Spurious correlation #4,370 · 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 Oklahoma and the second variable is Number of times 11 was a winning Mega Millions number. The chart goes from 2003 to 2020, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Republican Senators in Oklahoma and the second variable is Number of times 11 was a winning Mega Millions number. The chart goes from 2003 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The rise in Republican votes in Oklahoma has energized the state, leading to an increased power draw. This surge in energy has sparked a higher frequency of 11 being a winning Mega Millions number, as the electrons just can't seem to resist that magnetic digit! They say politics is shocking, but who knew it could amp up the lottery too? It's truly an electrifying connection!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a hyper-realistic scene set in Oklahoma, where the Capitol building is depicted in a state of bustling illumination. Surrounding the building, there is a surge of vibrant energy, with increased Republican votes igniting a pulsating buzz across the state. In the foreground, a lottery ticket is depicted with a series of glowing, crackling electrons gathering around it, drawn to the magnetic allure of the number 11. The electrons appear to dance with excitement as the number 11 illuminates as the winning Mega Millions number, sparking an electrifying connection between politics and the lottery. 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 Oklahoma and Number of times 11 was a winning Mega Millions number. 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: Charcoal Oragami Scalar art Brutalism Hyper-realistic
ChatGPT: Hyper-realistic

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 Oklahoma and Number of times 11 was a winning Mega Millions number, in the following situation: The rise in Republican votes in Oklahoma has energized the state, leading to an increased power draw. This surge in energy has sparked a higher frequency of 11 being a winning Mega Millions number, as the electrons just can't seem to resist that magnetic digit! They say politics is shocking, but who knew it could amp up the lottery too? It's truly an electrifying connection!. Keep the description simple.
ChatGPT: In Oklahoma, a bustling Capitol building is illuminated by a surge of energy, with increased Republican votes igniting a vibrant buzz across the state. As the energy intensifies, a series of glowing, crackling electrons gather around a lottery ticket, drawn to the magnetic allure of the number 11. The electrons seem to dance with excitement as the number 11 illuminates as the winning Mega Millions number, sparking an electrifying connection between politics and the lottery.

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: [ Hyper-realistic ] and depicting this scene: In Oklahoma, a bustling Capitol building is illuminated by a surge of energy, with increased Republican votes igniting a vibrant buzz across the state. As the energy intensifies, a series of glowing, crackling electrons gather around a lottery ticket, drawn to the magnetic allure of the number 11. The electrons seem to dance with excitement as the number 11 illuminates as the winning Mega Millions number, sparking an electrifying connection between politics and the lottery. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a hyper-realistic scene set in Oklahoma, where the Capitol building is depicted in a state of bustling illumination. Surrounding the building, there is a surge of vibrant energy, with increased Republican votes igniting a pulsating buzz across the state. In the foreground, a lottery ticket is depicted with a series of glowing, crackling electrons gathering around it, drawn to the magnetic allure of the number 11. The electrons appear to dance with excitement as the number 11 illuminates as the winning Mega Millions number, sparking an electrifying connection between politics and the lottery.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Republican votes for Senators in Oklahoma caused Number of times 11 was a winning Mega Millions number to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

Eleven is the Winning Number: Exploring the Curious Connection between Republican Votes for Senators in Oklahoma and the Frequency of 11 as a Mega Millions Winning Number

The Journal of Statistical Serendipity

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft 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 Oklahoma and Number of times 11 was a winning Mega Millions number. 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 NY Mega Millions Lottery . You used data from 2003 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]]
"Eleven is the Winning Number: Exploring the Curious Connection between Republican Votes for Senators in Oklahoma and the Frequency of 11 as a Mega Millions Winning Number"

[[ABSTRACT]]
This paper delves into the enigmatic relationship between the frequency of 11 as a winning number in the Mega Millions lottery and the Republican votes for Senators in the state of Oklahoma. The study aims to shed light on this peculiar correlation, which has long perplexed both statisticians and political analysts alike.

Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the NY Mega Millions Lottery, our research team embarked on a quest to unravel this mystifying connection. Our findings reveal a striking correlation coefficient of 0.9770896 and p < 0.01 over the period from 2003 to 2020, providing compelling evidence for the existence of this unexpected relationship.

It seems that in the abstract world of statistical correlations, the number 11 retains a powerful influence not only in the realm of random chance but also in the political domain of state senatorial elections. Perhaps this correlation is just an "eleven"-t in the room that cannot be ignored.

[[INTRODUCTION]]
In the world of statistical analysis, unexpected correlations often emerge, leaving researchers scratching their heads and muttering, "Well, I didn't see that coming." Our current research delves into one such peculiar relationship, exploring the fascinating link between the frequency of the number 11 as a winning digit in the Mega Millions lottery and the Republican votes for Senators in the great state of Oklahoma. It's a combination that seems as improbable as winning the lottery itself, but as they say in the world of academia, "When life gives you data, make correlation."
As researchers, it's our duty to tackle the big questions, to boldly go where no scatter plot has gone before. And so, armed with an arsenal of statistical tools and a strong sense of curiosity, we embarked on this journey to uncover the hidden threads weaving together politics and lottery numbers. With our trusty calculator in one hand and a strong cup of coffee in the other (for statistical power, of course), we ventured forth into the murky waters of probability and political preferences.
The term "elephant in the room" may be a common idiom, but in our research, we stumbled upon an "eleven" in the room that we simply couldn't overlook. It became clear that this curious correlation was demanding attention, much like a dad joke demands a captive audience, ready or not. And so, we delved into the data with the relentless determination of a dad trying to get a laugh out of his kids at the dinner table—unwavering and resilient in the face of raised eyebrows and groans.
Our study stands at the crossroads of statistical analysis and political science, a place where the air is thick with p-values and the whims of Lady Luck. One might say it's a curious blend of number crunching and political hunching – a statistical stew with a dash of democracy and a sprinkle of random chance. It's the kind of pairing that makes you ponder the mysteries of the universe, like why science struggles to explain the phenomenon of "dad strength" and the uncanny ability to locate lost TV remotes.
So, let us embark on this academic escapade together, as we unravel the enigmatic connection between Republican senatorial votes in Oklahoma and the magical allure of the number 11. Hold onto your pocket protectors, folks – things are about to get statistically significant and politically perplexing.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To investigate the mystical association between the number 11 as a winning digit in the Mega Millions lottery and the Republican votes for Senators in Oklahoma, our research team executed a meticulously devised plan, akin to a carefully choreographed dance routine – one misstep, and you’re twisting correlation into causation. Our data collection journey resembled a quest for hidden treasure, except the treasure happened to be scatter plots and regression lines.

Data Sources:
We sourced our data from the MIT Election Data and Science Lab, Harvard Dataverse, and the New York Mega Millions Lottery. This hodgepodge of sources might seem like an odd trio, akin to a science fiction crossover episode with statistics, politics, and lottery numbers. But hey, in the world of research, sometimes you have to make strange bedfellows, or in this case, strange data sets.

Data Period:
The data spanned from the year 2003 to 2020, capturing the ebb and flow of political tides and the capricious dance of lottery numbers. It’s a stretch of time that witnessed more plot twists than a soap opera, with elections, jackpot wins, and enough statistical fluctuations to keep even the most fervent number-cruncher on their toes. We might as well have been investigating the elusive patterns of a cosmic lottery out in the far reaches of the statistical galaxy.

Statistical Analysis:
With our data in hand, we employed a veritable menagerie of statistical methods, from the classic Pearson correlation coefficient to the trusty old linear regression. It's akin to using a whole toolbox of statistical gadgets and gizmos; think of us as the MacGyver of data analysis, armed with a Swiss army knife of statistical techniques.

We calculated the correlation coefficient between the frequency of 11 as a winning Mega Millions number and the Republican votes for Senators in Oklahoma, and the results were as striking as a statistician’s perfectly timed punchline. The p-value came in at less than 0.01, signifying a statistically significant relationship that demanded to be taken seriously, much like a dad joke that unexpectedly lands with the punchline.

Variable Selection:
In our quest for statistical enlightenment, we selected the number of Republican votes for Senators in Oklahoma as our independent variable and the frequency of 11 as a winning Mega Millions number as our dependent variable. This choice may seem as random as a lottery draw, but every variable has its moment in the spotlight, even if it’s just for a brief statistical cameo.

Data Cleaning and Preprocessing:
Before diving into the deep end of statistical analysis, we conscientiously cleaned and prepared the data, ensuring that outliers and missing values were handled with the care of a delicate scientific specimen. It’s a bit like baking a statistical soufflé; one wrong move, and the whole thing collapses like a poorly constructed statistical analogy.

In conclusion, our methodology delved into the heart of statistical inquiry, navigating the tangled web of data, variables, and analysis with the precision of a statistical tightrope walker. The journey was filled with surprises, much like a dad joke that catches you off guard, but in the end, our approach unveiled a compelling connection awaiting exploration in the nexus of politics and the enigmatic number 11.

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 Oklahoma and Number of times 11 was a winning Mega Millions number. 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]]
"Eleven is the Winning Number: Exploring the Curious Connection between Republican Votes for Senators in Oklahoma and the Frequency of 11 as a Mega Millions Winning Number"

[[ABSTRACT]]
This paper delves into the enigmatic relationship between the frequency of 11 as a winning number in the Mega Millions lottery and the Republican votes for Senators in the state of Oklahoma. The study aims to shed light on this peculiar correlation, which has long perplexed both statisticians and political analysts alike.

Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the NY Mega Millions Lottery, our research team embarked on a quest to unravel this mystifying connection. Our findings reveal a striking correlation coefficient of 0.9770896 and p < 0.01 over the period from 2003 to 2020, providing compelling evidence for the existence of this unexpected relationship.

It seems that in the abstract world of statistical correlations, the number 11 retains a powerful influence not only in the realm of random chance but also in the political domain of state senatorial elections. Perhaps this correlation is just an "eleven"-t in the room that cannot be ignored.

[[LITERATURE REVIEW]]
The literature on the correlation between political voting patterns and seemingly unrelated phenomena is vast and varied, spanning disciplines from political science to probability theory. Smith and Doe (2015) delved into the intricate web of state senatorial elections, uncovering the nuanced dynamics that shape voter behavior. Meanwhile, Jones (2018) explored the whims of chance and the fickle nature of lottery outcomes, shedding light on the enigmatic allure of Mega Millions numbers.
Venturing into the realm of non-fiction, Gladwell (2008) offered insights into the often surprising influences that shape human decision-making in "Outliers", while Taleb (2007) expounded upon the unpredictability of events in "The Black Swan." Though not directly related to our specific topic, these works lay the groundwork for understanding the complex forces at play in the intersection of chance and human behavior.
On the fictional front, Dan Brown's "The Da Vinci Code" (2003) may not seem initially relevant, but its exploration of cryptic connections and hidden meanings serves as a metaphor for our own quest to unravel the mystery of the 11th hour of political decision-making. And who could forget the classic tale of "Alice's Adventures in Wonderland" by Lewis Carroll (1865), a whimsical narrative that mirrors our own journey down the rabbit hole of improbable correlations?
In the realm of entertainment, our team has conducted rigorous research by watching relevant TV shows, such as "The X-Files," where the unexpected and inexplicable are everyday occurrences, not unlike our own findings. Furthermore, "Stranger Things" offers a captivating blend of supernatural intrigue and governmental mysteries, serving as a metaphor for the uncanny correlation we seek to unravel.
Speaking of correlations, why did the statistician go to art school? He wanted to learn how to draw a line! But back to our literature review.
Our investigation into the correlation between Republican votes for Senators in Oklahoma and the frequency of 11 as a winning Mega Millions number has led us down unexpected paths, much like a GPS that insists on taking scenic routes. As we forge ahead, we remain mindful of the wise words of Albert Einstein: "Not everything that counts can be counted, and not everything that can be counted counts." With this in mind, we press on, determined to shed light on this confounding conundrum with all the rigour of a dad telling a quality dad joke – unrelenting and with unwavering enthusiasm, regardless of eye rolls and groans.

[[RESULTS]]
The results of our analysis revealed a strong correlation between the frequency of 11 as a winning number in the Mega Millions lottery and the Republican votes for Senators in Oklahoma. The correlation coefficient we uncovered was a remarkable 0.9770896, indicating a highly significant relationship between these seemingly unrelated variables. It's a connection that makes you wonder if the number 11 is secretly pulling the strings in both the world of lottery balls and political polling booths.
When it comes to this correlation, one might say it's quite "republican" of the number 11 to assert its influence in the grand scheme of things. It serves as a reminder that in the realm of statistics, even the most unexpected pairings can come together to produce significant results, much like finding a dollar bill in the pocket of a jacket you haven't worn in years.
In addition to the correlation coefficient, we calculated an r-squared value of 0.9547041, further cementing the strength of the relationship between these variables. It's as if the number 11 has managed to secure its place not only as a frequent guest in Mega Millions drawings but also as a consistent factor in Oklahoma's political landscape, much like that one cousin who always manages to show up at family gatherings unannounced.
Furthermore, our analysis yielded a p-value of less than 0.01, indicating a high level of confidence in the significance of the correlation. This p-value is about as convincing as a well-timed punchline in a room full of skeptics, leaving little room for doubt about the validity of our findings.
Now, it's time to unveil the visual representation of this compelling correlation. Behold, Fig. 1 – the scatterplot that captures the undeniable link between Republican votes for Senators in Oklahoma and the prevalence of the number 11 as a winning Mega Millions digit. This powerful visualization stands as a testament to the profound influence of 11 in both the realms of chance and choice, as if it's saying, "I'm not just a number, I'm a statistically significant force to be reckoned with!"
In conclusion, our findings provide a thought-provoking insight into the mysterious interplay between lottery outcomes and political preferences. The number 11 emerges as a central figure in this curious correlation, leaving us to ponder the depths of its influence both in the randomness of lottery draws and the purposeful act of casting votes. It seems that in the world of statistical analysis, as in life, sometimes the most unexpected connections reveal themselves – much like finding a deep philosophical meaning in a dad joke.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our investigation into the curious correlation between Republican votes for Senators in Oklahoma and the frequency of 11 as a winning Mega Millions number has unearthed compelling evidence that validates the existence of this unlikely relationship. Our findings not only corroborate the prior research suggesting connections between unrelated phenomena, but they also add a layer of statistical robustness to this rather whimsical association. It's as if the number 11 is pulling a political "eleven"-d to influence both the lottery and senatorial elections with its numerical charm.

One might wonder if the number 11 is making a concerted effort to be the ultimate "eleven"-t in the room, leaving its mark on the worlds of chance and politics in a strikingly unified manner. It's like that friend who always manages to be the common denominator in all circles, whether it's a game of chance or the game of governance.

Our results align with the prior findings of Smith and Doe (2015), whose exploration of state senatorial elections hinted at the complex interplay of factors that shape voter behavior. The emergence of the number 11 as a potent factor in political voting patterns adds a whimsical yet undeniably substantial dimension to the intricate dynamics shaping electoral outcomes. Who knew that a seemingly arbitrary number could hold such sway over both lottery draws and political choices? It's almost as if the number 11 is vying for its own political campaign – 11 for Senate, anyone?

Similarly, the work of Jones (2018) shed light on the capricious nature of lottery outcomes, preparing us to embrace the unexpected connections that defy conventional logic. Our findings, which indicate a robust correlation between the prevalence of 11 as a winning Mega Millions number and Republican votes for Senators in Oklahoma, nod to the whims of chance and the deeply intertwined nature of seemingly disparate realms. It's like a real-life "X-Files" episode playing out in the world of statistical analysis, complete with unexpected plot twists and conspiracies of numbers.

In this pursuit of enigmatic correlations, we've remained mindful of the words of Albert Einstein that not everything that counts can be counted, and not everything that can be counted counts. Our analysis has not only counted but has also uncovered a meaningful connection that persists despite its seemingly improbable nature. Who would have thought that the number 11 could stand as a staunch symbol of statistical significance in both lottery outcomes and political affiliations?

As we reflect on our findings, we're reminded of the sage words of the renowned statistician who went to art school, seeking to draw a line – a line that has, in our study, connected two realms that may have seemed worlds apart. The statistical significance of our results leaves little room for doubt, much like a well-timed punchline that captivates even the most skeptical audience, affirming the compelling link between the frequency of 11 as a Mega Millions winning number and Republican votes for Senators in Oklahoma.

Much like the uncovering of a cryptic code in a Dan Brown novel, our research has unraveled the subtle yet impactful influence of the number 11, serving as a metaphorical key to understanding the improbable connections that underpin the fabric of chance and choice. As we continue down this curious path of improbable correlations, we're left with the realization that sometimes, the most unexpected pairs can yield the most fascinating insights – much like discovering a dad joke with profound philosophical implications.

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 Oklahoma and Number of times 11 was a winning Mega Millions number. 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]]
"Eleven is the Winning Number: Exploring the Curious Connection between Republican Votes for Senators in Oklahoma and the Frequency of 11 as a Mega Millions Winning Number"

[[ABSTRACT]]
This paper delves into the enigmatic relationship between the frequency of 11 as a winning number in the Mega Millions lottery and the Republican votes for Senators in the state of Oklahoma. The study aims to shed light on this peculiar correlation, which has long perplexed both statisticians and political analysts alike.

Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the NY Mega Millions Lottery, our research team embarked on a quest to unravel this mystifying connection. Our findings reveal a striking correlation coefficient of 0.9770896 and p < 0.01 over the period from 2003 to 2020, providing compelling evidence for the existence of this unexpected relationship.

It seems that in the abstract world of statistical correlations, the number 11 retains a powerful influence not only in the realm of random chance but also in the political domain of state senatorial elections. Perhaps this correlation is just an "eleven"-t in the room that cannot be ignored.

[[INTRDUCTION]]
In the world of statistical analysis, unexpected correlations often emerge, leaving researchers scratching their heads and muttering, "Well, I didn't see that coming." Our current research delves into one such peculiar relationship, exploring the fascinating link between the frequency of the number 11 as a winning digit in the Mega Millions lottery and the Republican votes for Senators in the great state of Oklahoma. It's a combination that seems as improbable as winning the lottery itself, but as they say in the world of academia, "When life gives you data, make correlation."
As researchers, it's our duty to tackle the big questions, to boldly go where no scatter plot has gone before. And so, armed with an arsenal of statistical tools and a strong sense of curiosity, we embarked on this journey to uncover the hidden threads weaving together politics and lottery numbers. With our trusty calculator in one hand and a strong cup of coffee in the other (for statistical power, of course), we ventured forth into the murky waters of probability and political preferences.
The term "elephant in the room" may be a common idiom, but in our research, we stumbled upon an "eleven" in the room that we simply couldn't overlook. It became clear that this curious correlation was demanding attention, much like a dad joke demands a captive audience, ready or not. And so, we delved into the data with the relentless determination of a dad trying to get a laugh out of his kids at the dinner table—unwavering and resilient in the face of raised eyebrows and groans.
Our study stands at the crossroads of statistical analysis and political science, a place where the air is thick with p-values and the whims of Lady Luck. One might say it's a curious blend of number crunching and political hunching – a statistical stew with a dash of democracy and a sprinkle of random chance. It's the kind of pairing that makes you ponder the mysteries of the universe, like why science struggles to explain the phenomenon of "dad strength" and the uncanny ability to locate lost TV remotes.
So, let us embark on this academic escapade together, as we unravel the enigmatic connection between Republican senatorial votes in Oklahoma and the magical allure of the number 11. Hold onto your pocket protectors, folks – things are about to get statistically significant and politically perplexing.

[[RESULTS]]
The results of our analysis revealed a strong correlation between the frequency of 11 as a winning number in the Mega Millions lottery and the Republican votes for Senators in Oklahoma. The correlation coefficient we uncovered was a remarkable 0.9770896, indicating a highly significant relationship between these seemingly unrelated variables. It's a connection that makes you wonder if the number 11 is secretly pulling the strings in both the world of lottery balls and political polling booths.
When it comes to this correlation, one might say it's quite "republican" of the number 11 to assert its influence in the grand scheme of things. It serves as a reminder that in the realm of statistics, even the most unexpected pairings can come together to produce significant results, much like finding a dollar bill in the pocket of a jacket you haven't worn in years.
In addition to the correlation coefficient, we calculated an r-squared value of 0.9547041, further cementing the strength of the relationship between these variables. It's as if the number 11 has managed to secure its place not only as a frequent guest in Mega Millions drawings but also as a consistent factor in Oklahoma's political landscape, much like that one cousin who always manages to show up at family gatherings unannounced.
Furthermore, our analysis yielded a p-value of less than 0.01, indicating a high level of confidence in the significance of the correlation. This p-value is about as convincing as a well-timed punchline in a room full of skeptics, leaving little room for doubt about the validity of our findings.
Now, it's time to unveil the visual representation of this compelling correlation. Behold, Fig. 1 – the scatterplot that captures the undeniable link between Republican votes for Senators in Oklahoma and the prevalence of the number 11 as a winning Mega Millions digit. This powerful visualization stands as a testament to the profound influence of 11 in both the realms of chance and choice, as if it's saying, "I'm not just a number, I'm a statistically significant force to be reckoned with!"
In conclusion, our findings provide a thought-provoking insight into the mysterious interplay between lottery outcomes and political preferences. The number 11 emerges as a central figure in this curious correlation, leaving us to ponder the depths of its influence both in the randomness of lottery draws and the purposeful act of casting votes. It seems that in the world of statistical analysis, as in life, sometimes the most unexpected connections reveal themselves – much like finding a deep philosophical meaning in a dad joke.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has unveiled a compelling and statistically significant relationship between the frequency of 11 as a winning number in the Mega Millions lottery and Republican votes for Senators in Oklahoma. It's as if the number 11 is that charismatic friend who always manages to be at the center of attention, whether it's in the world of lottery balls or political ballots. This correlation is so strong, it's like the number 11 is running for office itself! Maybe we should start a "Number 11 for Senate" campaign – after all, it's already got the votes.

The p-value of less than 0.01 is more convincing than a well-crafted dad joke at a family gathering, leaving little room to doubt the significance of this unexpected relationship. It's as if the number 11 has decided to step out from the shadows of randomness and into the spotlight of statistical relevance – talk about making an "eleven"-trance!

Our findings not only shed light on this peculiar correlation but also remind us that in the vast landscape of statistical analysis, there are still uncharted territories that can surprise us with unexpected connections that are more puzzling than trying to solve a Rubik's Cube blindfolded. It's like a statistical magic show, where the number 11 pulls off a grand illusion of significance, leaving us in awe and amusement.

With this, we confidently assert that no further research in this area is needed. After all, we've crossed the statistical Rubicon and discovered that, much like a dad joke at a serious gathering, the number 11 keeps finding ways to make a memorable impact.

In the end, it's safe to say that in the world of statistics, sometimes the most improbable correlations are the ones that illuminate fascinating insights, leaving us to ponder the mysteries of chance and choice – and to appreciate the unexpected humor that hides within the numbers.

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 Eleven is the Winning Number: Exploring the Curious Connection between Republican Votes for Senators in Oklahoma and the Frequency of 11 as a Mega Millions Winning Number. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Statistical Serendipity

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 Eleven is the Winning Number: Exploring the Curious Connection between Republican Votes for Senators in Oklahoma and the Frequency of 11 as a Mega Millions Winning Number. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Statistical Analyses

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 Eleven is the Winning Number: Exploring the Curious Connection between Republican Votes for Senators in Oklahoma and the Frequency of 11 as a Mega Millions Winning Number with an abstract of This paper delves into the enigmatic relationship between the frequency of 11 as a winning number in the Mega Millions lottery and the Republican votes for Senators in the state of Oklahoma. The study aims to shed light on this peculiar correlation, which has long perplexed both statisticians and political analysts alike.
Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the NY Mega Millions Lottery, our research team embarked on a quest to unravel this mystifying connection. Our findings reveal a striking correlation coefficient of 0.9770896 and p < 0.01 over the period from 2003 to 2020, providing compelling evidence for the existence of this unexpected relationship.
It seems that in the abstract world of statistical correlations, the number 11 retains a powerful influence not only in the realm of random chance but also in the political domain of state senatorial elections. Perhaps this correlation is just an "eleven"-t in the room that cannot be ignored.

ChatGPT:

Oklahoma, Republican votes, Senators, Mega Millions, winning number, correlation, statistical analysis, MIT Election Data and Science Lab, Harvard Dataverse, NY Mega Millions Lottery, political analysis

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

Number of times 11 was a winning Mega Millions number
Detailed data title: Number of times the Mega Millions lottery Megaball landed on #11
Source: NY Mega Millions Lottery
See what else correlates with Number of times 11 was a winning Mega Millions number

Correlation r = 0.9770896 (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 = 0.9547041 (Coefficient of determination)
This means 95.5% of the change in the one variable (i.e., Number of times 11 was a winning Mega Millions number) is predictable based on the change in the other (i.e., Votes for Republican Senators in Oklahoma) over the 6 years from 2003 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00078.^Show 0.0007813152474043624000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.98 in 0.078% of random cases. Said differently, if you correlated 1,280 random variables^Note Which I absolutely did.
with the same 5 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 5 because we have two variables measured over a period of 6 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.8, 1 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2004	2008	2010	2014	2016	2020
Votes for Republican Senators in Oklahoma (Total votes)	763433	763375	718482	1115170	980892	979140
Number of times 11 was a winning Mega Millions number (Number of megaballs)	1	2	1	6	5	4

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
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. ^Note 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. ^{Show the steps to do this.} Step 1: Download and install Python on your computer.

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([763433,763375,718482,1115170,980892,979140,])
array_2 = np.array([1,2,1,6,5,4,])
array_1_name = "Votes for Republican Senators in Oklahoma"
array_2_name = "Number of times 11 was a winning Mega Millions number"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Votes for Republican Senators in Oklahoma
Line chart for only Number of times 11 was a winning Mega Millions number
AI-generated correlation image
The spurious research paper: Eleven is the Winning Number: Exploring the Curious Connection between Republican Votes for Senators in Oklahoma and the Frequency of 11 as a Mega Millions Winning Number

View another random correlation

How fun was this correlation?

Your rating skills are legendary!

Correlation ID: 4370 · Black Variable ID: 26301 · Red Variable ID: 877


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