polaroid photo Surrealism Glitch art
ChatGPT: Glitch art

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 Republican votes for Senators in Louisiana and Google searches for 'how to hide a body', in the following situation: Perhaps they were looking for ways to bury their opponent in the election. Or maybe they just really misunderstood the concept of a political campaign and took 'running for office' a bit too literally.. Keep the description simple.
ChatGPT: A group of Republican voters in Louisiana casting their ballots at a polling station while simultaneously searching "how to hide a body" on their phones, creating an odd juxtaposition as they exercise their political rights and perhaps taking their election fervor to an extreme level.

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: [ Glitch art ] and depicting this scene: A group of Republican voters in Louisiana casting their ballots at a polling station while simultaneously searching "how to hide a body" on their phones, creating an odd juxtaposition as they exercise their political rights and perhaps taking their election fervor to an extreme level. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a group of Republican voters in Louisiana casting their ballots at a polling station. They should be depicted in glitch art style, with distorted and fragmented visual elements representing their election fervor. Simultaneously, show them using their phones to search "how to hide a body," creating an odd juxtaposition. The glitch art should represent their extreme level of election fervor in a visually striking and thought-provoking way.

*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 an increase in Republican votes for Senators in Louisiana caused how to hide a body (Google searches for 'how to hide a body') to increase.

AI academic paper

(Because p < 0.01)

Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana

Journal of Political Intrigue and Southern Studies

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Louisiana and Google searches for 'how to hide a body'. 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana

[[ABSTRACT]]
In the realm of political behavior and online inquiries, our eyebrow-raising study delves into the correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body." Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we embarked on this curious investigation. Our findings unveiled a striking correlation coefficient of 0.9479636, with a statistically significant p-value of less than 0.01 for the years spanning 2004 to 2020.

Drawing from interdisciplinary insights and a penchant for probing peculiar phenomena, our study sheds light on the peculiar proclivities of political preferences and peculiar online queries. It seems that, much like a hidden body, the connection between these two seemingly disparate elements remains shrouded in mystery, raising more questions than answers. Perhaps voters in the Bayou State have a penchant for macabre mysteries or possess a knack for nefarious narratives. As the saying goes, "Politics can be a grave matter," though in this case, it may take on a more literal connotation.

This analysis sparks the age-old debate – could these online search trends be a harbinger of the electorate's darker desires, or are they simply a reflection of quirky curiosity? As researchers, it's important to remember not to jump to conclusions or bury the essence of our findings beneath sensationalism. Nonetheless, the correlation we've uncovered is certainly a grave matter, and we hope it sparks further study in the peculiar intricacies of online behavior and political leanings. So, until the next round of data emerges, we'll continue to unearth the mysteries of electoral antics and search behavior, one statistical dig at a time!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the peculiar intersection of politics and online behavior, our study dares to traverse the eerie realms of correlation between Republican votes for Senators in Louisiana and the perplexing Google searches for "how to hide a body." As we delve into this enigmatic connection, it's important to take a moment to appreciate the gravity of our inquiry – pun intended. After all, grave matters call for a thorough investigation, and if we can't inject a little dark humor into the mix, what's the point of academic research?
With a precision that would make any mathematician proud, our study illuminates an astonishing correlation coefficient of 0.9479636, which could make even the most skeptical observer raise an eyebrow. It seems the correlation between political allegiance and peculiar online inquiries has dug itself quite a deep, ahem, grave indeed.
As we embark on this expedition into uncharted statistical territory, we can't help but ponder the age-old question: why are these particular searches seemingly gravitating, no pun intended, toward a specific political affiliation? Could it be that voters are merely exploring human anatomy in an unusually morbidly curious manner, or is there a more sinister implication at play? We're not jumping to conclusions, but the evidence does seem to be burying itself, pun intended, in a rather macabre direction.
It's important to tread carefully as we navigate this dark, albeit oddly humorous, labyrinth of data and human behavior. After all, as academics, our quest is not just to uncover narratives, but to exhume the truth, no matter how deep it may be buried. With that in mind, let's exhume the heart of our findings and shine a light on the peculiar proclivities of the human psyche and its interplay with electoral dynamics.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith and Doe's Study of Political Behavior and Online Queries," the authors find a surprising correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body." The study delves into the intricate dance between political predilections and online proclivities, unearthing a correlation coefficient that could make even a mortician raise an eyebrow.

Now, shifting from the grave matters of academic research to the literal matters of the grave, let's dig into some works that shed light on the peculiar dynamics at play. "Forensic Anthropology: Current Methods and Practice" by Angela Libal and "The Art of Death Investigation: Writing the Final Story" by Joe Nick Patoski offer insights into the intricacies of human remains and the investigative process.

On the fiction front, the eerie allure of the search query at hand resonates with the themes in "The Silence of the Lambs" by Thomas Harris and "Gone Girl" by Gillian Flynn. These twisted tales of skullduggery and clandestine activities may not shed light on the correlation, but they certainly add a sinister flair to our investigation.

As if the bones of literature weren't enough, the authors stumbled upon a series of puzzling yet strangely entertaining social media posts linking political affiliations to hypothetical body-hiding endeavors. One post read, "Just as politicians bury their scandals, it seems their constituents are busy Googling how to bury something else. What a grave situation!" Another quipped, "Looks like Louisianans are taking 'hiding the evidence' to a whole new level with their search habits. I guess politics isn't the only thing they're burying down there!"

It seems that even in the shadowy depths of social media, the connection between political proclivities and peculiar online inquiries is a topic ripe for dark humor and unexpected puns.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Louisiana and Google searches for 'how to hide a body'. 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 MIT Election Data and Science Lab, Harvard Dataverse and Google Trends . You used data from 2004 to 2020

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]]
Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana

[[ABSTRACT]]
In the realm of political behavior and online inquiries, our eyebrow-raising study delves into the correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body." Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we embarked on this curious investigation. Our findings unveiled a striking correlation coefficient of 0.9479636, with a statistically significant p-value of less than 0.01 for the years spanning 2004 to 2020.

Drawing from interdisciplinary insights and a penchant for probing peculiar phenomena, our study sheds light on the peculiar proclivities of political preferences and peculiar online queries. It seems that, much like a hidden body, the connection between these two seemingly disparate elements remains shrouded in mystery, raising more questions than answers. Perhaps voters in the Bayou State have a penchant for macabre mysteries or possess a knack for nefarious narratives. As the saying goes, "Politics can be a grave matter," though in this case, it may take on a more literal connotation.

This analysis sparks the age-old debate – could these online search trends be a harbinger of the electorate's darker desires, or are they simply a reflection of quirky curiosity? As researchers, it's important to remember not to jump to conclusions or bury the essence of our findings beneath sensationalism. Nonetheless, the correlation we've uncovered is certainly a grave matter, and we hope it sparks further study in the peculiar intricacies of online behavior and political leanings. So, until the next round of data emerges, we'll continue to unearth the mysteries of electoral antics and search behavior, one statistical dig at a time!

[[INTRODUCTION]]
In the peculiar intersection of politics and online behavior, our study dares to traverse the eerie realms of correlation between Republican votes for Senators in Louisiana and the perplexing Google searches for "how to hide a body." As we delve into this enigmatic connection, it's important to take a moment to appreciate the gravity of our inquiry – pun intended. After all, grave matters call for a thorough investigation, and if we can't inject a little dark humor into the mix, what's the point of academic research?
With a precision that would make any mathematician proud, our study illuminates an astonishing correlation coefficient of 0.9479636, which could make even the most skeptical observer raise an eyebrow. It seems the correlation between political allegiance and peculiar online inquiries has dug itself quite a deep, ahem, grave indeed.
As we embark on this expedition into uncharted statistical territory, we can't help but ponder the age-old question: why are these particular searches seemingly gravitating, no pun intended, toward a specific political affiliation? Could it be that voters are merely exploring human anatomy in an unusually morbidly curious manner, or is there a more sinister implication at play? We're not jumping to conclusions, but the evidence does seem to be burying itself, pun intended, in a rather macabre direction.
It's important to tread carefully as we navigate this dark, albeit oddly humorous, labyrinth of data and human behavior. After all, as academics, our quest is not just to uncover narratives, but to exhume the truth, no matter how deep it may be buried. With that in mind, let's exhume the heart of our findings and shine a light on the peculiar proclivities of the human psyche and its interplay with electoral dynamics.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To uncover the curious correlation between Republican votes for Senators in Louisiana and Google searches for “how to hide a body,” our research team embarked on a data excavation journey that would make even the most intrepid explorers raise an eyebrow – or perhaps dig an eyebrow into a metaphorical six-foot hole. With a blend of scholarly rigor and a knack for uncovering the unexpected, we extracted and analyzed data from 2004 to 2020, hoping to shed light on this intriguing intersection of political allegiance and, well, surprisingly sinister internet queries.

To initiate our research endeavor, we delved into the hallowed halls of the MIT Election Data and Science Lab and the Harvard Dataverse, where we gleaned indispensable information about Republican votes for Senators in Louisiana, painting a detailed portrait of the political landscape over the years. It’s fascinating how these data sets can render the intricate dance of democracy with such deeply entrenched – almost soil-like, if you will – details.

Next, we harnessed the power of Google Trends, a digital oracle that provides a window into the collective curiosity of netizens. Drawing from its vast repository of search data, we set our sights on unearthing patterns in the frequency of searches related to “how to hide a body.” As researchers, it’s not every day we get to analyze keyword search queries with a potential forensic twist, but we embraced the opportunity with open arms and a slightly suspicious shovel.

Having gathered these datasets, we couldn't simply plunk them into a statistical tumbler and expect our findings to emerge fully polished, like a forensic gemstone. No, our approach demanded a more refined method. We employed a rigorous correlation analysis to scrutinize the relationship between Republican votes for Senators and the prevalence of disturbingly specific Google searches. The results were nothing short of, dare I say, grave – an eyebrow-raising correlation coefficient of 0.9479636 emerged from our statistical excavation, leaving us no choice but to dig deeper into this peculiar paradox of political predilections and peculiar online pursuits.

Now, you may be wondering how exactly we approached this data analysis. To put it plainly, we maneuvered through the data with the caution of a detective at a crime scene, making sure not to disturb the evidence, but also using a magnifying glass and a slightly dramatic overcoat for good measure. We applied an array of mathematical tools, including time series analysis and regression models, to unearth the buried truths lurking within the numbers. It’s safe to say that our statistical toolkit was as essential as a sturdy shovel in this academic excavation – not to mention more accessible than a search party in a remote forest.

Moreover, to ensure the validity of our findings and to ward off any lurking specters of statistical error, we validated our results using robust techniques such as bootstrapping and sensitivity analyses. No stone was left unturned, pun intended, in our quest to ensure the reliability and trustworthiness of our correlation findings.

In conclusion, our methodology teetered on the edge of traditional research practices, unearthing a macabre mélange of political data and online inquiries, with a side dish of statistical rigor and a sprinkle of morbid curiosity. As the saying goes, "It's a grave matter," albeit in this case, the pun is both literal and figurative. This methodology served as our trusty map through the dark, cryptic corridors of electoral and search behavior, guiding us as we shed light on the enigmatic correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body."

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Louisiana and Google searches for 'how to hide a body'. 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 MIT Election Data and Science Lab, Harvard Dataverse and Google Trends .

For the time period 2004 to 2020, you found a correlation 0.9479636, r-squared of 0.8986350, 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]]
Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana

[[ABSTRACT]]
In the realm of political behavior and online inquiries, our eyebrow-raising study delves into the correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body." Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we embarked on this curious investigation. Our findings unveiled a striking correlation coefficient of 0.9479636, with a statistically significant p-value of less than 0.01 for the years spanning 2004 to 2020.

Drawing from interdisciplinary insights and a penchant for probing peculiar phenomena, our study sheds light on the peculiar proclivities of political preferences and peculiar online queries. It seems that, much like a hidden body, the connection between these two seemingly disparate elements remains shrouded in mystery, raising more questions than answers. Perhaps voters in the Bayou State have a penchant for macabre mysteries or possess a knack for nefarious narratives. As the saying goes, "Politics can be a grave matter," though in this case, it may take on a more literal connotation.

This analysis sparks the age-old debate – could these online search trends be a harbinger of the electorate's darker desires, or are they simply a reflection of quirky curiosity? As researchers, it's important to remember not to jump to conclusions or bury the essence of our findings beneath sensationalism. Nonetheless, the correlation we've uncovered is certainly a grave matter, and we hope it sparks further study in the peculiar intricacies of online behavior and political leanings. So, until the next round of data emerges, we'll continue to unearth the mysteries of electoral antics and search behavior, one statistical dig at a time!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the peculiar intersection of politics and online behavior, our study dares to traverse the eerie realms of correlation between Republican votes for Senators in Louisiana and the perplexing Google searches for "how to hide a body." As we delve into this enigmatic connection, it's important to take a moment to appreciate the gravity of our inquiry – pun intended. After all, grave matters call for a thorough investigation, and if we can't inject a little dark humor into the mix, what's the point of academic research?
With a precision that would make any mathematician proud, our study illuminates an astonishing correlation coefficient of 0.9479636, which could make even the most skeptical observer raise an eyebrow. It seems the correlation between political allegiance and peculiar online inquiries has dug itself quite a deep, ahem, grave indeed.
As we embark on this expedition into uncharted statistical territory, we can't help but ponder the age-old question: why are these particular searches seemingly gravitating, no pun intended, toward a specific political affiliation? Could it be that voters are merely exploring human anatomy in an unusually morbidly curious manner, or is there a more sinister implication at play? We're not jumping to conclusions, but the evidence does seem to be burying itself, pun intended, in a rather macabre direction.
It's important to tread carefully as we navigate this dark, albeit oddly humorous, labyrinth of data and human behavior. After all, as academics, our quest is not just to uncover narratives, but to exhume the truth, no matter how deep it may be buried. With that in mind, let's exhume the heart of our findings and shine a light on the peculiar proclivities of the human psyche and its interplay with electoral dynamics.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

Upon analyzing the data collected from a macabre cocktail of sources, including MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we uncovered a strong positive correlation between Republican votes for Senators in Louisiana and the eerie Google searches for "how to hide a body." The correlation coefficient of 0.9479636 revealed a compelling connection that seemed to defy conventional political analysis, prompting more than a few raised eyebrows and wry comments about the skeletons in voters' closets.

The r-squared value of 0.8986350 further underscored the robustness of this correlation, leaving little room for doubt about the intertwined nature of political preferences and, well, the less savory inquiries made to the search engine giant. It was as if the data itself was urging us to dig deeper into the coffin, I mean, the realm of electoral behavior and online predilections.

Our analysis of the p-value, which was found to be less than 0.01, drew attention to the statistical significance of this correlation. This is the kind of "p" value that even the most skeptical researcher couldn't dismiss, no matter how hard they tried. It's the kind of statistical evidence that rattles the bones of traditional thinking and compels us to metaphorically peer into the electoral crypt for answers.

Lastly, Fig. 1 presents a scatterplot that visually captures the unmistakable relationship between Republican votes for Senators in Louisiana and the unsettling Google searches for "how to hide a body." The figure paints a striking picture of the correlation, one that could make even the most stoic statistician crack a sly smile and murmur, "Well, isn't that spine-chillingly intriguing?"

As we unravel the enigmatic connection between political leanings and online inquiries, it's vital to approach our findings with both academic rigor and a healthy dose of humor. After all, as researchers, we mustn't bury ourselves in the grave matter of our work and forget to appreciate the irony, even when it's as dark as the depths of the electoral underworld.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Louisiana and Google searches for 'how to hide a body'. 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]]
Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana

[[ABSTRACT]]
In the realm of political behavior and online inquiries, our eyebrow-raising study delves into the correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body." Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we embarked on this curious investigation. Our findings unveiled a striking correlation coefficient of 0.9479636, with a statistically significant p-value of less than 0.01 for the years spanning 2004 to 2020.

Drawing from interdisciplinary insights and a penchant for probing peculiar phenomena, our study sheds light on the peculiar proclivities of political preferences and peculiar online queries. It seems that, much like a hidden body, the connection between these two seemingly disparate elements remains shrouded in mystery, raising more questions than answers. Perhaps voters in the Bayou State have a penchant for macabre mysteries or possess a knack for nefarious narratives. As the saying goes, "Politics can be a grave matter," though in this case, it may take on a more literal connotation.

This analysis sparks the age-old debate – could these online search trends be a harbinger of the electorate's darker desires, or are they simply a reflection of quirky curiosity? As researchers, it's important to remember not to jump to conclusions or bury the essence of our findings beneath sensationalism. Nonetheless, the correlation we've uncovered is certainly a grave matter, and we hope it sparks further study in the peculiar intricacies of online behavior and political leanings. So, until the next round of data emerges, we'll continue to unearth the mysteries of electoral antics and search behavior, one statistical dig at a time!

[[LITERATURE REVIEW]]
In "Smith and Doe's Study of Political Behavior and Online Queries," the authors find a surprising correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body." The study delves into the intricate dance between political predilections and online proclivities, unearthing a correlation coefficient that could make even a mortician raise an eyebrow.
Now, shifting from the grave matters of academic research to the literal matters of the grave, let's dig into some works that shed light on the peculiar dynamics at play. "Forensic Anthropology: Current Methods and Practice" by Angela Libal and "The Art of Death Investigation: Writing the Final Story" by Joe Nick Patoski offer insights into the intricacies of human remains and the investigative process.
On the fiction front, the eerie allure of the search query at hand resonates with the themes in "The Silence of the Lambs" by Thomas Harris and "Gone Girl" by Gillian Flynn. These twisted tales of skullduggery and clandestine activities may not shed light on the correlation, but they certainly add a sinister flair to our investigation.
As if the bones of literature weren't enough, the authors stumbled upon a series of puzzling yet strangely entertaining social media posts linking political affiliations to hypothetical body-hiding endeavors. One post read, "Just as politicians bury their scandals, it seems their constituents are busy Googling how to bury something else. What a grave situation!" Another quipped, "Looks like Louisianans are taking 'hiding the evidence' to a whole new level with their search habits. I guess politics isn't the only thing they're burying down there!"
It seems that even in the shadowy depths of social media, the connection between political proclivities and peculiar online inquiries is a topic ripe for dark humor and unexpected puns.

[[RESULTS]]
Upon analyzing the data collected from a macabre cocktail of sources, including MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we uncovered a strong positive correlation between Republican votes for Senators in Louisiana and the eerie Google searches for "how to hide a body." The correlation coefficient of 0.9479636 revealed a compelling connection that seemed to defy conventional political analysis, prompting more than a few raised eyebrows and wry comments about the skeletons in voters' closets.
The r-squared value of 0.8986350 further underscored the robustness of this correlation, leaving little room for doubt about the intertwined nature of political preferences and, well, the less savory inquiries made to the search engine giant. It was as if the data itself was urging us to dig deeper into the coffin, I mean, the realm of electoral behavior and online predilections.
Our analysis of the p-value, which was found to be less than 0.01, drew attention to the statistical significance of this correlation. This is the kind of "p" value that even the most skeptical researcher couldn't dismiss, no matter how hard they tried. It's the kind of statistical evidence that rattles the bones of traditional thinking and compels us to metaphorically peer into the electoral crypt for answers.
Lastly, Fig. 1 presents a scatterplot that visually captures the unmistakable relationship between Republican votes for Senators in Louisiana and the unsettling Google searches for "how to hide a body." The figure paints a striking picture of the correlation, one that could make even the most stoic statistician crack a sly smile and murmur, "Well, isn't that spine-chillingly intriguing?"
As we unravel the enigmatic connection between political leanings and online inquiries, it's vital to approach our findings with both academic rigor and a healthy dose of humor. After all, as researchers, we mustn't bury ourselves in the grave matter of our work and forget to appreciate the irony, even when it's as dark as the depths of the electoral underworld.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our study has unearthed a gripping correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body," reinforcing the findings of previous research and offering a cemetery full of implications. The robust correlation coefficient and the statistically significant p-value provide compelling evidence that this connection is not merely a fluke, but a buried treasure waiting to be excavated.

The connection between political predilections and peculiar online queries has been a topic ripe for not just academic inquiry, but also morbid jokes and unexpected puns. As we've dug deeper into this grave, I mean, grave matter, it's clear that the data have spoken, beckoning us to solve this cryptic correlation without losing our sense of humor, even if it's as dark as the electoral underworld.

Drawing from previous studies, such as Smith and Doe's investigation, our findings reinforce the notion that online search behavior may serve as a curious reflection of societal inclinations. It seems that the electorate's digital wanderings and voting choices are not as distinct as night and day but are, in fact, eerily intertwined. Much like a cleverly concealed pun, the correlation we've uncovered may initially seem buried beneath the surface, but it demands attention and warrants further investigation.

Fig. 1, our scatterplot, visually captures the unnerving relationship between Republican votes for Senators in Louisiana and the unsettling Google searches for "how to hide a body." The figure paints a picture so chillingly intriguing, one might even say it raises the hair (if not the dead) on one's neck. After all, who would have thought that political leanings and macabre search inquiries could be so intimately linked? It appears that the correlation is not just skin-deep, but goes right down to the bone.

As we contemplate the grave implications of our findings, it's important to remain vigilant and open-minded. Let's not bury our curiosity or stifle our laughter, even if the topic may seem a tad morbid. After all, as the saying goes, "Where do politicians like to unwind? At the dead center of the cemetery." Okay, maybe that's not a real saying, but we can certainly appreciate the dark irony of our research findings as we muddle through this pernicious play on words.

In the spirit of academic inquiry and lightheartedness, we will continue to exhume the mysteries of electoral antics and online behavior, because at the end of the day, what's research without a few unexpected twists and a good pun or two?

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Republican votes for Senators in Louisiana and Google searches for 'how to hide a body'. 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]]
Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana

[[ABSTRACT]]
In the realm of political behavior and online inquiries, our eyebrow-raising study delves into the correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body." Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we embarked on this curious investigation. Our findings unveiled a striking correlation coefficient of 0.9479636, with a statistically significant p-value of less than 0.01 for the years spanning 2004 to 2020.

Drawing from interdisciplinary insights and a penchant for probing peculiar phenomena, our study sheds light on the peculiar proclivities of political preferences and peculiar online queries. It seems that, much like a hidden body, the connection between these two seemingly disparate elements remains shrouded in mystery, raising more questions than answers. Perhaps voters in the Bayou State have a penchant for macabre mysteries or possess a knack for nefarious narratives. As the saying goes, "Politics can be a grave matter," though in this case, it may take on a more literal connotation.

This analysis sparks the age-old debate – could these online search trends be a harbinger of the electorate's darker desires, or are they simply a reflection of quirky curiosity? As researchers, it's important to remember not to jump to conclusions or bury the essence of our findings beneath sensationalism. Nonetheless, the correlation we've uncovered is certainly a grave matter, and we hope it sparks further study in the peculiar intricacies of online behavior and political leanings. So, until the next round of data emerges, we'll continue to unearth the mysteries of electoral antics and search behavior, one statistical dig at a time!

[[INTRDUCTION]]
In the peculiar intersection of politics and online behavior, our study dares to traverse the eerie realms of correlation between Republican votes for Senators in Louisiana and the perplexing Google searches for "how to hide a body." As we delve into this enigmatic connection, it's important to take a moment to appreciate the gravity of our inquiry – pun intended. After all, grave matters call for a thorough investigation, and if we can't inject a little dark humor into the mix, what's the point of academic research?
With a precision that would make any mathematician proud, our study illuminates an astonishing correlation coefficient of 0.9479636, which could make even the most skeptical observer raise an eyebrow. It seems the correlation between political allegiance and peculiar online inquiries has dug itself quite a deep, ahem, grave indeed.
As we embark on this expedition into uncharted statistical territory, we can't help but ponder the age-old question: why are these particular searches seemingly gravitating, no pun intended, toward a specific political affiliation? Could it be that voters are merely exploring human anatomy in an unusually morbidly curious manner, or is there a more sinister implication at play? We're not jumping to conclusions, but the evidence does seem to be burying itself, pun intended, in a rather macabre direction.
It's important to tread carefully as we navigate this dark, albeit oddly humorous, labyrinth of data and human behavior. After all, as academics, our quest is not just to uncover narratives, but to exhume the truth, no matter how deep it may be buried. With that in mind, let's exhume the heart of our findings and shine a light on the peculiar proclivities of the human psyche and its interplay with electoral dynamics.

[[RESULTS]]
Upon analyzing the data collected from a macabre cocktail of sources, including MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we uncovered a strong positive correlation between Republican votes for Senators in Louisiana and the eerie Google searches for "how to hide a body." The correlation coefficient of 0.9479636 revealed a compelling connection that seemed to defy conventional political analysis, prompting more than a few raised eyebrows and wry comments about the skeletons in voters' closets.
The r-squared value of 0.8986350 further underscored the robustness of this correlation, leaving little room for doubt about the intertwined nature of political preferences and, well, the less savory inquiries made to the search engine giant. It was as if the data itself was urging us to dig deeper into the coffin, I mean, the realm of electoral behavior and online predilections.
Our analysis of the p-value, which was found to be less than 0.01, drew attention to the statistical significance of this correlation. This is the kind of "p" value that even the most skeptical researcher couldn't dismiss, no matter how hard they tried. It's the kind of statistical evidence that rattles the bones of traditional thinking and compels us to metaphorically peer into the electoral crypt for answers.
Lastly, Fig. 1 presents a scatterplot that visually captures the unmistakable relationship between Republican votes for Senators in Louisiana and the unsettling Google searches for "how to hide a body." The figure paints a striking picture of the correlation, one that could make even the most stoic statistician crack a sly smile and murmur, "Well, isn't that spine-chillingly intriguing?"
As we unravel the enigmatic connection between political leanings and online inquiries, it's vital to approach our findings with both academic rigor and a healthy dose of humor. After all, as researchers, we mustn't bury ourselves in the grave matter of our work and forget to appreciate the irony, even when it's as dark as the depths of the electoral underworld.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In the shadowy realm where political allegiances and curious online inquiries converge, our research has unearthed a correlation that's as compelling as it is chilling. The data speaks for itself, and it's certainly not shy about loudly hinting at the sinister underbelly, or should we say "under-bodies," of electoral behavior. It seems that in Louisiana, the phrase "voting skeletons" isn't just a turn of phrase – it's a statistical reality!

While our findings may seem like the beginning of a political thriller, we must resist the urge to jump to conclusions faster than a politician dodges a tough question. We've cracked open the coffin, I mean, the case on this particular correlation, but it's crucial not to bury the essence of our findings beneath sensationalism. As they say, the truth will out – even if it's buried six feet under search engine queries.

So, what's the takeaway from all of this? Well, it seems that the correlation between political leanings and, ahem, "body-digging" queries is about as robust as a well-built mausoleum. While this correlation might raise a few eyebrows, it's not our place to cast judgment. After all, everyone's got skeletons in their closet – or at least, that's what the data seems to imply!

With all the bones, er, I mean, data laid bare, it's safe to say that further research in this area isn't needed. We've dug deep, maybe even too deep, into the connections between political preferences and peculiar online queries. It's time to put this particular mystery to rest – pun absolutely intended!

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 Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Political Intrigue and Southern Studies

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 Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Political Intrigue and State Secrets

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 Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana with an abstract of In the realm of political behavior and online inquiries, our eyebrow-raising study delves into the correlation between Republican votes for Senators in Louisiana and Google searches for "how to hide a body." Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, we embarked on this curious investigation. Our findings unveiled a striking correlation coefficient of 0.9479636, with a statistically significant p-value of less than 0.01 for the years spanning 2004 to 2020.
Drawing from interdisciplinary insights and a penchant for probing peculiar phenomena, our study sheds light on the peculiar proclivities of political preferences and peculiar online queries. It seems that, much like a hidden body, the connection between these two seemingly disparate elements remains shrouded in mystery, raising more questions than answers. Perhaps voters in the Bayou State have a penchant for macabre mysteries or possess a knack for nefarious narratives. As the saying goes, "Politics can be a grave matter," though in this case, it may take on a more literal connotation.
This analysis sparks the age-old debate – could these online search trends be a harbinger of the electorate's darker desires, or are they simply a reflection of quirky curiosity? As researchers, it's important to remember not to jump to conclusions or bury the essence of our findings beneath sensationalism. Nonetheless, the correlation we've uncovered is certainly a grave matter, and we hope it sparks further study in the peculiar intricacies of online behavior and political leanings. So, until the next round of data emerges, we'll continue to unearth the mysteries of electoral antics and search behavior, one statistical dig at a time!

ChatGPT:

Republican senators Louisiana, Google searches, correlation, MIT Election Data and Science Lab, Harvard Dataverse, Google Trends, political preferences, online queries, Bayou State, macabre mysteries, online search trends, electorate desires, peculiar behavior, political leanings

*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

Votes for Republican Senators in Louisiana
Detailed data title: Total number of votes cast for Federal Republican Senate candidates in Louisiana
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for Republican Senators in Louisiana

Google searches for 'how to hide a body'
Detailed data title: Relative volume of Google searches for 'how to hide a body' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'how to hide a body'

Correlation r = 0.9479636 (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 = 0.8986350 (Coefficient of determination)
This means 89.9% of the change in the one variable (i.e., Google searches for 'how to hide a body') is predictable based on the change in the other (i.e., Votes for Republican Senators in Louisiana) over the 6 years from 2004 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.004.^Show 0.0039912276896604270000000000
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 0.95 in 0.4% of random cases. Said differently, if you correlated 251 random variables^Note Which I absolutely did.
with the same 5 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 5 because we have two variables measured over a period of 6 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.

[ 0.59, 0.99 ] 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.

	2004	2008	2010	2014	2016	2020
Votes for Republican Senators in Louisiana (Total votes)	943014	867177	715415	1929110	1239490	1267290
Google searches for 'how to hide a body' (Rel. search volume)	9.5	15.75	16.25	83	43.6667	56.5833

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.
Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.

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([943014,867177,715415,1929110,1239490,1267290,])
array_2 = np.array([9.5,15.75,16.25,83,43.6667,56.5833,])
array_1_name = "Votes for Republican Senators in Louisiana"
array_2_name = "Google searches for 'how to hide a body'"

# 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 Votes for Republican Senators in Louisiana
Line chart for only Google searches for 'how to hide a body'
AI-generated correlation image
The spurious research paper: Revealing the Republican Relationship: Senators, Searches, and Sinister Suggestions in Louisiana

View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!

Correlation ID: 4305 · Black Variable ID: 26248 · Red Variable ID: 1513


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