about · email me · subscribe
Spurious correlation #5,170 · 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 Montana and the second variable is Google searches for 'that is sus'.  The chart goes from 2004 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The increase in Republican votes for Senators in Montana has led to more suspicions about political dealings and decisions. You could say the state's political climate is truly 'Montana sus.' It seems like residents are engaging in some elec-tile dysfunction, as they question the trustworthiness of their elected officials. Perhaps there's a belief that certain political moves just don't seem re-publican of their best interests. It's a situation that's definitely raising eyebrows and prompting people to cast their doubts, turning the state into a hotbed of political intrigue.

Model: dalle-3
Prompt: Generate an image of a futuristic election headquarters in a small Montana town, where clusters of people are seen casting their votes for Republican senators. The scene should capture the palpable tension in the air, with shadows of doubt and suspicion looming over the political dealings. In the background, show households with individuals fervently typing "that is sus" into their keyboards, creating an atmosphere where politics and skepticism intertwine. The image should evoke the feeling of a futuristic dystopian setting, with subtle visual cues to convey the intertwining of politics and skepticism. 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 Montana and Google searches for 'that is sus'. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Cubism Brutalism 3D Pixar Style Photorealism Futuristic
ChatGPT: Futuristic

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 Montana and Google searches for 'that is sus', in the following situation: The increase in Republican votes for Senators in Montana has led to more suspicions about political dealings and decisions. You could say the state's political climate is truly 'Montana sus.' It seems like residents are engaging in some elec-tile dysfunction, as they question the trustworthiness of their elected officials. Perhaps there's a belief that certain political moves just don't seem re-publican of their best interests. It's a situation that's definitely raising eyebrows and prompting people to cast their doubts, turning the state into a hotbed of political intrigue.. Keep the description simple.
ChatGPT: In a small Montana town, a bustling election headquarters is filled with clusters of people casting their votes for Republican senators. Meanwhile, in households across the state, individuals are fervently typing "that is sus" into their keyboards, their screens illuminated with search results. The air is filled with a palpable tension as the increasing Republican votes cast shadows of doubt and suspicion over political dealings in Montana, creating an atmosphere where politics and skepticism intertwine.

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: [ Futuristic ] and depicting this scene: In a small Montana town, a bustling election headquarters is filled with clusters of people casting their votes for Republican senators. Meanwhile, in households across the state, individuals are fervently typing "that is sus" into their keyboards, their screens illuminated with search results. The air is filled with a palpable tension as the increasing Republican votes cast shadows of doubt and suspicion over political dealings in Montana, creating an atmosphere where politics and skepticism intertwine. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a futuristic election headquarters in a small Montana town, where clusters of people are seen casting their votes for Republican senators. The scene should capture the palpable tension in the air, with shadows of doubt and suspicion looming over the political dealings. In the background, show households with individuals fervently typing "that is sus" into their keyboards, creating an atmosphere where politics and skepticism intertwine. The image should evoke the feeling of a futuristic dystopian setting, with subtle visual cues to convey the intertwining of politics and skepticism.

*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 an increase in Republican votes for Senators in Montana caused that is sus (Google searches for 'that is sus') to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'

The Journal of Political Meme Analysis

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Republican votes for Senators in Montana and Google searches for 'that is sus'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to assess this nagging question. You found a correlation coefficient of 0.9577578 and p < 0.01 for 2004 to 2020.

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]]
"The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'"

[[ABSTRACT]]
In this study, we examine the inexplicable connection between Republican votes for Senators in Montana and Google searches for "That Is Sus". While some may question the relevance of this investigation, we are determined to uncover the 'sus'-picious relationship between political inclinations and online gaming slang. Our research team pored over data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, leaving no 'sus'-picion unturned.

Drawing from the years 2004 to 2020, our analysis revealed a striking correlation coefficient of 0.9577578 and p < 0.01, establishing a robust link between these seemingly disparate variables. It appears that when Montanans cast their votes in favor of Republican Senators, Google searches for 'That Is Sus' spike like a caffeinated hedgehog. This unexpected correlation left our research team pondering whether there's a political 'imposter' lurking in the data, or if Montanans simply enjoy a good ol' game of political chess.

Indeed, the findings of this study pose more questions than answers, as we grapple with the mysterious ways of human behavior and online search trends. However, as the saying goes, "When in doubt, vent your 'sus'-picions to Google," or was it "When in doubt, consult the data"? Ah, the perils of suspicious correlations and overreliance on dad jokes.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Republican votes for Senators in Montana and Google searches for 'that is sus'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Here is the title and abstract of the paper:
[[TITLE]]
"The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'"

[[ABSTRACT]]
In this study, we examine the inexplicable connection between Republican votes for Senators in Montana and Google searches for "That Is Sus". While some may question the relevance of this investigation, we are determined to uncover the 'sus'-picious relationship between political inclinations and online gaming slang. Our research team pored over data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, leaving no 'sus'-picion unturned.

Drawing from the years 2004 to 2020, our analysis revealed a striking correlation coefficient of 0.9577578 and p < 0.01, establishing a robust link between these seemingly disparate variables. It appears that when Montanans cast their votes in favor of Republican Senators, Google searches for 'That Is Sus' spike like a caffeinated hedgehog. This unexpected correlation left our research team pondering whether there's a political 'imposter' lurking in the data, or if Montanans simply enjoy a good ol' game of political chess.

Indeed, the findings of this study pose more questions than answers, as we grapple with the mysterious ways of human behavior and online search trends. However, as the saying goes, "When in doubt, vent your 'sus'-picions to Google," or was it "When in doubt, consult the data"? Ah, the perils of suspicious correlations and overreliance on dad jokes.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The relationship between political behavior and cultural phenomena has long fascinated scholars and casual observers alike. In recent years, the rise of online gaming jargon in mainstream discourse has added a new layer of intrigue to this inquiry. Our study delves into the unexpected convergence of these realms, specifically focusing on the peculiar association between Republican votes for Senators in Montana and Google searches for "That Is Sus." It's almost as if the data is saying, "Vote for Republicans? That is sus, bro!"

Montana, known for its stunning landscapes and independent spirit, might seem an unlikely stage for this curious correlation. However, our investigation reveals a statistically robust link between political preferences and expressions of suspicion in the digital realm. It's as if the voters are saying, "I find your political stance very 'sus'-picious."

As we navigate this uncharted territory, it is crucial to approach the analysis with a keen eye for verifiable patterns and not fall victim to mere coincidence. After all, we wouldn't want to mistakenly attribute correlation to causation and create a political 'imposter' out of thin air. As a wise dad once said, "Correlation does not imply causation, but it sure makes for an intriguing plot twist."

Our research aims to shed light on the underlying motivations and contextual factors driving these uncanny parallel trends. Perhaps there's a deeper socio-cultural undercurrent at play, or maybe Montanans are simply adept at multitasking, exercising their political rights while honing their gaming lingo skills. As the old saying goes, "Why settle for a political debate when you can also navigate the tricky world of 'Among Us' imposters?"

In the following sections, we will delve into the methodological approach, data analysis, and implications of our findings, all while resisting the temptation to make "sus-piciously good" puns at every turn. Just kidding – we won't resist that temptation at all!


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 Montana and Google searches for 'that is sus'. 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
"The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'"

[[ABSTRACT]]
In this study, we examine the inexplicable connection between Republican votes for Senators in Montana and Google searches for "That Is Sus". While some may question the relevance of this investigation, we are determined to uncover the 'sus'-picious relationship between political inclinations and online gaming slang. Our research team pored over data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, leaving no 'sus'-picion unturned.

Drawing from the years 2004 to 2020, our analysis revealed a striking correlation coefficient of 0.9577578 and p < 0.01, establishing a robust link between these seemingly disparate variables. It appears that when Montanans cast their votes in favor of Republican Senators, Google searches for 'That Is Sus' spike like a caffeinated hedgehog. This unexpected correlation left our research team pondering whether there's a political 'imposter' lurking in the data, or if Montanans simply enjoy a good ol' game of political chess.

Indeed, the findings of this study pose more questions than answers, as we grapple with the mysterious ways of human behavior and online search trends. However, as the saying goes, "When in doubt, vent your 'sus'-picions to Google," or was it "When in doubt, consult the data"? Ah, the perils of suspicious correlations and overreliance on dad jokes.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between political behavior and cultural phenomena has long fascinated scholars and casual observers alike. In recent years, the rise of online gaming jargon in mainstream discourse has added a new layer of intrigue to this inquiry. Our study delves into the unexpected convergence of these realms, specifically focusing on the peculiar association between Republican votes for Senators in Montana and Google searches for "That Is Sus." It's almost as if the data is saying, "Vote for Republicans? That is sus, bro!"
Montana, known for its stunning landscapes and independent spirit, might seem an unlikely stage for this curious correlation. However, our investigation reveals a statistically robust link between political preferences and expressions of suspicion in the digital realm. It's as if the voters are saying, "I find your political stance very 'sus'-picious."
As we navigate this uncharted territory, it is crucial to approach the analysis with a keen eye for verifiable patterns and not fall victim to mere coincidence. After all, we wouldn't want to mistakenly attribute correlation to causation and create a political 'imposter' out of thin air. As a wise dad once said, "Correlation does not imply causation, but it sure makes for an intriguing plot twist."
Our research aims to shed light on the underlying motivations and contextual factors driving these uncanny parallel trends. Perhaps there's a deeper socio-cultural undercurrent at play, or maybe Montanans are simply adept at multitasking, exercising their political rights while honing their gaming lingo skills. As the old saying goes, "Why settle for a political debate when you can also navigate the tricky world of 'Among Us' imposters?"
In the following sections, we will delve into the methodological approach, data analysis, and implications of our findings, all while resisting the temptation to make "sus-piciously good" puns at every turn. Just kidding – we won't resist that temptation at all!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The correlation between political behavior and seemingly unrelated cultural trends has been a subject of great interest in the academic community. In "Smith et al.'s Study of Political Behavior and Cultural Phenomena," the authors find evidence of surprising connections between voter preferences and online linguistic expressions. However, none could have predicted the peculiar link our study seeks to explore – the correlation between Republican votes for Senators in Montana and Google searches for "That Is Sus."

As we venture into this uncharted territory of political 'sus'-picion, it's important to acknowledge the influence of popular culture on societal dynamics. In "Doe and Jones' Analysis of Pop Culture and Political Identity," the authors delve into the intersection of gaming slang and political inclination, providing a framework for understanding the unexpected convergence of these disparate realms. Little did they know that their work would serve as a precursor to our investigation of the 'sus'-pect relationship between Montanan political allegiances and online gaming expressions.

Now, as we wade deeper into the pool of interdisciplinarity, it's crucial to recognize the impact of literature on shaping societal norms and behaviors. Works such as "The Sociology of Video Game Culture" by Jane Doe and "The Politics of Suspicion" by John Smith shed light on the interconnectedness of gaming vernacular and political leanings. However, while these scholarly contributions provide valuable insights, they could not have prepared us for the absurdity of our current inquiry.

Moving away from non-fiction, we turn our attention to the realm of fiction and speculative storytelling. Books like "The Game of Politics: A Tale of Intrigue and Deception" by A. J. R. R. Martin and "Suspect Allegiances: A Political Mystery" by Agatha Christie offer fictional narratives that, while entertaining, fail to capture the sheer 'sus'-pense of our real-world data analysis. Nevertheless, in the spirit of investigation, we dream of a world where political maneuvers are as thrilling as an 'Among Us' game night.

In an unorthodox turn of events, we delved into sources outside the traditional academic landscape, perusing the annals of unconventional wisdom for insights. Alas, our literature review led us to the unlikeliest of places – the unassuming CVS receipts. Amidst the barrage of coupons and promotions, we stumbled upon cryptic messages encrypted in the small print – "Vote 'Sus'-piciously for a Senator, earn 10% off your next purchase." While we remain skeptical of the scholarly reliability of such sources, the temptation of uncovering 'sus'-picious correlations proved too irresistible to resist.

In conclusion, the literature surrounding our investigation presents a tapestry of scholarly, fictional, and outright ludicrous sources that attempt to contextualize the unprecedented correlation between Republican votes for Senators in Montana and Google searches for "That Is Sus." As we continue our journey through this enigmatic correlation, we must remember the immortal words of the academic dad joke: "Why did the statistician go to the art exhibit? To find the 'sus'-pended relationships!" Cue the groans – and the data analysis.


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 Montana and Google searches for 'that is sus'. 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]]
"The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'"

[[ABSTRACT]]
In this study, we examine the inexplicable connection between Republican votes for Senators in Montana and Google searches for "That Is Sus". While some may question the relevance of this investigation, we are determined to uncover the 'sus'-picious relationship between political inclinations and online gaming slang. Our research team pored over data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, leaving no 'sus'-picion unturned.

Drawing from the years 2004 to 2020, our analysis revealed a striking correlation coefficient of 0.9577578 and p < 0.01, establishing a robust link between these seemingly disparate variables. It appears that when Montanans cast their votes in favor of Republican Senators, Google searches for 'That Is Sus' spike like a caffeinated hedgehog. This unexpected correlation left our research team pondering whether there's a political 'imposter' lurking in the data, or if Montanans simply enjoy a good ol' game of political chess.

Indeed, the findings of this study pose more questions than answers, as we grapple with the mysterious ways of human behavior and online search trends. However, as the saying goes, "When in doubt, vent your 'sus'-picions to Google," or was it "When in doubt, consult the data"? Ah, the perils of suspicious correlations and overreliance on dad jokes.

[[INTRODUCTION]]
The relationship between political behavior and cultural phenomena has long fascinated scholars and casual observers alike. In recent years, the rise of online gaming jargon in mainstream discourse has added a new layer of intrigue to this inquiry. Our study delves into the unexpected convergence of these realms, specifically focusing on the peculiar association between Republican votes for Senators in Montana and Google searches for "That Is Sus." It's almost as if the data is saying, "Vote for Republicans? That is sus, bro!"
Montana, known for its stunning landscapes and independent spirit, might seem an unlikely stage for this curious correlation. However, our investigation reveals a statistically robust link between political preferences and expressions of suspicion in the digital realm. It's as if the voters are saying, "I find your political stance very 'sus'-picious."
As we navigate this uncharted territory, it is crucial to approach the analysis with a keen eye for verifiable patterns and not fall victim to mere coincidence. After all, we wouldn't want to mistakenly attribute correlation to causation and create a political 'imposter' out of thin air. As a wise dad once said, "Correlation does not imply causation, but it sure makes for an intriguing plot twist."
Our research aims to shed light on the underlying motivations and contextual factors driving these uncanny parallel trends. Perhaps there's a deeper socio-cultural undercurrent at play, or maybe Montanans are simply adept at multitasking, exercising their political rights while honing their gaming lingo skills. As the old saying goes, "Why settle for a political debate when you can also navigate the tricky world of 'Among Us' imposters?"
In the following sections, we will delve into the methodological approach, data analysis, and implications of our findings, all while resisting the temptation to make "sus-piciously good" puns at every turn. Just kidding – we won't resist that temptation at all!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unearth the perplexing link between Republican votes for Senators in Montana and Google searches for 'That Is Sus', our research methodology combined rigorous statistical analysis with an astute awareness of the 'sus'-picious nature of our investigation. We meticulously collected data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, harnessing the power of information from 2004 to 2020. It's safe to say we traversed the labyrinth of data with the tenacity of a detective searching for clues – or perhaps a crewmate unmasking an imposter in 'Among Us'.

Our first step in this 'suspicious' journey involved obtaining the historical voting records for Republican Senators in Montana. This process required traversing the political archives as meticulously as one would navigate a maze in search of the imposter. After all, a wrong turn in data collection can lead to a false accusation – or an erroneous statistical inference. We then culled data from Google Trends, diligently tracking the frequency of searches for the phrase 'That Is Sus'. It's almost as if we were surveying the gaming landscape for signs of shifty behavior, only in this case, our suspects were political allegiances and online search queries.

Once armed with this arsenal of data, we employed a variety of statistical techniques to unveil the 'sus'-picious patterns hidden within. Our analysis commenced with a correlation matrix, reminiscent of a detective's evidence board, wherein we diligently sought connections between Republican votes and 'That Is Sus' searches. We then calculated a Pearson correlation coefficient, a statistical measure often employed to reveal the underlying relationships between variables. The correlation coefficient stood at a striking 0.9577578, indicating a near-perfect positive correlation between our enigmatic variables. It's as if the data was saying, "I see you, imposter. That political allegiance is 'sus'!"

The next phase of our analysis involved conducting a time-series examination, tracking the fluctuations of Republican votes and 'That Is Sus' searches over the years. This method allowed us to discern any temporal nuances in the 'sus'-picious relationship. Much like a skilled detective piecing together a timeline of events, we reconstructed the narrative of political preferences and online queries, noting how they seemed to shadow each other like 'Among Us' characters traversing the map.

In addition to our statistical inquiries, we also engaged in qualitative analyses, scrutinizing local events, political campaigns, and cultural shifts in Montana during the studied period. We sought to contextualize our findings within the socio-political landscape, as understanding the broader environment is vital to deciphering 'sus'-pect behavior – whether in politics or online gaming realms.

Lastly, to ensure the robustness of our findings, we employed sensitivity analyses and cross-validated our results through a simulated 'emergency meeting' with peer researchers to deliberate the reliability of our conclusions. After all, in the pursuit of scientific inquiry, it's essential to have a trusted crew to corroborate your findings, or in this case, to ensure we weren't being 'sus' ourselves.


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 Montana and Google searches for 'that is sus'. 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 0.9577578, r-squared of 0.9173000, 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]]
"The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'"

[[ABSTRACT]]
In this study, we examine the inexplicable connection between Republican votes for Senators in Montana and Google searches for "That Is Sus". While some may question the relevance of this investigation, we are determined to uncover the 'sus'-picious relationship between political inclinations and online gaming slang. Our research team pored over data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, leaving no 'sus'-picion unturned.

Drawing from the years 2004 to 2020, our analysis revealed a striking correlation coefficient of 0.9577578 and p < 0.01, establishing a robust link between these seemingly disparate variables. It appears that when Montanans cast their votes in favor of Republican Senators, Google searches for 'That Is Sus' spike like a caffeinated hedgehog. This unexpected correlation left our research team pondering whether there's a political 'imposter' lurking in the data, or if Montanans simply enjoy a good ol' game of political chess.

Indeed, the findings of this study pose more questions than answers, as we grapple with the mysterious ways of human behavior and online search trends. However, as the saying goes, "When in doubt, vent your 'sus'-picions to Google," or was it "When in doubt, consult the data"? Ah, the perils of suspicious correlations and overreliance on dad jokes.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The relationship between political behavior and cultural phenomena has long fascinated scholars and casual observers alike. In recent years, the rise of online gaming jargon in mainstream discourse has added a new layer of intrigue to this inquiry. Our study delves into the unexpected convergence of these realms, specifically focusing on the peculiar association between Republican votes for Senators in Montana and Google searches for "That Is Sus." It's almost as if the data is saying, "Vote for Republicans? That is sus, bro!"
Montana, known for its stunning landscapes and independent spirit, might seem an unlikely stage for this curious correlation. However, our investigation reveals a statistically robust link between political preferences and expressions of suspicion in the digital realm. It's as if the voters are saying, "I find your political stance very 'sus'-picious."
As we navigate this uncharted territory, it is crucial to approach the analysis with a keen eye for verifiable patterns and not fall victim to mere coincidence. After all, we wouldn't want to mistakenly attribute correlation to causation and create a political 'imposter' out of thin air. As a wise dad once said, "Correlation does not imply causation, but it sure makes for an intriguing plot twist."
Our research aims to shed light on the underlying motivations and contextual factors driving these uncanny parallel trends. Perhaps there's a deeper socio-cultural undercurrent at play, or maybe Montanans are simply adept at multitasking, exercising their political rights while honing their gaming lingo skills. As the old saying goes, "Why settle for a political debate when you can also navigate the tricky world of 'Among Us' imposters?"
In the following sections, we will delve into the methodological approach, data analysis, and implications of our findings, all while resisting the temptation to make "sus-piciously good" puns at every turn. Just kidding – we won't resist that temptation at all!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our study revealed a remarkably strong correlation of 0.9577578 between Republican votes for Senators in Montana and Google searches for "That Is Sus" over the period from 2004 to 2020. This correlation was statistically significant, with an r-squared value of 0.9173000 and p < 0.01, indicating that the likelihood of this relationship occurring by mere chance is about as rare as finding a politician without a well-rehearsed handshake.

We observed that as the Republican vote share increased in Montana, there was a simultaneous surge in Google searches for "That Is Sus". It's as if the voters were expressing their skepticism in both the political and digital realms. One might even say that the voters were 'imposter-ing' as savvy online gamers while casting their political choices. After all, why settle for electing officials when you can also navigate the treacherous world of 'Among Us' imposters?

**Dad Joke Alert:** If a politician plays 'Among Us', do they make sus-piciously good imposters, or are they just well-versed in political maneuvering?

As illustrated in Fig. 1, the scatterplot depicts a clear, upward trend, demonstrating the close relationship between these two seemingly distinct variables. The data points are so closely clustered together, it's as if they were conspiring to reveal this suspicious correlation all along. One might even think of them as a digital caucus, whispering 'sus'-picious nothings to one another in a language only interpretable by seasoned internet sleuths.

**Dad Joke Alert:** What do you call a group of data points that always stick together? A sus-picion of correlation!

The unexpectedness of this correlation leaves us with more questions than answers. Are Montanans slyly expressing their reservations through online search behavior, or are they simply adept at multi-tasking their political and gaming sensibilities? It's almost as if they're saying, "Your political stance is 'sus'-picious, but don't worry, we'll vote first and then join you for a game of 'Among Us' to discuss it further."

In conclusion, this study unravels a peculiar link between Republican votes for Senators in Montana and the surge in Google searches for 'That Is Sus', shedding light on the intertwined nature of political behavior and digital culture. As we consider the implications of these findings, let us not forget the immortal words of a dad: "When in doubt, always check for 'sus'-picious activity – whether it's in politics or a game of 'Among Us'."


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 Montana and Google searches for 'that is sus'. 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]]
"The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'"

[[ABSTRACT]]
In this study, we examine the inexplicable connection between Republican votes for Senators in Montana and Google searches for "That Is Sus". While some may question the relevance of this investigation, we are determined to uncover the 'sus'-picious relationship between political inclinations and online gaming slang. Our research team pored over data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, leaving no 'sus'-picion unturned.

Drawing from the years 2004 to 2020, our analysis revealed a striking correlation coefficient of 0.9577578 and p < 0.01, establishing a robust link between these seemingly disparate variables. It appears that when Montanans cast their votes in favor of Republican Senators, Google searches for 'That Is Sus' spike like a caffeinated hedgehog. This unexpected correlation left our research team pondering whether there's a political 'imposter' lurking in the data, or if Montanans simply enjoy a good ol' game of political chess.

Indeed, the findings of this study pose more questions than answers, as we grapple with the mysterious ways of human behavior and online search trends. However, as the saying goes, "When in doubt, vent your 'sus'-picions to Google," or was it "When in doubt, consult the data"? Ah, the perils of suspicious correlations and overreliance on dad jokes.

[[LITERATURE REVIEW]]
The correlation between political behavior and seemingly unrelated cultural trends has been a subject of great interest in the academic community. In "Smith et al.'s Study of Political Behavior and Cultural Phenomena," the authors find evidence of surprising connections between voter preferences and online linguistic expressions. However, none could have predicted the peculiar link our study seeks to explore – the correlation between Republican votes for Senators in Montana and Google searches for "That Is Sus."
As we venture into this uncharted territory of political 'sus'-picion, it's important to acknowledge the influence of popular culture on societal dynamics. In "Doe and Jones' Analysis of Pop Culture and Political Identity," the authors delve into the intersection of gaming slang and political inclination, providing a framework for understanding the unexpected convergence of these disparate realms. Little did they know that their work would serve as a precursor to our investigation of the 'sus'-pect relationship between Montanan political allegiances and online gaming expressions.
Now, as we wade deeper into the pool of interdisciplinarity, it's crucial to recognize the impact of literature on shaping societal norms and behaviors. Works such as "The Sociology of Video Game Culture" by Jane Doe and "The Politics of Suspicion" by John Smith shed light on the interconnectedness of gaming vernacular and political leanings. However, while these scholarly contributions provide valuable insights, they could not have prepared us for the absurdity of our current inquiry.
Moving away from non-fiction, we turn our attention to the realm of fiction and speculative storytelling. Books like "The Game of Politics: A Tale of Intrigue and Deception" by A. J. R. R. Martin and "Suspect Allegiances: A Political Mystery" by Agatha Christie offer fictional narratives that, while entertaining, fail to capture the sheer 'sus'-pense of our real-world data analysis. Nevertheless, in the spirit of investigation, we dream of a world where political maneuvers are as thrilling as an 'Among Us' game night.
In an unorthodox turn of events, we delved into sources outside the traditional academic landscape, perusing the annals of unconventional wisdom for insights. Alas, our literature review led us to the unlikeliest of places – the unassuming CVS receipts. Amidst the barrage of coupons and promotions, we stumbled upon cryptic messages encrypted in the small print – "Vote 'Sus'-piciously for a Senator, earn 10% off your next purchase." While we remain skeptical of the scholarly reliability of such sources, the temptation of uncovering 'sus'-picious correlations proved too irresistible to resist.
In conclusion, the literature surrounding our investigation presents a tapestry of scholarly, fictional, and outright ludicrous sources that attempt to contextualize the unprecedented correlation between Republican votes for Senators in Montana and Google searches for "That Is Sus." As we continue our journey through this enigmatic correlation, we must remember the immortal words of the academic dad joke: "Why did the statistician go to the art exhibit? To find the 'sus'-pended relationships!" Cue the groans – and the data analysis.

[[RESULTS]]
The results of our study revealed a remarkably strong correlation of 0.9577578 between Republican votes for Senators in Montana and Google searches for "That Is Sus" over the period from 2004 to 2020. This correlation was statistically significant, with an r-squared value of 0.9173000 and p < 0.01, indicating that the likelihood of this relationship occurring by mere chance is about as rare as finding a politician without a well-rehearsed handshake.
We observed that as the Republican vote share increased in Montana, there was a simultaneous surge in Google searches for "That Is Sus". It's as if the voters were expressing their skepticism in both the political and digital realms. One might even say that the voters were 'imposter-ing' as savvy online gamers while casting their political choices. After all, why settle for electing officials when you can also navigate the treacherous world of 'Among Us' imposters?
If a politician plays 'Among Us', do they make sus-piciously good imposters, or are they just well-versed in political maneuvering?
As illustrated in Fig. 1, the scatterplot depicts a clear, upward trend, demonstrating the close relationship between these two seemingly distinct variables. The data points are so closely clustered together, it's as if they were conspiring to reveal this suspicious correlation all along. One might even think of them as a digital caucus, whispering 'sus'-picious nothings to one another in a language only interpretable by seasoned internet sleuths.
What do you call a group of data points that always stick together? A sus-picion of correlation!
The unexpectedness of this correlation leaves us with more questions than answers. Are Montanans slyly expressing their reservations through online search behavior, or are they simply adept at multi-tasking their political and gaming sensibilities? It's almost as if they're saying, "Your political stance is 'sus'-picious, but don't worry, we'll vote first and then join you for a game of 'Among Us' to discuss it further."
In conclusion, this study unravels a peculiar link between Republican votes for Senators in Montana and the surge in Google searches for 'That Is Sus', shedding light on the intertwined nature of political behavior and digital culture. As we consider the implications of these findings, let us not forget the immortal words of a dad: "When in doubt, always check for 'sus'-picious activity – whether it's in politics or a game of 'Among Us'."

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our study have unearthed a surprisingly robust connection between Republican votes for Senators in Montana and the escalation of Google searches for "That Is Sus". It seems that as political preferences lean towards the GOP, Montanans channel their 'sus'-picion into the digital sphere with fervor. One might say they're voting with their ballots and their keyboards, all in the name of political and gaming intrigue. Speaking of intrigue, if a Senator played 'Among Us', would they be a particularly sly imposter, or are their skills limited to the world of political maneuvering?

Our findings further strengthen the existing body of research that delves into the amalgamation of political proclivities and modern cultural phenomena. The surprising convergence of these seemingly unrelated domains not only aligns with Smith et al.'s work on political behavior and linguistic expressions but also lends empirical credence to Doe and Jones' exploration of the intersection of gaming vernacular and political inclinations. It's as if our data is whispering 'sus'-picious confirmations of prior research, like a cohort of data points plotting a statistical conspiracy. Honestly, what do you call a group of data points that always stick together? A sus-picion of correlation!

Our study echoes the pivotal role of popular culture in shaping societal dynamics, shedding light on the unanticipated interplay between online gaming slang and political leanings. From a statistical standpoint, the strength of the correlation coefficient and the significant p-value reaffirm the importance of considering the 'sus'-picious patterns that defy conventional wisdom and statistical expectations. In the wise words of a dad statistician at an art exhibit, "When in doubt, vent your 'sus'-picions to Google Trends!"

As we grapple with the enigma of this correlation, we're reminded of an academic dad joke: "Why don't data points ever go to parties? They're afraid of being labeled 'sus'-picious outliers." In a similar vein, it's as if our data points are colluding in a digital caucus, with each point serving as a 'sus'-picion cast upon the seemingly disparate worlds of political allegiance and online gaming expressions. The perplexing nature of this linkage propels us further into the realm of interdisciplinary exploration, as we endeavor to comprehend the intricate dance of voter sentiments and digital 'sus'-picion.

Indeed, the riddle of this correlation persists, leaving us with more questions than answers. Are Montanans leveraging Google searches to covertly express their reservations, or are they weaving a tapestry of multifaceted political and gaming sensibilities? It's as though they're announcing, "Your political stance is 'sus'-picious, but fear not - we'll cast our votes first, then convene for a game of 'Among Us' to hash it out further."

Thus, our research contributes a fascinating layer to the intricate fabric of societal interactions, one that intertwines political behavior and digital culture in an unexpected yet undeniable connection. In the words of an academic dad, "When in doubt, always check for 'sus'-picious activity - whether it's in politics or a game of 'Among Us'." And with that, let the digital 'sus'-pense continue!


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 Montana and Google searches for 'that is sus'. 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]]
"The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'"

[[ABSTRACT]]
In this study, we examine the inexplicable connection between Republican votes for Senators in Montana and Google searches for "That Is Sus". While some may question the relevance of this investigation, we are determined to uncover the 'sus'-picious relationship between political inclinations and online gaming slang. Our research team pored over data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, leaving no 'sus'-picion unturned.

Drawing from the years 2004 to 2020, our analysis revealed a striking correlation coefficient of 0.9577578 and p < 0.01, establishing a robust link between these seemingly disparate variables. It appears that when Montanans cast their votes in favor of Republican Senators, Google searches for 'That Is Sus' spike like a caffeinated hedgehog. This unexpected correlation left our research team pondering whether there's a political 'imposter' lurking in the data, or if Montanans simply enjoy a good ol' game of political chess.

Indeed, the findings of this study pose more questions than answers, as we grapple with the mysterious ways of human behavior and online search trends. However, as the saying goes, "When in doubt, vent your 'sus'-picions to Google," or was it "When in doubt, consult the data"? Ah, the perils of suspicious correlations and overreliance on dad jokes.

[[INTRDUCTION]]
The relationship between political behavior and cultural phenomena has long fascinated scholars and casual observers alike. In recent years, the rise of online gaming jargon in mainstream discourse has added a new layer of intrigue to this inquiry. Our study delves into the unexpected convergence of these realms, specifically focusing on the peculiar association between Republican votes for Senators in Montana and Google searches for "That Is Sus." It's almost as if the data is saying, "Vote for Republicans? That is sus, bro!"
Montana, known for its stunning landscapes and independent spirit, might seem an unlikely stage for this curious correlation. However, our investigation reveals a statistically robust link between political preferences and expressions of suspicion in the digital realm. It's as if the voters are saying, "I find your political stance very 'sus'-picious."
As we navigate this uncharted territory, it is crucial to approach the analysis with a keen eye for verifiable patterns and not fall victim to mere coincidence. After all, we wouldn't want to mistakenly attribute correlation to causation and create a political 'imposter' out of thin air. As a wise dad once said, "Correlation does not imply causation, but it sure makes for an intriguing plot twist."
Our research aims to shed light on the underlying motivations and contextual factors driving these uncanny parallel trends. Perhaps there's a deeper socio-cultural undercurrent at play, or maybe Montanans are simply adept at multitasking, exercising their political rights while honing their gaming lingo skills. As the old saying goes, "Why settle for a political debate when you can also navigate the tricky world of 'Among Us' imposters?"
In the following sections, we will delve into the methodological approach, data analysis, and implications of our findings, all while resisting the temptation to make "sus-piciously good" puns at every turn. Just kidding – we won't resist that temptation at all!

[[RESULTS]]
The results of our study revealed a remarkably strong correlation of 0.9577578 between Republican votes for Senators in Montana and Google searches for "That Is Sus" over the period from 2004 to 2020. This correlation was statistically significant, with an r-squared value of 0.9173000 and p < 0.01, indicating that the likelihood of this relationship occurring by mere chance is about as rare as finding a politician without a well-rehearsed handshake.
We observed that as the Republican vote share increased in Montana, there was a simultaneous surge in Google searches for "That Is Sus". It's as if the voters were expressing their skepticism in both the political and digital realms. One might even say that the voters were 'imposter-ing' as savvy online gamers while casting their political choices. After all, why settle for electing officials when you can also navigate the treacherous world of 'Among Us' imposters?
If a politician plays 'Among Us', do they make sus-piciously good imposters, or are they just well-versed in political maneuvering?
As illustrated in Fig. 1, the scatterplot depicts a clear, upward trend, demonstrating the close relationship between these two seemingly distinct variables. The data points are so closely clustered together, it's as if they were conspiring to reveal this suspicious correlation all along. One might even think of them as a digital caucus, whispering 'sus'-picious nothings to one another in a language only interpretable by seasoned internet sleuths.
What do you call a group of data points that always stick together? A sus-picion of correlation!
The unexpectedness of this correlation leaves us with more questions than answers. Are Montanans slyly expressing their reservations through online search behavior, or are they simply adept at multi-tasking their political and gaming sensibilities? It's almost as if they're saying, "Your political stance is 'sus'-picious, but don't worry, we'll vote first and then join you for a game of 'Among Us' to discuss it further."
In conclusion, this study unravels a peculiar link between Republican votes for Senators in Montana and the surge in Google searches for 'That Is Sus', shedding light on the intertwined nature of political behavior and digital culture. As we consider the implications of these findings, let us not forget the immortal words of a dad: "When in doubt, always check for 'sus'-picious activity – whether it's in politics or a game of 'Among Us'."

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has illuminated an unexpected and rather 'sus'-picious correlation between Republican votes for Senators in Montana and the surge in Google searches for "That Is Sus". It's as if the voters were covertly signaling their skepticism through both the ballot box and the keyboard, leaving us to wonder if there's a game of political 'Among Us' happening right under our noses. One thing's for sure: the plot certainly thickens faster than a politician's campaign promises!

As we wrap up this investigation, it's worth remembering that while correlation does not imply causation, it does imply a good opportunity for racking up 'sus'-piciously delightful puns. After all, why settle for serious discussions when you can sprinkle them with humor and dad jokes like confetti?

These findings prompt us to ponder the intricate dance between political inclinations and online culture. It appears that Montanans have found a way to blend their civic duties with a flair for online gaming lingo, creating a digital mosaic of intrigue and 'sus'-pense that even Sherlock Holmes would find compelling. Perhaps the next Montana Senate race will be decided not only by policy platforms but also by the ability to suss out the 'imposters' in our midst, both online and in the voting booth.

In the grand tradition of dad jokes, let's all remember that when it comes to uncovering 'sus'-picious correlations, we should always seek the wisdom of our fathers – or at least consult Google Trends. After all, as a wise dad once said, "When in doubt, trust the data, and when in double-doubt, consult the online wisdom of the 'sus'-pecting crowd."

In conclusion, it's clear that no more research is needed in this area. The correlation is as real as a genuine apology from an 'Among Us' player caught red-handed venting.


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 The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Meme Analysis


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 The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus'. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Political Meme Analysis and Research


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 The GOP is Sus: A Correlational Study of Republican Votes for Senators in Montana and Google Searches for 'That Is Sus' with an abstract of In this study, we examine the inexplicable connection between Republican votes for Senators in Montana and Google searches for "That Is Sus". While some may question the relevance of this investigation, we are determined to uncover the 'sus'-picious relationship between political inclinations and online gaming slang. Our research team pored over data from the MIT Election Data and Science Lab, Harvard Dataverse, and Google Trends, leaving no 'sus'-picion unturned.
Drawing from the years 2004 to 2020, our analysis revealed a striking correlation coefficient of 0.9577578 and p < 0.01, establishing a robust link between these seemingly disparate variables. It appears that when Montanans cast their votes in favor of Republican Senators, Google searches for 'That Is Sus' spike like a caffeinated hedgehog. This unexpected correlation left our research team pondering whether there's a political 'imposter' lurking in the data, or if Montanans simply enjoy a good ol' game of political chess.
Indeed, the findings of this study pose more questions than answers, as we grapple with the mysterious ways of human behavior and online search trends. However, as the saying goes, "When in doubt, vent your 'sus'-picions to Google," or was it "When in doubt, consult the data"? Ah, the perils of suspicious correlations and overreliance on dad jokes.

ChatGPT:

Republican votes, Senators, Montana, Google searches, "That Is Sus", correlation study, election data, online gaming slang, political inclinations, MIT Election Data and Science Lab, Harvard Dataverse, Google Trends, correlation coefficient, Montanans, political behavior, online search trends

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

Google searches for 'that is sus'
Detailed data title: Relative volume of Google searches for 'that is sus' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'that is sus'

Correlation r = 0.9577578 (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 = 0.9173000 (Coefficient of determination)
This means 91.7% of the change in the one variable (i.e., Google searches for 'that is sus') is predictable based on the change in the other (i.e., Votes for Republican Senators in Montana) over the 6 years from 2004 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0026. 0.0026389161582989116000000000
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 0.96 in 0.26% of random cases. Said differently, if you correlated 379 random variables Which I absolutely did.
with the same 5 degrees of freedom, 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.

[ 0.66, 1 ] 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.
200620082012201420182020
Votes for Republican Senators in Montana (Total votes)196283129369218051213709235963333174
Google searches for 'that is sus' (Rel. search volume)8.666671.3333310.258.6666715.416740.8333




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. Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
  5. 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.
  6. 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([196283,129369,218051,213709,235963,333174,])
array_2 = np.array([8.66667,1.33333,10.25,8.66667,15.4167,40.8333,])
array_1_name = "Votes for Republican Senators in Montana"
array_2_name = "Google searches for 'that is sus'"

# 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?

You're the correlation whisperer we needed!


Correlation ID: 5170 · Black Variable ID: 26271 · Red Variable ID: 1367
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0