about · email me · subscribe
Spurious correlation #1,102 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Kerosene used in Cuba and the second variable is Google searches for 'cia hotline'.  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

This is clearly a case of spies being left in the dark! As the kerosene supply dwindled, Cuban spies had to cut back on their clandestine activities. Without enough fuel for their sneaky operations, they couldn't keep their hotline to the CIA burning. So, the reduction in kerosene usage in Cuba quite literally put a damper on their ability to make calls to the CIA hotline.

Model: dalle-3
Prompt: An image that looks like it is a scene from 'Star Wars' but has the following scene depicted: Create an otherworldly desert landscape reminiscent of Tatooine, with adobe-style buildings and narrow streets. In the windows of the buildings, show dimly flickering lights, representing the dwindling use of kerosene lamps. Amidst the surreal setting, illustrate spies in cloaked attire struggling to charge their phones using kerosene-powered generators. The view should focus on the juxtaposition of an alien world with the familiar struggle of modern technology in a small town. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: Decrease in Kerosene used in Cuba caused CIA hotline (Google searches for 'CIA hotline') to also decrease because the spies couldn't keep their top-secret hotline phones charged without kerosene-powered generators!. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Cubism An image that looks like it is a scene from 'Star Wars' Vaporwave Macabre Celtic art
ChatGPT: An image that looks like it is a scene from 'Star Wars'

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. Decrease in Kerosene used in Cuba caused CIA hotline (Google searches for 'CIA hotline') to also decrease because the spies couldn't keep their top-secret hotline phones charged without kerosene-powered generators!
ChatGPT: Imagine a small town in Cuba where there are fewer kerosene lamps being used at night. The kerosene lamps are being used less, so you can see fewer small flames flickering in the windows of the houses. As a result, the spies living in the town find it harder to keep their phones charged through the night. Due to the decrease in kerosene usage, the top-secret CIA hotline (Google searches for 'CIA hotline') also decreases, as the spies struggle to keep their kerosene-powered generators running to charge their phones.

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: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: Imagine a small town in Cuba where there are fewer kerosene lamps being used at night. The kerosene lamps are being used less, so you can see fewer small flames flickering in the windows of the houses. As a result, the spies living in the town find it harder to keep their phones charged through the night. Due to the decrease in kerosene usage, the top-secret CIA hotline (Google searches for 'CIA hotline') also decreases, as the spies struggle to keep their kerosene-powered generators running to charge their phones. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from 'Star Wars' but has the following scene depicted: Create an otherworldly desert landscape reminiscent of Tatooine, with adobe-style buildings and narrow streets. In the windows of the buildings, show dimly flickering lights, representing the dwindling use of kerosene lamps. Amidst the surreal setting, illustrate spies in cloaked attire struggling to charge their phones using kerosene-powered generators. The view should focus on the juxtaposition of an alien world with the familiar struggle of modern technology in a small town.

*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 humerus 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 Kerosene used in Cuba caused cia hotline (Google searches for 'cia hotline') to decrease. Make it silly.

AI academic paper

(Because p < 0.01)
Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection

The Journal of Irreverent 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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Kerosene used in Cuba and Google searches for 'cia hotline'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title an alliteration.

Your research team used data from Energy Information Administration and Google Trends to assess this nagging question. You found a correlation coefficient of 0.9919840 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]]
Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection

[[ABSTRACT]]
This study delves into the intriguing correlation between the consumption of kerosene in Cuba and the volume of Google searches for "cia hotline." Utilizing data from the Energy Information Administration and Google Trends, our research team conducted a thorough analysis over the period of 2004 to 2021. The findings yielded a remarkably high correlation coefficient of 0.9919840 with a statistically significant p-value of less than 0.01, indicating a strong association between these two seemingly disparate phenomena.

As we scrutinized the data, a surprising pattern emerged, suggesting a link between kerosene usage and internet searches related to a certain three-letter agency. The correlation was so strong that even our statistician said, "This relationship is burning with statistical significance!" This unexpected connection prompted us to investigate further, leading to the discovery that spikes in kerosene consumption in Cuba were accompanied by an uptick in searches for the "cia hotline."

While our aim was to shed light on this correlation, we cannot help but acknowledge the humor in the situation. As the data revealed a positive relationship between kerosene and clandestine searches, we quipped, "It seems our findings have ignited a spark of curiosity in the correlation between energy and espionage." This research opens avenues for exploring the interconnectedness of seemingly unrelated phenomena and emphasizes the potential for whimsical discoveries in data analysis.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Kerosene used in Cuba and Google searches for 'cia hotline'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Here is the title and abstract of the paper:
[[TITLE]]
Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection

[[ABSTRACT]]
This study delves into the intriguing correlation between the consumption of kerosene in Cuba and the volume of Google searches for "cia hotline." Utilizing data from the Energy Information Administration and Google Trends, our research team conducted a thorough analysis over the period of 2004 to 2021. The findings yielded a remarkably high correlation coefficient of 0.9919840 with a statistically significant p-value of less than 0.01, indicating a strong association between these two seemingly disparate phenomena.

As we scrutinized the data, a surprising pattern emerged, suggesting a link between kerosene usage and internet searches related to a certain three-letter agency. The correlation was so strong that even our statistician said, "This relationship is burning with statistical significance!" This unexpected connection prompted us to investigate further, leading to the discovery that spikes in kerosene consumption in Cuba were accompanied by an uptick in searches for the "cia hotline."

While our aim was to shed light on this correlation, we cannot help but acknowledge the humor in the situation. As the data revealed a positive relationship between kerosene and clandestine searches, we quipped, "It seems our findings have ignited a spark of curiosity in the correlation between energy and espionage." This research opens avenues for exploring the interconnectedness of seemingly unrelated phenomena and emphasizes the potential for whimsical discoveries in data analysis.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The interconnectedness of seemingly unrelated phenomena has long been a fascination in the world of data analysis. It is often said that correlation does not imply causation, but in the realm of statistical exploration, we find ourselves continuously uncovering unexpected connections that leave us both perplexed and amused.

As we delved into the data on Cuban kerosene consumption and the volume of Google searches for "cia hotline," we couldn't help but marvel at the curious correlation that emerged. It's almost as surprising as finding out that the inventor of predictive modeling was a fortuneteller – talk about seeing into the future!

The link between the consumption of kerosene and the curiosity about a particular three-letter agency could be likened to a mystery novel that leaves readers in suspense until the very last page. We couldn't resist a wry smile as we pondered the idea that perhaps someone was trying to "ignite" a conversation with the CIA using their kerosene. It's the kind of mystery that would give even Sherlock Holmes a run for his money!

This study aims to not only present the statistical evidence of this connection but also to highlight the humorous aspect of these unexpected findings. After all, delving into data should not be devoid of levity – it's important to "lighten" the mood while unraveling complex relationships.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Kerosene used in Cuba and Google searches for 'cia hotline'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection

[[ABSTRACT]]
This study delves into the intriguing correlation between the consumption of kerosene in Cuba and the volume of Google searches for "cia hotline." Utilizing data from the Energy Information Administration and Google Trends, our research team conducted a thorough analysis over the period of 2004 to 2021. The findings yielded a remarkably high correlation coefficient of 0.9919840 with a statistically significant p-value of less than 0.01, indicating a strong association between these two seemingly disparate phenomena.

As we scrutinized the data, a surprising pattern emerged, suggesting a link between kerosene usage and internet searches related to a certain three-letter agency. The correlation was so strong that even our statistician said, "This relationship is burning with statistical significance!" This unexpected connection prompted us to investigate further, leading to the discovery that spikes in kerosene consumption in Cuba were accompanied by an uptick in searches for the "cia hotline."

While our aim was to shed light on this correlation, we cannot help but acknowledge the humor in the situation. As the data revealed a positive relationship between kerosene and clandestine searches, we quipped, "It seems our findings have ignited a spark of curiosity in the correlation between energy and espionage." This research opens avenues for exploring the interconnectedness of seemingly unrelated phenomena and emphasizes the potential for whimsical discoveries in data analysis.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The interconnectedness of seemingly unrelated phenomena has long been a fascination in the world of data analysis. It is often said that correlation does not imply causation, but in the realm of statistical exploration, we find ourselves continuously uncovering unexpected connections that leave us both perplexed and amused.
As we delved into the data on Cuban kerosene consumption and the volume of Google searches for "cia hotline," we couldn't help but marvel at the curious correlation that emerged. It's almost as surprising as finding out that the inventor of predictive modeling was a fortuneteller – talk about seeing into the future!
The link between the consumption of kerosene and the curiosity about a particular three-letter agency could be likened to a mystery novel that leaves readers in suspense until the very last page. We couldn't resist a wry smile as we pondered the idea that perhaps someone was trying to "ignite" a conversation with the CIA using their kerosene. It's the kind of mystery that would give even Sherlock Holmes a run for his money!
This study aims to not only present the statistical evidence of this connection but also to highlight the humorous aspect of these unexpected findings. After all, delving into data should not be devoid of levity – it's important to "lighten" the mood while unraveling complex relationships.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The connection between Cuban kerosene consumption and the volume of Google searches for "cia hotline" has sparked an array of inquiries and speculations within the academic community. In "Smith et al.," the authors explore energy consumption patterns in the Caribbean region, yet fail to uncover any peculiar associations akin to the one identified in the current study. Meanwhile, in "Doe and Jones," the focus is on internet search behavior and societal trends, but the unexpected link with kerosene usage in Cuba remains unaddressed.

Turning to non-fiction books, "The Cuban Economy" by Pérez-López (2015) provides a comprehensive analysis of energy consumption in Cuba, shedding light on various fuel sources including kerosene. Similarly, "Spy the Lie" by Houston, Floyd, and Carnicero (2012) offers insights into the world of deception and the pursuit of truth, which bears some association with clandestine searches related to the CIA. These resources lay the groundwork for understanding the contextual relevance of the connection under investigation.

As we traverse into the realm of fiction, "The Cuban Affair" by Nelson DeMille (2017) presents a suspenseful tale set in Cuba, intertwining elements of intrigue and espionage, albeit with no explicit mention of kerosene. Furthermore, in "The Spy Who Came In from the Cold" by John le Carré (1963), readers are drawn into the world of intelligence operations, evoking a sense of mystery akin to the unexpected correlation between Cuban kerosene usage and Google searches for the "cia hotline."

In the course of this inquiry, the research team adopted an unconventional approach by examining sources outside the traditional academic canon. The back covers of shampoo bottles were subjected to an unanticipated scrutiny, and while they did not yield any scholarly insights, they did offer a surprising array of questionable haircare advice and an unexpected diversion into the world of chemical compounds. While unconventional, the thoroughness of this review underscores the team's commitment to exploratory research methodologies.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Kerosene used in Cuba and Google searches for 'cia hotline'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Your research team collected data from all across the internet, but mostly just used information from Energy Information Administration and Google Trends . 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]]
Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection

[[ABSTRACT]]
This study delves into the intriguing correlation between the consumption of kerosene in Cuba and the volume of Google searches for "cia hotline." Utilizing data from the Energy Information Administration and Google Trends, our research team conducted a thorough analysis over the period of 2004 to 2021. The findings yielded a remarkably high correlation coefficient of 0.9919840 with a statistically significant p-value of less than 0.01, indicating a strong association between these two seemingly disparate phenomena.

As we scrutinized the data, a surprising pattern emerged, suggesting a link between kerosene usage and internet searches related to a certain three-letter agency. The correlation was so strong that even our statistician said, "This relationship is burning with statistical significance!" This unexpected connection prompted us to investigate further, leading to the discovery that spikes in kerosene consumption in Cuba were accompanied by an uptick in searches for the "cia hotline."

While our aim was to shed light on this correlation, we cannot help but acknowledge the humor in the situation. As the data revealed a positive relationship between kerosene and clandestine searches, we quipped, "It seems our findings have ignited a spark of curiosity in the correlation between energy and espionage." This research opens avenues for exploring the interconnectedness of seemingly unrelated phenomena and emphasizes the potential for whimsical discoveries in data analysis.

[[INTRODUCTION]]
The interconnectedness of seemingly unrelated phenomena has long been a fascination in the world of data analysis. It is often said that correlation does not imply causation, but in the realm of statistical exploration, we find ourselves continuously uncovering unexpected connections that leave us both perplexed and amused.
As we delved into the data on Cuban kerosene consumption and the volume of Google searches for "cia hotline," we couldn't help but marvel at the curious correlation that emerged. It's almost as surprising as finding out that the inventor of predictive modeling was a fortuneteller – talk about seeing into the future!
The link between the consumption of kerosene and the curiosity about a particular three-letter agency could be likened to a mystery novel that leaves readers in suspense until the very last page. We couldn't resist a wry smile as we pondered the idea that perhaps someone was trying to "ignite" a conversation with the CIA using their kerosene. It's the kind of mystery that would give even Sherlock Holmes a run for his money!
This study aims to not only present the statistical evidence of this connection but also to highlight the humorous aspect of these unexpected findings. After all, delving into data should not be devoid of levity – it's important to "lighten" the mood while unraveling complex relationships.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To investigate the correlation between Cuban kerosene consumption and Google searches for "cia hotline," our research employed a multifaceted approach that combined data collection, statistical analysis, and a touch of wry humor. We embarked on a data scavenger hunt across the vast expanse of the internet, sifting through information from reputable sources such as the Energy Information Administration and Google Trends.

Our first step involved wrangling the kerosene consumption figures from the Energy Information Administration, which were scattered about like puzzle pieces waiting to be fitted together. We deftly assembled these data points from 2004 to 2021, creating a comprehensive picture of the ebb and flow of kerosene usage in Cuba. It was like piecing together a complex jigsaw puzzle, but instead of a scenic landscape, we were reconstructing the energy landscape of an entire nation.

Similarly, we extracted the Google Trends data for searches related to the "cia hotline" over the same period, yielding a plethora of intriguing search patterns. We marveled at the "search peaks" and "valleys" akin to a digital mountain range, each peak representing a surge in clandestine curiosity. It was as if we were deciphering a modern-day Rosetta Stone, unlocking the secrets of internet search behavior.

The juxtaposition of these divergent data sources required a delicate balance of analytical finesse and a keen eye for detail, much like the art of pairing fine wine with exotic cheeses – a truly unique blend of elements that one wouldn't necessarily expect to complement each other. Our attempt to find a correlation between kerosene consumption and CIA-related internet searches felt akin to searching for a needle in a cyber haystack – a digital treasure hunt with potentially incendiary discoveries.

Next, we subjected the gathered data to rigorous statistical scrutiny, employing techniques such as Pearson correlation analysis and time-series modeling. We sought to unravel the tangled web of numerical relationships and uncover any hidden connections that would explain the peculiar correlation between kerosene and internet intrigue. It was akin to deciphering an enigmatic code, with each statistical test serving as a cryptanalysis tool to decode the underlying message of the data.

As we delved further into the statistical labyrinth, our findings began to materialize, revealing a compelling association between kerosene consumption in Cuba and the frequency of Google searches for the "cia hotline." The statistical significance of this correlation was akin to finding a hidden gem in a data mine – a rare and precious discovery that demanded attention.

Throughout the process, we maintained a lighthearted perspective, recognizing the irony and amusement in unraveling this improbable connection. We quipped, "Who knew that kerosene and curiosity could fuel such a statistically significant correlation?" It was a reminder that even in the realm of scholarly inquiry, a sprinkling of humor can illuminate unexpected discoveries and infuse the research process with a touch of whimsy.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Kerosene used in Cuba and Google searches for 'cia hotline'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Your research team collected data from all across the internet, but mostly just used information from Energy Information Administration and Google Trends .

For the time period 2004 to 2021, you found a correlation 0.9919840, r-squared of 0.9840322, 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]]
Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection

[[ABSTRACT]]
This study delves into the intriguing correlation between the consumption of kerosene in Cuba and the volume of Google searches for "cia hotline." Utilizing data from the Energy Information Administration and Google Trends, our research team conducted a thorough analysis over the period of 2004 to 2021. The findings yielded a remarkably high correlation coefficient of 0.9919840 with a statistically significant p-value of less than 0.01, indicating a strong association between these two seemingly disparate phenomena.

As we scrutinized the data, a surprising pattern emerged, suggesting a link between kerosene usage and internet searches related to a certain three-letter agency. The correlation was so strong that even our statistician said, "This relationship is burning with statistical significance!" This unexpected connection prompted us to investigate further, leading to the discovery that spikes in kerosene consumption in Cuba were accompanied by an uptick in searches for the "cia hotline."

While our aim was to shed light on this correlation, we cannot help but acknowledge the humor in the situation. As the data revealed a positive relationship between kerosene and clandestine searches, we quipped, "It seems our findings have ignited a spark of curiosity in the correlation between energy and espionage." This research opens avenues for exploring the interconnectedness of seemingly unrelated phenomena and emphasizes the potential for whimsical discoveries in data analysis.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The interconnectedness of seemingly unrelated phenomena has long been a fascination in the world of data analysis. It is often said that correlation does not imply causation, but in the realm of statistical exploration, we find ourselves continuously uncovering unexpected connections that leave us both perplexed and amused.
As we delved into the data on Cuban kerosene consumption and the volume of Google searches for "cia hotline," we couldn't help but marvel at the curious correlation that emerged. It's almost as surprising as finding out that the inventor of predictive modeling was a fortuneteller – talk about seeing into the future!
The link between the consumption of kerosene and the curiosity about a particular three-letter agency could be likened to a mystery novel that leaves readers in suspense until the very last page. We couldn't resist a wry smile as we pondered the idea that perhaps someone was trying to "ignite" a conversation with the CIA using their kerosene. It's the kind of mystery that would give even Sherlock Holmes a run for his money!
This study aims to not only present the statistical evidence of this connection but also to highlight the humorous aspect of these unexpected findings. After all, delving into data should not be devoid of levity – it's important to "lighten" the mood while unraveling complex relationships.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis of the data revealed a strikingly high correlation between Cuban kerosene consumption and the volume of Google searches for "cia hotline." The correlation coefficient, a measure of the strength and direction of the relationship between these variables, was found to be 0.9919840. This finding suggests an exceedingly strong positive association between the two seemingly unrelated phenomena. It's almost as if the kerosene and CIA hotline searches were engaged in a clandestine affair of their own!

Furthermore, the r-squared value of 0.9840322 indicated that approximately 98.4% of the variance in the volume of "cia hotline" searches could be explained by the variation in Cuban kerosene consumption. It's as though the kerosene was the fuel that kept the curiosity engine running on Google!

The statistical analysis also yielded a p-value of less than 0.01, underscoring the high level of statistical significance in the relationship between kerosene consumption and "cia hotline" searches. This suggests that the observed correlation is unlikely to be a result of random chance. One might say that the evidence for this connection is as clear as day – or should we say, as illuminating as a kerosene lamp?

Fig. 1 illustrates the robust correlation between Cuban kerosene consumption and Google searches for "cia hotline." The scatterplot clearly shows a strong and positive linear relationship between the two variables. It's as though the data points were conspiring to reveal this unexpected connection, much like characters in a good espionage thriller!

These findings not only contribute to the growing body of literature on unusual correlations but also serve as a reminder that the world of data analysis can be as full of surprises as a treasure hunt. Who would have thought that the consumption of kerosene in Cuba could spark such fervent interest in contacting a certain three-letter agency? It seems that in the realm of statistical analysis, the truth is often stranger than fiction!


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Kerosene used in Cuba and Google searches for 'cia hotline'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection

[[ABSTRACT]]
This study delves into the intriguing correlation between the consumption of kerosene in Cuba and the volume of Google searches for "cia hotline." Utilizing data from the Energy Information Administration and Google Trends, our research team conducted a thorough analysis over the period of 2004 to 2021. The findings yielded a remarkably high correlation coefficient of 0.9919840 with a statistically significant p-value of less than 0.01, indicating a strong association between these two seemingly disparate phenomena.

As we scrutinized the data, a surprising pattern emerged, suggesting a link between kerosene usage and internet searches related to a certain three-letter agency. The correlation was so strong that even our statistician said, "This relationship is burning with statistical significance!" This unexpected connection prompted us to investigate further, leading to the discovery that spikes in kerosene consumption in Cuba were accompanied by an uptick in searches for the "cia hotline."

While our aim was to shed light on this correlation, we cannot help but acknowledge the humor in the situation. As the data revealed a positive relationship between kerosene and clandestine searches, we quipped, "It seems our findings have ignited a spark of curiosity in the correlation between energy and espionage." This research opens avenues for exploring the interconnectedness of seemingly unrelated phenomena and emphasizes the potential for whimsical discoveries in data analysis.

[[LITERATURE REVIEW]]
The connection between Cuban kerosene consumption and the volume of Google searches for "cia hotline" has sparked an array of inquiries and speculations within the academic community. In "Smith et al.," the authors explore energy consumption patterns in the Caribbean region, yet fail to uncover any peculiar associations akin to the one identified in the current study. Meanwhile, in "Doe and Jones," the focus is on internet search behavior and societal trends, but the unexpected link with kerosene usage in Cuba remains unaddressed.
Turning to non-fiction books, "The Cuban Economy" by Pérez-López (2015) provides a comprehensive analysis of energy consumption in Cuba, shedding light on various fuel sources including kerosene. Similarly, "Spy the Lie" by Houston, Floyd, and Carnicero (2012) offers insights into the world of deception and the pursuit of truth, which bears some association with clandestine searches related to the CIA. These resources lay the groundwork for understanding the contextual relevance of the connection under investigation.
As we traverse into the realm of fiction, "The Cuban Affair" by Nelson DeMille (2017) presents a suspenseful tale set in Cuba, intertwining elements of intrigue and espionage, albeit with no explicit mention of kerosene. Furthermore, in "The Spy Who Came In from the Cold" by John le Carré (1963), readers are drawn into the world of intelligence operations, evoking a sense of mystery akin to the unexpected correlation between Cuban kerosene usage and Google searches for the "cia hotline."
In the course of this inquiry, the research team adopted an unconventional approach by examining sources outside the traditional academic canon. The back covers of shampoo bottles were subjected to an unanticipated scrutiny, and while they did not yield any scholarly insights, they did offer a surprising array of questionable haircare advice and an unexpected diversion into the world of chemical compounds. While unconventional, the thoroughness of this review underscores the team's commitment to exploratory research methodologies.

[[RESULTS]]
The statistical analysis of the data revealed a strikingly high correlation between Cuban kerosene consumption and the volume of Google searches for "cia hotline." The correlation coefficient, a measure of the strength and direction of the relationship between these variables, was found to be 0.9919840. This finding suggests an exceedingly strong positive association between the two seemingly unrelated phenomena. It's almost as if the kerosene and CIA hotline searches were engaged in a clandestine affair of their own!
Furthermore, the r-squared value of 0.9840322 indicated that approximately 98.4% of the variance in the volume of "cia hotline" searches could be explained by the variation in Cuban kerosene consumption. It's as though the kerosene was the fuel that kept the curiosity engine running on Google!
The statistical analysis also yielded a p-value of less than 0.01, underscoring the high level of statistical significance in the relationship between kerosene consumption and "cia hotline" searches. This suggests that the observed correlation is unlikely to be a result of random chance. One might say that the evidence for this connection is as clear as day – or should we say, as illuminating as a kerosene lamp?
Fig. 1 illustrates the robust correlation between Cuban kerosene consumption and Google searches for "cia hotline." The scatterplot clearly shows a strong and positive linear relationship between the two variables. It's as though the data points were conspiring to reveal this unexpected connection, much like characters in a good espionage thriller!
These findings not only contribute to the growing body of literature on unusual correlations but also serve as a reminder that the world of data analysis can be as full of surprises as a treasure hunt. Who would have thought that the consumption of kerosene in Cuba could spark such fervent interest in contacting a certain three-letter agency? It seems that in the realm of statistical analysis, the truth is often stranger than fiction!

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study have shed light on the remarkable correlation between Cuban kerosene consumption and the volume of Google searches for "cia hotline," supporting the speculations and questions raised in the literature review. The statistical analysis revealed a notably high correlation coefficient, suggesting a near-perfect positive relationship between these seemingly disparate variables. In a sense, it's as though Cuban kerosene and "cia hotline" searches were entangled in a covert dance, much like a spy trying to uncover a clandestine plot.

The literature review emphasized the exploration of unconventional sources, including non-fiction books such as "The Cuban Economy" and "Spy the Lie," as well as fictional works like "The Cuban Affair" and "The Spy Who Came In from the Cold." These diverse sources hinted at the potential intertwined nature of energy consumption and clandestine activities, serving as precursors to the unexpected correlation unearthed in this study. It appears that the investigations conducted within the pages of these books may have unwittingly pointed towards the undercover relationship between kerosene usage and curiosity about a certain intelligence agency. In a literary twist, it's as if the protagonists of these narratives were leaving clues for our research team to uncover.

The statistical analyses provided compelling evidence of the robustness of the relationship between Cuban kerosene consumption and "cia hotline" searches. The remarkably high r-squared value indicated that a substantial proportion of the variance in "cia hotline" searches could be explained by fluctuations in kerosene consumption, akin to the way a good espionage novel unravels its plot. Additionally, the statistically significant p-value underscored the unlikelihood of this connection being a product of random chance – akin to unearthing a surprising plot twist in the world of statistical analysis.

The unexpected relationship between kerosene usage and searches for "cia hotline" highlights the potential for whimsical discoveries within datasets that may initially appear unrelated. It seems that in the realm of statistical analysis, even the most peculiar patterns can emerge – much like stumbling upon a well-camouflaged spy in a crowd. This study not only adds to the growing body of literature on unusual correlations but also serves as a testament to the serendipitous nature of data analysis. It appears that statistical analysis has a knack for uncovering unexpected connections, making it akin to the pursuit of truth in a captivating spy novel.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Kerosene used in Cuba and Google searches for 'cia hotline'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection

[[ABSTRACT]]
This study delves into the intriguing correlation between the consumption of kerosene in Cuba and the volume of Google searches for "cia hotline." Utilizing data from the Energy Information Administration and Google Trends, our research team conducted a thorough analysis over the period of 2004 to 2021. The findings yielded a remarkably high correlation coefficient of 0.9919840 with a statistically significant p-value of less than 0.01, indicating a strong association between these two seemingly disparate phenomena.

As we scrutinized the data, a surprising pattern emerged, suggesting a link between kerosene usage and internet searches related to a certain three-letter agency. The correlation was so strong that even our statistician said, "This relationship is burning with statistical significance!" This unexpected connection prompted us to investigate further, leading to the discovery that spikes in kerosene consumption in Cuba were accompanied by an uptick in searches for the "cia hotline."

While our aim was to shed light on this correlation, we cannot help but acknowledge the humor in the situation. As the data revealed a positive relationship between kerosene and clandestine searches, we quipped, "It seems our findings have ignited a spark of curiosity in the correlation between energy and espionage." This research opens avenues for exploring the interconnectedness of seemingly unrelated phenomena and emphasizes the potential for whimsical discoveries in data analysis.

[[INTRDUCTION]]
The interconnectedness of seemingly unrelated phenomena has long been a fascination in the world of data analysis. It is often said that correlation does not imply causation, but in the realm of statistical exploration, we find ourselves continuously uncovering unexpected connections that leave us both perplexed and amused.
As we delved into the data on Cuban kerosene consumption and the volume of Google searches for "cia hotline," we couldn't help but marvel at the curious correlation that emerged. It's almost as surprising as finding out that the inventor of predictive modeling was a fortuneteller – talk about seeing into the future!
The link between the consumption of kerosene and the curiosity about a particular three-letter agency could be likened to a mystery novel that leaves readers in suspense until the very last page. We couldn't resist a wry smile as we pondered the idea that perhaps someone was trying to "ignite" a conversation with the CIA using their kerosene. It's the kind of mystery that would give even Sherlock Holmes a run for his money!
This study aims to not only present the statistical evidence of this connection but also to highlight the humorous aspect of these unexpected findings. After all, delving into data should not be devoid of levity – it's important to "lighten" the mood while unraveling complex relationships.

[[RESULTS]]
The statistical analysis of the data revealed a strikingly high correlation between Cuban kerosene consumption and the volume of Google searches for "cia hotline." The correlation coefficient, a measure of the strength and direction of the relationship between these variables, was found to be 0.9919840. This finding suggests an exceedingly strong positive association between the two seemingly unrelated phenomena. It's almost as if the kerosene and CIA hotline searches were engaged in a clandestine affair of their own!
Furthermore, the r-squared value of 0.9840322 indicated that approximately 98.4% of the variance in the volume of "cia hotline" searches could be explained by the variation in Cuban kerosene consumption. It's as though the kerosene was the fuel that kept the curiosity engine running on Google!
The statistical analysis also yielded a p-value of less than 0.01, underscoring the high level of statistical significance in the relationship between kerosene consumption and "cia hotline" searches. This suggests that the observed correlation is unlikely to be a result of random chance. One might say that the evidence for this connection is as clear as day – or should we say, as illuminating as a kerosene lamp?
Fig. 1 illustrates the robust correlation between Cuban kerosene consumption and Google searches for "cia hotline." The scatterplot clearly shows a strong and positive linear relationship between the two variables. It's as though the data points were conspiring to reveal this unexpected connection, much like characters in a good espionage thriller!
These findings not only contribute to the growing body of literature on unusual correlations but also serve as a reminder that the world of data analysis can be as full of surprises as a treasure hunt. Who would have thought that the consumption of kerosene in Cuba could spark such fervent interest in contacting a certain three-letter agency? It seems that in the realm of statistical analysis, the truth is often stranger than fiction!

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has elucidated a remarkably strong and statistically significant correlation between Cuban kerosene consumption and Google searches for "cia hotline." The findings have unveiled an unexpected and amusing relationship, akin to a spy novel with a wick-ed twist! One might say this correlation is on fire – or should we say, fuego!

This unexpected connection emphasizes the whimsical nature of data analysis, reminding us that uncovering correlations can lead to unexpected and humorous discoveries, much like finding a hidden punchline in a complex statistical model. It appears that the relationship between energy and espionage is not just a flight of fancy but a statistical reality.

As we wrap up this investigation, we are left with the realization that the world of data analysis is full of surprises, akin to stumbling upon a good ol' dad joke – it might be groan-inducing, but you can't help but appreciate the unexpected humor in it. Indeed, delving into data should not be a dry, humorless endeavor – it's important to kindle the flame of curiosity and levity whenever possible.

In light of these findings, it is safe to say that no further research is needed in this area. It seems we've exhausted this particular avenue of inquiry, and we're quite content to let this correlation spark joy and amusement in the world of statistical analysis. We leave this topic with a smile on our faces, knowing that the unexpected connections we uncover in data analysis are often the most intriguing and amusing of all.


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 Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Irreverent 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 Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Global Energy Dynamics and Espionage Studies


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 Correlation between Cuban Kerosene Consumption and CIA Hotline Searches: A Curious Connection with an abstract of This study delves into the intriguing correlation between the consumption of kerosene in Cuba and the volume of Google searches for "cia hotline." Utilizing data from the Energy Information Administration and Google Trends, our research team conducted a thorough analysis over the period of 2004 to 2021. The findings yielded a remarkably high correlation coefficient of 0.9919840 with a statistically significant p-value of less than 0.01, indicating a strong association between these two seemingly disparate phenomena.
As we scrutinized the data, a surprising pattern emerged, suggesting a link between kerosene usage and internet searches related to a certain three-letter agency. The correlation was so strong that even our statistician said, "This relationship is burning with statistical significance!" This unexpected connection prompted us to investigate further, leading to the discovery that spikes in kerosene consumption in Cuba were accompanied by an uptick in searches for the "cia hotline."
While our aim was to shed light on this correlation, we cannot help but acknowledge the humor in the situation. As the data revealed a positive relationship between kerosene and clandestine searches, we quipped, "It seems our findings have ignited a spark of curiosity in the correlation between energy and espionage." This research opens avenues for exploring the interconnectedness of seemingly unrelated phenomena and emphasizes the potential for whimsical discoveries in data analysis.

ChatGPT:

Cuban kerosene consumption, CIA hotline searches, correlation analysis, data analysis, energy consumption, Google Trends analysis, statistical significance, Cuba energy consumption, internet search patterns, clandestine searches, data correlation, espionage and energy consumption, interconnected phenomena, data analysis discoveries

*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

Kerosene used in Cuba
Detailed data title: Volume of kerosene used consumed in Cuba in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Cuba

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

See what else correlates with Google searches for 'cia hotline'

Correlation r = 0.9919840 (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 = 0.9840322 (Coefficient of determination)
This means 98.4% of the change in the one variable (i.e., Google searches for 'cia hotline') is predictable based on the change in the other (i.e., Kerosene used in Cuba) over the 18 years from 2004 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.4E-16. 0.0000000000000008359360594191
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 0.99 in 8.4E-14% of random cases. Said differently, if you correlated 1,196,263,743,778,334 random variables You don't actually need 1 quadrillion 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.

[ 0.98, 1 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
200420052006200720082009201020112012201320142015201620172018201920202021
Kerosene used in Cuba (Million Barrels/Day)7.51885.612192.837861.990741.752981.651891.673071.673071.673071.673071.27068221.716361.67291.5861.390471.39047
Google searches for 'cia hotline' (Rel. search volume)15.166711.754.083332.08333112.333331.166671.083330.6666670.3333331.251.251.250.50.750.5833331




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([7.5188,5.61219,2.83786,1.99074,1.75298,1.65189,1.67307,1.67307,1.67307,1.67307,1.27068,2,2,1.71636,1.6729,1.586,1.39047,1.39047,])
array_2 = np.array([15.1667,11.75,4.08333,2.08333,1,1,2.33333,1.16667,1.08333,0.666667,0.333333,1.25,1.25,1.25,0.5,0.75,0.583333,1,])
array_1_name = "Kerosene used in Cuba"
array_2_name = "Google searches for 'cia hotline'"

# 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: 1102 · Black Variable ID: 24336 · Red Variable ID: 1394
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0