Spurious correlation #2,261 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of statisticians in New Mexico and the second variable is Liquefied petroleum gas used in Angola. The chart goes from 2003 to 2020, 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 The number of statisticians in New Mexico and the second variable is Liquefied petroleum gas used in Angola. The chart goes from 2003 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of statisticians in New Mexico rises, so too does the accuracy of weather predictions. This leads to an unexpected uptick in demand for gas grills in the state, as residents can now confidently plan outdoor barbecues. And as we all know, the purchase of additional gas grills eventually translates to an increase in the production and export of liquefied petroleum gas used in Angola. Who would have thought that the statisticians of New Mexico hold the sizzling key to the global LPG market!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a vibrant marketplace in New Mexico, with a group of statisticians huddled together, exchanging ideas and analyzing data. The scene should showcase the bustling marketplace and the arrival of a shipment of liquefied petroleum gas from Angola. The statisticians should be engaged in conversation amidst the activity of unloading large tanks from a truck nearby. The image should emphasize the presence of statisticians in New Mexico and the import of liquefied petroleum gas from Angola. Capture the energy and diversity of the marketplace while featuring the dynamic interaction between the statisticians and the incoming shipment. 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: The number of statisticians in New Mexico and Liquefied petroleum gas used in Angola. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: An image that looks like it is a scene from a Pixar movie Photorealism Whimsical illustration A Discovery magazine cover image A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s
ChatGPT: A Discovery magazine cover image

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 The number of statisticians in New Mexico and Liquefied petroleum gas used in Angola together. Keep the description simple.
ChatGPT: In a vibrant marketplace in New Mexico, a group of statisticians huddle together, exchanging ideas and analyzing data as they work on various projects. Amidst their discussions, a shipment of liquefied petroleum gas from Angola arrives, with large tanks being unloaded from a truck nearby. The bustling scene showcases both the presence of statisticians in New Mexico and the import of liquefied petroleum gas from Angola.

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 Discovery magazine cover image ] and depicting this scene: In a vibrant marketplace in New Mexico, a group of statisticians huddle together, exchanging ideas and analyzing data as they work on various projects. Amidst their discussions, a shipment of liquefied petroleum gas from Angola arrives, with large tanks being unloaded from a truck nearby. The bustling scene showcases both the presence of statisticians in New Mexico and the import of liquefied petroleum gas from Angola. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a vibrant marketplace in New Mexico, with a group of statisticians huddled together, exchanging ideas and analyzing data. The scene should showcase the bustling marketplace and the arrival of a shipment of liquefied petroleum gas from Angola. The statisticians should be engaged in conversation amidst the activity of unloading large tanks from a truck nearby. The image should emphasize the presence of statisticians in New Mexico and the import of liquefied petroleum gas from Angola. Capture the energy and diversity of the marketplace while featuring the dynamic interaction between the statisticians and the incoming shipment.

*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 The number of statisticians in New Mexico caused Liquefied petroleum gas used in Angola to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

Statistically Significant: The Surprising Correlation Between Statisticians in New Mexico and Liquefied Petroleum Gas Use in Angola

The Journal of Unlikely Statistical Associations

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 The number of statisticians in New Mexico and Liquefied petroleum gas used in Angola. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Statistically Significant: The Surprising Correlation Between Statisticians in New Mexico and Liquefied Petroleum Gas Use in Angola

[[ABSTRACT]]
The purpose of this study was to analyze the connection between the number of statisticians in New Mexico and the utilization of liquefied petroleum gas in Angola. Through rigorous examination of data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2020, our research team uncovered a startling correlation coefficient of 0.9264599, with a p-value of less than 0.01.

The findings not only shed light on an unexpected association but also prompt reflection on the global interconnectedness of seemingly disparate factors. As our data delved into the realm of statistical analysis, we couldn't help but remark that "correlations are like jokes - they're only funny if they're statistically significant."

This study contributes not only to the fields of statistics and energy economics but also to the appreciation of serendipity in research. After all, uncovering such a correlation between New Mexico and Angola exemplifies that "sometimes, correlations can be as surprising as finding your car keys in the fridge – statistically unlikely yet undeniably significant."

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the world of statistical analysis, one often seeks to uncover relationships and connections that may not be immediately apparent. Our study delves into the intriguing correlation between the number of statisticians in New Mexico and the consumption of liquefied petroleum gas in Angola. As we embarked on this research, we couldn't help but quip that "finding a correlation is like finding money in your pocket – it's always a pleasant surprise, but it's even better when it's a significant one."
The idea that the presence of statisticians in one location could be linked to the use of liquefied petroleum gas in an entirely different geographical region may seem far-fetched at first glance. However, as we delved into the data, we were reminded of the wise words of our statistical forefathers, who famously mused that "correlation does not imply causation, but it sure does hint at it, much like a strong nudge from a persistent friend."
While the initial premise of our study may elicit a raised eyebrow or a quizzical expression, our findings have exceeded expectations. The correlation coefficient of 0.9264599 between these seemingly unrelated variables left us pondering the very nature of cosmic coincidences. We couldn't help but muse that "there's a statistically significant connection between New Mexico and Angola – it's as if the statistical gods are playing a game of connect the dots with us."
This unexpected association not only challenges conventional wisdom but also underscores the interconnectedness of global phenomena. As we navigated through the labyrinth of statistical analysis, we were struck by the realization that "correlations, much like good wine, become more potent with age – or in our case, with a larger sample size."
Our study aims to unravel the mystery behind this astonishing correlation, prompting us to embrace the serendipity that often accompanies research endeavors. After all, as we uncovered this unlikely link, we couldn't help but recall that "finding a strong correlation is like finding a four-leaf clover – statistically rare, but undeniably fortunate."

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The surprising correlation between the number of statisticians in New Mexico and the utilization of liquefied petroleum gas in Angola has sparked considerable interest in the academic community. Smith et al. (2015) first explored the potential relationship between statistical expertise and energy consumption patterns, paving the way for subsequent investigations. Doe and Jones (2018) further examined the impact of human capital in statistical analysis on global energy markets, providing valuable insights into the interconnectedness of seemingly unrelated variables.

Moving beyond the academic sphere, non-fiction works such as "Statistics for Dummies" and "The Power of Petroleum: A Global Perspective" have contributed to a broader understanding of statistical principles and energy economics. These seminal texts have offered foundational knowledge that underpins our current investigation, reminding us that "the world of statistics and energy economics is a curious mix – it's like trying to balance a seesaw with a barrel of oil on one end and a data set on the other."

Furthermore, fictional narratives such as "The Statistical Sleuth" and "The Petrochemical Paradox" have captured the imagination of readers, intertwining statistical intrigue with the complexities of global energy dynamics. While these literary works may not provide empirical evidence, they have inspired us to approach our research with a sense of adventure and a touch of whimsy, acknowledging that "sometimes, statistical analysis feels like solving a mystery novel – except the culprit is lurking in the data, not in the pages."

In our quest for unconventional insights, we ventured beyond the traditional realms of academic literature and turned to unconventional sources. Delving into the backs of shampoo bottles, we encountered an unexpected revelation: the "statistically proven formula for voluminous hair" bore a striking resemblance to the statistical models we employed in our research. This comical yet thought-provoking encounter led us to reflect on the ubiquitous nature of statistical concepts, prompting the realization that "even shampoo bottles can teach us a thing or two about correlations – after all, they're experts in 'highly significant volume.'"

In summary, the literature surrounding the correlation between statisticians in New Mexico and liquefied petroleum gas use in Angola spans a wide spectrum, encompassing rigorous academic studies, informative non-fiction works, engaging fictional narratives, and even the unlikeliest of sources. With each literary encounter, we couldn't help but be reminded that "in the world of statistics, even the most improbable connections can yield meaningful insights – much like the statistical significance we've uncovered between New Mexico and Angola."

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 The number of statisticians in New Mexico and Liquefied petroleum gas used in Angola. 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]]
Statistically Significant: The Surprising Correlation Between Statisticians in New Mexico and Liquefied Petroleum Gas Use in Angola

[[ABSTRACT]]
The purpose of this study was to analyze the connection between the number of statisticians in New Mexico and the utilization of liquefied petroleum gas in Angola. Through rigorous examination of data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2020, our research team uncovered a startling correlation coefficient of 0.9264599, with a p-value of less than 0.01.

The findings not only shed light on an unexpected association but also prompt reflection on the global interconnectedness of seemingly disparate factors. As our data delved into the realm of statistical analysis, we couldn't help but remark that "correlations are like jokes - they're only funny if they're statistically significant."

This study contributes not only to the fields of statistics and energy economics but also to the appreciation of serendipity in research. After all, uncovering such a correlation between New Mexico and Angola exemplifies that "sometimes, correlations can be as surprising as finding your car keys in the fridge – statistically unlikely yet undeniably significant."

[[LITERATURE REVIEW]]
The surprising correlation between the number of statisticians in New Mexico and the utilization of liquefied petroleum gas in Angola has sparked considerable interest in the academic community. Smith et al. (2015) first explored the potential relationship between statistical expertise and energy consumption patterns, paving the way for subsequent investigations. Doe and Jones (2018) further examined the impact of human capital in statistical analysis on global energy markets, providing valuable insights into the interconnectedness of seemingly unrelated variables.
Moving beyond the academic sphere, non-fiction works such as "Statistics for Dummies" and "The Power of Petroleum: A Global Perspective" have contributed to a broader understanding of statistical principles and energy economics. These seminal texts have offered foundational knowledge that underpins our current investigation, reminding us that "the world of statistics and energy economics is a curious mix – it's like trying to balance a seesaw with a barrel of oil on one end and a data set on the other."
Furthermore, fictional narratives such as "The Statistical Sleuth" and "The Petrochemical Paradox" have captured the imagination of readers, intertwining statistical intrigue with the complexities of global energy dynamics. While these literary works may not provide empirical evidence, they have inspired us to approach our research with a sense of adventure and a touch of whimsy, acknowledging that "sometimes, statistical analysis feels like solving a mystery novel – except the culprit is lurking in the data, not in the pages."
In our quest for unconventional insights, we ventured beyond the traditional realms of academic literature and turned to unconventional sources. Delving into the backs of shampoo bottles, we encountered an unexpected revelation: the "statistically proven formula for voluminous hair" bore a striking resemblance to the statistical models we employed in our research. This comical yet thought-provoking encounter led us to reflect on the ubiquitous nature of statistical concepts, prompting the realization that "even shampoo bottles can teach us a thing or two about correlations – after all, they're experts in 'highly significant volume.'"
In summary, the literature surrounding the correlation between statisticians in New Mexico and liquefied petroleum gas use in Angola spans a wide spectrum, encompassing rigorous academic studies, informative non-fiction works, engaging fictional narratives, and even the unlikeliest of sources. With each literary encounter, we couldn't help but be reminded that "in the world of statistics, even the most improbable connections can yield meaningful insights – much like the statistical significance we've uncovered between New Mexico and Angola."

[[RESULTS]]
The analysis of the relationship between the number of statisticians in New Mexico and the usage of liquefied petroleum gas (LPG) in Angola yielded an impressive correlation coefficient of 0.9264599. This indicates a remarkably strong positive linear relationship between the two variables. It's almost as if these seemingly unrelated factors are engaged in a statistical tango – one, two, cha-cha-cha!
Moreover, the coefficient of determination (r-squared) was calculated to be 0.8583280, signifying that approximately 85.83% of the variability in LPG usage in Angola can be explained by the number of statisticians in New Mexico. It's as if the statisticians in New Mexico are whispering statistical secrets to the LPG users in Angola, influencing their consumption patterns. Looks like someone has been spreading statistical rumors around the globe!
The p-value obtained for this correlation was less than 0.01, indicating that the observed correlation is statistically significant at the 1% level. It's like the statistical universe is telling us, "Hey, this relationship is no random fluke – it's the real deal!" Moving forward with analysis, our research team found that the data points indeed fit the regression line snugly, resembling a perfectly tailored statistical suit.
(Fig. 1), the accompanying scatterplot, visually illustrates the robust correlation between the number of statisticians in New Mexico and LPG usage in Angola. The tight cluster of data points forms a striking upward trend, akin to a statistical arrow pointing towards the connection between these two variables. It's almost as if the data itself is saying, "Look, we're not just correlation – we're causation's distant cousin."
In conclusion, the findings of this study defy conventional wisdom and highlight the unforeseen interconnectedness of global phenomena. Who would have thought that statisticians in the land of enchantment would be linked to gas consumption in Angola? It's as unexpected as finding a "mean" statistician – statistically, they're rare!
This research not only showcases the unanticipated nature of statistical relationships but also underscores the intricate fabric of our interconnected world. As our analysis came to a close, we couldn't help but reflect that statistical surprises are a bit like a good joke – you never know when they're coming, but when they do, they leave quite an impression. And this correlation between statisticians in New Mexico and LPG usage in Angola is certainly leaving its mark on the statistical landscape!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our study delved into the intriguing connection between the number of statisticians in New Mexico and the usage of liquefied petroleum gas (LPG) in Angola, and the results have left us with more than just statistical food for thought. Our findings not only corroborate previous research but also add a touch of statistical sparkle to the broader understanding of global energy dynamics.

One might initially question the plausibility of a link between these two seemingly unrelated variables, as skeptics may quip, "What do statistics in New Mexico have to do with gas consumption in Angola? It all seems as unlikely as a statistical outlier at a family reunion." However, our study supports the notion that statistical expertise, like a good punchline, can transcend geographic boundaries and impact diverse sectors.

Echoing the sentiment of Smith et al. (2015) and Doe and Jones (2018), our research reinforces the idea that human capital in statistical analysis can indeed influence energy consumption patterns on a global scale. It's as if statisticians in New Mexico are part of an elite statistical squad, wielding their data prowess to sway energy dynamics in faraway lands like some sort of statistical Avengers. Who knew that the heroes of numerical analysis had such a far-reaching influence?

The robust correlation coefficient of 0.9264599 and an r-squared value of 0.8583280 indicative of a strong linear relationship between statisticians in New Mexico and LPG usage in Angola affirm the statistical significance of this unexpected connection. It's like these two variables are engaged in a statistical waltz – gracefully dancing to the rhythm of numeric patterns with the finesse of a seasoned statistical virtuoso.

Our study not only aligns with previous academic insights but also integrates a touch of statistical humor, much like the whimsical encounters we found in unconventional sources during our literature review. It's as if statistical revelations are hiding in plain sight, waiting to be uncovered and celebrated with a statistical dad joke or two. After all, statistical correlations are not just about numbers; they can also be a source of statistical amusement, much like a well-timed pun at a mathematics convention.

Overall, our research upholds the unexpected interconnectedness of statistical phenomena and global dynamics. It's a bit like stumbling upon a statistical surprise – you never quite know what you'll find, but when you do, it's a revelation worthy of a statistical high-five. As the statistical landscape continues to unfold, we eagerly anticipate further insights and perhaps a few more unexpected statistical connections that will keep our research endeavors as surprising and delightful as uncovering a hidden joke in a mathematical equation.

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 The number of statisticians in New Mexico and Liquefied petroleum gas used in Angola. 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]]
Statistically Significant: The Surprising Correlation Between Statisticians in New Mexico and Liquefied Petroleum Gas Use in Angola

[[ABSTRACT]]
The purpose of this study was to analyze the connection between the number of statisticians in New Mexico and the utilization of liquefied petroleum gas in Angola. Through rigorous examination of data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2020, our research team uncovered a startling correlation coefficient of 0.9264599, with a p-value of less than 0.01.

The findings not only shed light on an unexpected association but also prompt reflection on the global interconnectedness of seemingly disparate factors. As our data delved into the realm of statistical analysis, we couldn't help but remark that "correlations are like jokes - they're only funny if they're statistically significant."

This study contributes not only to the fields of statistics and energy economics but also to the appreciation of serendipity in research. After all, uncovering such a correlation between New Mexico and Angola exemplifies that "sometimes, correlations can be as surprising as finding your car keys in the fridge – statistically unlikely yet undeniably significant."

[[INTRDUCTION]]
In the world of statistical analysis, one often seeks to uncover relationships and connections that may not be immediately apparent. Our study delves into the intriguing correlation between the number of statisticians in New Mexico and the consumption of liquefied petroleum gas in Angola. As we embarked on this research, we couldn't help but quip that "finding a correlation is like finding money in your pocket – it's always a pleasant surprise, but it's even better when it's a significant one."
The idea that the presence of statisticians in one location could be linked to the use of liquefied petroleum gas in an entirely different geographical region may seem far-fetched at first glance. However, as we delved into the data, we were reminded of the wise words of our statistical forefathers, who famously mused that "correlation does not imply causation, but it sure does hint at it, much like a strong nudge from a persistent friend."
While the initial premise of our study may elicit a raised eyebrow or a quizzical expression, our findings have exceeded expectations. The correlation coefficient of 0.9264599 between these seemingly unrelated variables left us pondering the very nature of cosmic coincidences. We couldn't help but muse that "there's a statistically significant connection between New Mexico and Angola – it's as if the statistical gods are playing a game of connect the dots with us."
This unexpected association not only challenges conventional wisdom but also underscores the interconnectedness of global phenomena. As we navigated through the labyrinth of statistical analysis, we were struck by the realization that "correlations, much like good wine, become more potent with age – or in our case, with a larger sample size."
Our study aims to unravel the mystery behind this astonishing correlation, prompting us to embrace the serendipity that often accompanies research endeavors. After all, as we uncovered this unlikely link, we couldn't help but recall that "finding a strong correlation is like finding a four-leaf clover – statistically rare, but undeniably fortunate."

[[RESULTS]]
The analysis of the relationship between the number of statisticians in New Mexico and the usage of liquefied petroleum gas (LPG) in Angola yielded an impressive correlation coefficient of 0.9264599. This indicates a remarkably strong positive linear relationship between the two variables. It's almost as if these seemingly unrelated factors are engaged in a statistical tango – one, two, cha-cha-cha!
Moreover, the coefficient of determination (r-squared) was calculated to be 0.8583280, signifying that approximately 85.83% of the variability in LPG usage in Angola can be explained by the number of statisticians in New Mexico. It's as if the statisticians in New Mexico are whispering statistical secrets to the LPG users in Angola, influencing their consumption patterns. Looks like someone has been spreading statistical rumors around the globe!
The p-value obtained for this correlation was less than 0.01, indicating that the observed correlation is statistically significant at the 1% level. It's like the statistical universe is telling us, "Hey, this relationship is no random fluke – it's the real deal!" Moving forward with analysis, our research team found that the data points indeed fit the regression line snugly, resembling a perfectly tailored statistical suit.
(Fig. 1), the accompanying scatterplot, visually illustrates the robust correlation between the number of statisticians in New Mexico and LPG usage in Angola. The tight cluster of data points forms a striking upward trend, akin to a statistical arrow pointing towards the connection between these two variables. It's almost as if the data itself is saying, "Look, we're not just correlation – we're causation's distant cousin."
In conclusion, the findings of this study defy conventional wisdom and highlight the unforeseen interconnectedness of global phenomena. Who would have thought that statisticians in the land of enchantment would be linked to gas consumption in Angola? It's as unexpected as finding a "mean" statistician – statistically, they're rare!
This research not only showcases the unanticipated nature of statistical relationships but also underscores the intricate fabric of our interconnected world. As our analysis came to a close, we couldn't help but reflect that statistical surprises are a bit like a good joke – you never know when they're coming, but when they do, they leave quite an impression. And this correlation between statisticians in New Mexico and LPG usage in Angola is certainly leaving its mark on the statistical landscape!

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In wrapping up our study, we have unraveled a correlation between the number of statisticians in New Mexico and the consumption of liquefied petroleum gas in Angola that is as tight as a fitted statistical suit! This connection is as unexpected as finding a "mean" statistician - statistically, they're rare!

Our findings suggest that the statisticians in New Mexico and the LPG users in Angola are engaged in a statistical tango, with whispers of statistical secrets influencing consumption patterns. It's almost as if someone has been spreading statistical rumors around the globe - talk about a global game of telephone, statistical edition!

The statistically significant correlation coefficient of 0.9264599 and a p-value of less than 0.01 have left us pondering the statistical surprises akin to a good joke - they're unexpected, leave an impression, and sometimes, they're simply unexplainable.

In conclusion, we assert that no further research in this area is needed, as this study has shed light on the surprising interconnectedness of seemingly unrelated factors. After all, sometimes correlations are as surprising as finding your car keys in the fridge - statistically unlikely, yet undeniably significant. And this correlation between statisticians in New Mexico and LPG usage in Angola is no exception!

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 Statistically Significant: The Surprising Correlation Between Statisticians in New Mexico and Liquefied Petroleum Gas Use in Angola. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unlikely Statistical Associations

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 Statistically Significant: The Surprising Correlation Between Statisticians in New Mexico and Liquefied Petroleum Gas Use in Angola. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Cross-Cultural Statistical Analysis

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 Statistically Significant: The Surprising Correlation Between Statisticians in New Mexico and Liquefied Petroleum Gas Use in Angola with an abstract of The purpose of this study was to analyze the connection between the number of statisticians in New Mexico and the utilization of liquefied petroleum gas in Angola. Through rigorous examination of data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2020, our research team uncovered a startling correlation coefficient of 0.9264599, with a p-value of less than 0.01.
The findings not only shed light on an unexpected association but also prompt reflection on the global interconnectedness of seemingly disparate factors. As our data delved into the realm of statistical analysis, we couldn't help but remark that "correlations are like jokes - they're only funny if they're statistically significant."
This study contributes not only to the fields of statistics and energy economics but also to the appreciation of serendipity in research. After all, uncovering such a correlation between New Mexico and Angola exemplifies that "sometimes, correlations can be as surprising as finding your car keys in the fridge – statistically unlikely yet undeniably significant.

ChatGPT:

New Mexico statisticians, liquefied petroleum gas Angola, correlation study, statistical analysis, Bureau of Labor Statistics, Energy Information Administration, global interconnectedness, statistical significance, energy economics, serendipity in research

*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

The number of statisticians in New Mexico
Detailed data title: BLS estimate of statisticians in New Mexico
Source: Bureau of Larbor Statistics
See what else correlates with The number of statisticians in New Mexico

Liquefied petroleum gas used in Angola
Detailed data title: Volume of liquefied petroleum gas used consumed in Angola in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Liquefied petroleum gas used in Angola

Correlation r = 0.9264599 (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 = 0.8583280 (Coefficient of determination)
This means 85.8% of the change in the one variable (i.e., Liquefied petroleum gas used in Angola) is predictable based on the change in the other (i.e., The number of statisticians in New Mexico) over the 18 years from 2003 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.41E-8.^Show 0.0000000340910470056020530000
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 0.93 in 3.41E-6% of random cases. Said differently, if you correlated 29,333,215 random variables^Note You don't actually need 29 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 17 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 17 because we have two variables measured over a period of 18 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.81, 0.97 ] 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.

	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020
The number of statisticians in New Mexico (Statisticians)	60	40	30	50	70	50	70	70	90	70	90	80	130	90	90	70	190	200
Liquefied petroleum gas used in Angola (Million Barrels/Day)	2.68667	2.84077	0.559889	3.70593	5.42415	4.6158	6.40825	5	5	8	8	7.18247	7.91342	7.50027	10.3605	11.3458	31.5266	30.1029

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.
Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.

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([60,40,30,50,70,50,70,70,90,70,90,80,130,90,90,70,190,200,])
array_2 = np.array([2.68667,2.84077,0.559889,3.70593,5.42415,4.6158,6.40825,5,5,8,8,7.18247,7.91342,7.50027,10.3605,11.3458,31.5266,30.1029,])
array_1_name = "The number of statisticians in New Mexico"
array_2_name = "Liquefied petroleum gas used in Angola"

# 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 The number of statisticians in New Mexico
Line chart for only Liquefied petroleum gas used in Angola
AI-generated correlation image
The spurious research paper: Statistically Significant: The Surprising Correlation Between Statisticians in New Mexico and Liquefied Petroleum Gas Use in Angola

View another random correlation

How fun was this correlation?

Your rating skills are top-notch!

Correlation ID: 2261 · Black Variable ID: 11787 · Red Variable ID: 24137


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