Spurious correlation #2,217 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'ice bath' and the second variable is Inflation in the US. The chart goes from 2004 to 2022, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'ice bath' and the second variable is Inflation in the US. The chart goes from 2004 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As more people turned to ice baths for post-workout recovery, there was a surge in demand for ice, causing a slippery slope in the market. This led to an overall cooling effect on the economy, driving up prices for goods and services, and ultimately freezing the CPI-U in place.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image that evokes minimalism and depicts a person seated in a pristine white bathtub filled with ice, holding a smartphone displaying the Google search bar for "ice bath." In the background, show a subtle line graph charting the rise of the Consumer Price Index for Urban Consumers (CPI-U) in the United States. The overall image should exude a sense of serene simplicity amidst the juxtaposition of the person's chill and the economic data. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Google searches for 'ice bath' and Consumer Price Index for Urban Consumers (CPI-U) in the United States. 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 Vaporwave Minimalism inspired by bauhaus Sci-fi fantacy
ChatGPT: Minimalism

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Google searches for 'ice bath' and Consumer Price Index for Urban Consumers (CPI-U) in the United States together. Keep the description simple.
ChatGPT: A person sitting in a bathtub filled with ice while holding a smartphone with the Google search bar for "ice bath" open, with a line graph in the background showing the increase in the Consumer Price Index for Urban Consumers (CPI-U) in the United States.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ Minimalism ] and depicting this scene: A person sitting in a bathtub filled with ice while holding a smartphone with the Google search bar for "ice bath" open, with a line graph in the background showing the increase in the Consumer Price Index for Urban Consumers (CPI-U) in the United States. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that evokes minimalism and depicts a person seated in a pristine white bathtub filled with ice, holding a smartphone displaying the Google search bar for "ice bath." In the background, show a subtle line graph charting the rise of the Consumer Price Index for Urban Consumers (CPI-U) in the United States. The overall image should exude a sense of serene simplicity amidst the juxtaposition of the person's chill and the economic data.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in ice bath (Google searches for 'ice bath') caused Consumer Price Index for Urban Consumers (CPI-U) in the United States to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US

The Journal of Frigid Economics

Jan 2024

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

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

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Google searches for 'ice bath' and Consumer Price Index for Urban Consumers (CPI-U) in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name some cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US"

[[ABSTRACT]]
When it comes to the relationship between popular search queries and economic indicators, one might say it's all about a cold, hard correlation. In this study, we dive into the frosty depths of internet search behavior by analyzing the connection between the frequency of 'ice bath' searches and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. Our research team utilized data from Google Trends and Statista to perform a thorough investigation into this chilling phenomenon.

It's no secret that cooling off with some ice can be quite the relief, just like finding a strong correlation between 'ice bath' queries and consumer prices! The results revealed a robust correlation coefficient of 0.9730379 between 'ice bath' searches and CPI-U, with a statistically significant p-value of less than 0.01. These findings suggest a close link between the ebb and flow of individuals' interest in taking a bone-chilling plunge and the fluctuations in consumer prices over the span of 2004 to 2022.

This study sheds light on the potential implications of online search behavior on economic trends, reminding us that sometimes the coolest discoveries can come from the most unexpected places. Just like finding a frozen banana in your freezer - it's a-peeling!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The connection between online search behavior and economic indicators has become an area of interest in contemporary research, and it's no wonder why - the digital realm is as vast and mysterious as the deep ocean, and we researchers are merely trying to navigate it with our scientific sonar. Much like exploring the uncharted waters, delving into the realm of Google search queries is an adventure that can yield unexpected discoveries. It's like trying to find the wifi password at a family gathering - you never know what secrets you'll uncover!
Our study delves into the intriguing relationship between Google searches for 'ice bath' and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. We aim to examine whether there is a significant association between individuals' interest in frigid aquatic therapy and changes in consumer prices. After all, who wouldn't want to take a dip into the icy depths of internet searches and surface with some cool economic insights? Just like a penguin suited up for a swim, we're ready to take the plunge into this chilling investigation!
The allure of the 'ice bath' search term is intriguing, akin to a siren's call beckoning researchers to explore its depths. Our curiosity was piqued by the thought of discovering whether this chilly pursuit correlates with the financial temperatures of the market. It's like chasing after a snowflake in a blizzard – elusive, but oh so enticing!
As we embark on this research endeavor, it is important to recognize the potential implications of uncovering a substantial correlation between 'ice bath' queries and consumer prices. Sometimes, a seemingly innocuous search term can have deeper economic implications, much like finding a hidden ice cream bar at the back of the freezer - a delightful surprise among the frosty depths!

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their groundbreaking study, Smith and Doe (2018) explored the fascinating relationship between online search patterns and economic indicators, laying the foundation for our current investigation. The authors find a significant positive correlation between consumer search interest in winter activities and fluctuations in consumer expenditure. However, their study did not delve specifically into the association with 'ice bath' searches, leaving a gap in the understanding of this chilly phenomenon.

Speaking of chilly, did you hear about the snowman who refused to let go of his job? He was afraid of getting cold feet!

Jones et al. (2020) further expanded on this line of research by examining the impact of search queries related to cold therapies on inflation rates. Their findings indicated a potential connection between searches for ice-related treatments and changes in the Consumer Price Index. This study represents a step towards unraveling the frosty mysteries of internet search behavior and economic trends.

Now, let's splash into some non-fiction literature related to the topic at hand. In "The Ice Bath Handbook" by Winter Freeze, the author takes readers on a deep dive into the world of cold water immersion therapies and their potential effects on physical recovery and well-being. Talk about chilling out with a good book!

Here's a fictional twist along the wintry path: "Frostbite: A Tale of Consumer Prices" by Chilly McFreeze. This gripping novel follows the story of a researcher who stumbles upon a correlation between 'ice bath' searches and inflation rates, leading to an icy conspiracy that could freeze the economy.

On a lighter note, cartoons and children's shows have also touched on the subject of icy adventures and economic exploration. Who can forget the classic episode of "The Snowball Effect" in 'Economic Explorers,' where the characters navigate through a blizzard of Google search data to uncover the chilling truth about 'ice bath' queries and their impact on consumer prices? It's like a treasure hunt in the frozen tundra of economic research!

In summary, the existing literature provides a solid foundation for our investigation into the connection between 'ice bath' Google searches and Consumer Price Index for Urban Consumers (CPI-U) in the United States. However, our study aims to take a refreshing plunge into this frosty phenomenon, uncovering potential insights with a touch of humor and a sprinkle of puns. After all, a little lightheartedness can thaw even the iciest of research subjects!

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Google searches for 'ice bath' and Consumer Price Index for Urban Consumers (CPI-U) in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Google Trends and Statista . You used data from 2004 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]]
"What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US"

[[ABSTRACT]]
When it comes to the relationship between popular search queries and economic indicators, one might say it's all about a cold, hard correlation. In this study, we dive into the frosty depths of internet search behavior by analyzing the connection between the frequency of 'ice bath' searches and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. Our research team utilized data from Google Trends and Statista to perform a thorough investigation into this chilling phenomenon.

It's no secret that cooling off with some ice can be quite the relief, just like finding a strong correlation between 'ice bath' queries and consumer prices! The results revealed a robust correlation coefficient of 0.9730379 between 'ice bath' searches and CPI-U, with a statistically significant p-value of less than 0.01. These findings suggest a close link between the ebb and flow of individuals' interest in taking a bone-chilling plunge and the fluctuations in consumer prices over the span of 2004 to 2022.

This study sheds light on the potential implications of online search behavior on economic trends, reminding us that sometimes the coolest discoveries can come from the most unexpected places. Just like finding a frozen banana in your freezer - it's a-peeling!

[[INTRODUCTION]]
The connection between online search behavior and economic indicators has become an area of interest in contemporary research, and it's no wonder why - the digital realm is as vast and mysterious as the deep ocean, and we researchers are merely trying to navigate it with our scientific sonar. Much like exploring the uncharted waters, delving into the realm of Google search queries is an adventure that can yield unexpected discoveries. It's like trying to find the wifi password at a family gathering - you never know what secrets you'll uncover!
Our study delves into the intriguing relationship between Google searches for 'ice bath' and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. We aim to examine whether there is a significant association between individuals' interest in frigid aquatic therapy and changes in consumer prices. After all, who wouldn't want to take a dip into the icy depths of internet searches and surface with some cool economic insights? Just like a penguin suited up for a swim, we're ready to take the plunge into this chilling investigation!
The allure of the 'ice bath' search term is intriguing, akin to a siren's call beckoning researchers to explore its depths. Our curiosity was piqued by the thought of discovering whether this chilly pursuit correlates with the financial temperatures of the market. It's like chasing after a snowflake in a blizzard – elusive, but oh so enticing!
As we embark on this research endeavor, it is important to recognize the potential implications of uncovering a substantial correlation between 'ice bath' queries and consumer prices. Sometimes, a seemingly innocuous search term can have deeper economic implications, much like finding a hidden ice cream bar at the back of the freezer - a delightful surprise among the frosty depths!

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To investigate the connection between Google searches for 'ice bath' and the Consumer Price Index for Urban Consumers (CPI-U) in the United States, our research team embarked on a journey as exhilarating as diving into the Arctic Ocean - figuratively, of course. We waded through the icy waters of internet data, harnessing the technological buoyancy of Google Trends and the statistical life raft of Statista to stay afloat in this frozen sea of information. Much like explorers navigating uncharted territory, we charted a course through the digital waves of 2004 to 2022, seeking to uncover the hidden treasures of statistical correlation.

First, we conducted a thorough analysis of Google search trends for the term 'ice bath' using Google Trends. We dove deep into the tool's icy interface, extracting search volume data with the precision of polar bears hunting for seals. We then cleaned and processed the data, ensuring that our findings remained as crystal clear as an untouched layer of frost on a winter morning.

With the 'ice bath' search data in hand, we proceeded to examine the Consumer Price Index for Urban Consumers (CPI-U) provided by the U.S. Bureau of Labor Statistics. We navigated through the economic tides, extracting the monthly CPI-U values and transforming them into a format compatible with our statistical analyses. It was akin to navigating a statistical iceberg field, with the CPI-U values serving as our trusty compass through the ocean of economic fluctuations.

After preparing the data from both sources, we unleashed the power of statistical software to perform a rigorous analysis of the relationship between 'ice bath' searches and CPI-U values. Much like scientists conducting experiments in a frozen laboratory, we employed a variety of statistical techniques, such as time-series analysis and correlation tests, to uncover the frosty truth hidden within the data. We also utilized econometric models to control for potential confounding variables, ensuring that our findings remained as robust as a polar bear's grip on a freshly caught salmon.

In addition, we conducted a thorough sensitivity analysis to assess the stability of our results under various analytical conditions. We examined different time periods, subsets of the data, and modeling approaches to validate the consistency and reliability of our findings. It was like double-checking the ice thickness before skating on a frozen lake - ensuring that our conclusions remained rock-solid in the face of statistical scrutiny.

Finally, we performed a series of diagnostic tests to evaluate the assumptions and limitations of our statistical models, ensuring that they were as resilient as an Antarctic research station in the face of rigorous peer review. Our goal was to produce findings that would stand the test of scientific rigor, much like an ice sculpture enduring the scrutiny of a harsh winter.

Overall, our methodology combined the precision of statistical analysis with the daring spirit of Arctic exploration, allowing us to unravel the frosty mysteries of 'ice bath' searches and their connection to consumer prices. It was a journey filled with as many unexpected turns as a penguin's waddle, but in the end, we emerged with insights as refreshing as a polar plunge on a sweltering day.

Just like fishing for data in the digital sea, sometimes you have to break the ice to get to the good stuff!

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Google searches for 'ice bath' and Consumer Price Index for Urban Consumers (CPI-U) in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2004 to 2022, you found a correlation 0.9730379, r-squared of 0.9468028, 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]]
"What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US"

[[ABSTRACT]]
When it comes to the relationship between popular search queries and economic indicators, one might say it's all about a cold, hard correlation. In this study, we dive into the frosty depths of internet search behavior by analyzing the connection between the frequency of 'ice bath' searches and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. Our research team utilized data from Google Trends and Statista to perform a thorough investigation into this chilling phenomenon.

It's no secret that cooling off with some ice can be quite the relief, just like finding a strong correlation between 'ice bath' queries and consumer prices! The results revealed a robust correlation coefficient of 0.9730379 between 'ice bath' searches and CPI-U, with a statistically significant p-value of less than 0.01. These findings suggest a close link between the ebb and flow of individuals' interest in taking a bone-chilling plunge and the fluctuations in consumer prices over the span of 2004 to 2022.

This study sheds light on the potential implications of online search behavior on economic trends, reminding us that sometimes the coolest discoveries can come from the most unexpected places. Just like finding a frozen banana in your freezer - it's a-peeling!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The connection between online search behavior and economic indicators has become an area of interest in contemporary research, and it's no wonder why - the digital realm is as vast and mysterious as the deep ocean, and we researchers are merely trying to navigate it with our scientific sonar. Much like exploring the uncharted waters, delving into the realm of Google search queries is an adventure that can yield unexpected discoveries. It's like trying to find the wifi password at a family gathering - you never know what secrets you'll uncover!
Our study delves into the intriguing relationship between Google searches for 'ice bath' and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. We aim to examine whether there is a significant association between individuals' interest in frigid aquatic therapy and changes in consumer prices. After all, who wouldn't want to take a dip into the icy depths of internet searches and surface with some cool economic insights? Just like a penguin suited up for a swim, we're ready to take the plunge into this chilling investigation!
The allure of the 'ice bath' search term is intriguing, akin to a siren's call beckoning researchers to explore its depths. Our curiosity was piqued by the thought of discovering whether this chilly pursuit correlates with the financial temperatures of the market. It's like chasing after a snowflake in a blizzard – elusive, but oh so enticing!
As we embark on this research endeavor, it is important to recognize the potential implications of uncovering a substantial correlation between 'ice bath' queries and consumer prices. Sometimes, a seemingly innocuous search term can have deeper economic implications, much like finding a hidden ice cream bar at the back of the freezer - a delightful surprise among the frosty depths!

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the relationship between Google searches for 'ice bath' and the Consumer Price Index for Urban Consumers (CPI-U) in the United States yielded some rather chilling results - in a good way! The correlation coefficient of 0.9730379 indicates a strong positive association, suggesting that as the frequency of 'ice bath' searches rises, consumer prices also tend to climb. It's as if people are turning to icy remedies in response to economic fluctuations, seeking some cool relief from the heat of financial uncertainty.

Fig. 1 depicts the scatterplot showcasing the striking correlation between these two variables, clearly demonstrating a pattern reminiscent of snowflakes falling on a winter's day - beautiful and undeniably correlated. It's like a symphony of statistical significance, with each data point hitting the right note!

One might say that uncovering such a strong correlation between an unconventional search term and economic indicators is like stumbling upon a hidden gem in a pile of statistical rubble - a rare and delightful discovery that leaves you feeling as satisfied as finding a dollar bill in a coat pocket.

With an r-squared value of 0.9468028, it is apparent that a large proportion of the variability in consumer prices can be explained by the frequency of 'ice bath' searches. This robust r-squared value further solidifies the notion that there's more to this chilly search query than meets the eye. It's like discovering a hidden ice rink in the middle of summer - unexpected, but undeniably cool!

The p-value of less than 0.01 adds another layer of significance to our findings, underscoring the likelihood that the observed relationship between 'ice bath' searches and consumer prices is not due to random chance. This level of statistical significance is akin to finding a snowball in a snowstorm - it's hard to miss, and it's undeniable once you've found it!

Overall, the results of this investigation point to a compelling link between individuals' interest in 'ice bath' searches and the fluctuations in consumer prices, highlighting the potential influence of online search behavior on economic trends. It's like finding a polar bear in a snowstorm - a surprising yet fitting revelation given the frosty nature of our findings!

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Google searches for 'ice bath' and Consumer Price Index for Urban Consumers (CPI-U) in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US"

[[ABSTRACT]]
When it comes to the relationship between popular search queries and economic indicators, one might say it's all about a cold, hard correlation. In this study, we dive into the frosty depths of internet search behavior by analyzing the connection between the frequency of 'ice bath' searches and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. Our research team utilized data from Google Trends and Statista to perform a thorough investigation into this chilling phenomenon.

It's no secret that cooling off with some ice can be quite the relief, just like finding a strong correlation between 'ice bath' queries and consumer prices! The results revealed a robust correlation coefficient of 0.9730379 between 'ice bath' searches and CPI-U, with a statistically significant p-value of less than 0.01. These findings suggest a close link between the ebb and flow of individuals' interest in taking a bone-chilling plunge and the fluctuations in consumer prices over the span of 2004 to 2022.

This study sheds light on the potential implications of online search behavior on economic trends, reminding us that sometimes the coolest discoveries can come from the most unexpected places. Just like finding a frozen banana in your freezer - it's a-peeling!

[[LITERATURE REVIEW]]
In their groundbreaking study, Smith and Doe (2018) explored the fascinating relationship between online search patterns and economic indicators, laying the foundation for our current investigation. The authors find a significant positive correlation between consumer search interest in winter activities and fluctuations in consumer expenditure. However, their study did not delve specifically into the association with 'ice bath' searches, leaving a gap in the understanding of this chilly phenomenon.
Speaking of chilly, did you hear about the snowman who refused to let go of his job? He was afraid of getting cold feet!
Jones et al. (2020) further expanded on this line of research by examining the impact of search queries related to cold therapies on inflation rates. Their findings indicated a potential connection between searches for ice-related treatments and changes in the Consumer Price Index. This study represents a step towards unraveling the frosty mysteries of internet search behavior and economic trends.
Now, let's splash into some non-fiction literature related to the topic at hand. In "The Ice Bath Handbook" by Winter Freeze, the author takes readers on a deep dive into the world of cold water immersion therapies and their potential effects on physical recovery and well-being. Talk about chilling out with a good book!
Here's a fictional twist along the wintry path: "Frostbite: A Tale of Consumer Prices" by Chilly McFreeze. This gripping novel follows the story of a researcher who stumbles upon a correlation between 'ice bath' searches and inflation rates, leading to an icy conspiracy that could freeze the economy.
On a lighter note, cartoons and children's shows have also touched on the subject of icy adventures and economic exploration. Who can forget the classic episode of "The Snowball Effect" in 'Economic Explorers,' where the characters navigate through a blizzard of Google search data to uncover the chilling truth about 'ice bath' queries and their impact on consumer prices? It's like a treasure hunt in the frozen tundra of economic research!
In summary, the existing literature provides a solid foundation for our investigation into the connection between 'ice bath' Google searches and Consumer Price Index for Urban Consumers (CPI-U) in the United States. However, our study aims to take a refreshing plunge into this frosty phenomenon, uncovering potential insights with a touch of humor and a sprinkle of puns. After all, a little lightheartedness can thaw even the iciest of research subjects!

[[RESULTS]]
The analysis of the relationship between Google searches for 'ice bath' and the Consumer Price Index for Urban Consumers (CPI-U) in the United States yielded some rather chilling results - in a good way! The correlation coefficient of 0.9730379 indicates a strong positive association, suggesting that as the frequency of 'ice bath' searches rises, consumer prices also tend to climb. It's as if people are turning to icy remedies in response to economic fluctuations, seeking some cool relief from the heat of financial uncertainty.
Fig. 1 depicts the scatterplot showcasing the striking correlation between these two variables, clearly demonstrating a pattern reminiscent of snowflakes falling on a winter's day - beautiful and undeniably correlated. It's like a symphony of statistical significance, with each data point hitting the right note!
One might say that uncovering such a strong correlation between an unconventional search term and economic indicators is like stumbling upon a hidden gem in a pile of statistical rubble - a rare and delightful discovery that leaves you feeling as satisfied as finding a dollar bill in a coat pocket.
With an r-squared value of 0.9468028, it is apparent that a large proportion of the variability in consumer prices can be explained by the frequency of 'ice bath' searches. This robust r-squared value further solidifies the notion that there's more to this chilly search query than meets the eye. It's like discovering a hidden ice rink in the middle of summer - unexpected, but undeniably cool!
The p-value of less than 0.01 adds another layer of significance to our findings, underscoring the likelihood that the observed relationship between 'ice bath' searches and consumer prices is not due to random chance. This level of statistical significance is akin to finding a snowball in a snowstorm - it's hard to miss, and it's undeniable once you've found it!
Overall, the results of this investigation point to a compelling link between individuals' interest in 'ice bath' searches and the fluctuations in consumer prices, highlighting the potential influence of online search behavior on economic trends. It's like finding a polar bear in a snowstorm - a surprising yet fitting revelation given the frosty nature of our findings!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our research has plunged headfirst into the frosty waters of internet search behavior and its connection to consumer prices, and the results have left us feeling like we've stumbled upon a hidden ice-olated treasure. The incredibly strong positive correlation we found between 'ice bath' searches and the Consumer Price Index for Urban Consumers (CPI-U) in the United States supports prior research by Smith and Doe (2018) and Jones et al. (2020) while maintaining a surprising chill factor.

The significant relationship uncovered in this study is as clear as ice, and the statistical significance would make even the most seasoned statisticians shiver with delight. This correlation is no fluke - it's rock-solid, like discovering an untouched snowball in Antarctica.

Our findings underscore the potential impact of online search behavior on economic patterns, raising the question of whether individuals are turning to icy relaxation techniques in response to financial fluctuations. It's as if people are saying, "When the economy gets tough, the tough get chilling!"

The robust r-squared value further cemented our findings, demonstrating that a large proportion of the variability in consumer prices can be explained by the frequency of 'ice bath' searches. This icy intrigue goes beyond a mere statistical fluke - it's a polar bear in the snowstorm of economic indicators, impossible to ignore once uncovered.

The p-value of less than 0.01 in our analysis adds another layer of certainty to the solidity of our findings. It's like discovering a glacier in the desert - a remarkable, attention-grabbing revelation that practically screams, "This is no random chance, folks!"

As we thaw out from our arctic adventure of research, it's clear that our study has uncovered more than just a correlation - it has opened the door to a frosty realm of economic insights. Just as a good dad joke always has a twist, our findings twist and turn, revealing a connection between online search behavior and consumer prices that is as exhilarating as finding an ice cream truck at the North Pole!

Our journey into the frosty depths of 'ice bath' queries has certainly ignited a spark of curiosity, leaving us eager to explore the broader implications of internet search behavior on economic trends. After all, when it comes to uncovering unexpected connections, there's no harm in taking a plunge into the deep end of statistical analysis.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Google searches for 'ice bath' and Consumer Price Index for Urban Consumers (CPI-U) in the United States. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US"

[[ABSTRACT]]
When it comes to the relationship between popular search queries and economic indicators, one might say it's all about a cold, hard correlation. In this study, we dive into the frosty depths of internet search behavior by analyzing the connection between the frequency of 'ice bath' searches and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. Our research team utilized data from Google Trends and Statista to perform a thorough investigation into this chilling phenomenon.

It's no secret that cooling off with some ice can be quite the relief, just like finding a strong correlation between 'ice bath' queries and consumer prices! The results revealed a robust correlation coefficient of 0.9730379 between 'ice bath' searches and CPI-U, with a statistically significant p-value of less than 0.01. These findings suggest a close link between the ebb and flow of individuals' interest in taking a bone-chilling plunge and the fluctuations in consumer prices over the span of 2004 to 2022.

This study sheds light on the potential implications of online search behavior on economic trends, reminding us that sometimes the coolest discoveries can come from the most unexpected places. Just like finding a frozen banana in your freezer - it's a-peeling!

[[INTRDUCTION]]
The connection between online search behavior and economic indicators has become an area of interest in contemporary research, and it's no wonder why - the digital realm is as vast and mysterious as the deep ocean, and we researchers are merely trying to navigate it with our scientific sonar. Much like exploring the uncharted waters, delving into the realm of Google search queries is an adventure that can yield unexpected discoveries. It's like trying to find the wifi password at a family gathering - you never know what secrets you'll uncover!
Our study delves into the intriguing relationship between Google searches for 'ice bath' and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. We aim to examine whether there is a significant association between individuals' interest in frigid aquatic therapy and changes in consumer prices. After all, who wouldn't want to take a dip into the icy depths of internet searches and surface with some cool economic insights? Just like a penguin suited up for a swim, we're ready to take the plunge into this chilling investigation!
The allure of the 'ice bath' search term is intriguing, akin to a siren's call beckoning researchers to explore its depths. Our curiosity was piqued by the thought of discovering whether this chilly pursuit correlates with the financial temperatures of the market. It's like chasing after a snowflake in a blizzard – elusive, but oh so enticing!
As we embark on this research endeavor, it is important to recognize the potential implications of uncovering a substantial correlation between 'ice bath' queries and consumer prices. Sometimes, a seemingly innocuous search term can have deeper economic implications, much like finding a hidden ice cream bar at the back of the freezer - a delightful surprise among the frosty depths!

[[RESULTS]]
The analysis of the relationship between Google searches for 'ice bath' and the Consumer Price Index for Urban Consumers (CPI-U) in the United States yielded some rather chilling results - in a good way! The correlation coefficient of 0.9730379 indicates a strong positive association, suggesting that as the frequency of 'ice bath' searches rises, consumer prices also tend to climb. It's as if people are turning to icy remedies in response to economic fluctuations, seeking some cool relief from the heat of financial uncertainty.
Fig. 1 depicts the scatterplot showcasing the striking correlation between these two variables, clearly demonstrating a pattern reminiscent of snowflakes falling on a winter's day - beautiful and undeniably correlated. It's like a symphony of statistical significance, with each data point hitting the right note!
One might say that uncovering such a strong correlation between an unconventional search term and economic indicators is like stumbling upon a hidden gem in a pile of statistical rubble - a rare and delightful discovery that leaves you feeling as satisfied as finding a dollar bill in a coat pocket.
With an r-squared value of 0.9468028, it is apparent that a large proportion of the variability in consumer prices can be explained by the frequency of 'ice bath' searches. This robust r-squared value further solidifies the notion that there's more to this chilly search query than meets the eye. It's like discovering a hidden ice rink in the middle of summer - unexpected, but undeniably cool!
The p-value of less than 0.01 adds another layer of significance to our findings, underscoring the likelihood that the observed relationship between 'ice bath' searches and consumer prices is not due to random chance. This level of statistical significance is akin to finding a snowball in a snowstorm - it's hard to miss, and it's undeniable once you've found it!
Overall, the results of this investigation point to a compelling link between individuals' interest in 'ice bath' searches and the fluctuations in consumer prices, highlighting the potential influence of online search behavior on economic trends. It's like finding a polar bear in a snowstorm - a surprising yet fitting revelation given the frosty nature of our findings!

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has plunged into the frosty depths of internet search behavior and resurfaced with some chilling insights. The strong positive correlation between 'ice bath' searches and the Consumer Price Index for Urban Consumers (CPI-U) in the United States suggests that there may be more to this frigid pursuit than meets the eye. It's like finding a cool dad joke in the midst of a serious academic paper - unexpected, but undeniably refreshing!

Our findings point to a potential relationship between individuals' interest in icy remedies and the financial temperatures of the market, highlighting the intriguing influence of online search behavior on economic trends. It's akin to finding a snowman in your freezer - a reminder that sometimes the most unexpected places hold the coolest surprises.

Given the icy-cool correlation coefficient and the statistically significant p-value, it's safe to say that this study has provided some solid evidence of the association between 'ice bath' searches and consumer prices. Just like a well-chilled glass of lemonade on a hot summer day, these findings are undoubtedly refreshing.

In light of these results, it is safe to conclude that no more research is needed in this area. Attempting to further investigate this correlation would be like trying to reinvent the wheel - unnecessary and likely to leave us spinning in circles. It's time to chill out and embrace the undeniable connection between 'ice bath' searches and economic indicators. This relationship is as clear as ice, and it's time for us to thaw out any doubts and accept that it's as solid as a block of ice!

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 What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Frigid Economics

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 What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Ice Bath Economics and Trends

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 What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US with an abstract of When it comes to the relationship between popular search queries and economic indicators, one might say it's all about a cold, hard correlation. In this study, we dive into the frosty depths of internet search behavior by analyzing the connection between the frequency of 'ice bath' searches and the Consumer Price Index for Urban Consumers (CPI-U) in the United States. Our research team utilized data from Google Trends and Statista to perform a thorough investigation into this chilling phenomenon.
It's no secret that cooling off with some ice can be quite the relief, just like finding a strong correlation between 'ice bath' queries and consumer prices! The results revealed a robust correlation coefficient of 0.9730379 between 'ice bath' searches and CPI-U, with a statistically significant p-value of less than 0.01. These findings suggest a close link between the ebb and flow of individuals' interest in taking a bone-chilling plunge and the fluctuations in consumer prices over the span of 2004 to 2022.
This study sheds light on the potential implications of online search behavior on economic trends, reminding us that sometimes the coolest discoveries can come from the most unexpected places. Just like finding a frozen banana in your freezer - it's a-peeling!

ChatGPT:

"Ice bath search trends," "CPI-U correlation," "online search behavior economic indicators," "Google Trends analysis," "consumer price index correlation," "internet search behavior economic trends," "ice bath popularity and consumer prices," "Google search data analysis," "impact of search behavior on economic trends," "ice bath search frequency and CPI-U," "internet searching behavior economic research," "economic trends and search queries," "connection between search behavior and consumer prices."

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

Google searches for 'ice bath'
Detailed data title: Relative volume of Google searches for 'ice bath' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'ice bath'

Inflation in the US
Detailed data title: Consumer Price Index for Urban Consumers (CPI-U) in the United States
Source: Statista
See what else correlates with Inflation in the US

Correlation r = 0.9730379 (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 = 0.9468028 (Coefficient of determination)
This means 94.7% of the change in the one variable (i.e., Inflation in the US) is predictable based on the change in the other (i.e., Google searches for 'ice bath') over the 19 years from 2004 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.9E-12.^Show 0.0000000000028905668429449050
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.97 in 2.9E-10% of random cases. Said differently, if you correlated 345,952,906,241 random variables^Note You don't actually need 345 billion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 18 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 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.

[ 0.93, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Google searches for 'ice bath' (Rel. search volume)	8.91667	8.75	8.08333	9	9.66667	9.83333	12.25	13.6667	17.1667	17.5	19	19.9167	20.3333	20.9167	21.8333	23.5	23.75	27.0833	38.3333
Inflation in the US (CPI)	188.9	195.3	201.6	207.34	215.3	214.54	218.06	224.94	229.59	232.96	236.74	237.02	240.01	245.12	251.11	255.66	258.81	270.97	292.56

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([8.91667,8.75,8.08333,9,9.66667,9.83333,12.25,13.6667,17.1667,17.5,19,19.9167,20.3333,20.9167,21.8333,23.5,23.75,27.0833,38.3333,])
array_2 = np.array([188.9,195.3,201.6,207.34,215.3,214.54,218.06,224.94,229.59,232.96,236.74,237.02,240.01,245.12,251.11,255.66,258.81,270.97,292.56,])
array_1_name = "Google searches for 'ice bath'"
array_2_name = "Inflation in the US"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Google searches for 'ice bath'
Line chart for only Inflation in the US
AI-generated correlation image
The spurious research paper: What's the Bath on That? Exploring the Connection between 'Ice Bath' Google Searches and CPI-U in the US

View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!

Correlation ID: 2217 · Black Variable ID: 1408 · Red Variable ID: 212


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