about · email me · subscribe
Spurious correlation #4,356 · 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 South Carolina and the second variable is Google searches for 'where do birds go when it rains'.  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 Republican votes in South Carolina have sparked a new 'tweet-er in town' initiative, leading to the passing of legislation for bird-friendly shelters in the state. This has created a 'flock-ing' great environment, encouraging our feathered friends to seek cover and stay 'dry as a bone'. It seems like these political changes have truly 'ruffled some feathers' in the avian community, and now the birds have a whole new 'reign' of options when it pours.

Model: dalle-3
Prompt: Create an image of a tranquil rain-soaked landscape in South Carolina, with lush greenery and colorful bird-friendly shelters dotting the scene. Show a variety of birds nestled comfortably within the shelters, seeking cover from the rain, while the sky is filled with hints of vibrant blue and orange hues. The scene should evoke a sense of harmony and coexistence between humans and wildlife, capturing the spirit of the new legislation and the curiosity sparked by the increase in Google searches about birds and rain shelters. 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 South Carolina and Google searches for 'where do birds go when it rains'. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Woodblock painting a Polaroid photo Data cyber art An image that looks like it is a scene from A Disney Movie A photo-realistic image
ChatGPT: Data cyber 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 South Carolina and Google searches for 'where do birds go when it rains', in the following situation: The Republican votes in South Carolina have sparked a new 'tweet-er in town' initiative, leading to the passing of legislation for bird-friendly shelters in the state. This has created a 'flock-ing' great environment, encouraging our feathered friends to seek cover and stay 'dry as a bone'. It seems like these political changes have truly 'ruffled some feathers' in the avian community, and now the birds have a whole new 'reign' of options when it pours.. Keep the description simple.
ChatGPT: In South Carolina, Republican votes have led to new legislation for bird-friendly shelters. As a result, birds are now seeking cover from the rain in these shelters. Meanwhile, Google searches for 'where do birds go when it rains' in South Carolina have increased, reflecting the interest in the new initiative.

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: [ Data cyber art ] and depicting this scene: In South Carolina, Republican votes have led to new legislation for bird-friendly shelters. As a result, birds are now seeking cover from the rain in these shelters. Meanwhile, Google searches for 'where do birds go when it rains' in South Carolina have increased, reflecting the interest in the new initiative. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a tranquil rain-soaked landscape in South Carolina, with lush greenery and colorful bird-friendly shelters dotting the scene. Show a variety of birds nestled comfortably within the shelters, seeking cover from the rain, while the sky is filled with hints of vibrant blue and orange hues. The scene should evoke a sense of harmony and coexistence between humans and wildlife, capturing the spirit of the new legislation and the curiosity sparked by the increase in Google searches about birds and rain shelters.

*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 increases in Republican votes for Senators in South Carolina positively influenced where do birds go when it rains (Google searches for 'where do birds go when it rains'). Include one good pun.

AI academic paper

(Because p < 0.01)
Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts

The Journal of Political Avifauna Research

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 South Carolina and Google searches for 'where do birds go when it rains'. 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 0.9625829 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]]
"Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts"

[[ABSTRACT]]
In this paper, we investigate the relationship between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." Our research team delved into the MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to unravel this mysterious connection. We found a correlation coefficient of 0.9625829 and p < 0.01 for the time period spanning from 2004 to 2020, leading us to ponder: are the voters and the birds flocking together when rain starts to pour? *Caw*-relation or *caw*-incidence?

The study scrutinized the unexpected affinity between conservative votes and ornithological inquisitiveness during inclement weather. What's the *tweeting* point of this strange correlation, you ask? Well, our findings suggest that as Republican support increases in South Carolina, so does curiosity about the sheltering habits of our feathered friends during rainy spells. Is it possible that constituents' political leanings might be as predictable as a bird seeking refuge from a thunderstorm? *Chirp*haps!

The implication of our research extends beyond mere caw-ncidence. It raises intriguing questions about the intersection of human behavior and wildlife curiosity, not to mention the potential electoral impact of avian meteorological musings. Our findings add a light-hearted dimension to the serious realm of political science, reminding us that even the most unexpected correlations can surface when we spread our wings and take a closer look at the data.


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 South Carolina and Google searches for 'where do birds go when it rains'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts"

[[ABSTRACT]]
In this paper, we investigate the relationship between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." Our research team delved into the MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to unravel this mysterious connection. We found a correlation coefficient of 0.9625829 and p < 0.01 for the time period spanning from 2004 to 2020, leading us to ponder: are the voters and the birds flocking together when rain starts to pour? *Caw*-relation or *caw*-incidence?

The study scrutinized the unexpected affinity between conservative votes and ornithological inquisitiveness during inclement weather. What's the *tweeting* point of this strange correlation, you ask? Well, our findings suggest that as Republican support increases in South Carolina, so does curiosity about the sheltering habits of our feathered friends during rainy spells. Is it possible that constituents' political leanings might be as predictable as a bird seeking refuge from a thunderstorm? *Chirp*haps!

The implication of our research extends beyond mere caw-ncidence. It raises intriguing questions about the intersection of human behavior and wildlife curiosity, not to mention the potential electoral impact of avian meteorological musings. Our findings add a light-hearted dimension to the serious realm of political science, reminding us that even the most unexpected correlations can surface when we spread our wings and take a closer look at the data.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As the saying goes, "birds of a feather flock together," but little did we know that this adage might extend to political inclinations as well. In this paper, we soar into the uncharted territory of political science and avian behavior to uncover the surprising link between Republican votes for Senators in South Carolina and the peculiar curiosity about the whereabouts of our feathered friends during rainfall. It seems that our investigation has truly taken flight into unexplored territory, much like a bird on the hunt for a good nesting spot.

Our feather-brained curiosity about the connection between conservative politics and avian musings led us to embark on a data-driven journey. With a wing and a prayer, we ventured into the realm of electoral data from the MIT Election Data and Science Lab and Harvard Dataverse, alongside Google Trends data on the search inquiry "where do birds go when it rains." Like a flock of eager birdwatchers, we peered through the statistical binoculars, ready to spot any correlations that might *quack* us up.

The correlation coefficient of 0.9625829 and p < 0.01 that we uncovered left us feeling like we had discovered a rare bird indeed. As we dug deeper into the data, the question that lingered in our minds was one that truly ruffled our feathers: could it be that the voters who stand behind Republican candidates also harbor a deep-seated fascination for the rain-dodging tactics of our feathered neighbors? It's a conundrum that has sent us into a tailspin, not unlike a confused bird navigating a sudden gust of wind.

This unexpected bond between political allegiance and avian precipitation ponderings begs the question: are voters and birds truly *caw*-related, or is it merely a *waddle* and quirky happenstance? As we brace ourselves for the journey ahead, we invite the reader to spread their wings and join us in unraveling the mystery of this ornitho-political phenomenon. After all, in the world of research, it's important to remember that sometimes the most surprising discoveries come from taking a chance on an unassuming Google search.


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 South Carolina and Google searches for 'where do birds go when it rains'. 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]]
"Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts"

[[ABSTRACT]]
In this paper, we investigate the relationship between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." Our research team delved into the MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to unravel this mysterious connection. We found a correlation coefficient of 0.9625829 and p < 0.01 for the time period spanning from 2004 to 2020, leading us to ponder: are the voters and the birds flocking together when rain starts to pour? *Caw*-relation or *caw*-incidence?

The study scrutinized the unexpected affinity between conservative votes and ornithological inquisitiveness during inclement weather. What's the *tweeting* point of this strange correlation, you ask? Well, our findings suggest that as Republican support increases in South Carolina, so does curiosity about the sheltering habits of our feathered friends during rainy spells. Is it possible that constituents' political leanings might be as predictable as a bird seeking refuge from a thunderstorm? *Chirp*haps!

The implication of our research extends beyond mere caw-ncidence. It raises intriguing questions about the intersection of human behavior and wildlife curiosity, not to mention the potential electoral impact of avian meteorological musings. Our findings add a light-hearted dimension to the serious realm of political science, reminding us that even the most unexpected correlations can surface when we spread our wings and take a closer look at the data.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the saying goes, "birds of a feather flock together," but little did we know that this adage might extend to political inclinations as well. In this paper, we soar into the uncharted territory of political science and avian behavior to uncover the surprising link between Republican votes for Senators in South Carolina and the peculiar curiosity about the whereabouts of our feathered friends during rainfall. It seems that our investigation has truly taken flight into unexplored territory, much like a bird on the hunt for a good nesting spot.
Our feather-brained curiosity about the connection between conservative politics and avian musings led us to embark on a data-driven journey. With a wing and a prayer, we ventured into the realm of electoral data from the MIT Election Data and Science Lab and Harvard Dataverse, alongside Google Trends data on the search inquiry "where do birds go when it rains." Like a flock of eager birdwatchers, we peered through the statistical binoculars, ready to spot any correlations that might *quack* us up.
The correlation coefficient of 0.9625829 and p < 0.01 that we uncovered left us feeling like we had discovered a rare bird indeed. As we dug deeper into the data, the question that lingered in our minds was one that truly ruffled our feathers: could it be that the voters who stand behind Republican candidates also harbor a deep-seated fascination for the rain-dodging tactics of our feathered neighbors? It's a conundrum that has sent us into a tailspin, not unlike a confused bird navigating a sudden gust of wind.
This unexpected bond between political allegiance and avian precipitation ponderings begs the question: are voters and birds truly *caw*-related, or is it merely a *waddle* and quirky happenstance? As we brace ourselves for the journey ahead, we invite the reader to spread their wings and join us in unraveling the mystery of this ornitho-political phenomenon. After all, in the world of research, it's important to remember that sometimes the most surprising discoveries come from taking a chance on an unassuming Google search.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith and Doe (2010) conducted a comprehensive analysis of political voting patterns in South Carolina, shedding light on the complex dynamics of conservative support in the region. Their study, though insightful, failed to account for the potential influence of avian weather-related inquiries on voter behavior. Nevertheless, it laid a solid foundation for understanding the broader contextual factors at play.

Jones (2015) further examined the intricacies of online search behavior, highlighting the significance of understanding users' curiosity-driven queries. However, their focus remained predominantly on commercial intent, leaving an avian-sized gap in the exploration of political and ornithological intrigue.

Turning to works beyond the immediate scope of the field, "The Audubon Society Field Guide to North American Birds" (Peterson, 2008) and "Birdwatching for Dummies" (Dunning, 2012) offer valuable insights into bird behavior and habitat preferences but do not directly address the potential link between political voting and avian curiosity.

As we venture into more tangentially related literature, "To Kill a Mockingbird" (Lee, 1960) and "The Raven" (Poe, 1845) stimulate contemplation on avian symbolism in human culture and literature, yet regrettably diverge from the empirical inquiry at hand.

In a somewhat unorthodox approach to literature review, we also perused the contents of a CVS receipt unearthed from a local store, hoping to find hidden insights within its mundane details. While the receipt failed to yield any pertinent information, it did confirm the purchase of birdseed and a Republican candidate's flyer, hinting at a potential intersection between political advocacy and bird care--talk about multitasking!


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 South Carolina and Google searches for 'where do birds go when it rains'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts"

[[ABSTRACT]]
In this paper, we investigate the relationship between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." Our research team delved into the MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to unravel this mysterious connection. We found a correlation coefficient of 0.9625829 and p < 0.01 for the time period spanning from 2004 to 2020, leading us to ponder: are the voters and the birds flocking together when rain starts to pour? *Caw*-relation or *caw*-incidence?

The study scrutinized the unexpected affinity between conservative votes and ornithological inquisitiveness during inclement weather. What's the *tweeting* point of this strange correlation, you ask? Well, our findings suggest that as Republican support increases in South Carolina, so does curiosity about the sheltering habits of our feathered friends during rainy spells. Is it possible that constituents' political leanings might be as predictable as a bird seeking refuge from a thunderstorm? *Chirp*haps!

The implication of our research extends beyond mere caw-ncidence. It raises intriguing questions about the intersection of human behavior and wildlife curiosity, not to mention the potential electoral impact of avian meteorological musings. Our findings add a light-hearted dimension to the serious realm of political science, reminding us that even the most unexpected correlations can surface when we spread our wings and take a closer look at the data.

[[INTRODUCTION]]
As the saying goes, "birds of a feather flock together," but little did we know that this adage might extend to political inclinations as well. In this paper, we soar into the uncharted territory of political science and avian behavior to uncover the surprising link between Republican votes for Senators in South Carolina and the peculiar curiosity about the whereabouts of our feathered friends during rainfall. It seems that our investigation has truly taken flight into unexplored territory, much like a bird on the hunt for a good nesting spot.
Our feather-brained curiosity about the connection between conservative politics and avian musings led us to embark on a data-driven journey. With a wing and a prayer, we ventured into the realm of electoral data from the MIT Election Data and Science Lab and Harvard Dataverse, alongside Google Trends data on the search inquiry "where do birds go when it rains." Like a flock of eager birdwatchers, we peered through the statistical binoculars, ready to spot any correlations that might *quack* us up.
The correlation coefficient of 0.9625829 and p < 0.01 that we uncovered left us feeling like we had discovered a rare bird indeed. As we dug deeper into the data, the question that lingered in our minds was one that truly ruffled our feathers: could it be that the voters who stand behind Republican candidates also harbor a deep-seated fascination for the rain-dodging tactics of our feathered neighbors? It's a conundrum that has sent us into a tailspin, not unlike a confused bird navigating a sudden gust of wind.
This unexpected bond between political allegiance and avian precipitation ponderings begs the question: are voters and birds truly *caw*-related, or is it merely a *waddle* and quirky happenstance? As we brace ourselves for the journey ahead, we invite the reader to spread their wings and join us in unraveling the mystery of this ornitho-political phenomenon. After all, in the world of research, it's important to remember that sometimes the most surprising discoveries come from taking a chance on an unassuming Google search.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:


[[METHODOLOGY]]

In order to untangle the elusive correlation between Republican votes for South Carolina Senators and the Google inquiries into the whereabouts of rain-dodging birds, our research team embarked on a methodological odyssey worthy of a convoluted treasure map. First, we amassed electoral data from the MIT Election Data and Science Lab and Harvard Dataverse, meticulously combing through the digital haystack to find the proverbial political needles in the data haystack. It was a bit like looking for a specific nest in a forest full of nests - a proper *egg* hunt, if you will.

To complement our electoral data, we turned to Google Trends, using the search query "where do birds go when it rains" as our avian curiosity litmus test. This endeavor had us feeling like modern-day bird whisperers, except instead of whispering sweet nothings to our feathered friends, we were eavesdropping on the global chatter about their rainy day retreat strategies. We assure you, it was a hoot — or should we say, a *hoot*enanny?

Next, armed with spreadsheets and statistical software, we engaged in a delicate mating dance with the data, performing a synchronized tango of regression analyses and time series modeling to tease out any potential patterns between political preferences and avian meteorological musings. This part of the process was not for the faint of heart - much like the elaborate courtship rituals of certain bird species, it required finesse, patience, and a knack for picking up on subtle cues. In other words, we had to be as perceptive as a bird on the lookout for a potential mate. We do apologize that our methodology is not for the birds, but we assure you that these puns are absolutely *eggs*-quisite.

After applying rigorous statistical techniques to our data, we emerged with a correlation coefficient of 0.9625829 and a p-value less than 0.01, leaving us perched on the edge of a statistical precipice, much like a bird ready to take flight. These findings reinforced our hypothesis that there exists a peculiar linkage between conservative votes and the urge to delve into the mysterious world of avian rainy day hideouts. It was a revelation that spread our wings and left us feeling as uplifted as a soaring eagle, or perhaps a particularly buoyant seabird.


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 South Carolina and Google searches for 'where do birds go when it rains'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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 0.9625829, r-squared of 0.9265659, 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]]
"Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts"

[[ABSTRACT]]
In this paper, we investigate the relationship between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." Our research team delved into the MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to unravel this mysterious connection. We found a correlation coefficient of 0.9625829 and p < 0.01 for the time period spanning from 2004 to 2020, leading us to ponder: are the voters and the birds flocking together when rain starts to pour? *Caw*-relation or *caw*-incidence?

The study scrutinized the unexpected affinity between conservative votes and ornithological inquisitiveness during inclement weather. What's the *tweeting* point of this strange correlation, you ask? Well, our findings suggest that as Republican support increases in South Carolina, so does curiosity about the sheltering habits of our feathered friends during rainy spells. Is it possible that constituents' political leanings might be as predictable as a bird seeking refuge from a thunderstorm? *Chirp*haps!

The implication of our research extends beyond mere caw-ncidence. It raises intriguing questions about the intersection of human behavior and wildlife curiosity, not to mention the potential electoral impact of avian meteorological musings. Our findings add a light-hearted dimension to the serious realm of political science, reminding us that even the most unexpected correlations can surface when we spread our wings and take a closer look at the data.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As the saying goes, "birds of a feather flock together," but little did we know that this adage might extend to political inclinations as well. In this paper, we soar into the uncharted territory of political science and avian behavior to uncover the surprising link between Republican votes for Senators in South Carolina and the peculiar curiosity about the whereabouts of our feathered friends during rainfall. It seems that our investigation has truly taken flight into unexplored territory, much like a bird on the hunt for a good nesting spot.
Our feather-brained curiosity about the connection between conservative politics and avian musings led us to embark on a data-driven journey. With a wing and a prayer, we ventured into the realm of electoral data from the MIT Election Data and Science Lab and Harvard Dataverse, alongside Google Trends data on the search inquiry "where do birds go when it rains." Like a flock of eager birdwatchers, we peered through the statistical binoculars, ready to spot any correlations that might *quack* us up.
The correlation coefficient of 0.9625829 and p < 0.01 that we uncovered left us feeling like we had discovered a rare bird indeed. As we dug deeper into the data, the question that lingered in our minds was one that truly ruffled our feathers: could it be that the voters who stand behind Republican candidates also harbor a deep-seated fascination for the rain-dodging tactics of our feathered neighbors? It's a conundrum that has sent us into a tailspin, not unlike a confused bird navigating a sudden gust of wind.
This unexpected bond between political allegiance and avian precipitation ponderings begs the question: are voters and birds truly *caw*-related, or is it merely a *waddle* and quirky happenstance? As we brace ourselves for the journey ahead, we invite the reader to spread their wings and join us in unraveling the mystery of this ornitho-political phenomenon. After all, in the world of research, it's important to remember that sometimes the most surprising discoveries come from taking a chance on an unassuming Google search.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis unveiled a striking correlation between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." The correlation coefficient was determined to be 0.9625829, with an r-squared value of 0.9265659, and a p-value less than 0.01. If this correlation was any more pronounced, it would've nested itself comfortably in the realm of ornithology. *Eagle* eye needed to spot that one, folks!

Fig. 1 depicts the scatterplot illustrating the robust relationship between these seemingly disparate variables. The tight clustering of data points on the graph is enough to make even the most stoic statistician squawk with surprise. It's a compelling visual representation that leaves little room for chirping away the significance of our findings. And as the saying goes, a picture is worth a thousand hypotheses!

Our statistical analysis leaves us with the feather-ruffling realization that there may be more to this avian-political rendezvous than meets the eye. It's enough to make even the most hardened data skeptic exclaim, "Well, I'll be owl darned!" This unexpected intersection of political behavior and ornithological curiosities has left us perched on the edge of our seats, eager to dive deeper into the implications of our caw-rrelation.

One might wonder if our findings add a new dimension to the age-old adage – "birds of a feather vote together." Or perhaps it's time to coin a new phrase – "voters who share a nest tend to invest." Either way, our results have set the stage for further inquiry into the whimsical yet thought-provoking interplay between human voting patterns and avian weather-related musings.

In the grand scheme of things, our data-driven foray into this uncharted territory serves as a reminder that when it comes to research, it pays to keep an open mind and a keen eye for unexpected correlations. After all, as researchers, it's our duty to spread our wings and venture into unexplored realms of inquiry, no matter how *bird-brained* they may seem at first glance.


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 South Carolina and Google searches for 'where do birds go when it rains'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts"

[[ABSTRACT]]
In this paper, we investigate the relationship between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." Our research team delved into the MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to unravel this mysterious connection. We found a correlation coefficient of 0.9625829 and p < 0.01 for the time period spanning from 2004 to 2020, leading us to ponder: are the voters and the birds flocking together when rain starts to pour? *Caw*-relation or *caw*-incidence?

The study scrutinized the unexpected affinity between conservative votes and ornithological inquisitiveness during inclement weather. What's the *tweeting* point of this strange correlation, you ask? Well, our findings suggest that as Republican support increases in South Carolina, so does curiosity about the sheltering habits of our feathered friends during rainy spells. Is it possible that constituents' political leanings might be as predictable as a bird seeking refuge from a thunderstorm? *Chirp*haps!

The implication of our research extends beyond mere caw-ncidence. It raises intriguing questions about the intersection of human behavior and wildlife curiosity, not to mention the potential electoral impact of avian meteorological musings. Our findings add a light-hearted dimension to the serious realm of political science, reminding us that even the most unexpected correlations can surface when we spread our wings and take a closer look at the data.

[[LITERATURE REVIEW]]
In their seminal work, Smith and Doe (2010) conducted a comprehensive analysis of political voting patterns in South Carolina, shedding light on the complex dynamics of conservative support in the region. Their study, though insightful, failed to account for the potential influence of avian weather-related inquiries on voter behavior. Nevertheless, it laid a solid foundation for understanding the broader contextual factors at play.
Jones (2015) further examined the intricacies of online search behavior, highlighting the significance of understanding users' curiosity-driven queries. However, their focus remained predominantly on commercial intent, leaving an avian-sized gap in the exploration of political and ornithological intrigue.
Turning to works beyond the immediate scope of the field, "The Audubon Society Field Guide to North American Birds" (Peterson, 2008) and "Birdwatching for Dummies" (Dunning, 2012) offer valuable insights into bird behavior and habitat preferences but do not directly address the potential link between political voting and avian curiosity.
As we venture into more tangentially related literature, "To Kill a Mockingbird" (Lee, 1960) and "The Raven" (Poe, 1845) stimulate contemplation on avian symbolism in human culture and literature, yet regrettably diverge from the empirical inquiry at hand.
In a somewhat unorthodox approach to literature review, we also perused the contents of a CVS receipt unearthed from a local store, hoping to find hidden insights within its mundane details. While the receipt failed to yield any pertinent information, it did confirm the purchase of birdseed and a Republican candidate's flyer, hinting at a potential intersection between political advocacy and bird care--talk about multitasking!

[[RESULTS]]
The results of our analysis unveiled a striking correlation between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." The correlation coefficient was determined to be 0.9625829, with an r-squared value of 0.9265659, and a p-value less than 0.01. If this correlation was any more pronounced, it would've nested itself comfortably in the realm of ornithology. *Eagle* eye needed to spot that one, folks!
Fig. 1 depicts the scatterplot illustrating the robust relationship between these seemingly disparate variables. The tight clustering of data points on the graph is enough to make even the most stoic statistician squawk with surprise. It's a compelling visual representation that leaves little room for chirping away the significance of our findings. And as the saying goes, a picture is worth a thousand hypotheses!
Our statistical analysis leaves us with the feather-ruffling realization that there may be more to this avian-political rendezvous than meets the eye. It's enough to make even the most hardened data skeptic exclaim, "Well, I'll be owl darned!" This unexpected intersection of political behavior and ornithological curiosities has left us perched on the edge of our seats, eager to dive deeper into the implications of our caw-rrelation.
One might wonder if our findings add a new dimension to the age-old adage – "birds of a feather vote together." Or perhaps it's time to coin a new phrase – "voters who share a nest tend to invest." Either way, our results have set the stage for further inquiry into the whimsical yet thought-provoking interplay between human voting patterns and avian weather-related musings.
In the grand scheme of things, our data-driven foray into this uncharted territory serves as a reminder that when it comes to research, it pays to keep an open mind and a keen eye for unexpected correlations. After all, as researchers, it's our duty to spread our wings and venture into unexplored realms of inquiry, no matter how *bird-brained* they may seem at first glance.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our investigation has unearthed an unexpectedly robust correlation between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." The high correlation coefficient and the p-value less than 0.01 indicate a compelling connection between conservative political support and avian meteorological inquiries. It seems that alongside casting their ballots, South Carolinian constituents are also casting a curious gaze toward our feathered friends when the rain starts to fall.

The aggregation of our findings supports the prior research by Smith and Doe (2010), who delved into the intricate dynamics of conservative support in South Carolina. Our study adds a feather to their cap by introducing the novel perspective that avian weather-related queries may play a previously overlooked role in shaping voter behavior. Could it be that the political climate is not the only thing affecting constituents' inclinations, but also the actual climate? It’s a thought that might make even the most serious political analyst ruffle their feathers with amusement.

In addition, Jones (2015) highlighted the significance of understanding users' curiosity-driven queries, a notion that our findings corroborate in a surprising fashion. Who would have thought that political allegiance and ornithological intrigue could share such a snug nest in the realm of online search behavior? It's as though the voters are not just voting for their preferred candidates, but also voting for a closer look into where our avian friends seek shelter during downpours. *Preen* and proper political analysis indeed!

The scatterplot in Fig. 1 visually captures the stark relationship we uncovered, showcasing the striking alignment of Republican votes and bird-centric searches. It's a graphic representation that, much like a well-timed pun, leaves little room for avian wiggle room. The strength of this correlation is something to crow* about, and it sheds light on the intricate interplay between political alignment and ornithological curiosity in a manner that few could have anticipated.

Our research hints at the idea that when it comes to predicting voter behavior, understanding the diverse factors that influence constituents' decision-making is crucial. It's no longer just about economic policies and social issues; it's also about understanding the influence of a rainy day on the inclination to ponder avian shelters. As researchers, it's our duty to be vigilant about exploring all potential factors that shape public opinion, even when they ruffle a few feathers along the way.

Our study serves as a reminder that science can take us to unexpected places, and that even the most far-fetched hypotheses can sometimes find a *flight*ing chance at proving their worth. So, let us continue to spread our wings in the pursuit of knowledge, embracing the quirky correlations, unexpected findings, and perhaps the occasional dad joke that emerges along the way. After all, sometimes the most profound insights come from the unlikeliest sources – even if those sources happen to have feathers.


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 South Carolina and Google searches for 'where do birds go when it rains'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts"

[[ABSTRACT]]
In this paper, we investigate the relationship between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." Our research team delved into the MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to unravel this mysterious connection. We found a correlation coefficient of 0.9625829 and p < 0.01 for the time period spanning from 2004 to 2020, leading us to ponder: are the voters and the birds flocking together when rain starts to pour? *Caw*-relation or *caw*-incidence?

The study scrutinized the unexpected affinity between conservative votes and ornithological inquisitiveness during inclement weather. What's the *tweeting* point of this strange correlation, you ask? Well, our findings suggest that as Republican support increases in South Carolina, so does curiosity about the sheltering habits of our feathered friends during rainy spells. Is it possible that constituents' political leanings might be as predictable as a bird seeking refuge from a thunderstorm? *Chirp*haps!

The implication of our research extends beyond mere caw-ncidence. It raises intriguing questions about the intersection of human behavior and wildlife curiosity, not to mention the potential electoral impact of avian meteorological musings. Our findings add a light-hearted dimension to the serious realm of political science, reminding us that even the most unexpected correlations can surface when we spread our wings and take a closer look at the data.

[[INTRDUCTION]]
As the saying goes, "birds of a feather flock together," but little did we know that this adage might extend to political inclinations as well. In this paper, we soar into the uncharted territory of political science and avian behavior to uncover the surprising link between Republican votes for Senators in South Carolina and the peculiar curiosity about the whereabouts of our feathered friends during rainfall. It seems that our investigation has truly taken flight into unexplored territory, much like a bird on the hunt for a good nesting spot.
Our feather-brained curiosity about the connection between conservative politics and avian musings led us to embark on a data-driven journey. With a wing and a prayer, we ventured into the realm of electoral data from the MIT Election Data and Science Lab and Harvard Dataverse, alongside Google Trends data on the search inquiry "where do birds go when it rains." Like a flock of eager birdwatchers, we peered through the statistical binoculars, ready to spot any correlations that might *quack* us up.
The correlation coefficient of 0.9625829 and p < 0.01 that we uncovered left us feeling like we had discovered a rare bird indeed. As we dug deeper into the data, the question that lingered in our minds was one that truly ruffled our feathers: could it be that the voters who stand behind Republican candidates also harbor a deep-seated fascination for the rain-dodging tactics of our feathered neighbors? It's a conundrum that has sent us into a tailspin, not unlike a confused bird navigating a sudden gust of wind.
This unexpected bond between political allegiance and avian precipitation ponderings begs the question: are voters and birds truly *caw*-related, or is it merely a *waddle* and quirky happenstance? As we brace ourselves for the journey ahead, we invite the reader to spread their wings and join us in unraveling the mystery of this ornitho-political phenomenon. After all, in the world of research, it's important to remember that sometimes the most surprising discoveries come from taking a chance on an unassuming Google search.

[[RESULTS]]
The results of our analysis unveiled a striking correlation between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." The correlation coefficient was determined to be 0.9625829, with an r-squared value of 0.9265659, and a p-value less than 0.01. If this correlation was any more pronounced, it would've nested itself comfortably in the realm of ornithology. *Eagle* eye needed to spot that one, folks!
Fig. 1 depicts the scatterplot illustrating the robust relationship between these seemingly disparate variables. The tight clustering of data points on the graph is enough to make even the most stoic statistician squawk with surprise. It's a compelling visual representation that leaves little room for chirping away the significance of our findings. And as the saying goes, a picture is worth a thousand hypotheses!
Our statistical analysis leaves us with the feather-ruffling realization that there may be more to this avian-political rendezvous than meets the eye. It's enough to make even the most hardened data skeptic exclaim, "Well, I'll be owl darned!" This unexpected intersection of political behavior and ornithological curiosities has left us perched on the edge of our seats, eager to dive deeper into the implications of our caw-rrelation.
One might wonder if our findings add a new dimension to the age-old adage – "birds of a feather vote together." Or perhaps it's time to coin a new phrase – "voters who share a nest tend to invest." Either way, our results have set the stage for further inquiry into the whimsical yet thought-provoking interplay between human voting patterns and avian weather-related musings.
In the grand scheme of things, our data-driven foray into this uncharted territory serves as a reminder that when it comes to research, it pays to keep an open mind and a keen eye for unexpected correlations. After all, as researchers, it's our duty to spread our wings and venture into unexplored realms of inquiry, no matter how *bird-brained* they may seem at first glance.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has demonstrated a striking and robust correlation between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." This unexpected interplay between political allegiance and avian precipitation ponderings has ruffled our feathers and left us perched on the edge of our seats. It's a *tweet*-worthy discovery, to say the least!

Our findings have not only added a new dimension to the adage "birds of a feather vote together," but they've also sparked a new saying in the political science community – "voters who share a nest tend to invest." It's not every day that a research project yields such ornitho-political revelations, but here we are, soaring into uncharted territories of correlation.

As we wrap up our study, it's important to note that further research in this curious realm may very well be unnecessary. After all, when you've uncovered a correlation as convincing as this one, it's time to let the research roost and allow our feathered friends to take center stage once more. It's been a hoot, but all good things must come to an end. And in the immortal words of a wise old owl, "whoo is done, is done."


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 Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Avifauna Research


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 Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts. Respond only with the name of a fictional organization.

ChatGPT:

Society for Political Ornithological Research and Analysis


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 Birds of a Feather Vote Together? Exploring the Correlation Between Republican Votes for South Carolina Senators and Curiosity About Avian Rainy Day Hideouts with an abstract of In this paper, we investigate the relationship between Republican votes for Senators in South Carolina and Google searches for "where do birds go when it rains." Our research team delved into the MIT Election Data and Science Lab, Harvard Dataverse and Google Trends to unravel this mysterious connection. We found a correlation coefficient of 0.9625829 and p < 0.01 for the time period spanning from 2004 to 2020, leading us to ponder: are the voters and the birds flocking together when rain starts to pour? *Caw*-relation or *caw*-incidence?
The study scrutinized the unexpected affinity between conservative votes and ornithological inquisitiveness during inclement weather. What's the *tweeting* point of this strange correlation, you ask? Well, our findings suggest that as Republican support increases in South Carolina, so does curiosity about the sheltering habits of our feathered friends during rainy spells. Is it possible that constituents' political leanings might be as predictable as a bird seeking refuge from a thunderstorm? *Chirp*haps!
The implication of our research extends beyond mere caw-ncidence. It raises intriguing questions about the intersection of human behavior and wildlife curiosity, not to mention the potential electoral impact of avian meteorological musings. Our findings add a light-hearted dimension to the serious realm of political science, reminding us that even the most unexpected correlations can surface when we spread our wings and take a closer look at the data.

ChatGPT:

Republican votes, South Carolina Senators, avian rainy day hideouts, correlation, Google searches, birds in rain, MIT Election Data and Science Lab, Harvard Dataverse, Google Trends, correlation coefficient, p-value, conservative votes, ornithological, inclement weather, political leanings, constituents, wildlife curiosity, electoral impact, avian meteorological musings

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

Google searches for 'where do birds go when it rains'
Detailed data title: Relative volume of Google searches for 'where do birds go when it rains' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'where do birds go when it rains'

Correlation r = 0.9625829 (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 = 0.9265659 (Coefficient of determination)
This means 92.7% of the change in the one variable (i.e., Google searches for 'where do birds go when it rains') is predictable based on the change in the other (i.e., Votes for Republican Senators in South Carolina) over the 6 years from 2004 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00207. 0.0020738642687204373000000000
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 0.207% of random cases. Said differently, if you correlated 482 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.

[ 0.69, 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.
200420082010201420162020
Votes for Republican Senators in South Carolina (Percentage of votes)53.666157.524661.4782115.38260.569554.4366
Google searches for 'where do birds go when it rains' (Rel. search volume)2.833331.083331.1666710.752.083331.91667




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. 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.
  5. 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([53.6661,57.5246,61.4782,115.382,60.5695,54.4366,])
array_2 = np.array([2.83333,1.08333,1.16667,10.75,2.08333,1.91667,])
array_1_name = "Votes for Republican Senators in South Carolina"
array_2_name = "Google searches for 'where do birds go when it rains'"

# 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?

Your correlation rating is out of this world!


Correlation ID: 4356 · Black Variable ID: 26459 · Red Variable ID: 1468
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0