about · email me · subscribe
Spurious correlation #4,738 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is How good Vihart's YouTube video titles are and the second variable is Kerosene used in Tanzania.  The chart goes from 2009 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the availability of kerosene in Tanzania dwindles, Vihart, the mathematical wizard, realizes that her video titles need to shine even brighter to attract viewers. This prompts a wave of title innovation as Vihart ingeniously incorporates the principles of kerosene combustion into her video titles, creating a fiery resurgence of interest in mathematics. And that's how the diminishing kerosene in Tanzania leads to a exponential surge in the quality of Vihart's YouTube video titles. Math-magical, isn't it?

Model: dalle-3
Prompt: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s. Depict Vihart, the mathematical genius, sitting at her desk in the small Tanzanian village, surrounded by swirling mathematical formulas and vintage scientific instruments. Show the kerosene lamp casting a warm, flickering glow as Vihart, immersed in thought, draws inspiration from its flames. Meanwhile, families in the village are seen using their kerosene sparingly for crucial tasks, emphasizing the scarcity of this resource. Lastly, illustrate the internet as a web, with sparks of fiery mathematical symbols and equations spreading across it from Vihart's study, symbolizing the resurgence of interest in mathematics ignited by her creativity. 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: How good Vihart YouTube video titles are and Kerosene used in Tanzania. 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: An image that looks like it is a scene from A Disney Movie Cute cartoon Futuristic A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Low poly
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 How good Vihart YouTube video titles are and Kerosene used in Tanzania, in the following situation: As the availability of kerosene in Tanzania dwindles, Vihart, the mathematical wizard, realizes that her video titles need to shine even brighter to attract viewers. This prompts a wave of title innovation as Vihart ingeniously incorporates the principles of kerosene combustion into her video titles, creating a fiery resurgence of interest in mathematics. And that's how the diminishing kerosene in Tanzania leads to a exponential surge in the quality of Vihart's YouTube video titles. Math-magical, isn't it?. Keep the description simple.
ChatGPT: In a small Tanzanian village, the dwindling supply of kerosene has forced families to conserve their fuel for essential tasks. Meanwhile, in her enchanting study, Vihart, the mathematical genius, finds inspiration from the flickering flames of her kerosene lamp. As she crafts her YouTube video titles, the glow of knowledge ignites within her, leading to a burst of creativity as she weaves the principles of kerosene combustion into her captivating titles. The radiance of her math-magic, fueled by the scarcity of kerosene, begins to spread across the internet, drawing a fiery resurgence of interest in mathematics.

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 a small Tanzanian village, the dwindling supply of kerosene has forced families to conserve their fuel for essential tasks. Meanwhile, in her enchanting study, Vihart, the mathematical genius, finds inspiration from the flickering flames of her kerosene lamp. As she crafts her YouTube video titles, the glow of knowledge ignites within her, leading to a burst of creativity as she weaves the principles of kerosene combustion into her captivating titles. The radiance of her math-magic, fueled by the scarcity of kerosene, begins to spread across the internet, drawing a fiery resurgence of interest in mathematics. 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. Depict Vihart, the mathematical genius, sitting at her desk in the small Tanzanian village, surrounded by swirling mathematical formulas and vintage scientific instruments. Show the kerosene lamp casting a warm, flickering glow as Vihart, immersed in thought, draws inspiration from its flames. Meanwhile, families in the village are seen using their kerosene sparingly for crucial tasks, emphasizing the scarcity of this resource. Lastly, illustrate the internet as a web, with sparks of fiery mathematical symbols and equations spreading across it from Vihart's study, symbolizing the resurgence of interest in mathematics ignited by her creativity.

*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 How good Vihart YouTube video titles are caused Kerosene used in Tanzania to decrease.

AI academic paper

(Because p < 0.01)
From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania

The International Journal of Interdisciplinary Kerosene Studies

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 witty academic researcher. Your writing sounds like it belongs in a statistics 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 How good Vihart YouTube video titles are and Kerosene used in Tanzania. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

Your research team used data from AI analysis of YouTube video titles and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.6838366 and p < 0.01 for 2009 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]]
From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania

[[ABSTRACT]]
This paper investigates the peculiar link between the creativity of Vihart YouTube video titles and the consumption of kerosene in Tanzania. Employing a unique blend of econometric and linguistic analysis, we uncover the unexpected relationship between these seemingly disparate phenomena. Utilizing data from the Energy Information Administration and AI-driven text mining of Vihart YouTube channel titles, we establish a significant correlation coefficient of 0.6838366 (p < 0.01) during the period from 2009 to 2021.

Our findings reveal not only a statistically robust association between the linguistic prowess of Vihart's video titles and kerosene usage in Tanzania, but also provide an opportunity for a "lighter" approach to understanding energy trends in developing countries. However, the correlation does not imply causation, prompting us to acknowledge that while "Vihart" may "ignite" creativity, it may not necessarily extinguish the need for kerosene. Thus, we urge policymakers and researchers to consider the broader social and cultural factors at play, illuminating the need for a more nuanced understanding of energy consumption in the digital age. And remember, whether it's data or dad jokes, correlation does not imply causation, unless it's about in-laws and headaches!


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 How good Vihart YouTube video titles are and Kerosene used in Tanzania. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania

[[ABSTRACT]]
This paper investigates the peculiar link between the creativity of Vihart YouTube video titles and the consumption of kerosene in Tanzania. Employing a unique blend of econometric and linguistic analysis, we uncover the unexpected relationship between these seemingly disparate phenomena. Utilizing data from the Energy Information Administration and AI-driven text mining of Vihart YouTube channel titles, we establish a significant correlation coefficient of 0.6838366 (p < 0.01) during the period from 2009 to 2021.

Our findings reveal not only a statistically robust association between the linguistic prowess of Vihart's video titles and kerosene usage in Tanzania, but also provide an opportunity for a "lighter" approach to understanding energy trends in developing countries. However, the correlation does not imply causation, prompting us to acknowledge that while "Vihart" may "ignite" creativity, it may not necessarily extinguish the need for kerosene. Thus, we urge policymakers and researchers to consider the broader social and cultural factors at play, illuminating the need for a more nuanced understanding of energy consumption in the digital age. And remember, whether it's data or dad jokes, correlation does not imply causation, unless it's about in-laws and headaches!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In recent years, the intersection of linguistic analysis and energy consumption has presented a unique avenue for research. Straying from more conventional investigations, this study delves into the intriguing connection between the creativity of Vihart YouTube video titles and the utilization of kerosene in Tanzania. One might say we are embarking on a "novel" expedition, as we seek to illuminate a correlation that is both unexpected and, dare I say, illuminating.

The decision to explore such an unorthodox relationship stemmed from a desire to shed light on an unconventional aspect of energy consumption. The correlation might seem "far-fetched," but as we unpack the data, we aim to demonstrate the relevance of linguistic analysis in understanding societal behaviors. After all, in the world of statistics, a good pun is statistically significant, right?

The juxtaposition of Vihart's captivating video titles with the conventional use of kerosene for lighting in Tanzania may appear to be as incongruous as a "match" in the desert, but our preliminary analysis suggests otherwise. This study draws on a captivating blend of textual analysis and econometric modeling to unravel what could be described as a "bright" correlation, sure to "spark" the interest of both linguists and energy researchers alike.

Our investigation extends beyond the realms of statistical significance to unearth a relationship that holds potential implications for policy and societal change. Yet, as we endeavor to unravel this unconventional connection, we remain cognizant of the age-old adage that correlation does not imply causation, unless, of course, we are discussing the meticulous crafting of YouTube video titles and the illumination provided by kerosene. After all, one might say that "Vihart" may "light up" creativity, but it may not necessarily dim the demand for kerosene.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 How good Vihart YouTube video titles are and Kerosene used in Tanzania. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania

[[ABSTRACT]]
This paper investigates the peculiar link between the creativity of Vihart YouTube video titles and the consumption of kerosene in Tanzania. Employing a unique blend of econometric and linguistic analysis, we uncover the unexpected relationship between these seemingly disparate phenomena. Utilizing data from the Energy Information Administration and AI-driven text mining of Vihart YouTube channel titles, we establish a significant correlation coefficient of 0.6838366 (p < 0.01) during the period from 2009 to 2021.

Our findings reveal not only a statistically robust association between the linguistic prowess of Vihart's video titles and kerosene usage in Tanzania, but also provide an opportunity for a "lighter" approach to understanding energy trends in developing countries. However, the correlation does not imply causation, prompting us to acknowledge that while "Vihart" may "ignite" creativity, it may not necessarily extinguish the need for kerosene. Thus, we urge policymakers and researchers to consider the broader social and cultural factors at play, illuminating the need for a more nuanced understanding of energy consumption in the digital age. And remember, whether it's data or dad jokes, correlation does not imply causation, unless it's about in-laws and headaches!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In recent years, the intersection of linguistic analysis and energy consumption has presented a unique avenue for research. Straying from more conventional investigations, this study delves into the intriguing connection between the creativity of Vihart YouTube video titles and the utilization of kerosene in Tanzania. One might say we are embarking on a "novel" expedition, as we seek to illuminate a correlation that is both unexpected and, dare I say, illuminating.
The decision to explore such an unorthodox relationship stemmed from a desire to shed light on an unconventional aspect of energy consumption. The correlation might seem "far-fetched," but as we unpack the data, we aim to demonstrate the relevance of linguistic analysis in understanding societal behaviors. After all, in the world of statistics, a good pun is statistically significant, right?
The juxtaposition of Vihart's captivating video titles with the conventional use of kerosene for lighting in Tanzania may appear to be as incongruous as a "match" in the desert, but our preliminary analysis suggests otherwise. This study draws on a captivating blend of textual analysis and econometric modeling to unravel what could be described as a "bright" correlation, sure to "spark" the interest of both linguists and energy researchers alike.
Our investigation extends beyond the realms of statistical significance to unearth a relationship that holds potential implications for policy and societal change. Yet, as we endeavor to unravel this unconventional connection, we remain cognizant of the age-old adage that correlation does not imply causation, unless, of course, we are discussing the meticulous crafting of YouTube video titles and the illumination provided by kerosene. After all, one might say that "Vihart" may "light up" creativity, but it may not necessarily dim the demand for kerosene.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The conversation surrounding the interplay of linguistic expressions and energy consumption has historically been as dry as Vihart's wit. However, recent trends in interdisciplinary research have led scholars to brighten this area of study with a kerosene lamp's worth of new insights. Smith (2015) remarks that the correlation between creative language and energy trends is akin to "finding light in unexpected places," shedding a bright glow on our understanding of societal behaviors and linguistic influences. This correlates rather nicely with our own findings, doesn't it?

Speaking of illumination, it is impossible to ignore the work of Doe (2017), who postulates a potential link between the linguistic appeal of YouTube video titles and their impact on viewers' cognitive and emotive responses. It's quite a "bright idea" to consider the potential influence of language on human behavior, wouldn't you say? And speaking of bright ideas, did you hear about the Italian chef who died? He pasta way.

Jones (2019) uniquely explores the cultural dynamics of kerosene usage in developing countries and the potential impact of linguistic artifacts on energy consumption patterns. This study brings to light the importance of cultural context in understanding energy choices, not to mention the potential impact of a good dad joke on academic writing. After all, the pressure in academia can be intense. Speaking of dad jokes, did you hear about the kidnapping at the playground? They woke up, it's okay.

Turning to non-fiction literature that may inform our analysis, "Economics of Energy: A Holistic Perspective" by Chang (2018) provides an insightful framework for understanding the socio-economic dimensions of energy consumption. While we are more interested in illuminating the linguistic dimensions, integrating economic perspectives is essential to shedding light on the holistic understanding of energy trends. And speaking of holistic understanding, have you heard about the new restaurant on the moon? Great food, no atmosphere.

When considering fictional works that may tangentially relate to our investigation, "The Light Between Oceans" by M.L. Stedman comes to mind. Although the novel is set in a different context, the metaphor of light and its interplay with human experiences may offer some valuable insights into how language shapes societal behavior. And speaking of societal behavior, did you hear about the claustrophobic astronaut? He needed a little space.

In a delightful twist, "Kerosene Cowboys" by Randy Denmon stands out in the realm of fictional literature. While the title brings about images of burning rubber rather than kerosene, one might quip that the linguistic flair of the title matches our interest in intriguing linguistic expressions. And speaking of intriguing linguistic expressions, did you hear about the verb that became a noun? It was "verbing" its own issues.

Furthermore, the board game "Flash Point: Fire Rescue" may not only provide a lighthearted respite from our extensive analyses but also offers a tangential connection to the theme of fire and rescue, reflecting the importance of alternative energy sources and innovative solutions in addressing societal needs. And speaking of alternative energy sources, did you hear about the energized restaurant? The food was great; it had a lot of potential.

In summary, this brief yet elucidating literature review serves as the "match" igniting our inquiry into the unexpected correlation between Vihart's compelling YouTube video titles and kerosene usage in Tanzania. With each source contributing to our understanding in varying "degrees," we are poised to shed light on a correlation that is as illuminating as it is unexpected. And speaking of shedding light, why did the bicycle fall over? It was two-tired.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 How good Vihart YouTube video titles are and Kerosene used in Tanzania. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from AI analysis of YouTube video titles and Energy Information Administration . You used data from 2009 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]]
From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania

[[ABSTRACT]]
This paper investigates the peculiar link between the creativity of Vihart YouTube video titles and the consumption of kerosene in Tanzania. Employing a unique blend of econometric and linguistic analysis, we uncover the unexpected relationship between these seemingly disparate phenomena. Utilizing data from the Energy Information Administration and AI-driven text mining of Vihart YouTube channel titles, we establish a significant correlation coefficient of 0.6838366 (p < 0.01) during the period from 2009 to 2021.

Our findings reveal not only a statistically robust association between the linguistic prowess of Vihart's video titles and kerosene usage in Tanzania, but also provide an opportunity for a "lighter" approach to understanding energy trends in developing countries. However, the correlation does not imply causation, prompting us to acknowledge that while "Vihart" may "ignite" creativity, it may not necessarily extinguish the need for kerosene. Thus, we urge policymakers and researchers to consider the broader social and cultural factors at play, illuminating the need for a more nuanced understanding of energy consumption in the digital age. And remember, whether it's data or dad jokes, correlation does not imply causation, unless it's about in-laws and headaches!

[[INTRODUCTION]]
In recent years, the intersection of linguistic analysis and energy consumption has presented a unique avenue for research. Straying from more conventional investigations, this study delves into the intriguing connection between the creativity of Vihart YouTube video titles and the utilization of kerosene in Tanzania. One might say we are embarking on a "novel" expedition, as we seek to illuminate a correlation that is both unexpected and, dare I say, illuminating.
The decision to explore such an unorthodox relationship stemmed from a desire to shed light on an unconventional aspect of energy consumption. The correlation might seem "far-fetched," but as we unpack the data, we aim to demonstrate the relevance of linguistic analysis in understanding societal behaviors. After all, in the world of statistics, a good pun is statistically significant, right?
The juxtaposition of Vihart's captivating video titles with the conventional use of kerosene for lighting in Tanzania may appear to be as incongruous as a "match" in the desert, but our preliminary analysis suggests otherwise. This study draws on a captivating blend of textual analysis and econometric modeling to unravel what could be described as a "bright" correlation, sure to "spark" the interest of both linguists and energy researchers alike.
Our investigation extends beyond the realms of statistical significance to unearth a relationship that holds potential implications for policy and societal change. Yet, as we endeavor to unravel this unconventional connection, we remain cognizant of the age-old adage that correlation does not imply causation, unless, of course, we are discussing the meticulous crafting of YouTube video titles and the illumination provided by kerosene. After all, one might say that "Vihart" may "light up" creativity, but it may not necessarily dim the demand for kerosene.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To investigate the connection between the creativity of Vihart YouTube video titles and kerosene usage in Tanzania, we employed a multifaceted methodology that combined linguistic analysis with econometric modeling. Our approach drew on data spanning the years 2009 to 2021, sourced from the Energy Information Administration for kerosene consumption trends and employing AI-driven text mining for the linguistic analysis of Vihart YouTube channel titles. We chose this time frame as it allowed for a comprehensive examination of the relationship between these variables while capturing any potential shifts in usage patterns over the years.

The linguistic analysis of Vihart YouTube video titles involved a rigorous process of natural language processing and sentiment analysis. We used sophisticated algorithms to assess the lexical richness, emotional undertones, and semantic complexity of the video titles. This approach allowed us to quantitatively measure the creativity and engagement level of the titles, providing a robust foundation for the linguistic aspect of our investigation. As we dove into this linguistic rabbit hole, we encountered a plethora of puns and wordplay, and it became clear that analyzing YouTube titles is not just "clickbait" for researchers.

Simultaneously, we utilized econometric modeling to examine the correlation between the linguistic attributes of Vihart's video titles and the kerosene consumption patterns in Tanzania. Employing advanced statistical techniques, such as regression analysis and time series modeling, we sought to establish a robust quantitative relationship between these variables. This analytical approach served as the cornerstone of our investigation, offering a systematic means to assess the association between linguistic creativity and energy consumption. As we sifted through the data, we encountered statistical distributions that were as skewed as a badly told joke at a statistics convention.

To ensure the integrity and reliability of our findings, we also conducted sensitivity and robustness analyses to test the stability of the observed correlation over different time periods and under varying model specifications. This rigorous evaluation minimized the potential for spurious results and heightened the validity of our conclusions, providing assurance that our findings were not as fragile as a delicate correlation coefficient, but rather as sturdy as a well-supported research paper.

Furthermore, we conducted a series of robustness checks, including instrumental variable analyses and Granger causality tests, to fortify the robustness of our findings and guard against potential endogeneity and omitted variable biases. These methodological safeguards served as a shield against spurious correlations and confounding factors, ensuring that our conclusions were as secure as a solidly constructed statistical hypothesis.

In sum, our methodology integrated linguistic analysis with econometric modeling, underpinned by comprehensive data sources and robust statistical techniques. This approach allowed us to unravel the unexpected correlation between Vihart YouTube video titles and kerosene usage in Tanzania, shedding light on a relationship that is both statistically compelling and linguistically illuminating. And remember, a statistically significant correlation does not imply causation, unless it's about the illuminating effects of linguistic creativity on kerosene consumption in Tanzania.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 How good Vihart YouTube video titles are and Kerosene used in Tanzania. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from AI analysis of YouTube video titles and Energy Information Administration .

For the time period 2009 to 2021, you found a correlation 0.6838366, r-squared of 0.4676325, 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]]
From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania

[[ABSTRACT]]
This paper investigates the peculiar link between the creativity of Vihart YouTube video titles and the consumption of kerosene in Tanzania. Employing a unique blend of econometric and linguistic analysis, we uncover the unexpected relationship between these seemingly disparate phenomena. Utilizing data from the Energy Information Administration and AI-driven text mining of Vihart YouTube channel titles, we establish a significant correlation coefficient of 0.6838366 (p < 0.01) during the period from 2009 to 2021.

Our findings reveal not only a statistically robust association between the linguistic prowess of Vihart's video titles and kerosene usage in Tanzania, but also provide an opportunity for a "lighter" approach to understanding energy trends in developing countries. However, the correlation does not imply causation, prompting us to acknowledge that while "Vihart" may "ignite" creativity, it may not necessarily extinguish the need for kerosene. Thus, we urge policymakers and researchers to consider the broader social and cultural factors at play, illuminating the need for a more nuanced understanding of energy consumption in the digital age. And remember, whether it's data or dad jokes, correlation does not imply causation, unless it's about in-laws and headaches!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In recent years, the intersection of linguistic analysis and energy consumption has presented a unique avenue for research. Straying from more conventional investigations, this study delves into the intriguing connection between the creativity of Vihart YouTube video titles and the utilization of kerosene in Tanzania. One might say we are embarking on a "novel" expedition, as we seek to illuminate a correlation that is both unexpected and, dare I say, illuminating.
The decision to explore such an unorthodox relationship stemmed from a desire to shed light on an unconventional aspect of energy consumption. The correlation might seem "far-fetched," but as we unpack the data, we aim to demonstrate the relevance of linguistic analysis in understanding societal behaviors. After all, in the world of statistics, a good pun is statistically significant, right?
The juxtaposition of Vihart's captivating video titles with the conventional use of kerosene for lighting in Tanzania may appear to be as incongruous as a "match" in the desert, but our preliminary analysis suggests otherwise. This study draws on a captivating blend of textual analysis and econometric modeling to unravel what could be described as a "bright" correlation, sure to "spark" the interest of both linguists and energy researchers alike.
Our investigation extends beyond the realms of statistical significance to unearth a relationship that holds potential implications for policy and societal change. Yet, as we endeavor to unravel this unconventional connection, we remain cognizant of the age-old adage that correlation does not imply causation, unless, of course, we are discussing the meticulous crafting of YouTube video titles and the illumination provided by kerosene. After all, one might say that "Vihart" may "light up" creativity, but it may not necessarily dim the demand for kerosene.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis of the connection between Vihart YouTube video titles and kerosene usage in Tanzania yielded an intriguing correlation coefficient of 0.6838366 (p < 0.01) for the time period from 2009 to 2021. This strong correlation suggests a potentially "illuminating" relationship between linguistic creativity and energy consumption. However, let's not "burn out" on these results just yet, as we must remember that correlation does not imply causation, unless we're talking about the correlation between "dad jokes" and "eye rolls"!

The r-squared value of 0.4676325 further underscores the robustness of the association between the linguistic allure of Vihart's video titles and the usage of kerosene in Tanzania. This finding provides quantitative support for the notion that perhaps there is more to a unique YouTube video title than meets the eye. As we delve deeper into this correlation, one can't help but wonder if a punny video title can really "ignite" changes in energy usage. However, we maintain our academic rigor and acknowledge that while the correlation is strong, a myriad of factors could be at play, and much like a good dad joke, causation is not to be assumed lightly.

The scatterplot (Fig. 1) vividly illustrates the pronounced relationship between the linguistic creativity of Vihart's video titles and kerosene usage in Tanzania. As we look at the plot, we can't help but wonder if perhaps a well-crafted YouTube title has the power to "light up" not just our screens, but also our energy consumption patterns. Yet, our research strongly emphasizes the need for careful interpretation of these results, reminding us that even the most compelling correlations should be scrutinized with a discerning eye. After all, in the world of research, just like in the world of YouTube videos, it's important to bring the "light" of skepticism into each analysis.

In conclusion, our findings provide a meaningful "spark" for further exploration of the intersection between linguistic creativity and energy usage. However, we stress the significance of comprehensive and nuanced understanding, as well as a healthy dose of humor, in uncovering the intricate dynamics at play. And remember, when it comes to research, just like in Vihart's witty video titles, a little creativity can go a long way in shedding light on unexpected correlations.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 How good Vihart YouTube video titles are and Kerosene used in Tanzania. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania

[[ABSTRACT]]
This paper investigates the peculiar link between the creativity of Vihart YouTube video titles and the consumption of kerosene in Tanzania. Employing a unique blend of econometric and linguistic analysis, we uncover the unexpected relationship between these seemingly disparate phenomena. Utilizing data from the Energy Information Administration and AI-driven text mining of Vihart YouTube channel titles, we establish a significant correlation coefficient of 0.6838366 (p < 0.01) during the period from 2009 to 2021.

Our findings reveal not only a statistically robust association between the linguistic prowess of Vihart's video titles and kerosene usage in Tanzania, but also provide an opportunity for a "lighter" approach to understanding energy trends in developing countries. However, the correlation does not imply causation, prompting us to acknowledge that while "Vihart" may "ignite" creativity, it may not necessarily extinguish the need for kerosene. Thus, we urge policymakers and researchers to consider the broader social and cultural factors at play, illuminating the need for a more nuanced understanding of energy consumption in the digital age. And remember, whether it's data or dad jokes, correlation does not imply causation, unless it's about in-laws and headaches!

[[LITERATURE REVIEW]]
The conversation surrounding the interplay of linguistic expressions and energy consumption has historically been as dry as Vihart's wit. However, recent trends in interdisciplinary research have led scholars to brighten this area of study with a kerosene lamp's worth of new insights. Smith (2015) remarks that the correlation between creative language and energy trends is akin to "finding light in unexpected places," shedding a bright glow on our understanding of societal behaviors and linguistic influences. This correlates rather nicely with our own findings, doesn't it?
Speaking of illumination, it is impossible to ignore the work of Doe (2017), who postulates a potential link between the linguistic appeal of YouTube video titles and their impact on viewers' cognitive and emotive responses. It's quite a "bright idea" to consider the potential influence of language on human behavior, wouldn't you say? And speaking of bright ideas, did you hear about the Italian chef who died? He pasta way.
Jones (2019) uniquely explores the cultural dynamics of kerosene usage in developing countries and the potential impact of linguistic artifacts on energy consumption patterns. This study brings to light the importance of cultural context in understanding energy choices, not to mention the potential impact of a good dad joke on academic writing. After all, the pressure in academia can be intense. Speaking of dad jokes, did you hear about the kidnapping at the playground? They woke up, it's okay.
Turning to non-fiction literature that may inform our analysis, "Economics of Energy: A Holistic Perspective" by Chang (2018) provides an insightful framework for understanding the socio-economic dimensions of energy consumption. While we are more interested in illuminating the linguistic dimensions, integrating economic perspectives is essential to shedding light on the holistic understanding of energy trends. And speaking of holistic understanding, have you heard about the new restaurant on the moon? Great food, no atmosphere.
When considering fictional works that may tangentially relate to our investigation, "The Light Between Oceans" by M.L. Stedman comes to mind. Although the novel is set in a different context, the metaphor of light and its interplay with human experiences may offer some valuable insights into how language shapes societal behavior. And speaking of societal behavior, did you hear about the claustrophobic astronaut? He needed a little space.
In a delightful twist, "Kerosene Cowboys" by Randy Denmon stands out in the realm of fictional literature. While the title brings about images of burning rubber rather than kerosene, one might quip that the linguistic flair of the title matches our interest in intriguing linguistic expressions. And speaking of intriguing linguistic expressions, did you hear about the verb that became a noun? It was "verbing" its own issues.
Furthermore, the board game "Flash Point: Fire Rescue" may not only provide a lighthearted respite from our extensive analyses but also offers a tangential connection to the theme of fire and rescue, reflecting the importance of alternative energy sources and innovative solutions in addressing societal needs. And speaking of alternative energy sources, did you hear about the energized restaurant? The food was great; it had a lot of potential.
In summary, this brief yet elucidating literature review serves as the "match" igniting our inquiry into the unexpected correlation between Vihart's compelling YouTube video titles and kerosene usage in Tanzania. With each source contributing to our understanding in varying "degrees," we are poised to shed light on a correlation that is as illuminating as it is unexpected. And speaking of shedding light, why did the bicycle fall over? It was two-tired.

[[RESULTS]]
Our analysis of the connection between Vihart YouTube video titles and kerosene usage in Tanzania yielded an intriguing correlation coefficient of 0.6838366 (p < 0.01) for the time period from 2009 to 2021. This strong correlation suggests a potentially "illuminating" relationship between linguistic creativity and energy consumption. However, let's not "burn out" on these results just yet, as we must remember that correlation does not imply causation, unless we're talking about the correlation between "dad jokes" and "eye rolls"!
The r-squared value of 0.4676325 further underscores the robustness of the association between the linguistic allure of Vihart's video titles and the usage of kerosene in Tanzania. This finding provides quantitative support for the notion that perhaps there is more to a unique YouTube video title than meets the eye. As we delve deeper into this correlation, one can't help but wonder if a punny video title can really "ignite" changes in energy usage. However, we maintain our academic rigor and acknowledge that while the correlation is strong, a myriad of factors could be at play, and much like a good dad joke, causation is not to be assumed lightly.
The scatterplot (Fig. 1) vividly illustrates the pronounced relationship between the linguistic creativity of Vihart's video titles and kerosene usage in Tanzania. As we look at the plot, we can't help but wonder if perhaps a well-crafted YouTube title has the power to "light up" not just our screens, but also our energy consumption patterns. Yet, our research strongly emphasizes the need for careful interpretation of these results, reminding us that even the most compelling correlations should be scrutinized with a discerning eye. After all, in the world of research, just like in the world of YouTube videos, it's important to bring the "light" of skepticism into each analysis.
In conclusion, our findings provide a meaningful "spark" for further exploration of the intersection between linguistic creativity and energy usage. However, we stress the significance of comprehensive and nuanced understanding, as well as a healthy dose of humor, in uncovering the intricate dynamics at play. And remember, when it comes to research, just like in Vihart's witty video titles, a little creativity can go a long way in shedding light on unexpected correlations.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of our study have illuminated an unexpected correlation between the linguistic creativity of Vihart's YouTube video titles and kerosene usage in Tanzania. While this correlation is strong and statistically significant, it is important to note that correlation does not imply causation, unless we're discussing the correlation between "energy levels" and "caffeine intake"!

Our results align with previous research by Smith (2015) and Doe (2017), who emphasized the potential influence of creative language on energy consumption patterns. This corroborates the idea that language, much like a good dad joke, has the power to evoke responses that impact societal behavior. Additionally, Jones (2019) provided insights into the cultural dynamics of kerosene usage, which resonates with our own exploration of linguistic artifacts and their impact on energy consumption. It seems that a well-placed dad joke can illuminate even the most serious of academic discussions!

The statistically robust association we have identified serves as a testament to the power of linguistic expression in shaping societal trends, much like how a cleverly crafted YouTube title can captivate an audience. The correlation coefficient of 0.6838366 indicates a compelling link between Vihart's linguistic creativity and kerosene usage, shedding a light on the potentially intricate dynamics at play. However, much like a good pun, we must exercise caution in interpreting the implications of this association.

The r-squared value of 0.4676325 further enhances the credibility of our findings, emphasizing the significance of linguistic allure in influencing energy consumption patterns. This quantitatively supports the notion that perhaps there is more to a witty YouTube video title than meets the eye. Yet, we acknowledge, much like a well-timed dad joke, the need for careful scrutiny before drawing definitive conclusions.

Our results, illustrated in the scatterplot with a vivid depiction of the pronounced relationship between linguistic creativity and kerosene usage, invite us to consider the potential impact of a well-crafted YouTube title on energy consumption patterns. However, we stress the need for cautious interpretation, reminding ourselves that even the most compelling correlations should be approached with a discerning eye and a good sense of humor. After all, in the world of research, as in the world of witty video titles, a little creativity can indeed go a long way in shedding light on unexpected correlations.

In summary, our findings provide a meaningful "spark" for further inquiry into the interplay of linguistic creativity and energy usage. We are reminded that research, much like Vihart's witty video titles, benefits from the infusion of creativity and a healthy dose of humor, illuminating the unexpected phenomena that may lie at the curious intersections of language and energy consumption. And remember, in the world of academic research, just as in the world of dad jokes, a well-timed twist can light up the discourse in unexpected ways!


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 How good Vihart YouTube video titles are and Kerosene used in Tanzania. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania

[[ABSTRACT]]
This paper investigates the peculiar link between the creativity of Vihart YouTube video titles and the consumption of kerosene in Tanzania. Employing a unique blend of econometric and linguistic analysis, we uncover the unexpected relationship between these seemingly disparate phenomena. Utilizing data from the Energy Information Administration and AI-driven text mining of Vihart YouTube channel titles, we establish a significant correlation coefficient of 0.6838366 (p < 0.01) during the period from 2009 to 2021.

Our findings reveal not only a statistically robust association between the linguistic prowess of Vihart's video titles and kerosene usage in Tanzania, but also provide an opportunity for a "lighter" approach to understanding energy trends in developing countries. However, the correlation does not imply causation, prompting us to acknowledge that while "Vihart" may "ignite" creativity, it may not necessarily extinguish the need for kerosene. Thus, we urge policymakers and researchers to consider the broader social and cultural factors at play, illuminating the need for a more nuanced understanding of energy consumption in the digital age. And remember, whether it's data or dad jokes, correlation does not imply causation, unless it's about in-laws and headaches!

[[INTRDUCTION]]
In recent years, the intersection of linguistic analysis and energy consumption has presented a unique avenue for research. Straying from more conventional investigations, this study delves into the intriguing connection between the creativity of Vihart YouTube video titles and the utilization of kerosene in Tanzania. One might say we are embarking on a "novel" expedition, as we seek to illuminate a correlation that is both unexpected and, dare I say, illuminating.
The decision to explore such an unorthodox relationship stemmed from a desire to shed light on an unconventional aspect of energy consumption. The correlation might seem "far-fetched," but as we unpack the data, we aim to demonstrate the relevance of linguistic analysis in understanding societal behaviors. After all, in the world of statistics, a good pun is statistically significant, right?
The juxtaposition of Vihart's captivating video titles with the conventional use of kerosene for lighting in Tanzania may appear to be as incongruous as a "match" in the desert, but our preliminary analysis suggests otherwise. This study draws on a captivating blend of textual analysis and econometric modeling to unravel what could be described as a "bright" correlation, sure to "spark" the interest of both linguists and energy researchers alike.
Our investigation extends beyond the realms of statistical significance to unearth a relationship that holds potential implications for policy and societal change. Yet, as we endeavor to unravel this unconventional connection, we remain cognizant of the age-old adage that correlation does not imply causation, unless, of course, we are discussing the meticulous crafting of YouTube video titles and the illumination provided by kerosene. After all, one might say that "Vihart" may "light up" creativity, but it may not necessarily dim the demand for kerosene.

[[RESULTS]]
Our analysis of the connection between Vihart YouTube video titles and kerosene usage in Tanzania yielded an intriguing correlation coefficient of 0.6838366 (p < 0.01) for the time period from 2009 to 2021. This strong correlation suggests a potentially "illuminating" relationship between linguistic creativity and energy consumption. However, let's not "burn out" on these results just yet, as we must remember that correlation does not imply causation, unless we're talking about the correlation between "dad jokes" and "eye rolls"!
The r-squared value of 0.4676325 further underscores the robustness of the association between the linguistic allure of Vihart's video titles and the usage of kerosene in Tanzania. This finding provides quantitative support for the notion that perhaps there is more to a unique YouTube video title than meets the eye. As we delve deeper into this correlation, one can't help but wonder if a punny video title can really "ignite" changes in energy usage. However, we maintain our academic rigor and acknowledge that while the correlation is strong, a myriad of factors could be at play, and much like a good dad joke, causation is not to be assumed lightly.
The scatterplot (Fig. 1) vividly illustrates the pronounced relationship between the linguistic creativity of Vihart's video titles and kerosene usage in Tanzania. As we look at the plot, we can't help but wonder if perhaps a well-crafted YouTube title has the power to "light up" not just our screens, but also our energy consumption patterns. Yet, our research strongly emphasizes the need for careful interpretation of these results, reminding us that even the most compelling correlations should be scrutinized with a discerning eye. After all, in the world of research, just like in the world of YouTube videos, it's important to bring the "light" of skepticism into each analysis.
In conclusion, our findings provide a meaningful "spark" for further exploration of the intersection between linguistic creativity and energy usage. However, we stress the significance of comprehensive and nuanced understanding, as well as a healthy dose of humor, in uncovering the intricate dynamics at play. And remember, when it comes to research, just like in Vihart's witty video titles, a little creativity can go a long way in shedding light on unexpected correlations.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has illuminated a statistically significant correlation between the linguistic creativity of Vihart's YouTube video titles and the consumption of kerosene in Tanzania. This unexpected relationship underscores the potential influence of unconventional factors on energy usage, demonstrating that a well-crafted title can "shine a light" on societal behaviors. However, as we wrap up our discussion, it's important to remember that correlation does not imply causation, unless we're discussing the correlation between "Vihart" and "vibrant video titles."

Our findings suggest that linguistic allure plays an intriguing role in shaping energy consumption patterns, offering a "bright" opportunity for policymakers and researchers to adopt a more "enlightened" approach to understanding societal behaviors. However, it's crucial to bear in mind that while "Vihart" may "spark" creativity, it may not necessarily extinguish the need for kerosene, prompting us to approach these results with cautious optimism.

Moving forward, our research urges for a deeper exploration of the dynamic interplay between linguistic creativity and energy trends. As we embark on this journey, we must not overlook the importance of a "lighthearted" approach and a sprinkle of humor to illuminate the often unexpected associations in our data. After all, in the world of research, just like in the world of YouTube videos, a little creativity can go a long way in shedding light on unexpected correlations. And speaking of shedding light, have you heard about the kidnapping at the lightbulb factory? Don't worry, though – it was just a "light-hearted" joke!

In light of our comprehensive analysis, we assert that no further research is needed in this area. After all, much like a well-crafted video title, our findings "shine a light" on the unexpected correlations that can be unearthed through a blend of linguistic analysis and energy trends.


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 From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Interdisciplinary Kerosene Studies


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 From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Quirky Inquiry and Research (CQIR)


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 From Kerosene to Kreative Kerosene: Exploring the Correlation between Vihart YouTube Video Titles and Kerosene Usage in Tanzania with an abstract of This paper investigates the peculiar link between the creativity of Vihart YouTube video titles and the consumption of kerosene in Tanzania. Employing a unique blend of econometric and linguistic analysis, we uncover the unexpected relationship between these seemingly disparate phenomena. Utilizing data from the Energy Information Administration and AI-driven text mining of Vihart YouTube channel titles, we establish a significant correlation coefficient of 0.6838366 (p < 0.01) during the period from 2009 to 2021.
Our findings reveal not only a statistically robust association between the linguistic prowess of Vihart's video titles and kerosene usage in Tanzania, but also provide an opportunity for a "lighter" approach to understanding energy trends in developing countries. However, the correlation does not imply causation, prompting us to acknowledge that while "Vihart" may "ignite" creativity, it may not necessarily extinguish the need for kerosene. Thus, we urge policymakers and researchers to consider the broader social and cultural factors at play, illuminating the need for a more nuanced understanding of energy consumption in the digital age. And remember, whether it's data or dad jokes, correlation does not imply causation, unless it's about in-laws and headaches!

ChatGPT:

Vihart, YouTube, video titles, kerosene, Tanzania, correlation, linguistic analysis, econometric analysis, Energy Information Administration, text mining, energy trends, developing countries, causation, social factors, cultural factors, digital age, energy consumption, correlation coefficient

*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

How good Vihart's YouTube video titles are
Detailed data title: How good Vihart YouTube video titles are, as rated by an AI.
Source: AI analysis of YouTube video titles
Additional Info: I asked a large language model, 'On a scale of 1-10, how _______ do you think this YouTube video title is?' for every video.

See what else correlates with How good Vihart's YouTube video titles are

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

Correlation r = 0.6838366 (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 = 0.4676325 (Coefficient of determination)
This means 46.8% of the change in the one variable (i.e., Kerosene used in Tanzania) is predictable based on the change in the other (i.e., How good Vihart's YouTube video titles are) over the 13 years from 2009 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.01. 0.0099530748517291310000000000
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 0.68 in 1% of random cases. Said differently, if you correlated 100 random variables Which I absolutely did.
with the same 12 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 12 because we have two variables measured over a period of 13 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.21, 0.9 ] 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.
2009201020112012201320142015201620172018201920202021
How good Vihart's YouTube video titles are (Score (out of 10))6.8758.33336.41186.77426.69236.714366.55567.14296.72735.666765.6667
Kerosene used in Tanzania (Million Barrels/Day)3.261424.405041.249512.830110.7835890.6565210.4870951000.3476160.3319030.350214




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([6.875,8.3333,6.4118,6.7742,6.6923,6.7143,6,6.5556,7.1429,6.7273,5.6667,6,5.6667,])
array_2 = np.array([3.26142,4.40504,1.24951,2.83011,0.783589,0.656521,0.487095,1,0,0,0.347616,0.331903,0.350214,])
array_1_name = "How good Vihart's YouTube video titles are"
array_2_name = "Kerosene used in Tanzania"

# 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?

Big thanks for reviewing!


Correlation ID: 4738 · Black Variable ID: 25560 · Red Variable ID: 24979
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0