about · email me · subscribe
Spurious correlation #5,569 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is How provocative Tom Scott's YouTube video titles are and the second variable is Snowfall in Dallas.  The chart goes from 2009 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The more titillating Tom Scott's video titles become, the more they inexplicably attract a sudden influx of spicy salsa enthusiasts to Dallas. This leads to a sharp increase in salsa dancing, creating enough heat to induce unseasonable snowfall. It's a case of clickbait causing a cold front!

Model: dalle-3
Prompt: Generate an image inspired by the scene in Dallas. Create a vibrant city skyline at night, with the glowing YouTube video titles showcasing Tom Scott's provocative content. In the foreground, depict a bustling street filled with salsa enthusiasts engaging in passionate dancing, while the atmosphere is alive with energetic salsa music. Incorporate delicate snowflakes falling gently from the sky, adding a touch of rarity and beauty to the scene. 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 provocative Tom Scott's YouTube video titles are and Snowfall in Dallas. 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: Art nouveau Cutsy art illustration High-tech Minimalism a funny image you would see on reddit
ChatGPT: a funny image you would see on reddit

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 provocative Tom Scott's YouTube video titles are and Snowfall in Dallas, in the following situation: The more titillating Tom Scott's video titles become, the more they inexplicably attract a sudden influx of spicy salsa enthusiasts to Dallas. This leads to a sharp increase in salsa dancing, creating enough heat to induce unseasonable snowfall. It's a case of clickbait causing a cold front!. Keep the description simple.
ChatGPT: In the heart of Dallas, a mesmerizing sight unfolds. Tom Scott's provocative YouTube video titles, glowing brightly against the city skyline, are drawing a throng of spicy salsa enthusiasts from all corners. As they gather, the rhythm of salsa music fills the air, and soon, the streets are alive with passionate dancing. The fervent energy and heat generate an unexpected consequence - delicate snowflakes begin to fall gently, blanketing the city in a rare and beautiful snowfall.

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 funny image you would see on reddit ] and depicting this scene: In the heart of Dallas, a mesmerizing sight unfolds. Tom Scott's provocative YouTube video titles, glowing brightly against the city skyline, are drawing a throng of spicy salsa enthusiasts from all corners. As they gather, the rhythm of salsa music fills the air, and soon, the streets are alive with passionate dancing. The fervent energy and heat generate an unexpected consequence - delicate snowflakes begin to fall gently, blanketing the city in a rare and beautiful snowfall. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image inspired by the scene in Dallas. Create a vibrant city skyline at night, with the glowing YouTube video titles showcasing Tom Scott's provocative content. In the foreground, depict a bustling street filled with salsa enthusiasts engaging in passionate dancing, while the atmosphere is alive with energetic salsa music. Incorporate delicate snowflakes falling gently from the sky, adding a touch of rarity and beauty to the scene.

*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 increases in How provocative Tom Scott YouTube video titles are positively influenced Snowfall in Dallas. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas

The Journal of Clickbait 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 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 How provocative Tom Scott YouTube video titles are and Snowfall in Dallas. 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, make it sound serious.

Your research team used data from AI analysis of YouTube video titles and NOAA National Climate Data Center to assess this nagging question. You found a correlation coefficient of 0.8590713 and p < 0.01 for 2009 to 2022.

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]]
Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas

[[ABSTRACT]]
This study examines the relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas. By using data from AI analysis of YouTube video titles and the NOAA National Climate Data Center, we sought to explore the impact of Tom Scott's click-worthy titles on a seemingly unrelated variable - winter weather in the Dallas area. Our findings revealed a rather unexpected and, some might say, flaky connection.

The correlation coefficient of 0.8590713 and p < 0.01 for the years 2009 to 2022 suggested a strong and statistically significant association between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles! While the exact mechanisms behind this correlation remain elusive, one could say the data just needed a little bit of a chill to reveal this frosty relationship. This research not only sheds light on a peculiar link but also reminds us of the cold, hard truth that statistical relationships can sometimes be as unpredictable as the weather.


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 How provocative Tom Scott YouTube video titles are and Snowfall in Dallas. 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]]
Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas

[[ABSTRACT]]
This study examines the relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas. By using data from AI analysis of YouTube video titles and the NOAA National Climate Data Center, we sought to explore the impact of Tom Scott's click-worthy titles on a seemingly unrelated variable - winter weather in the Dallas area. Our findings revealed a rather unexpected and, some might say, flaky connection.

The correlation coefficient of 0.8590713 and p < 0.01 for the years 2009 to 2022 suggested a strong and statistically significant association between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles! While the exact mechanisms behind this correlation remain elusive, one could say the data just needed a little bit of a chill to reveal this frosty relationship. This research not only sheds light on a peculiar link but also reminds us of the cold, hard truth that statistical relationships can sometimes be as unpredictable as the weather.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The relationship between seemingly unrelated variables has long been a subject of fascination and intrigue in the field of research. As the saying goes, "correlation does not imply causation" – but what if it does, in a rather unexpected way? In a world filled with data, patterns, and surprises, it is not uncommon to stumble upon correlations that seem to defy logic. Such is the case with the connection between the provocative nature of Tom Scott's YouTube video titles and the annual snowfall in Dallas, Texas.

When it comes to exploring unexpected correlations, it's important to approach the topic with an open mind – after all, sometimes the most impactful discoveries are, quite literally, hidden in the snow. With this in mind, we embarked on a journey to investigate the extent to which Tom Scott's click-worthy titles may influence the amount of snowfall in the Dallas area. However, as the old adage goes, the devil is in the details – or in this case, the snowflakes.

The idea that the provocative nature of YouTube video titles could have any bearing on the weather may seem far-fetched, if not downright flaky. However, as researchers, it's important to remember that every snowflake is unique, just like every correlation we uncover. As the data began to accumulate, it became increasingly clear that there might be more to this snowy tale than meets the eye.

In the world of academia, it's not uncommon to encounter unexpected relationships, much like stumbling upon a patch of black ice on a sunny day – it may catch you off guard, but it certainly makes for an interesting journey. Speaking of unexpected relationships, have you heard about the snowman who fell in love with a furnace? It was a case of a frosty reception!

As we delve into the findings of our study, it's important to approach the data with a healthy dose of skepticism and a willingness to entertain alternative explanations. After all, just as no two snowflakes are exactly alike, no two research findings are entirely identical. This study sets out to unravel the mysterious intertwining of click-worthy YouTube titles and snowfall in Dallas, shedding light on a correlation that is as intriguing as it is improbable. Let's not let this chilly connection slip through our fingers – after all, a good discovery is as rare as a February heatwave!


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 How provocative Tom Scott YouTube video titles are and Snowfall in Dallas. 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]]
Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas

[[ABSTRACT]]
This study examines the relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas. By using data from AI analysis of YouTube video titles and the NOAA National Climate Data Center, we sought to explore the impact of Tom Scott's click-worthy titles on a seemingly unrelated variable - winter weather in the Dallas area. Our findings revealed a rather unexpected and, some might say, flaky connection.

The correlation coefficient of 0.8590713 and p < 0.01 for the years 2009 to 2022 suggested a strong and statistically significant association between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles! While the exact mechanisms behind this correlation remain elusive, one could say the data just needed a little bit of a chill to reveal this frosty relationship. This research not only sheds light on a peculiar link but also reminds us of the cold, hard truth that statistical relationships can sometimes be as unpredictable as the weather.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between seemingly unrelated variables has long been a subject of fascination and intrigue in the field of research. As the saying goes, "correlation does not imply causation" – but what if it does, in a rather unexpected way? In a world filled with data, patterns, and surprises, it is not uncommon to stumble upon correlations that seem to defy logic. Such is the case with the connection between the provocative nature of Tom Scott's YouTube video titles and the annual snowfall in Dallas, Texas.
When it comes to exploring unexpected correlations, it's important to approach the topic with an open mind – after all, sometimes the most impactful discoveries are, quite literally, hidden in the snow. With this in mind, we embarked on a journey to investigate the extent to which Tom Scott's click-worthy titles may influence the amount of snowfall in the Dallas area. However, as the old adage goes, the devil is in the details – or in this case, the snowflakes.
The idea that the provocative nature of YouTube video titles could have any bearing on the weather may seem far-fetched, if not downright flaky. However, as researchers, it's important to remember that every snowflake is unique, just like every correlation we uncover. As the data began to accumulate, it became increasingly clear that there might be more to this snowy tale than meets the eye.
In the world of academia, it's not uncommon to encounter unexpected relationships, much like stumbling upon a patch of black ice on a sunny day – it may catch you off guard, but it certainly makes for an interesting journey. Speaking of unexpected relationships, have you heard about the snowman who fell in love with a furnace? It was a case of a frosty reception!
As we delve into the findings of our study, it's important to approach the data with a healthy dose of skepticism and a willingness to entertain alternative explanations. After all, just as no two snowflakes are exactly alike, no two research findings are entirely identical. This study sets out to unravel the mysterious intertwining of click-worthy YouTube titles and snowfall in Dallas, shedding light on a correlation that is as intriguing as it is improbable. Let's not let this chilly connection slip through our fingers – after all, a good discovery is as rare as a February heatwave!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The connection between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas is a topic that has garnered surprisingly little academic attention. However, a few notable studies have explored the impact of digital media on weather patterns and human behavior. Smith (2015) investigated the influence of online content on public perceptions of local climates, finding a modest correlation between engaging video titles and perceived temperature changes. Similarly, Doe (2018) examined the relationship between social media posts and atmospheric conditions, with intriguing implications for meteorological forecasting. These studies set the stage for our investigation into the influence of provocative YouTube titles on winter weather patterns in a specific geographic area.

Turning to the realm of non-fiction literature, books such as "The Influential Mind" by Tali Sharot and "Everybody Lies" by Seth Stephens-Davidowitz provide insights into the subtle ways in which digital content shapes human cognition and decision-making. These works offer valuable perspectives on the potential influence of online media, including YouTube titles, on individual perceptions and behaviors. This broader context underscores the relevance and timeliness of our inquiry into the connection between Tom Scott's video titles and snowfall in Dallas.

In the domain of fiction, novels such as "Snow Falling on Cedars" by David Guterson and "The Winter of Our Discontent" by John Steinbeck may not directly address the relationship between YouTube titles and weather phenomena, but their thematic focus on snow and changing seasons speaks to the enduring fascination with meteorological events in literary narratives. It is within this rich tapestry of cultural representations of snow and provocative media that our investigation seeks to carve out a unique niche, not unlike a snow sculptor crafting a masterpiece in a winter wonderland.

Furthermore, the world of board games offers intriguing parallels to our research inquiry. In games such as "Ticket to Ride: Nordic Countries" and "Snow Tails," players navigate wintry landscapes and strategize amidst challenging weather conditions. These ludic experiences mirror the complexities of navigating unexpected correlations in real-world data, albeit with a more lighthearted and playful tone.

As we delve deeper into the burgeoning literature on seemingly improbable connections and their unexpected implications, it becomes apparent that the intersection of digital media, human perception, and natural phenomena is a terrain ripe for exploration. In the words of the empirically-minded jesters of yore, "Why did the statistician break up with the meteorologist? There was too much uncertainty in their relationship!" Nonetheless, it is precisely within this uncertainty that our study aims to unearth a "cold case" worthy of scholarly scrutiny, even if it means weathering a blizzard of skepticism along the way.


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 How provocative Tom Scott YouTube video titles are and Snowfall in Dallas. 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 AI analysis of YouTube video titles and NOAA National Climate Data Center . You used data from 2009 to 2022

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]]
Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas

[[ABSTRACT]]
This study examines the relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas. By using data from AI analysis of YouTube video titles and the NOAA National Climate Data Center, we sought to explore the impact of Tom Scott's click-worthy titles on a seemingly unrelated variable - winter weather in the Dallas area. Our findings revealed a rather unexpected and, some might say, flaky connection.

The correlation coefficient of 0.8590713 and p < 0.01 for the years 2009 to 2022 suggested a strong and statistically significant association between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles! While the exact mechanisms behind this correlation remain elusive, one could say the data just needed a little bit of a chill to reveal this frosty relationship. This research not only sheds light on a peculiar link but also reminds us of the cold, hard truth that statistical relationships can sometimes be as unpredictable as the weather.

[[INTRODUCTION]]
The relationship between seemingly unrelated variables has long been a subject of fascination and intrigue in the field of research. As the saying goes, "correlation does not imply causation" – but what if it does, in a rather unexpected way? In a world filled with data, patterns, and surprises, it is not uncommon to stumble upon correlations that seem to defy logic. Such is the case with the connection between the provocative nature of Tom Scott's YouTube video titles and the annual snowfall in Dallas, Texas.
When it comes to exploring unexpected correlations, it's important to approach the topic with an open mind – after all, sometimes the most impactful discoveries are, quite literally, hidden in the snow. With this in mind, we embarked on a journey to investigate the extent to which Tom Scott's click-worthy titles may influence the amount of snowfall in the Dallas area. However, as the old adage goes, the devil is in the details – or in this case, the snowflakes.
The idea that the provocative nature of YouTube video titles could have any bearing on the weather may seem far-fetched, if not downright flaky. However, as researchers, it's important to remember that every snowflake is unique, just like every correlation we uncover. As the data began to accumulate, it became increasingly clear that there might be more to this snowy tale than meets the eye.
In the world of academia, it's not uncommon to encounter unexpected relationships, much like stumbling upon a patch of black ice on a sunny day – it may catch you off guard, but it certainly makes for an interesting journey. Speaking of unexpected relationships, have you heard about the snowman who fell in love with a furnace? It was a case of a frosty reception!
As we delve into the findings of our study, it's important to approach the data with a healthy dose of skepticism and a willingness to entertain alternative explanations. After all, just as no two snowflakes are exactly alike, no two research findings are entirely identical. This study sets out to unravel the mysterious intertwining of click-worthy YouTube titles and snowfall in Dallas, shedding light on a correlation that is as intriguing as it is improbable. Let's not let this chilly connection slip through our fingers – after all, a good discovery is as rare as a February heatwave!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To investigate the correlation between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas, a multi-faceted approach was employed. The data collection process commenced with the utilization of advanced AI algorithms to analyze the click-worthiness and provocativeness of Tom Scott's YouTube video titles. These algorithms were trained to detect patterns in language use, emotional triggers, and attention-grabbing phrases, all in pursuit of capturing the essence of a truly captivating title. This approach allowed for a quantitative assessment of the level of clickability that each title possessed, ensuring that no potential snowflake in the data was left unturned. As we sifted through the vast expanse of video titles, it became clear that the provocative power of language is, indeed, a force to be reckoned with – much like a sudden snowstorm on a sunny day.

Additionally, historical snowfall data for the Dallas area was obtained from the NOAA National Climate Data Center. This dataset provided a comprehensive record of snowfall measurements from 2009 to 2022, allowing for a thorough examination of the winter weather patterns in Dallas over the course of multiple years. The snowfall data, much like a delicate snowflake, provided a canvas upon which the influence of Tom Scott's provocative titles could be measured, juxtaposed, and examined for any semblance of a meaningful relationship. It was as if each snowfall measurement whispered a tale of seasons past, waiting to be compared and contrasted with the captivating allure of a YouTube video title.

The next step in the methodology involved the application of advanced statistical analyses to tease out any potential connections between the provocativeness of Tom Scott's video titles and the snowfall in Dallas. Correlation coefficients, regression models, and time series analyses were harnessed to discern the extent of the relationship between these seemingly disparate variables. Like a game of hopscotch in a snow-covered playground, these statistical methods leaped and bounded across the data, seeking to uncover any hidden leaps of logic or unexpected twists in the relationship. As the analyses unfolded, it became evident that the data was not just cold, hard numbers – it was a story waiting to be told, much like a well-crafted dad joke in the midst of a serious academic study.

Furthermore, in an effort to control for potential confounding variables, additional comparative analyses were conducted. These analyses sought to explore whether the observed relationship between the provocativeness of Tom Scott's video titles and snowfall in Dallas could be attributed to external factors such as geographic location, time of year, or other meteorological phenomena. Through this process, the research team aimed to ensure that the identified relationship was not simply a fluke of nature, but rather a robust and meaningful discovery – much like stumbling upon a snowman in summer, where the unexpected becomes the norm.

Lastly, a series of sensitivity analyses were undertaken to evaluate the robustness of the findings and to assess the potential impact of outliers or extreme weather events on the observed relationship. These analyses allowed for a nuanced understanding of the nuances of the correlation and illuminated the potential areas in which the relationship may be less crystal clear. In doing so, the research team aimed to encapsulate the full spectrum of the connection between Tom Scott's YouTube titles and snowfall in Dallas, acknowledging that, much like a gentle snowfall, the relationship may have both its soft and its unexpected edges.

In summary, the methodology employed in this study encompassed a comprehensive and multi-dimensional approach, combining AI analysis of YouTube video titles, historical snowfall data, advanced statistical techniques, comparative analyses, and sensitivity assessments to explore the quirky and unanticipated relationship between the provocative power of Tom Scott's titles and snowfall in Dallas. The research journey was one paved with unexpected twists and melodious surprises, much like a well-timed dad joke on a frosty winter's day.


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 How provocative Tom Scott YouTube video titles are and Snowfall in Dallas. 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 AI analysis of YouTube video titles and NOAA National Climate Data Center .

For the time period 2009 to 2022, you found a correlation 0.8590713, r-squared of 0.7380035, 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]]
Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas

[[ABSTRACT]]
This study examines the relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas. By using data from AI analysis of YouTube video titles and the NOAA National Climate Data Center, we sought to explore the impact of Tom Scott's click-worthy titles on a seemingly unrelated variable - winter weather in the Dallas area. Our findings revealed a rather unexpected and, some might say, flaky connection.

The correlation coefficient of 0.8590713 and p < 0.01 for the years 2009 to 2022 suggested a strong and statistically significant association between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles! While the exact mechanisms behind this correlation remain elusive, one could say the data just needed a little bit of a chill to reveal this frosty relationship. This research not only sheds light on a peculiar link but also reminds us of the cold, hard truth that statistical relationships can sometimes be as unpredictable as the weather.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The relationship between seemingly unrelated variables has long been a subject of fascination and intrigue in the field of research. As the saying goes, "correlation does not imply causation" – but what if it does, in a rather unexpected way? In a world filled with data, patterns, and surprises, it is not uncommon to stumble upon correlations that seem to defy logic. Such is the case with the connection between the provocative nature of Tom Scott's YouTube video titles and the annual snowfall in Dallas, Texas.
When it comes to exploring unexpected correlations, it's important to approach the topic with an open mind – after all, sometimes the most impactful discoveries are, quite literally, hidden in the snow. With this in mind, we embarked on a journey to investigate the extent to which Tom Scott's click-worthy titles may influence the amount of snowfall in the Dallas area. However, as the old adage goes, the devil is in the details – or in this case, the snowflakes.
The idea that the provocative nature of YouTube video titles could have any bearing on the weather may seem far-fetched, if not downright flaky. However, as researchers, it's important to remember that every snowflake is unique, just like every correlation we uncover. As the data began to accumulate, it became increasingly clear that there might be more to this snowy tale than meets the eye.
In the world of academia, it's not uncommon to encounter unexpected relationships, much like stumbling upon a patch of black ice on a sunny day – it may catch you off guard, but it certainly makes for an interesting journey. Speaking of unexpected relationships, have you heard about the snowman who fell in love with a furnace? It was a case of a frosty reception!
As we delve into the findings of our study, it's important to approach the data with a healthy dose of skepticism and a willingness to entertain alternative explanations. After all, just as no two snowflakes are exactly alike, no two research findings are entirely identical. This study sets out to unravel the mysterious intertwining of click-worthy YouTube titles and snowfall in Dallas, shedding light on a correlation that is as intriguing as it is improbable. Let's not let this chilly connection slip through our fingers – after all, a good discovery is as rare as a February heatwave!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data collected from Tom Scott's YouTube video titles and the snowfall in Dallas for the period 2009 to 2022 revealed a remarkably strong correlation coefficient of 0.8590713. This correlation implies that there is a robust relationship between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas, Texas. It seems that the snow in Dallas is not the only thing piling up – Tom Scott's provocative titles are also accumulating quite the following! This unexpected correlation certainly snowballed into a noteworthy finding.

Furthermore, the coefficient of determination (r-squared) was calculated to be 0.7380035, indicating that approximately 73.8% of the variability in snowfall in Dallas can be explained by the level of provocativeness in Tom Scott's YouTube video titles. Talk about a snowstorm of influence! It appears that Tom Scott's catchy titles may have more impact than one might have initially thought. Perhaps we should start calling him "Snow" Scott!

Moreover, the statistical significance of this association was supported by a p-value of less than 0.01. This suggests that the observed correlation is unlikely to have occurred purely by chance and is indeed a real and significant relationship. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles!

Fig. 1 illustrates the strong positive correlation between the provocative nature of Tom Scott's YouTube video titles and the annual snowfall in Dallas. The scatterplot portrays a clear and compelling relationship, further reinforcing the statistical findings of our study. It appears that Tom Scott's titles have the power to snowball into a significant influence on the weather patterns in Dallas.

In summary, our research has uncovered a surprising and robust correlation between the level of provocativeness in Tom Scott's YouTube video titles and the amount of snowfall in Dallas. This unexpected connection serves as a reminder that in the vast landscape of data, one should always keep an open mind and be prepared to embrace the unexpected – much like encountering a sudden snow flurry in the midst of spring. This study not only sheds light on a peculiar link but also serves as a lighthearted reminder that statistical relationships can be as unpredictable as, well, the weather.


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 How provocative Tom Scott YouTube video titles are and Snowfall in Dallas. 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]]
Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas

[[ABSTRACT]]
This study examines the relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas. By using data from AI analysis of YouTube video titles and the NOAA National Climate Data Center, we sought to explore the impact of Tom Scott's click-worthy titles on a seemingly unrelated variable - winter weather in the Dallas area. Our findings revealed a rather unexpected and, some might say, flaky connection.

The correlation coefficient of 0.8590713 and p < 0.01 for the years 2009 to 2022 suggested a strong and statistically significant association between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles! While the exact mechanisms behind this correlation remain elusive, one could say the data just needed a little bit of a chill to reveal this frosty relationship. This research not only sheds light on a peculiar link but also reminds us of the cold, hard truth that statistical relationships can sometimes be as unpredictable as the weather.

[[LITERATURE REVIEW]]
The connection between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas is a topic that has garnered surprisingly little academic attention. However, a few notable studies have explored the impact of digital media on weather patterns and human behavior. Smith (2015) investigated the influence of online content on public perceptions of local climates, finding a modest correlation between engaging video titles and perceived temperature changes. Similarly, Doe (2018) examined the relationship between social media posts and atmospheric conditions, with intriguing implications for meteorological forecasting. These studies set the stage for our investigation into the influence of provocative YouTube titles on winter weather patterns in a specific geographic area.
Turning to the realm of non-fiction literature, books such as "The Influential Mind" by Tali Sharot and "Everybody Lies" by Seth Stephens-Davidowitz provide insights into the subtle ways in which digital content shapes human cognition and decision-making. These works offer valuable perspectives on the potential influence of online media, including YouTube titles, on individual perceptions and behaviors. This broader context underscores the relevance and timeliness of our inquiry into the connection between Tom Scott's video titles and snowfall in Dallas.
In the domain of fiction, novels such as "Snow Falling on Cedars" by David Guterson and "The Winter of Our Discontent" by John Steinbeck may not directly address the relationship between YouTube titles and weather phenomena, but their thematic focus on snow and changing seasons speaks to the enduring fascination with meteorological events in literary narratives. It is within this rich tapestry of cultural representations of snow and provocative media that our investigation seeks to carve out a unique niche, not unlike a snow sculptor crafting a masterpiece in a winter wonderland.
Furthermore, the world of board games offers intriguing parallels to our research inquiry. In games such as "Ticket to Ride: Nordic Countries" and "Snow Tails," players navigate wintry landscapes and strategize amidst challenging weather conditions. These ludic experiences mirror the complexities of navigating unexpected correlations in real-world data, albeit with a more lighthearted and playful tone.
As we delve deeper into the burgeoning literature on seemingly improbable connections and their unexpected implications, it becomes apparent that the intersection of digital media, human perception, and natural phenomena is a terrain ripe for exploration. In the words of the empirically-minded jesters of yore, "Why did the statistician break up with the meteorologist? There was too much uncertainty in their relationship!" Nonetheless, it is precisely within this uncertainty that our study aims to unearth a "cold case" worthy of scholarly scrutiny, even if it means weathering a blizzard of skepticism along the way.

[[RESULTS]]
The analysis of the data collected from Tom Scott's YouTube video titles and the snowfall in Dallas for the period 2009 to 2022 revealed a remarkably strong correlation coefficient of 0.8590713. This correlation implies that there is a robust relationship between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas, Texas. It seems that the snow in Dallas is not the only thing piling up – Tom Scott's provocative titles are also accumulating quite the following! This unexpected correlation certainly snowballed into a noteworthy finding.
Furthermore, the coefficient of determination (r-squared) was calculated to be 0.7380035, indicating that approximately 73.8% of the variability in snowfall in Dallas can be explained by the level of provocativeness in Tom Scott's YouTube video titles. Talk about a snowstorm of influence! It appears that Tom Scott's catchy titles may have more impact than one might have initially thought. Perhaps we should start calling him "Snow" Scott!
Moreover, the statistical significance of this association was supported by a p-value of less than 0.01. This suggests that the observed correlation is unlikely to have occurred purely by chance and is indeed a real and significant relationship. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles!
Fig. 1 illustrates the strong positive correlation between the provocative nature of Tom Scott's YouTube video titles and the annual snowfall in Dallas. The scatterplot portrays a clear and compelling relationship, further reinforcing the statistical findings of our study. It appears that Tom Scott's titles have the power to snowball into a significant influence on the weather patterns in Dallas.
In summary, our research has uncovered a surprising and robust correlation between the level of provocativeness in Tom Scott's YouTube video titles and the amount of snowfall in Dallas. This unexpected connection serves as a reminder that in the vast landscape of data, one should always keep an open mind and be prepared to embrace the unexpected – much like encountering a sudden snow flurry in the midst of spring. This study not only sheds light on a peculiar link but also serves as a lighthearted reminder that statistical relationships can be as unpredictable as, well, the weather.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study provide compelling evidence for a strong and previously unexplored correlation between the level of provocativeness in Tom Scott's YouTube video titles and the amount of snowfall in Dallas. As tempting as it may be to dismiss these results as mere flurries of coincidence, the robust statistical significance and high coefficient of determination suggest a genuine and substantial relationship. It appears that Tom Scott's provocative titles are as influential as an unexpected blizzard in shaping the winter weather patterns in Dallas.

Building upon the scant literature addressing the influence of digital media on weather and human behavior, this study offers a unique contribution to the burgeoning field of interdisciplinary research. Despite the initial skepticism surrounding the prospect of Tom Scott's YouTube titles impacting snowfall in Dallas, this investigation has convincingly demonstrated that statistical relationships can indeed be as capricious as the weather. It seems that Tom Scott's titles have the power to not only attract clicks, but also to conjure up snowflakes in an unlikely locale.

The unexpected nature of this correlation underscores the importance of approaching research with an open mind, much like the opportunities presented by encountering a patch of unexpected snow. Despite the leveling of serious scientific inquiry, this study also serves as a lighthearted reminder of the delightful unpredictability inherent in statistical analyses. One might say that this correlation is as surprising as finding a Yeti sipping hot cocoa in the midst of a summertime heatwave.

The significant association between the level of provocativeness in Tom Scott's YouTube video titles and snowfall in Dallas casts a frosty new light on the potential impact of digital media on natural phenomena. It is clear that the nuances of human perception and behavior extend far beyond traditional domains of investigation, resembling a symphony of snowflakes falling in the unlikeliest of places. As the saying goes, "Where there's a chill, there's a way," and it seems that Tom Scott's titles have found their way into the algorithms of atmospheric whimsy.

In conclusion, this study has uncovered a remarkably robust and unexpected relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, providing a chilly reminder that statistical associations can be as enchantingly unpredictable as the weather. As with any surprising discovery, these findings invite further inquiry and contemplation, much like a sudden snowfall in the midst of an otherwise balmy day.


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 How provocative Tom Scott YouTube video titles are and Snowfall in Dallas. 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]]
Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas

[[ABSTRACT]]
This study examines the relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas. By using data from AI analysis of YouTube video titles and the NOAA National Climate Data Center, we sought to explore the impact of Tom Scott's click-worthy titles on a seemingly unrelated variable - winter weather in the Dallas area. Our findings revealed a rather unexpected and, some might say, flaky connection.

The correlation coefficient of 0.8590713 and p < 0.01 for the years 2009 to 2022 suggested a strong and statistically significant association between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles! While the exact mechanisms behind this correlation remain elusive, one could say the data just needed a little bit of a chill to reveal this frosty relationship. This research not only sheds light on a peculiar link but also reminds us of the cold, hard truth that statistical relationships can sometimes be as unpredictable as the weather.

[[INTRDUCTION]]
The relationship between seemingly unrelated variables has long been a subject of fascination and intrigue in the field of research. As the saying goes, "correlation does not imply causation" – but what if it does, in a rather unexpected way? In a world filled with data, patterns, and surprises, it is not uncommon to stumble upon correlations that seem to defy logic. Such is the case with the connection between the provocative nature of Tom Scott's YouTube video titles and the annual snowfall in Dallas, Texas.
When it comes to exploring unexpected correlations, it's important to approach the topic with an open mind – after all, sometimes the most impactful discoveries are, quite literally, hidden in the snow. With this in mind, we embarked on a journey to investigate the extent to which Tom Scott's click-worthy titles may influence the amount of snowfall in the Dallas area. However, as the old adage goes, the devil is in the details – or in this case, the snowflakes.
The idea that the provocative nature of YouTube video titles could have any bearing on the weather may seem far-fetched, if not downright flaky. However, as researchers, it's important to remember that every snowflake is unique, just like every correlation we uncover. As the data began to accumulate, it became increasingly clear that there might be more to this snowy tale than meets the eye.
In the world of academia, it's not uncommon to encounter unexpected relationships, much like stumbling upon a patch of black ice on a sunny day – it may catch you off guard, but it certainly makes for an interesting journey. Speaking of unexpected relationships, have you heard about the snowman who fell in love with a furnace? It was a case of a frosty reception!
As we delve into the findings of our study, it's important to approach the data with a healthy dose of skepticism and a willingness to entertain alternative explanations. After all, just as no two snowflakes are exactly alike, no two research findings are entirely identical. This study sets out to unravel the mysterious intertwining of click-worthy YouTube titles and snowfall in Dallas, shedding light on a correlation that is as intriguing as it is improbable. Let's not let this chilly connection slip through our fingers – after all, a good discovery is as rare as a February heatwave!

[[RESULTS]]
The analysis of the data collected from Tom Scott's YouTube video titles and the snowfall in Dallas for the period 2009 to 2022 revealed a remarkably strong correlation coefficient of 0.8590713. This correlation implies that there is a robust relationship between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas, Texas. It seems that the snow in Dallas is not the only thing piling up – Tom Scott's provocative titles are also accumulating quite the following! This unexpected correlation certainly snowballed into a noteworthy finding.
Furthermore, the coefficient of determination (r-squared) was calculated to be 0.7380035, indicating that approximately 73.8% of the variability in snowfall in Dallas can be explained by the level of provocativeness in Tom Scott's YouTube video titles. Talk about a snowstorm of influence! It appears that Tom Scott's catchy titles may have more impact than one might have initially thought. Perhaps we should start calling him "Snow" Scott!
Moreover, the statistical significance of this association was supported by a p-value of less than 0.01. This suggests that the observed correlation is unlikely to have occurred purely by chance and is indeed a real and significant relationship. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles!
Fig. 1 illustrates the strong positive correlation between the provocative nature of Tom Scott's YouTube video titles and the annual snowfall in Dallas. The scatterplot portrays a clear and compelling relationship, further reinforcing the statistical findings of our study. It appears that Tom Scott's titles have the power to snowball into a significant influence on the weather patterns in Dallas.
In summary, our research has uncovered a surprising and robust correlation between the level of provocativeness in Tom Scott's YouTube video titles and the amount of snowfall in Dallas. This unexpected connection serves as a reminder that in the vast landscape of data, one should always keep an open mind and be prepared to embrace the unexpected – much like encountering a sudden snow flurry in the midst of spring. This study not only sheds light on a peculiar link but also serves as a lighthearted reminder that statistical relationships can be as unpredictable as, well, the weather.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has brought to light a striking and unexpected correlation between the level of provocativeness in Tom Scott's YouTube video titles and the annual snowfall in Dallas. It seems that Tom Scott's titles have "snow" much influence!

The statistically significant association we uncovered reinforces the notion that correlations, no matter how surprising, warrant attention and further exploration. As the saying goes, "every snowflake is unique," and so too are the unexpected relationships we encounter in the world of data analysis. Speaking of unique snowflakes, have you heard about the one that refused to melt? It had a real "flake" identity crisis!

While the exact mechanisms behind this correlation remain a subject for future investigation, one cannot help but marvel at the curious nature of statistical relationships. Much like a snowball gaining momentum down a hill, our findings have gathered quite the accumulation of interest. This correlation may have just "blown" the lid off conventional thinking!

Additionally, our results underscore the importance of approaching data with an open mind and a willingness to entertain unconventional hypotheses. As researchers, it's crucial to remember that the most groundbreaking discoveries often emerge from the most unexpected sources, much like finding a frozen chicken in the snow – a true case of "fowl" play!

Given the robustness and significance of the revealed correlation, it is evident that no more research is needed in this area. The findings of our study provide a whimsical yet thought-provoking glimpse into the interconnectedness of seemingly unrelated phenomena. It's time to "chill" out on further investigations, knowing that this peculiar connection between provocative YouTube titles and snowfall in Dallas has been thoroughly uncovered.


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 Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Clickbait 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 Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Internet Influences and Environmental Eccentricities


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 Snow Much Clicking: The Provocative Power of Tom Scott's YouTube Titles on Winter Weather in Dallas with an abstract of This study examines the relationship between the provocative nature of Tom Scott's YouTube video titles and snowfall in Dallas, Texas. By using data from AI analysis of YouTube video titles and the NOAA National Climate Data Center, we sought to explore the impact of Tom Scott's click-worthy titles on a seemingly unrelated variable - winter weather in the Dallas area. Our findings revealed a rather unexpected and, some might say, flaky connection.
The correlation coefficient of 0.8590713 and p < 0.01 for the years 2009 to 2022 suggested a strong and statistically significant association between the level of provocativeness in Tom Scott's video titles and the amount of snowfall in Dallas. It seems that the snowflakes in Dallas aren't the only ones falling for those catchy titles! While the exact mechanisms behind this correlation remain elusive, one could say the data just needed a little bit of a chill to reveal this frosty relationship. This research not only sheds light on a peculiar link but also reminds us of the cold, hard truth that statistical relationships can sometimes be as unpredictable as the weather.

ChatGPT:

Tom Scott, YouTube titles, snowfall, Dallas, Texas, AI analysis, NOAA National Climate Data Center, correlation coefficient, winter weather, provocative titles, snowfall correlation, catchy titles, statistical significance, weather unpredictability

*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 provocative Tom Scott's YouTube video titles are
Detailed data title: How provocative Tom Scott YouTube video titles are, as rated by an AI.
Source: AI analysis of Tom Scott's 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 provocative Tom Scott's YouTube video titles are

Snowfall in Dallas
Detailed data title: Total Annual Snowfall at DALLAS FAA AIRPORT, TX US
Source: NOAA National Climate Data Center
See what else correlates with Snowfall in Dallas

Correlation r = 0.8590713 (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 = 0.7380035 (Coefficient of determination)
This means 73.8% of the change in the one variable (i.e., Snowfall in Dallas) is predictable based on the change in the other (i.e., How provocative Tom Scott's YouTube video titles are) over the 14 years from 2009 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.3E-5. 0.0000829061504738711400000000
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 0.86 in 0.0083% of random cases. Said differently, if you correlated 12,062 random variables Which I absolutely did.
with the same 13 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 13 because we have two variables measured over a period of 14 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.

[ 0.6, 0.95 ] 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.
20092010201120122013201420152016201720182019202020212022
How provocative Tom Scott's YouTube video titles are (Provacative score)4.10535.5543.78264.02783.83333.55423.52383.84383.69493.754.58824.3269
Snowfall in Dallas (Inches of snow)2.7116.522.30.86.100.20005.31.5




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. 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([4.1053,5.5,5,4,3.7826,4.0278,3.8333,3.5542,3.5238,3.8438,3.6949,3.75,4.5882,4.3269,])
array_2 = np.array([2.7,11,6.5,2,2.3,0.8,6.1,0,0.2,0,0,0,5.3,1.5,])
array_1_name = "How provocative Tom Scott's YouTube video titles are"
array_2_name = "Snowfall in Dallas"

# 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?

You're the correlation whisperer we needed!


Correlation ID: 5569 · Black Variable ID: 25462 · Red Variable ID: 25256
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0