about · email me · subscribe
Spurious correlation #5,378 · 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 Democratic Senators in Maine and the second variable is Mega millions lottery numbers.  The chart goes from 2002 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The extra votes were actually write-in numbers on the ballots, creating a surge in numerical energy across the state. As the Democratic support grew, so did the collective desire for larger numbers, inadvertently influencing the Mega Millions lottery outcomes. It seems like Maine's political climate was truly a jackpot for numerical expansion!

Model: dalle-3
Prompt: Generate an image of a sea of energized numerals rising from the state of Maine, merging with ballots for Democratic Senators and intertwining with the collective desire for larger numbers. The numbers should radiate energy and influence, spilling over into the Mega Millions lottery outcomes. The scene should convey a sense of political and numerical potency, with the state of Maine turning into a jackpot for numerical expansion. 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: Votes for Democratic Senators in Maine and Mega millions lottery numbers. 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: 3D Pixar Style Magic realism A scene from Skyrim Symbolism High-tech
ChatGPT: Symbolism

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 Votes for Democratic Senators in Maine and Mega millions lottery numbers, in the following situation: The extra votes were actually write-in numbers on the ballots, creating a surge in numerical energy across the state. As the Democratic support grew, so did the collective desire for larger numbers, inadvertently influencing the Mega Millions lottery outcomes. It seems like Maine's political climate was truly a jackpot for numerical expansion!. Keep the description simple.
ChatGPT: In the state of Maine, ballots for Democratic Senators were filled with energized write-in numbers, intertwining with the collective desire for larger numbers across the state. The numerical surge spilled over, influencing the Mega Millions lottery outcomes, as the political climate in Maine turned into a jackpot for numerical expansion.

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: [ Symbolism ] and depicting this scene: In the state of Maine, ballots for Democratic Senators were filled with energized write-in numbers, intertwining with the collective desire for larger numbers across the state. The numerical surge spilled over, influencing the Mega Millions lottery outcomes, as the political climate in Maine turned into a jackpot for numerical expansion. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a sea of energized numerals rising from the state of Maine, merging with ballots for Democratic Senators and intertwining with the collective desire for larger numbers. The numbers should radiate energy and influence, spilling over into the Mega Millions lottery outcomes. The scene should convey a sense of political and numerical potency, with the state of Maine turning into a jackpot for numerical expansion.

*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 Democrat votes for Senators in Maine caused Mega millions lottery numbers to increase.

AI academic paper

(Because p < 0.05)
Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers

The Multidisciplinary Journal of Quirky Statistical Analyses

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 researcher writing an academic paper.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 Democrat votes for Senators in Maine and Mega millions lottery numbers. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title a clever pun.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and NY Mega Millions Lottery to assess this nagging question. You found a correlation coefficient of 0.8306736 and p < 0.05 for 2002 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]]
Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers

[[ABSTRACT]]
In the illustrious world of academia, we often find ourselves embarking on peculiar research endeavors, and none more tantalizing than the nexus between political voting patterns and the serendipitous realm of lottery numbers. In this whimsical yet rigorous study, we put our proverbial thinking caps on and turned to the data with a keen eye for correlation and perhaps a sprinkle of optimism.

Focusing on the Pine Tree State of Maine, our research team delved into the labyrinthine archives of MIT Election Data and Science Lab, Harvard Dataverse, and the enigmatic NY Mega Millions Lottery, all in pursuit of the elusive connection between Democrat votes for Senators in Maine and those elusive, life-altering lottery numbers. With bated breath and a fair share of dad jokes to keep us energized, we unearthed a correlation coefficient of 0.8306736, sending ripples of ironic amusement throughout the hallowed halls of statistical analysis.

As we unveiled our findings spanning the years from 2002 to 2020, we were astounded to discover a statistically significant relationship (p < 0.05) between the political penchant of Mainers and the whims of chance associated with the Mega Millions lottery. One can't help but ponder the cosmic interplay of political inclinations and fortuitous number selection, prompting the spirited musing of whether the political landscape holds the key to predicting the lottery - or vice versa.

Alas, in this venerable pursuit of knowledge, we must not forget to inject levity into our scholarly pursuits, for as any pun-enthusiast will tell you: "The odds of winning the lottery are as slim as a politician's promise, but the correlations we found just might be the jackpot of political trivia."


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat votes for Senators in Maine and Mega millions lottery numbers. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers

[[ABSTRACT]]
In the illustrious world of academia, we often find ourselves embarking on peculiar research endeavors, and none more tantalizing than the nexus between political voting patterns and the serendipitous realm of lottery numbers. In this whimsical yet rigorous study, we put our proverbial thinking caps on and turned to the data with a keen eye for correlation and perhaps a sprinkle of optimism.

Focusing on the Pine Tree State of Maine, our research team delved into the labyrinthine archives of MIT Election Data and Science Lab, Harvard Dataverse, and the enigmatic NY Mega Millions Lottery, all in pursuit of the elusive connection between Democrat votes for Senators in Maine and those elusive, life-altering lottery numbers. With bated breath and a fair share of dad jokes to keep us energized, we unearthed a correlation coefficient of 0.8306736, sending ripples of ironic amusement throughout the hallowed halls of statistical analysis.

As we unveiled our findings spanning the years from 2002 to 2020, we were astounded to discover a statistically significant relationship (p < 0.05) between the political penchant of Mainers and the whims of chance associated with the Mega Millions lottery. One can't help but ponder the cosmic interplay of political inclinations and fortuitous number selection, prompting the spirited musing of whether the political landscape holds the key to predicting the lottery - or vice versa.

Alas, in this venerable pursuit of knowledge, we must not forget to inject levity into our scholarly pursuits, for as any pun-enthusiast will tell you: "The odds of winning the lottery are as slim as a politician's promise, but the correlations we found just might be the jackpot of political trivia."

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the realm of statistics and probability, researchers often tiptoe through the labyrinthine corridors of data, seeking to unveil unexpected connections and correlations. The intersection of politics and chance, though often a contentious topic in casual discussions, has seldom been rigorously explored. However, with a touch of academic whimsy and a craving for incongruous discoveries, our research team delved into the enigmatic realm of Maine’s political landscape and the capricious world of Mega Millions lottery numbers.

Now, the relationship between political leanings and lottery predictions may seem as incongruous as a cat trying to win a dog show, but our findings turned the spotlight on an unexpected correlation, much like finding a four-leaf clover in a statistics textbook. We embarked on this journey with a twinkle in our eyes and a spreadsheet full of numbers, all the while contemplating the enigmatic dance between Democrat votes for Senators in Maine and the whimsical selection of Mega Millions numbers.

As we unraveled the data, a correlation coefficient of 0.8306736 emerged, leaving us with a p-value small enough to make even the staunchest skeptic raise an eyebrow. It's almost as if the lottery numbers had been flirting with the election results, like a game of chance caught in a political tango. One can't help but appreciate the subtle humor in the juxtaposition of these seemingly disparate realms—a bit like finding a witty quip in an academic paper.

But let's not get carried away with too much frivolity; after all, this is serious academic research. The implications of these findings may be as far-reaching as trying to squeeze an elephant into a phone booth, but they offer a sliver of insight into the quirky interplay between political proclivities and the fickle hand of fate. As we plunge into the depths of this paper, let's remember the timeless words of wisdom: "If you're feeling lucky, play the lottery; if you're feeling statistically inclined, read on."


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat votes for Senators in Maine and Mega millions lottery numbers. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers

[[ABSTRACT]]
In the illustrious world of academia, we often find ourselves embarking on peculiar research endeavors, and none more tantalizing than the nexus between political voting patterns and the serendipitous realm of lottery numbers. In this whimsical yet rigorous study, we put our proverbial thinking caps on and turned to the data with a keen eye for correlation and perhaps a sprinkle of optimism.

Focusing on the Pine Tree State of Maine, our research team delved into the labyrinthine archives of MIT Election Data and Science Lab, Harvard Dataverse, and the enigmatic NY Mega Millions Lottery, all in pursuit of the elusive connection between Democrat votes for Senators in Maine and those elusive, life-altering lottery numbers. With bated breath and a fair share of dad jokes to keep us energized, we unearthed a correlation coefficient of 0.8306736, sending ripples of ironic amusement throughout the hallowed halls of statistical analysis.

As we unveiled our findings spanning the years from 2002 to 2020, we were astounded to discover a statistically significant relationship (p < 0.05) between the political penchant of Mainers and the whims of chance associated with the Mega Millions lottery. One can't help but ponder the cosmic interplay of political inclinations and fortuitous number selection, prompting the spirited musing of whether the political landscape holds the key to predicting the lottery - or vice versa.

Alas, in this venerable pursuit of knowledge, we must not forget to inject levity into our scholarly pursuits, for as any pun-enthusiast will tell you: "The odds of winning the lottery are as slim as a politician's promise, but the correlations we found just might be the jackpot of political trivia."

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the realm of statistics and probability, researchers often tiptoe through the labyrinthine corridors of data, seeking to unveil unexpected connections and correlations. The intersection of politics and chance, though often a contentious topic in casual discussions, has seldom been rigorously explored. However, with a touch of academic whimsy and a craving for incongruous discoveries, our research team delved into the enigmatic realm of Maine’s political landscape and the capricious world of Mega Millions lottery numbers.
Now, the relationship between political leanings and lottery predictions may seem as incongruous as a cat trying to win a dog show, but our findings turned the spotlight on an unexpected correlation, much like finding a four-leaf clover in a statistics textbook. We embarked on this journey with a twinkle in our eyes and a spreadsheet full of numbers, all the while contemplating the enigmatic dance between Democrat votes for Senators in Maine and the whimsical selection of Mega Millions numbers.
As we unraveled the data, a correlation coefficient of 0.8306736 emerged, leaving us with a p-value small enough to make even the staunchest skeptic raise an eyebrow. It's almost as if the lottery numbers had been flirting with the election results, like a game of chance caught in a political tango. One can't help but appreciate the subtle humor in the juxtaposition of these seemingly disparate realms—a bit like finding a witty quip in an academic paper.
But let's not get carried away with too much frivolity; after all, this is serious academic research. The implications of these findings may be as far-reaching as trying to squeeze an elephant into a phone booth, but they offer a sliver of insight into the quirky interplay between political proclivities and the fickle hand of fate. As we plunge into the depths of this paper, let's remember the timeless words of wisdom: "If you're feeling lucky, play the lottery; if you're feeling statistically inclined, read on."

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Smith (2015) delved into the political voting patterns in Maine, revealing intriguing insights into the factors influencing the electorate's decisions. Similarly, Doe and Jones (2018) conducted a comprehensive analysis of the Mega Millions lottery numbers, uncovering the enigmatic dance of chance and probability.

As we navigated through the academic terrain, we stumbled upon "The Art of Probability" by John von Neumann, and "The Signal and the Noise" by Nate Silver, which laid the groundwork for comprehending the capricious interplay of chance and prediction. Juxtaposing these serious works, we also found ourselves drawn into the captivating world of fiction with "The Lottery" by Shirley Jackson and "The Curious Incident of the Dog in the Night-Time" by Mark Haddon, adding a whimsical touch to our research journey.

In the annals of internet culture, the infamous "Distracted Boyfriend" meme provided an amusing analogy for the unexpected correlation we uncovered, much like the unpredictability of Senatorial votes and lottery numbers caught in an intricate dance. Similarly, the "Math Lady" meme encapsulated the bewildering yet fascinating relationship between statistical analysis and the whims of chance, injecting a dose of levity into our rigorous pursuit of knowledge.

As our investigation deepened, we couldn't resist but crack a dad joke or two. "Why don't scientists trust atoms? Because they make up everything, just like the correlations we found between political votes and lottery numbers!"



Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat votes for Senators in Maine and Mega millions lottery numbers. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and NY Mega Millions Lottery . You used data from 2002 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]]
Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers

[[ABSTRACT]]
In the illustrious world of academia, we often find ourselves embarking on peculiar research endeavors, and none more tantalizing than the nexus between political voting patterns and the serendipitous realm of lottery numbers. In this whimsical yet rigorous study, we put our proverbial thinking caps on and turned to the data with a keen eye for correlation and perhaps a sprinkle of optimism.

Focusing on the Pine Tree State of Maine, our research team delved into the labyrinthine archives of MIT Election Data and Science Lab, Harvard Dataverse, and the enigmatic NY Mega Millions Lottery, all in pursuit of the elusive connection between Democrat votes for Senators in Maine and those elusive, life-altering lottery numbers. With bated breath and a fair share of dad jokes to keep us energized, we unearthed a correlation coefficient of 0.8306736, sending ripples of ironic amusement throughout the hallowed halls of statistical analysis.

As we unveiled our findings spanning the years from 2002 to 2020, we were astounded to discover a statistically significant relationship (p < 0.05) between the political penchant of Mainers and the whims of chance associated with the Mega Millions lottery. One can't help but ponder the cosmic interplay of political inclinations and fortuitous number selection, prompting the spirited musing of whether the political landscape holds the key to predicting the lottery - or vice versa.

Alas, in this venerable pursuit of knowledge, we must not forget to inject levity into our scholarly pursuits, for as any pun-enthusiast will tell you: "The odds of winning the lottery are as slim as a politician's promise, but the correlations we found just might be the jackpot of political trivia."

[[INTRODUCTION]]
In the realm of statistics and probability, researchers often tiptoe through the labyrinthine corridors of data, seeking to unveil unexpected connections and correlations. The intersection of politics and chance, though often a contentious topic in casual discussions, has seldom been rigorously explored. However, with a touch of academic whimsy and a craving for incongruous discoveries, our research team delved into the enigmatic realm of Maine’s political landscape and the capricious world of Mega Millions lottery numbers.
Now, the relationship between political leanings and lottery predictions may seem as incongruous as a cat trying to win a dog show, but our findings turned the spotlight on an unexpected correlation, much like finding a four-leaf clover in a statistics textbook. We embarked on this journey with a twinkle in our eyes and a spreadsheet full of numbers, all the while contemplating the enigmatic dance between Democrat votes for Senators in Maine and the whimsical selection of Mega Millions numbers.
As we unraveled the data, a correlation coefficient of 0.8306736 emerged, leaving us with a p-value small enough to make even the staunchest skeptic raise an eyebrow. It's almost as if the lottery numbers had been flirting with the election results, like a game of chance caught in a political tango. One can't help but appreciate the subtle humor in the juxtaposition of these seemingly disparate realms—a bit like finding a witty quip in an academic paper.
But let's not get carried away with too much frivolity; after all, this is serious academic research. The implications of these findings may be as far-reaching as trying to squeeze an elephant into a phone booth, but they offer a sliver of insight into the quirky interplay between political proclivities and the fickle hand of fate. As we plunge into the depths of this paper, let's remember the timeless words of wisdom: "If you're feeling lucky, play the lottery; if you're feeling statistically inclined, read on."

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To embark on our riveting journey of unraveling the peculiar nexus between Democrats' votes for Senators in Maine and the enigmatic realm of Mega Millions lottery numbers, we harnessed an eclectic array of data from 2002 to 2020, sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the New York Mega Millions Lottery.

Our first step in this scholarly escapade was to meticulously compile the election data, isolating the voting patterns for Democrat Senators in Maine. We concocted an algorithm so convoluted it would make a Rube Goldberg machine blush, designed to sift through the vast electoral records like a discerning sommelier perusing an extensive wine list.

With the political landscape of Maine elucidated, we turned our quizzical gaze towards the Mega Millions lottery numbers. Our method for extracting this capricious data was akin to a treasure hunt in the realm of chance, involving an enigmatic blend of technical wizardry and delightful serendipity, not unlike trying to find the proverbial needle in a haystack.

Next, armed with our troves of data, we deployed the arcane arts of statistical analysis to untangle the veiled correlations and unveil the elusive dance between political predilections and fortuitous number selections. Our statistical models were as robust as a tank made of calculus textbooks, navigating the treacherous seas of data with pinpoint precision to extract meaningful insights.

In our quest for statistical illumination, we employed the venerable Pearson correlation coefficient to unearth the degree of association between Democrat votes for Senators in Maine and the ethereal lottery numbers. With each calculation, we delighted in the tantalizing dance of numbers, much like watching a graceful waltz between two seemingly incongruous partners.

Finally, we nestled our findings within the bosom of rigorous hypothesis testing, scrutinizing the significance of the uncovered correlations with the fervor of a detective solving a cryptic mystery. To add a whimsical flair to this otherwise arduous task, we liberally sprinkled our analysis with the immortal wisdom of dad jokes, for as any pun aficionado would posit, "A good dad joke is like a statistics lecture—odds are, it will make you groan, but there's a chance you'll crack a smile."

As we emerged from the enthralling labyrinth of data and statistical rigor, we found ourselves drenched in the glow of unexpected revelation, much like stumbling upon a quirk of fate when least expected. Our methodology, though lighthearted in its anecdotes, was as rigorous as a tightrope walk over the chasm of empirical inquiry, culminating in the whimsical yet robust study that follows.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat votes for Senators in Maine and Mega millions lottery numbers. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and NY Mega Millions Lottery .

For the time period 2002 to 2020, you found a correlation 0.8306736, r-squared of 0.6900186, and p < 0.05.

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]]
Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers

[[ABSTRACT]]
In the illustrious world of academia, we often find ourselves embarking on peculiar research endeavors, and none more tantalizing than the nexus between political voting patterns and the serendipitous realm of lottery numbers. In this whimsical yet rigorous study, we put our proverbial thinking caps on and turned to the data with a keen eye for correlation and perhaps a sprinkle of optimism.

Focusing on the Pine Tree State of Maine, our research team delved into the labyrinthine archives of MIT Election Data and Science Lab, Harvard Dataverse, and the enigmatic NY Mega Millions Lottery, all in pursuit of the elusive connection between Democrat votes for Senators in Maine and those elusive, life-altering lottery numbers. With bated breath and a fair share of dad jokes to keep us energized, we unearthed a correlation coefficient of 0.8306736, sending ripples of ironic amusement throughout the hallowed halls of statistical analysis.

As we unveiled our findings spanning the years from 2002 to 2020, we were astounded to discover a statistically significant relationship (p < 0.05) between the political penchant of Mainers and the whims of chance associated with the Mega Millions lottery. One can't help but ponder the cosmic interplay of political inclinations and fortuitous number selection, prompting the spirited musing of whether the political landscape holds the key to predicting the lottery - or vice versa.

Alas, in this venerable pursuit of knowledge, we must not forget to inject levity into our scholarly pursuits, for as any pun-enthusiast will tell you: "The odds of winning the lottery are as slim as a politician's promise, but the correlations we found just might be the jackpot of political trivia."

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the realm of statistics and probability, researchers often tiptoe through the labyrinthine corridors of data, seeking to unveil unexpected connections and correlations. The intersection of politics and chance, though often a contentious topic in casual discussions, has seldom been rigorously explored. However, with a touch of academic whimsy and a craving for incongruous discoveries, our research team delved into the enigmatic realm of Maine’s political landscape and the capricious world of Mega Millions lottery numbers.
Now, the relationship between political leanings and lottery predictions may seem as incongruous as a cat trying to win a dog show, but our findings turned the spotlight on an unexpected correlation, much like finding a four-leaf clover in a statistics textbook. We embarked on this journey with a twinkle in our eyes and a spreadsheet full of numbers, all the while contemplating the enigmatic dance between Democrat votes for Senators in Maine and the whimsical selection of Mega Millions numbers.
As we unraveled the data, a correlation coefficient of 0.8306736 emerged, leaving us with a p-value small enough to make even the staunchest skeptic raise an eyebrow. It's almost as if the lottery numbers had been flirting with the election results, like a game of chance caught in a political tango. One can't help but appreciate the subtle humor in the juxtaposition of these seemingly disparate realms—a bit like finding a witty quip in an academic paper.
But let's not get carried away with too much frivolity; after all, this is serious academic research. The implications of these findings may be as far-reaching as trying to squeeze an elephant into a phone booth, but they offer a sliver of insight into the quirky interplay between political proclivities and the fickle hand of fate. As we plunge into the depths of this paper, let's remember the timeless words of wisdom: "If you're feeling lucky, play the lottery; if you're feeling statistically inclined, read on."

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Upon diving into the treasure trove of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the bewitching NY Mega Millions Lottery, our research endeavors bore fruit in the form of a striking correlation between Democrat votes for Senators in Maine and the capricious Mega Millions lottery numbers. The correlation coefficient of 0.8306736 revealed a compelling relationship that defied conventional expectations, much like finding a winning lottery ticket in a forgotten coat pocket.

Accompanying this correlation was an r-squared value of 0.6900186, serving as a testament to the robustness of the observed relationship. It's almost as if the lottery numbers and political leanings were performing an airtight duet, leaving statisticians and pun enthusiasts alike to wilt under the weight of such an unexpected discovery.

In support of our findings, the p-value, resting comfortably below the conventional threshold of 0.05, cemented the statistical significance of the correlation. This result sparked an array of quips and jests within our research team, prompting one daring soul to proclaim, "These findings have higher odds than a rabbit in a carrot-eating contest!"

To visually encapsulate this fortuitous revelation, we present Fig. 1, a scatterplot emblematic of the undeniable link between Democrat votes for Senators in Maine and the coy dance of Mega Millions numbers. One can't help but appreciate the whimsy of our findings, much like stumbling upon a lighthearted jest in a cerebral exchange.

In conclusion, the interplay between political preferences and lottery numbers invites a peculiar blend of statistical analysis and fortuitous whimsy. Our findings unveil a hitherto unexplored connection, invoking laughter and scholarly reflection in equal measure. After all, as the timeless aphorism goes: "In the world of statistics, sometimes the most improbable connections yield the most wondrous results!"


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat votes for Senators in Maine and Mega millions lottery numbers. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers

[[ABSTRACT]]
In the illustrious world of academia, we often find ourselves embarking on peculiar research endeavors, and none more tantalizing than the nexus between political voting patterns and the serendipitous realm of lottery numbers. In this whimsical yet rigorous study, we put our proverbial thinking caps on and turned to the data with a keen eye for correlation and perhaps a sprinkle of optimism.

Focusing on the Pine Tree State of Maine, our research team delved into the labyrinthine archives of MIT Election Data and Science Lab, Harvard Dataverse, and the enigmatic NY Mega Millions Lottery, all in pursuit of the elusive connection between Democrat votes for Senators in Maine and those elusive, life-altering lottery numbers. With bated breath and a fair share of dad jokes to keep us energized, we unearthed a correlation coefficient of 0.8306736, sending ripples of ironic amusement throughout the hallowed halls of statistical analysis.

As we unveiled our findings spanning the years from 2002 to 2020, we were astounded to discover a statistically significant relationship (p < 0.05) between the political penchant of Mainers and the whims of chance associated with the Mega Millions lottery. One can't help but ponder the cosmic interplay of political inclinations and fortuitous number selection, prompting the spirited musing of whether the political landscape holds the key to predicting the lottery - or vice versa.

Alas, in this venerable pursuit of knowledge, we must not forget to inject levity into our scholarly pursuits, for as any pun-enthusiast will tell you: "The odds of winning the lottery are as slim as a politician's promise, but the correlations we found just might be the jackpot of political trivia."

[[LITERATURE REVIEW]]
Smith (2015) delved into the political voting patterns in Maine, revealing intriguing insights into the factors influencing the electorate's decisions. Similarly, Doe and Jones (2018) conducted a comprehensive analysis of the Mega Millions lottery numbers, uncovering the enigmatic dance of chance and probability.
As we navigated through the academic terrain, we stumbled upon "The Art of Probability" by John von Neumann, and "The Signal and the Noise" by Nate Silver, which laid the groundwork for comprehending the capricious interplay of chance and prediction. Juxtaposing these serious works, we also found ourselves drawn into the captivating world of fiction with "The Lottery" by Shirley Jackson and "The Curious Incident of the Dog in the Night-Time" by Mark Haddon, adding a whimsical touch to our research journey.
In the annals of internet culture, the infamous "Distracted Boyfriend" meme provided an amusing analogy for the unexpected correlation we uncovered, much like the unpredictability of Senatorial votes and lottery numbers caught in an intricate dance. Similarly, the "Math Lady" meme encapsulated the bewildering yet fascinating relationship between statistical analysis and the whims of chance, injecting a dose of levity into our rigorous pursuit of knowledge.
As our investigation deepened, we couldn't resist but crack a dad joke or two. "Why don't scientists trust atoms? Because they make up everything, just like the correlations we found between political votes and lottery numbers!"


[[RESULTS]]
Upon diving into the treasure trove of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the bewitching NY Mega Millions Lottery, our research endeavors bore fruit in the form of a striking correlation between Democrat votes for Senators in Maine and the capricious Mega Millions lottery numbers. The correlation coefficient of 0.8306736 revealed a compelling relationship that defied conventional expectations, much like finding a winning lottery ticket in a forgotten coat pocket.
Accompanying this correlation was an r-squared value of 0.6900186, serving as a testament to the robustness of the observed relationship. It's almost as if the lottery numbers and political leanings were performing an airtight duet, leaving statisticians and pun enthusiasts alike to wilt under the weight of such an unexpected discovery.
In support of our findings, the p-value, resting comfortably below the conventional threshold of 0.05, cemented the statistical significance of the correlation. This result sparked an array of quips and jests within our research team, prompting one daring soul to proclaim, "These findings have higher odds than a rabbit in a carrot-eating contest!"
To visually encapsulate this fortuitous revelation, we present Fig. 1, a scatterplot emblematic of the undeniable link between Democrat votes for Senators in Maine and the coy dance of Mega Millions numbers. One can't help but appreciate the whimsy of our findings, much like stumbling upon a lighthearted jest in a cerebral exchange.
In conclusion, the interplay between political preferences and lottery numbers invites a peculiar blend of statistical analysis and fortuitous whimsy. Our findings unveil a hitherto unexplored connection, invoking laughter and scholarly reflection in equal measure. After all, as the timeless aphorism goes: "In the world of statistics, sometimes the most improbable connections yield the most wondrous results!"

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our results shed light on a remarkable connection between the political proclivities of Mainers and the seemingly capricious Mega Millions lottery numbers. The striking correlation coefficient we uncovered, akin to finding a four-leaf clover in a field of statistics, aligns with the findings of Smith (2015) and Doe and Jones (2018), who delved into the intricacies of political voting patterns and lottery number selection.

As Smith (2015) adeptly discerned the underlying factors influencing Mainers' political decisions, our research furthers this understanding by highlighting a statistically significant relationship between Democrat votes for Senators in Maine and the lottery numbers drawn in the Mega Millions. Our findings not only echo and expand upon the works of previous scholars but also add a whimsical twist to the serious discourse on voter behavior and the enigmatic dance of probability.

The unexpected correlation uncovered in our research bears a remarkable resemblance to the unpredictable yet precisely calculated nature of chance, mirroring the paradoxical nature of political promises and lottery winnings. Our results not only tantalize the academic community with their novelty but also offer a rare intersection of statistical analysis and the whims of chance, much like a fortuitous alignment of stars in the scholarly firmament.

In addition to upholding the rigorous statistical significance of our findings, our study boldly navigates the uncharted territory of political predictions and lottery numbers, prompting moments of scholarly musing and lighthearted banter within our research team. Our results, encapsulated in the scatterplot presented in Fig. 1, serve as a testament to the improbable yet undeniable link between the political landscape and the profusion of lucky numbers, evoking both scholarly reflection and jovial amusement.

While we must remain mindful of the solemn scholarly pursuit at hand, it is equally crucial to embrace the unexpected connections and whimsical surprises that enliven our scientific voyage. As our research journey through the annals of statistical analysis and indicative correlations culminates, we are reminded of the timeless words of wisdom: "Why don't skeletons fight each other? They don't have the guts!" As we reckon with the intricate interplay of political preferences and lottery whims, such playful jests serve as a whimsical reminder that scholarly pursuits need not be devoid of lighthearted surprises and unexpected connections.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat votes for Senators in Maine and Mega millions lottery numbers. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers

[[ABSTRACT]]
In the illustrious world of academia, we often find ourselves embarking on peculiar research endeavors, and none more tantalizing than the nexus between political voting patterns and the serendipitous realm of lottery numbers. In this whimsical yet rigorous study, we put our proverbial thinking caps on and turned to the data with a keen eye for correlation and perhaps a sprinkle of optimism.

Focusing on the Pine Tree State of Maine, our research team delved into the labyrinthine archives of MIT Election Data and Science Lab, Harvard Dataverse, and the enigmatic NY Mega Millions Lottery, all in pursuit of the elusive connection between Democrat votes for Senators in Maine and those elusive, life-altering lottery numbers. With bated breath and a fair share of dad jokes to keep us energized, we unearthed a correlation coefficient of 0.8306736, sending ripples of ironic amusement throughout the hallowed halls of statistical analysis.

As we unveiled our findings spanning the years from 2002 to 2020, we were astounded to discover a statistically significant relationship (p < 0.05) between the political penchant of Mainers and the whims of chance associated with the Mega Millions lottery. One can't help but ponder the cosmic interplay of political inclinations and fortuitous number selection, prompting the spirited musing of whether the political landscape holds the key to predicting the lottery - or vice versa.

Alas, in this venerable pursuit of knowledge, we must not forget to inject levity into our scholarly pursuits, for as any pun-enthusiast will tell you: "The odds of winning the lottery are as slim as a politician's promise, but the correlations we found just might be the jackpot of political trivia."

[[INTRDUCTION]]
In the realm of statistics and probability, researchers often tiptoe through the labyrinthine corridors of data, seeking to unveil unexpected connections and correlations. The intersection of politics and chance, though often a contentious topic in casual discussions, has seldom been rigorously explored. However, with a touch of academic whimsy and a craving for incongruous discoveries, our research team delved into the enigmatic realm of Maine’s political landscape and the capricious world of Mega Millions lottery numbers.
Now, the relationship between political leanings and lottery predictions may seem as incongruous as a cat trying to win a dog show, but our findings turned the spotlight on an unexpected correlation, much like finding a four-leaf clover in a statistics textbook. We embarked on this journey with a twinkle in our eyes and a spreadsheet full of numbers, all the while contemplating the enigmatic dance between Democrat votes for Senators in Maine and the whimsical selection of Mega Millions numbers.
As we unraveled the data, a correlation coefficient of 0.8306736 emerged, leaving us with a p-value small enough to make even the staunchest skeptic raise an eyebrow. It's almost as if the lottery numbers had been flirting with the election results, like a game of chance caught in a political tango. One can't help but appreciate the subtle humor in the juxtaposition of these seemingly disparate realms—a bit like finding a witty quip in an academic paper.
But let's not get carried away with too much frivolity; after all, this is serious academic research. The implications of these findings may be as far-reaching as trying to squeeze an elephant into a phone booth, but they offer a sliver of insight into the quirky interplay between political proclivities and the fickle hand of fate. As we plunge into the depths of this paper, let's remember the timeless words of wisdom: "If you're feeling lucky, play the lottery; if you're feeling statistically inclined, read on."

[[RESULTS]]
Upon diving into the treasure trove of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the bewitching NY Mega Millions Lottery, our research endeavors bore fruit in the form of a striking correlation between Democrat votes for Senators in Maine and the capricious Mega Millions lottery numbers. The correlation coefficient of 0.8306736 revealed a compelling relationship that defied conventional expectations, much like finding a winning lottery ticket in a forgotten coat pocket.
Accompanying this correlation was an r-squared value of 0.6900186, serving as a testament to the robustness of the observed relationship. It's almost as if the lottery numbers and political leanings were performing an airtight duet, leaving statisticians and pun enthusiasts alike to wilt under the weight of such an unexpected discovery.
In support of our findings, the p-value, resting comfortably below the conventional threshold of 0.05, cemented the statistical significance of the correlation. This result sparked an array of quips and jests within our research team, prompting one daring soul to proclaim, "These findings have higher odds than a rabbit in a carrot-eating contest!"
To visually encapsulate this fortuitous revelation, we present Fig. 1, a scatterplot emblematic of the undeniable link between Democrat votes for Senators in Maine and the coy dance of Mega Millions numbers. One can't help but appreciate the whimsy of our findings, much like stumbling upon a lighthearted jest in a cerebral exchange.
In conclusion, the interplay between political preferences and lottery numbers invites a peculiar blend of statistical analysis and fortuitous whimsy. Our findings unveil a hitherto unexplored connection, invoking laughter and scholarly reflection in equal measure. After all, as the timeless aphorism goes: "In the world of statistics, sometimes the most improbable connections yield the most wondrous results!"

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

As we draw the curtains on our capricious exploration into the nexus of Democrat votes for Senators in Maine and the serendipitous sphere of Mega Millions lottery numbers, one cannot help but chuckle at the unexpected waltz between politics and probability. Our findings, akin to stumbling upon a witty retort in a solemn debate, underscore the whimsical interplay that extends beyond the precincts of statistical convention.

With a correlation coefficient of 0.8306736 and an r-squared value of 0.6900186, our data paint a picture of an unlikely camaraderie between political leanings and the chameleon-like lottery numbers. It seems that the ballot and the bonanza may not be as estranged as one might assume - a revelation as surprising as finding a penny in a haystack.

In support of our revelatory correlation, the p-value, standing firm below the threshold of 0.05, grants credence to the statistical significance of our findings. Much like a well-timed dad joke, these results inject a dash of mirth into the solemnity of scholarly inquiry, prompting an appreciative chuckle from the scientific community.

As we lay our quirk-laden findings at the altar of research, we must bid adieu to this whimsical foray into the unfathomable marriage of politics and chance. We have unraveled a correlation that inspires equal parts fascination and amusement, much like discovering a politician with a sense of humor. With a nod to the timeless wisdom of dad jokes and the unwitting levity they bring, we assert that no further research in this eccentric domain is needed. For as any pun-enthusiast will tell you, "Sometimes, the most outlandish correlations are the ones worth celebrating - and this, my friends, is a jackpot of improbable delight."


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 Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers. Respond only with the name of a fictional academic journal.

ChatGPT:

The Multidisciplinary Journal of Quirky Statistical Analyses


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 Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Democratic Metrics and Lottery 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 Maine-ia to Win: How Democrat Votes for Senators in Maine Predict Mega Millions Lottery Numbers with an abstract of In the illustrious world of academia, we often find ourselves embarking on peculiar research endeavors, and none more tantalizing than the nexus between political voting patterns and the serendipitous realm of lottery numbers. In this whimsical yet rigorous study, we put our proverbial thinking caps on and turned to the data with a keen eye for correlation and perhaps a sprinkle of optimism.
Focusing on the Pine Tree State of Maine, our research team delved into the labyrinthine archives of MIT Election Data and Science Lab, Harvard Dataverse, and the enigmatic NY Mega Millions Lottery, all in pursuit of the elusive connection between Democrat votes for Senators in Maine and those elusive, life-altering lottery numbers. With bated breath and a fair share of dad jokes to keep us energized, we unearthed a correlation coefficient of 0.8306736, sending ripples of ironic amusement throughout the hallowed halls of statistical analysis.
As we unveiled our findings spanning the years from 2002 to 2020, we were astounded to discover a statistically significant relationship (p < 0.05) between the political penchant of Mainers and the whims of chance associated with the Mega Millions lottery. One can't help but ponder the cosmic interplay of political inclinations and fortuitous number selection, prompting the spirited musing of whether the political landscape holds the key to predicting the lottery - or vice versa.
Alas, in this venerable pursuit of knowledge, we must not forget to inject levity into our scholarly pursuits, for as any pun-enthusiast will tell you: "The odds of winning the lottery are as slim as a politician's promise, but the correlations we found just might be the jackpot of political trivia.

ChatGPT:

Maine, Democrat, Senators, voting patterns, lottery numbers, correlation, Maine Democrat votes, Mega Millions, lottery correlation, Maine political voting, lottery numbers prediction, political inclination, Maine political landscape, correlation coefficient, Maine voting patterns, NY Mega Millions Lottery, statistical analysis, Democrat votes for Senators in Maine, lottery number selection, Maine political research, lottery number prediction, Maine political trivia

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

Mega millions lottery numbers
Detailed data title: Second smallest winning Mega Millions Megaball number on the last draw of the year
Source: NY Mega Millions Lottery
See what else correlates with Mega millions lottery numbers

Correlation r = 0.8306736 (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 = 0.6900186 (Coefficient of determination)
This means 69% of the change in the one variable (i.e., Mega millions lottery numbers) is predictable based on the change in the other (i.e., Votes for Democratic Senators in Maine) over the 7 years from 2002 through 2020.

p < 0.05, which statistically significant(Null hypothesis significance test)
The p-value is 0.0206. 0.0206390172734316380000000000
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 0.83 in 2.06% of random cases. Said differently, if you correlated 48 random variables Which I absolutely did.
with the same 6 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 6 because we have two variables measured over a period of 7 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.

[ 0.21, 0.97 ] 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.
2002200620082012201420182020
Votes for Democratic Senators in Maine (Total votes)2098581131312795109290019025466268347223
Mega millions lottery numbers (Megaball number)214221371031




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 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.




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([209858,113131,279510,92900,190254,66268,347223,])
array_2 = np.array([21,4,22,13,7,10,31,])
array_1_name = "Votes for Democratic Senators in Maine"
array_2_name = "Mega millions lottery numbers"

# 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?

Bravo! Your evaluation rocks!


Correlation ID: 5378 · Black Variable ID: 26249 · Red Variable ID: 893
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0