about · email me · subscribe
Spurious correlation #2,318 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'report UFO sighting' and the second variable is US birth rates of triplets or more.  The chart goes from 2004 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Fewer UFO reports meant fewer aliens conducting their questionable experiments on unsuspecting earthlings. This led to a significant decrease in the number of surprise intergalactic multiples, ultimately giving a whole new meaning to the term "close encounters of the third kind."

Model: dalle-3
Prompt: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s depicting a person using a computer to search "report UFO sighting" on Google. In the background, show a hospital sign announcing the birth of triplets or more in the United States. The overall style should feature classic comic book elements but with a slightly retro, nostalgic feel. (Graphics are property of OpenAI and have been created by the DALL·E 3 model) 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: Google searches for 'report UFO sighting' and US birth rates of triplets or more. 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: Cute 2D animation A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s inspired by bauhaus Scalar art Steampunk
ChatGPT: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s

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 Google searches for 'report UFO sighting' and US birth rates of triplets or more together. Keep the description simple.
ChatGPT: In the scene, we see a person using a computer to search "report UFO sighting" on Google, while in the background, a hospital sign announces the birth of triplets or more in the United States.

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: [ A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s ] and depicting this scene: In the scene, we see a person using a computer to search "report UFO sighting" on Google, while in the background, a hospital sign announces the birth of triplets or more in the United States. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s depicting a person using a computer to search "report UFO sighting" on Google. In the background, show a hospital sign announcing the birth of triplets or more in the United States. The overall style should feature classic comic book elements but with a slightly retro, nostalgic feel. (Graphics are property of OpenAI and have been created by the DALL·E 3 model)

*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 a decrease in report UFO sighting (Google searches for 'report UFO sighting') caused US birth rates of triplets or more to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)
The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More

Journal of Extraterrestrial Phenomena Research

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Google searches for 'report UFO sighting' and US birth rates of triplets or more. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Your research team used data from Google Trends and CDC to assess this nagging question. You found a correlation coefficient of 0.9066327 and p < 0.01 for 2004 to 2021.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More

[[ABSTRACT]]
This paper investigates the curious relationship between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Using data from Google Trends and the Centers for Disease Control and Prevention (CDC) for the years 2004 to 2021, we found a remarkably high correlation coefficient of 0.9066327 and a p-value of less than 0.01, suggesting a strong statistical significance. Our analysis, while cautious to assert causation, hints at the existence of a mysterious force linking an increase in searches for unidentified flying objects with the delivery of multiples. The implications of these findings are undoubtedly out of this world, and further investigation is warranted to unravel this enigmatic connection.


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 Google searches for 'report UFO sighting' and US birth rates of triplets or more. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More

[[ABSTRACT]]
This paper investigates the curious relationship between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Using data from Google Trends and the Centers for Disease Control and Prevention (CDC) for the years 2004 to 2021, we found a remarkably high correlation coefficient of 0.9066327 and a p-value of less than 0.01, suggesting a strong statistical significance. Our analysis, while cautious to assert causation, hints at the existence of a mysterious force linking an increase in searches for unidentified flying objects with the delivery of multiples. The implications of these findings are undoubtedly out of this world, and further investigation is warranted to unravel this enigmatic connection.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of ufology and obstetrics might seem at first glance to be a cosmic leap, but as we delve into the peculiar world of statistical anomalies, the unexpected coalescence of Google searches for 'Report UFO Sighting' and the occurrence of triplet or higher-order multiple births in the United States presents an intriguing mystery. While the existence of UFOs and extraterrestrial visitors remains a subject of fervent debate, we are compelled to consider whether their presence - real or perceived - could be influencing earthly matters as remarkable as birth rates of triplets or more.

The topic at hand has long been relegated to the fringes of statistical inquiry, perhaps due to the unconventional nature of the subject matter. However, it is precisely this unpredictability and uncharted territory that makes the link between UFO search activity and the prevalence of rare multiple births such an irresistible enigma to unravel. With that in mind, the purpose of this study is to explore and statistically analyze any empirical relationship between these two seemingly disparate phenomena, and to discern whether there truly exists a correlation that defies earthly explanation.


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 Google searches for 'report UFO sighting' and US birth rates of triplets or more. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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 few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More

[[ABSTRACT]]
This paper investigates the curious relationship between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Using data from Google Trends and the Centers for Disease Control and Prevention (CDC) for the years 2004 to 2021, we found a remarkably high correlation coefficient of 0.9066327 and a p-value of less than 0.01, suggesting a strong statistical significance. Our analysis, while cautious to assert causation, hints at the existence of a mysterious force linking an increase in searches for unidentified flying objects with the delivery of multiples. The implications of these findings are undoubtedly out of this world, and further investigation is warranted to unravel this enigmatic connection.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of ufology and obstetrics might seem at first glance to be a cosmic leap, but as we delve into the peculiar world of statistical anomalies, the unexpected coalescence of Google searches for 'Report UFO Sighting' and the occurrence of triplet or higher-order multiple births in the United States presents an intriguing mystery. While the existence of UFOs and extraterrestrial visitors remains a subject of fervent debate, we are compelled to consider whether their presence - real or perceived - could be influencing earthly matters as remarkable as birth rates of triplets or more.
The topic at hand has long been relegated to the fringes of statistical inquiry, perhaps due to the unconventional nature of the subject matter. However, it is precisely this unpredictability and uncharted territory that makes the link between UFO search activity and the prevalence of rare multiple births such an irresistible enigma to unravel. With that in mind, the purpose of this study is to explore and statistically analyze any empirical relationship between these two seemingly disparate phenomena, and to discern whether there truly exists a correlation that defies earthly explanation.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Smith et al. (2015) examined the association between online UFO sighting reports and anomalous celestial events, but failed to find a significant relationship with earthly occurrences. Conversely, Doe and Jones (2018) explored the influence of lunar cycles on multiple births, yielding inconclusive results. While these studies have contributed valuable insights to their respective fields, they have yet to shed light on the peculiar nexus we seek to unravel in this investigation.

Turning to non-fiction literature, "UFOs: Myths, Conspiracies, and Realities" by Johnathan Denninger provides a comprehensive analysis of UFO sightings and the speculation surrounding their origins. "Multiple Blessings: Surviving to Thriving with Twins and Sextuplets" by Kate Gosselin delves into the challenges and triumphs of parenting multiples, offering a poignant perspective that resonates with our research focus.

In the realm of fiction, "The X-Files: Trust No One" by Jonathan Maberry and "Contact" by Carl Sagan offer captivating narratives that captivate the imagination with extraterrestrial encounters. The allure of these literary works is fittingly reminiscent of the intrigue we encounter in our own investigation.

Furthermore, the researchers diligently engaged with pop culture references, including "The X-Files," "Unsolved Mysteries," and "Ancient Aliens," to better understand the public fascination with UFO sightings and the potential impact on the perception of unusual occurrences.

The juxtaposition of serious academic studies with literary and popular culture references provided the researchers with a multifaceted understanding of the phenomenon under study, inspiring a blend of analytical rigor and imaginative curiosity in the pursuit of uncovering the extraordinary connection between UFO sightings and multiple births.


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 Google searches for 'report UFO sighting' and US birth rates of triplets or more. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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 Google Trends and CDC . You used data from 2004 to 2021

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More

[[ABSTRACT]]
This paper investigates the curious relationship between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Using data from Google Trends and the Centers for Disease Control and Prevention (CDC) for the years 2004 to 2021, we found a remarkably high correlation coefficient of 0.9066327 and a p-value of less than 0.01, suggesting a strong statistical significance. Our analysis, while cautious to assert causation, hints at the existence of a mysterious force linking an increase in searches for unidentified flying objects with the delivery of multiples. The implications of these findings are undoubtedly out of this world, and further investigation is warranted to unravel this enigmatic connection.

[[INTRODUCTION]]
The intersection of ufology and obstetrics might seem at first glance to be a cosmic leap, but as we delve into the peculiar world of statistical anomalies, the unexpected coalescence of Google searches for 'Report UFO Sighting' and the occurrence of triplet or higher-order multiple births in the United States presents an intriguing mystery. While the existence of UFOs and extraterrestrial visitors remains a subject of fervent debate, we are compelled to consider whether their presence - real or perceived - could be influencing earthly matters as remarkable as birth rates of triplets or more.
The topic at hand has long been relegated to the fringes of statistical inquiry, perhaps due to the unconventional nature of the subject matter. However, it is precisely this unpredictability and uncharted territory that makes the link between UFO search activity and the prevalence of rare multiple births such an irresistible enigma to unravel. With that in mind, the purpose of this study is to explore and statistically analyze any empirical relationship between these two seemingly disparate phenomena, and to discern whether there truly exists a correlation that defies earthly explanation.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To investigate the captivating correlation between Google searches for 'Report UFO Sighting' and US birth rates of triplets or more, we embarked on a methodical journey that traversed the realms of internet search trends and epidemiological data. The first step in our quest involved accessing Google Trends, a treasure trove of search query data that spans the expansive timeline from 2004 to 2021. Here, we carefully navigated the digital constellations, charting the surge and ebb of 'Report UFO Sighting' searches across the years, while remaining ever vigilant to avoid falling into the black holes of spurious spikes and anomalous blips.

Our expedition through the world wide web did not end with Google alone. We also voyaged into the domain of the Centers for Disease Control and Prevention (CDC), harnessing their birth data to illuminate the incidence of triplet or higher-order multiple births in the United States over the same time period. This data, akin to a celestial map guiding us through the complexities of human reproduction, provided the necessary coordinates to anchor our investigation within the earthly realm of obstetrics.

With our data sets in hand, we conducted a thorough statistical analysis, employing the age-old tools of correlation coefficients and p-values to discern any meaningful relationships. We did not leap to conclusions lightly, but rather traversed the statistical landscape with the precision of an astronaut navigating the cosmos. Our analysis proceeded cautiously, mindful of the vast expanse of spurious correlations that often lay hidden in the interstellar depths of data.

After traversing the quantitative terrain of statistical analysis, we had our feet firmly planted on the terra firma of empirical evidence. Our findings, akin to rare comets streaking across the night sky, revealed a correlation coefficient of 0.9066327 and a p-value of less than 0.01, indicating a statistically significant connection between Google searches for UFO sightings and US birth rates of triplets or more. These results, like a cosmic alignment of celestial bodies, pointed to a relationship that demands further scrutiny and exploration.


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 Google searches for 'report UFO sighting' and US birth rates of triplets or more. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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 Google Trends and CDC .

For the time period 2004 to 2021, you found a correlation 0.9066327, r-squared of 0.8219829, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More

[[ABSTRACT]]
This paper investigates the curious relationship between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Using data from Google Trends and the Centers for Disease Control and Prevention (CDC) for the years 2004 to 2021, we found a remarkably high correlation coefficient of 0.9066327 and a p-value of less than 0.01, suggesting a strong statistical significance. Our analysis, while cautious to assert causation, hints at the existence of a mysterious force linking an increase in searches for unidentified flying objects with the delivery of multiples. The implications of these findings are undoubtedly out of this world, and further investigation is warranted to unravel this enigmatic connection.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of ufology and obstetrics might seem at first glance to be a cosmic leap, but as we delve into the peculiar world of statistical anomalies, the unexpected coalescence of Google searches for 'Report UFO Sighting' and the occurrence of triplet or higher-order multiple births in the United States presents an intriguing mystery. While the existence of UFOs and extraterrestrial visitors remains a subject of fervent debate, we are compelled to consider whether their presence - real or perceived - could be influencing earthly matters as remarkable as birth rates of triplets or more.
The topic at hand has long been relegated to the fringes of statistical inquiry, perhaps due to the unconventional nature of the subject matter. However, it is precisely this unpredictability and uncharted territory that makes the link between UFO search activity and the prevalence of rare multiple births such an irresistible enigma to unravel. With that in mind, the purpose of this study is to explore and statistically analyze any empirical relationship between these two seemingly disparate phenomena, and to discern whether there truly exists a correlation that defies earthly explanation.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

The results of our analysis reveal a strikingly high correlation between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Over the period of 2004 to 2021, we found a correlation coefficient (r) of 0.9066327, indicating a strong positive linear relationship between these two variables. The r-squared value of 0.8219829 further emphasizes the robustness of this association, explaining approximately 82.20% of the variance in the birth rates of triplets or more.

Furthermore, the p-value of less than 0.01 provides compelling evidence of the statistical significance of this correlation, suggesting that it is highly unlikely to have occurred by chance. Our findings point to a clear and substantial relationship between the intensity of public interest in unidentified flying objects, as evidenced by Google search frequency, and the occurrence of rare multiple births in the United States.

Fig. 1 depicts the scatterplot illustrating the strong positive correlation between the frequency of Google searches for 'Report UFO Sighting' and the US birth rates of triplets or more.

These results underscore the need for a deeper and more comprehensive investigation into the potential underlying mechanisms driving this unexpected connection. The implications of this correlation are certainly otherworldly, and while we tread cautiously in avoiding claims of causation, our analysis suggests that a mysterious force may be at play. This discovery raises more questions than answers, and such a peculiar relationship between these seemingly unrelated phenomena demands further elucidation.

It is worth highlighting that our study is not without limitations. While our data analysis has identified a compelling statistical association, it remains essential to consider the possibility of other influencing factors that were not directly examined in this investigation. Nevertheless, the substantial correlation between Google searches for 'Report UFO Sighting' and US birth rates of triplets or more opens a window into an uncharted realm of inquiry, transcending the boundaries of conventional statistical analysis. Further research is imperative to unravel the enigmatic connection between ufology and obstetrics, shedding light on the mysterious forces at play amidst the cosmic dance of statistical anomalies.


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 Google searches for 'report UFO sighting' and US birth rates of triplets or more. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More

[[ABSTRACT]]
This paper investigates the curious relationship between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Using data from Google Trends and the Centers for Disease Control and Prevention (CDC) for the years 2004 to 2021, we found a remarkably high correlation coefficient of 0.9066327 and a p-value of less than 0.01, suggesting a strong statistical significance. Our analysis, while cautious to assert causation, hints at the existence of a mysterious force linking an increase in searches for unidentified flying objects with the delivery of multiples. The implications of these findings are undoubtedly out of this world, and further investigation is warranted to unravel this enigmatic connection.

[[LITERATURE REVIEW]]
Smith et al. (2015) examined the association between online UFO sighting reports and anomalous celestial events, but failed to find a significant relationship with earthly occurrences. Conversely, Doe and Jones (2018) explored the influence of lunar cycles on multiple births, yielding inconclusive results. While these studies have contributed valuable insights to their respective fields, they have yet to shed light on the peculiar nexus we seek to unravel in this investigation.
Turning to non-fiction literature, "UFOs: Myths, Conspiracies, and Realities" by Johnathan Denninger provides a comprehensive analysis of UFO sightings and the speculation surrounding their origins. "Multiple Blessings: Surviving to Thriving with Twins and Sextuplets" by Kate Gosselin delves into the challenges and triumphs of parenting multiples, offering a poignant perspective that resonates with our research focus.
In the realm of fiction, "The X-Files: Trust No One" by Jonathan Maberry and "Contact" by Carl Sagan offer captivating narratives that captivate the imagination with extraterrestrial encounters. The allure of these literary works is fittingly reminiscent of the intrigue we encounter in our own investigation.
Furthermore, the researchers diligently engaged with pop culture references, including "The X-Files," "Unsolved Mysteries," and "Ancient Aliens," to better understand the public fascination with UFO sightings and the potential impact on the perception of unusual occurrences.
The juxtaposition of serious academic studies with literary and popular culture references provided the researchers with a multifaceted understanding of the phenomenon under study, inspiring a blend of analytical rigor and imaginative curiosity in the pursuit of uncovering the extraordinary connection between UFO sightings and multiple births.

[[RESULTS]]
The results of our analysis reveal a strikingly high correlation between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Over the period of 2004 to 2021, we found a correlation coefficient (r) of 0.9066327, indicating a strong positive linear relationship between these two variables. The r-squared value of 0.8219829 further emphasizes the robustness of this association, explaining approximately 82.20% of the variance in the birth rates of triplets or more.
Furthermore, the p-value of less than 0.01 provides compelling evidence of the statistical significance of this correlation, suggesting that it is highly unlikely to have occurred by chance. Our findings point to a clear and substantial relationship between the intensity of public interest in unidentified flying objects, as evidenced by Google search frequency, and the occurrence of rare multiple births in the United States.
Fig. 1 depicts the scatterplot illustrating the strong positive correlation between the frequency of Google searches for 'Report UFO Sighting' and the US birth rates of triplets or more.
These results underscore the need for a deeper and more comprehensive investigation into the potential underlying mechanisms driving this unexpected connection. The implications of this correlation are certainly otherworldly, and while we tread cautiously in avoiding claims of causation, our analysis suggests that a mysterious force may be at play. This discovery raises more questions than answers, and such a peculiar relationship between these seemingly unrelated phenomena demands further elucidation.
It is worth highlighting that our study is not without limitations. While our data analysis has identified a compelling statistical association, it remains essential to consider the possibility of other influencing factors that were not directly examined in this investigation. Nevertheless, the substantial correlation between Google searches for 'Report UFO Sighting' and US birth rates of triplets or more opens a window into an uncharted realm of inquiry, transcending the boundaries of conventional statistical analysis. Further research is imperative to unravel the enigmatic connection between ufology and obstetrics, shedding light on the mysterious forces at play amidst the cosmic dance of statistical anomalies.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The convergence of interest in UFO sightings and the occurrence of multiple births in the United States has led to a conundrum that seems straight out of a science fiction novel. Our findings not only substantiate a significant positive correlation between Google searches for 'Report UFO Sighting' and US birth rates of triplets or more but also reignite the age-old debate of "What on Earth is going on?" Our results support the notion that as the fascination with extraterrestrial encounters intensifies, a surge in the birth of triplets or more ensues, prompting us to consider the possibility of an ethereal influence on the phenomena of earthly fertility.

Building upon the literature review, the inconclusive results of past studies exploring celestial events and multiple births are now cast in a new light. While skeptics might quip, "The truth is out there," our findings provide evidence that seemingly disparate occurrences may, in fact, be intertwined by an elusive intergalactic force. These results also corroborate the multifaceted approach adopted in our literature review, demonstrating the value of blending the analytical rigor of serious academic studies with the imaginative curiosity gleaned from fictional works and pop culture references.

The significant correlation coefficient and the undeniably low p-value assert that the association between UFO sightings and the birth of triplets or more in the US is statistically robust. Nevertheless, our analysis remains grounded in the recognition that correlation does not imply causation, an admonition that scientists and conspiracy theorists alike are inclined to heed. As we delve into the intricacies of this unorthodox correlation, we must tread cautiously, channeling our inner Mulder and Scully to attentively unravel this enduring enigma.

Drawing on the wisdom of "The X-Files," "Unsolved Mysteries," and "Ancient Aliens," we are inspired to unearth the underlying mechanisms that precipitate this extraordinary connection. The implications of this correlation are undeniably otherworldly, leaving us to contemplate the possibility of a mind-bending cosmic choreography orchestrating the birth of triplets or more in response to the collective consciousness' wandering gaze toward the stars.

Our study's limitations warrant acknowledgment, recognizing the potential influence of unexplored factors that might intersect the celestial and terrestrial realms. Nonetheless, the harmony observed between the increased interest in UFO sightings and the occurrence of rare multiple births transcends the confines of conventional statistical analyses and beckons further exploration.

In unraveling the extraordinary connection between ufology and obstetrics, we urge fellow researchers to embrace the humorous conceit that, as we gaze toward the unknown, the unknown may also cast its gaze upon us, leaving us to ponder the cosmic chuckle that reverberates through the intertwined fabric of human and intergalactic existence. As we navigate this perplexing labyrinth of statistical anomalies and paranormal inklings, our inquiry into the nexus between UFO sightings and multiple births embodies both the rigor of scientific investigation and the whimsy of the cosmic unknown.




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 Google searches for 'report UFO sighting' and US birth rates of triplets or more. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More

[[ABSTRACT]]
This paper investigates the curious relationship between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Using data from Google Trends and the Centers for Disease Control and Prevention (CDC) for the years 2004 to 2021, we found a remarkably high correlation coefficient of 0.9066327 and a p-value of less than 0.01, suggesting a strong statistical significance. Our analysis, while cautious to assert causation, hints at the existence of a mysterious force linking an increase in searches for unidentified flying objects with the delivery of multiples. The implications of these findings are undoubtedly out of this world, and further investigation is warranted to unravel this enigmatic connection.

[[INTRDUCTION]]
The intersection of ufology and obstetrics might seem at first glance to be a cosmic leap, but as we delve into the peculiar world of statistical anomalies, the unexpected coalescence of Google searches for 'Report UFO Sighting' and the occurrence of triplet or higher-order multiple births in the United States presents an intriguing mystery. While the existence of UFOs and extraterrestrial visitors remains a subject of fervent debate, we are compelled to consider whether their presence - real or perceived - could be influencing earthly matters as remarkable as birth rates of triplets or more.
The topic at hand has long been relegated to the fringes of statistical inquiry, perhaps due to the unconventional nature of the subject matter. However, it is precisely this unpredictability and uncharted territory that makes the link between UFO search activity and the prevalence of rare multiple births such an irresistible enigma to unravel. With that in mind, the purpose of this study is to explore and statistically analyze any empirical relationship between these two seemingly disparate phenomena, and to discern whether there truly exists a correlation that defies earthly explanation.

[[RESULTS]]
The results of our analysis reveal a strikingly high correlation between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Over the period of 2004 to 2021, we found a correlation coefficient (r) of 0.9066327, indicating a strong positive linear relationship between these two variables. The r-squared value of 0.8219829 further emphasizes the robustness of this association, explaining approximately 82.20% of the variance in the birth rates of triplets or more.
Furthermore, the p-value of less than 0.01 provides compelling evidence of the statistical significance of this correlation, suggesting that it is highly unlikely to have occurred by chance. Our findings point to a clear and substantial relationship between the intensity of public interest in unidentified flying objects, as evidenced by Google search frequency, and the occurrence of rare multiple births in the United States.
Fig. 1 depicts the scatterplot illustrating the strong positive correlation between the frequency of Google searches for 'Report UFO Sighting' and the US birth rates of triplets or more.
These results underscore the need for a deeper and more comprehensive investigation into the potential underlying mechanisms driving this unexpected connection. The implications of this correlation are certainly otherworldly, and while we tread cautiously in avoiding claims of causation, our analysis suggests that a mysterious force may be at play. This discovery raises more questions than answers, and such a peculiar relationship between these seemingly unrelated phenomena demands further elucidation.
It is worth highlighting that our study is not without limitations. While our data analysis has identified a compelling statistical association, it remains essential to consider the possibility of other influencing factors that were not directly examined in this investigation. Nevertheless, the substantial correlation between Google searches for 'Report UFO Sighting' and US birth rates of triplets or more opens a window into an uncharted realm of inquiry, transcending the boundaries of conventional statistical analysis. Further research is imperative to unravel the enigmatic connection between ufology and obstetrics, shedding light on the mysterious forces at play amidst the cosmic dance of statistical anomalies.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the peculiar correlation between Google searches for 'Report UFO Sighting' and US birth rates of triplets or more has revealed a statistically significant and unanticipated relationship. The robust correlation coefficient of 0.9066327 and a p-value of less than 0.01 provide compelling evidence of a link that transcends earthly explanation. While our analysis refrains from making definitive claims of causation, the existence of a mysterious force orchestrating the cosmic waltz between UFO fervor and rare multiple births cannot be dismissed.

Despite the temptation to attribute this connection to extraterrestrial meddling, it is imperative to approach our findings with a healthy dose of skepticism. Observing the correlation does not equate to unraveling the causative mechanism, and there may well be other confounding variables that elude our statistical grasp. However, the statistical anomalies we have uncovered raise more questions than plausible explanations, rendering this an intriguing area for future exploration.

The implications of our discoveries stretch beyond the confines of routine statistical inquiry, probing the boundaries of the extraordinary. The enigmatic connection between ufology and obstetrics bears the potential for fascinating revelations, although perhaps not extraterrestrial in nature.

In light of these findings, it is apparent that no more research is needed in this area. The mysteries of the cosmos and the statistical anomalies they produce are, indeed, inexhaustible.


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Extraterrestrial Phenomena Research


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More. Respond only with the name of a fictional organization.

ChatGPT:

Center for Unexplained Phenomena Research


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The X-Files: Investigating the Connection Between Google Searches for 'Report UFO Sighting' and US Birth Rates of Triplets or More with an abstract of This paper investigates the curious relationship between the frequency of Google searches for 'Report UFO Sighting' and the incidence of triplets or higher order multiple births in the United States. Using data from Google Trends and the Centers for Disease Control and Prevention (CDC) for the years 2004 to 2021, we found a remarkably high correlation coefficient of 0.9066327 and a p-value of less than 0.01, suggesting a strong statistical significance. Our analysis, while cautious to assert causation, hints at the existence of a mysterious force linking an increase in searches for unidentified flying objects with the delivery of multiples. The implications of these findings are undoubtedly out of this world, and further investigation is warranted to unravel this enigmatic connection.

ChatGPT:

"Google Trends, 'Report UFO Sighting', US birth rates, Triplets, Higher order multiple births, Correlation coefficient, Statistical significance, Centers for Disease Control and Prevention, CDC data, Unidentified flying objects, Causation, Mysterious force, Multiple births, Enigmatic connection"

*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

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

See what else correlates with Google searches for 'report UFO sighting'

US birth rates of triplets or more
Source: CDC
See what else correlates with US birth rates of triplets or more

Correlation r = 0.9066327 (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 = 0.8219829 (Coefficient of determination)
This means 82.2% of the change in the one variable (i.e., US birth rates of triplets or more) is predictable based on the change in the other (i.e., Google searches for 'report UFO sighting') over the 18 years from 2004 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.2E-7. 0.0000002159071892899531400000
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 0.91 in 2.2E-5% of random cases. Said differently, if you correlated 4,631,620 random variables You don't actually need 4 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 17 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 17 because we have two variables measured over a period of 18 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.

[ 0.76, 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.
200420052006200720082009201020112012201320142015201620172018201920202021
Google searches for 'report UFO sighting' (Rel. search volume)18.666712.416713.259.833339.1666710.416711.83338.166676.55.416673.916675.333333.52.833333.583334.4166744.5
US birth rates of triplets or more (Birth rate per 100,000)180170156151148152138137124.4119.5113.5103.6101.4101.69387.779.680




Why this works

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




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([18.6667,12.4167,13.25,9.83333,9.16667,10.4167,11.8333,8.16667,6.5,5.41667,3.91667,5.33333,3.5,2.83333,3.58333,4.41667,4,4.5,])
array_2 = np.array([180,170,156,151,148,152,138,137,124.4,119.5,113.5,103.6,101.4,101.6,93,87.7,79.6,80,])
array_1_name = "Google searches for 'report UFO sighting'"
array_2_name = "US birth rates of triplets or more"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!


Correlation ID: 2318 · Black Variable ID: 1392 · Red Variable ID: 55
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0