Spurious correlation #1,414 · 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 real estate brokers in Missouri and the second variable is Liquefied petroleum gas used in Benin. The chart goes from 2003 to 2021, 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 real estate brokers in Missouri and the second variable is Liquefied petroleum gas used in Benin. The chart goes from 2003 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of real estate brokers in Missouri increases, there is a corresponding rise in the demand for stylish backyard fire pits. This trend leads to a surge in the import of liquefied petroleum gas used in Benin for a more 'lit' outdoor living experience. Remember, when it comes to real estate and LPG, it's all about keeping the market fired up!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image in the style of pop art depicting a vibrant neighborhood in Missouri. In the foreground, real estate brokers are engaging with clients and showcasing houses. In the background, a delivery truck pulls up, unloading large tanks of liquefied petroleum gas destined for homes in Benin. The colors should be bold and vibrant, with strong outlines and simplified shapes characteristic of pop art. The composition should emphasize the bustling activity and juxtaposition of real estate transactions and the delivery of gas for cooking in a distant location. 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 real estate brokers in Missouri and Liquefied petroleum gas used in Benin. 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: A scene from Skyrim Data cyber art 3D Pixar Style Pop art Cutsy graphics
ChatGPT: Pop art

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 real estate brokers in Missouri and Liquefied petroleum gas used in Benin together. Keep the description simple.
ChatGPT: In a bustling neighborhood in Missouri, there are several real estate brokers chatting and showing houses to clients. Among them, a truck pulls up delivering large tanks of liquefied petroleum gas to be used for cooking in homes all the way in Benin.

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: [ Pop art ] and depicting this scene: In a bustling neighborhood in Missouri, there are several real estate brokers chatting and showing houses to clients. Among them, a truck pulls up delivering large tanks of liquefied petroleum gas to be used for cooking in homes all the way in Benin. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image in the style of pop art depicting a vibrant neighborhood in Missouri. In the foreground, real estate brokers are engaging with clients and showcasing houses. In the background, a delivery truck pulls up, unloading large tanks of liquefied petroleum gas destined for homes in Benin. The colors should be bold and vibrant, with strong outlines and simplified shapes characteristic of pop art. The composition should emphasize the bustling activity and juxtaposition of real estate transactions and the delivery of gas for cooking in a distant location.

*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 increases in The number of real estate brokers in Missouri positively influenced Liquefied petroleum gas used in Benin. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)

Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin

Journal of Comparative Liquefied Petroleum Gas Studies

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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of real estate brokers in Missouri and Liquefied petroleum gas used in Benin. Make lots of jokes, goofy observations, and puns.

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 movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin"

[[ABSTRACT]]
This study sets out to explore the somewhat perplexing, yet intriguing, relationship between the density of real estate brokers in Missouri and the consumption of liquefied petroleum gas in Benin. With an eclectic mix of data from the Bureau of Labor Statistics and the Energy Information Administration, our research team delved into this thoroughly entertaining and slightly absurd intersection of real estate and energy markets. The correlation coefficient of 0.8598860 (p < 0.01) for the period from 2003 to 2021 suggests a surprisingly strong connection between these two seemingly unrelated variables. Our findings not only shed light on this unusual correlation but also bring a lighthearted perspective to the often serious world of economic and energy research. After all, who knew that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin?

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The curious case of the interplay between the real estate industry in Missouri and the consumption of liquefied petroleum gas (LPG) in Benin has garnered considerable attention in recent years. At first blush, one might be forgiven for dismissing this connection as nothing more than a whimsical bout of statistical happenstance. However, as researchers with a penchant for delving into the unexpected and inexplicable, we were compelled to probe deeper into this punning paradox.
The juxtaposition of the seemingly disparate domains of real estate and energy markets is not only a fascinating exercise in data analysis but also a delightful reprieve from the typically dour and unforgiving realms of economic research. After all, where else can one seamlessly segue from property values to propane volatility with such effortless panache?
As we embark on this scholarly journey, we invite our esteemed readers to suspend disbelief and embrace the whimsical nature of our investigation. For in the world of academia, as in life, there is often more to be gleaned from the quirks and idiosyncrasies than from the staid and predictable.
So, dear reader, fasten your seatbelts, because we are about to embark on a scholarly rollercoaster ride that promises not just statistical insights, but a hearty dose of levity and absurdity. After all, who would have thought that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin? Stay tuned for a journey that will leave you both scratching your head and chuckling in equal measure.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The study of the connection between the number of real estate brokers in Missouri and liquefied petroleum gas (LPG) consumption in Benin has eluded researchers for decades. Smith et al. (2010) have previously touched upon the interconnectedness of seemingly unrelated variables in economic landscapes, yet none have ventured into the peculiar pairing of real estate professionals and propane propensities with the unwavering dedication and whimsical charm exhibited in this present inquiry.

Doe and Jones (2015) conducted a rigorous analysis of energy consumption patterns in developing countries, emphasizing the role of market forces and regulatory frameworks. Despite their comprehensive evaluation, the peculiar influence of Missouri's real estate market on LPG usage in Benin appears to have evaded their scrutiny, providing yet another testament to the enigmatic nature of this correlation.

This study also draws from a variety of non-fiction sources on economics and energy, including "Economic Forces in Real Estate Markets" by Brown (2008) and "Fueling the Future: The Economics of LPG" by White (2013), both of which offer invaluable insights into the respective realms of real estate and energy. Additionally, renowned fiction works such as "The LPG Murders" by Green (1995) and "Brokers of Benin" by Black (2001) imaginatively explore themes related to the intriguing interplay between these otherwise unrelated domains.

In a similar vein, movies such as "House Hunters: LPG Edition" and "Propane, Properties, and Perplexities" have, albeit in a light-hearted manner, captured the captivating nuances of real estate dynamics and energy consumption trends, albeit in a much more dramatized fashion than the rigorous analysis presented in this paper.

The literature has provided essential foundations for understanding the complex dynamics at play, and the current study aims to build upon this knowledge with an approach that defies convention and embraces the unexpected. The authors contend that the correlation found in this study is not just statistically significant, but also delightfully absurd. After all, who would have guessed that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin?

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of real estate brokers in Missouri and Liquefied petroleum gas used in Benin. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Energy Information Administration . You used data from 2003 to 2021

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin"

[[ABSTRACT]]
This study sets out to explore the somewhat perplexing, yet intriguing, relationship between the density of real estate brokers in Missouri and the consumption of liquefied petroleum gas in Benin. With an eclectic mix of data from the Bureau of Labor Statistics and the Energy Information Administration, our research team delved into this thoroughly entertaining and slightly absurd intersection of real estate and energy markets. The correlation coefficient of 0.8598860 (p < 0.01) for the period from 2003 to 2021 suggests a surprisingly strong connection between these two seemingly unrelated variables. Our findings not only shed light on this unusual correlation but also bring a lighthearted perspective to the often serious world of economic and energy research. After all, who knew that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin?

[[INTRODUCTION]]
The curious case of the interplay between the real estate industry in Missouri and the consumption of liquefied petroleum gas (LPG) in Benin has garnered considerable attention in recent years. At first blush, one might be forgiven for dismissing this connection as nothing more than a whimsical bout of statistical happenstance. However, as researchers with a penchant for delving into the unexpected and inexplicable, we were compelled to probe deeper into this punning paradox.
The juxtaposition of the seemingly disparate domains of real estate and energy markets is not only a fascinating exercise in data analysis but also a delightful reprieve from the typically dour and unforgiving realms of economic research. After all, where else can one seamlessly segue from property values to propane volatility with such effortless panache?
As we embark on this scholarly journey, we invite our esteemed readers to suspend disbelief and embrace the whimsical nature of our investigation. For in the world of academia, as in life, there is often more to be gleaned from the quirks and idiosyncrasies than from the staid and predictable.
So, dear reader, fasten your seatbelts, because we are about to embark on a scholarly rollercoaster ride that promises not just statistical insights, but a hearty dose of levity and absurdity. After all, who would have thought that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin? Stay tuned for a journey that will leave you both scratching your head and chuckling in equal measure.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

This research employed an eclectic mix of data analysis techniques, combining traditional econometric methods with a sprinkle of whimsy and a dash of absurdity. The primary data sources included the Bureau of Labor Statistics and the Energy Information Administration, where our intrepid research team navigated the labyrinthine corridors of tabulated data to extract the requisite information.

To begin, we harnessed the power of multiple linear regression analysis to disentangle the intricate dance between the number of real estate brokers in Missouri and the consumption of liquefied petroleum gas in Benin. This technique allowed us to assess the individual and collective impact of various independent variables, all the while keeping an eye out for any mischievous outliers and confounding factors that might seek to obfuscate our findings.

Moreover, to account for potential endogeneity and omitted variable bias, we wielded instrumental variable estimation methods with the finesse of a magician pulling rabbits out of a hat. The concoction of instruments, carefully selected based on their exogeneity and relevance, served as our trusty companions in the quest for causal inference amidst the labyrinth of data points.

In addition, a battery of diagnostic tests was employed to scrutinize the robustness of our model, akin to an inquisitive detective examining clues at a crime scene. We subjected our regression to tests for multicollinearity, heteroscedasticity, and autocorrelation, ensuring that our statistical inferences remained free from the shackles of spurious relationships and erroneous assumptions.

Finally, to capture the temporal dynamics of the relationship, time series analysis was summoned forth, wielding autoregressive integrated moving average (ARIMA) modeling to parse through the temporal patterns of real estate brokerage density and LPG consumption. This approach allowed us to discern any underlying trends, seasonality, and potential shifts in the relationship over the years, uncovering the subtle rhythms of this unexpected tango between two distant economic spheres.

In sum, our methodological odyssey was marked by a spirited blend of academic rigor, methodological savvy, and a whimsical flair, akin to unraveling a riddle wrapped in a conundrum while dancing the salsa. The result is a robust analytical framework that not only dissects the statistical link between real estate brokers and LPG consumption but also does so with a touch of scholarly panache.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of real estate brokers in Missouri and Liquefied petroleum gas used in Benin. Make lots of jokes, goofy observations, and puns.

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]]
"Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin"

[[ABSTRACT]]
This study sets out to explore the somewhat perplexing, yet intriguing, relationship between the density of real estate brokers in Missouri and the consumption of liquefied petroleum gas in Benin. With an eclectic mix of data from the Bureau of Labor Statistics and the Energy Information Administration, our research team delved into this thoroughly entertaining and slightly absurd intersection of real estate and energy markets. The correlation coefficient of 0.8598860 (p < 0.01) for the period from 2003 to 2021 suggests a surprisingly strong connection between these two seemingly unrelated variables. Our findings not only shed light on this unusual correlation but also bring a lighthearted perspective to the often serious world of economic and energy research. After all, who knew that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin?

[[LITERATURE REVIEW]]
The study of the connection between the number of real estate brokers in Missouri and liquefied petroleum gas (LPG) consumption in Benin has eluded researchers for decades. Smith et al. (2010) have previously touched upon the interconnectedness of seemingly unrelated variables in economic landscapes, yet none have ventured into the peculiar pairing of real estate professionals and propane propensities with the unwavering dedication and whimsical charm exhibited in this present inquiry.
Doe and Jones (2015) conducted a rigorous analysis of energy consumption patterns in developing countries, emphasizing the role of market forces and regulatory frameworks. Despite their comprehensive evaluation, the peculiar influence of Missouri's real estate market on LPG usage in Benin appears to have evaded their scrutiny, providing yet another testament to the enigmatic nature of this correlation.
This study also draws from a variety of non-fiction sources on economics and energy, including "Economic Forces in Real Estate Markets" by Brown (2008) and "Fueling the Future: The Economics of LPG" by White (2013), both of which offer invaluable insights into the respective realms of real estate and energy. Additionally, renowned fiction works such as "The LPG Murders" by Green (1995) and "Brokers of Benin" by Black (2001) imaginatively explore themes related to the intriguing interplay between these otherwise unrelated domains.
In a similar vein, movies such as "House Hunters: LPG Edition" and "Propane, Properties, and Perplexities" have, albeit in a light-hearted manner, captured the captivating nuances of real estate dynamics and energy consumption trends, albeit in a much more dramatized fashion than the rigorous analysis presented in this paper.
The literature has provided essential foundations for understanding the complex dynamics at play, and the current study aims to build upon this knowledge with an approach that defies convention and embraces the unexpected. The authors contend that the correlation found in this study is not just statistically significant, but also delightfully absurd. After all, who would have guessed that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin?

[[RESULTS]]
The results of our investigation revealed a striking correlation between the number of real estate brokers in Missouri and the consumption of liquefied petroleum gas (LPG) in Benin. Over the period from 2003 to 2021, we found a correlation coefficient of 0.8598860, with an r-squared value of 0.7394040, and a p-value less than 0.01. These statistical measurements indicate a robust and significant relationship between these two seemingly incongruous variables.
The figure (Fig. 1) in this study depicts a scatterplot illustrating the strong correlation between the density of real estate brokers in Missouri and LPG consumption in Benin. While the figure cannot capture the full whimsy of this unexpected relationship, it nonetheless provides a visually compelling representation of the statistical findings.
In summary, our findings suggest that there may be more to the interplay between real estate markets in Missouri and energy consumption in Benin than meets the eye. This peculiar association prompts us to consider the possibility of an unexplored, perhaps even humorous, link between the dynamics of these two disparate domains. After all, who would have thought that the activities of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin? This correlation challenges traditional notions of causality and beckons us to further explore the delightful absurdities that lie within the realm of statistical analysis.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of this study have brought to the forefront the surprisingly strong and statistically significant correlation between the number of real estate brokers in Missouri and the consumption of liquefied petroleum gas (LPG) in Benin. These findings support the work of Smith et al. (2010), as well as Doe and Jones (2015), who have previously hinted at the interconnectedness of seemingly unrelated economic variables. The serendipitous link between the density of real estate brokers and LPG consumption not only challenges conventional understanding but adds a touch of humor to the often staid world of economic and energy research.

The correlation coefficient of 0.8598860, with an r-squared value of 0.7394040, and a p-value less than 0.01, indicates a robust relationship between these variables. This statistical evidence aligns with the amusing musings found in works like "The LPG Murders" by Green (1995) and "Brokers of Benin" by Black (2001), which, in a lighthearted manner, explore themes related to the enigmatic interplay between real estate and energy dynamics.

Furthermore, the figures presented in this study, particularly Fig. 1, provide a visually compelling representation of this unexpected relationship, capturing the statistical findings in an engaging manner. Although the study cannot fully capture the whimsy of this correlation, the figures serve as a reminder that research findings, even those with amusing implications, can be effectively communicated through visual means.

The correlation found in this study not only has surprising implications for economic and energy research but also adds a lighthearted touch to the scholarly discourse. As the literature review and results have shown, the interplay between real estate markets in Missouri and energy consumption in Benin is not just statistically significant, but also delightfully nonsensical. This study opens the door to exploring the delightful absurdities that exist within the realm of statistical analysis and beckons researchers to embrace the unexpected with humor and whimsy. After all, who knew that the activities of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin? This correlation challenges traditional notions of causality and encourages a more light-hearted perspective on research findings.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of real estate brokers in Missouri and Liquefied petroleum gas used in Benin. Make lots of jokes, goofy observations, and puns.

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]]
"Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin"

[[ABSTRACT]]
This study sets out to explore the somewhat perplexing, yet intriguing, relationship between the density of real estate brokers in Missouri and the consumption of liquefied petroleum gas in Benin. With an eclectic mix of data from the Bureau of Labor Statistics and the Energy Information Administration, our research team delved into this thoroughly entertaining and slightly absurd intersection of real estate and energy markets. The correlation coefficient of 0.8598860 (p < 0.01) for the period from 2003 to 2021 suggests a surprisingly strong connection between these two seemingly unrelated variables. Our findings not only shed light on this unusual correlation but also bring a lighthearted perspective to the often serious world of economic and energy research. After all, who knew that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin?

[[INTRDUCTION]]
The curious case of the interplay between the real estate industry in Missouri and the consumption of liquefied petroleum gas (LPG) in Benin has garnered considerable attention in recent years. At first blush, one might be forgiven for dismissing this connection as nothing more than a whimsical bout of statistical happenstance. However, as researchers with a penchant for delving into the unexpected and inexplicable, we were compelled to probe deeper into this punning paradox.
The juxtaposition of the seemingly disparate domains of real estate and energy markets is not only a fascinating exercise in data analysis but also a delightful reprieve from the typically dour and unforgiving realms of economic research. After all, where else can one seamlessly segue from property values to propane volatility with such effortless panache?
As we embark on this scholarly journey, we invite our esteemed readers to suspend disbelief and embrace the whimsical nature of our investigation. For in the world of academia, as in life, there is often more to be gleaned from the quirks and idiosyncrasies than from the staid and predictable.
So, dear reader, fasten your seatbelts, because we are about to embark on a scholarly rollercoaster ride that promises not just statistical insights, but a hearty dose of levity and absurdity. After all, who would have thought that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin? Stay tuned for a journey that will leave you both scratching your head and chuckling in equal measure.

[[RESULTS]]
The results of our investigation revealed a striking correlation between the number of real estate brokers in Missouri and the consumption of liquefied petroleum gas (LPG) in Benin. Over the period from 2003 to 2021, we found a correlation coefficient of 0.8598860, with an r-squared value of 0.7394040, and a p-value less than 0.01. These statistical measurements indicate a robust and significant relationship between these two seemingly incongruous variables.
The figure (Fig. 1) in this study depicts a scatterplot illustrating the strong correlation between the density of real estate brokers in Missouri and LPG consumption in Benin. While the figure cannot capture the full whimsy of this unexpected relationship, it nonetheless provides a visually compelling representation of the statistical findings.
In summary, our findings suggest that there may be more to the interplay between real estate markets in Missouri and energy consumption in Benin than meets the eye. This peculiar association prompts us to consider the possibility of an unexplored, perhaps even humorous, link between the dynamics of these two disparate domains. After all, who would have thought that the activities of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin? This correlation challenges traditional notions of causality and beckons us to further explore the delightful absurdities that lie within the realm of statistical analysis.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation has illuminated the unexpectedly strong correlation between the number of real estate brokers in Missouri and the consumption of liquefied petroleum gas (LPG) in Benin. The rather staggering correlation coefficient of 0.8598860 (p < 0.01) has left us gasping for breath, not due to any propane leaks, but from the sheer incredulity of this comical association. It seems that the real estate market in Missouri may indeed hold the key to unlocking the enigmatic patterns of LPG consumption in Benin. This probing probe into punning paradoxes has not only widened our statistical horizons but has also injected a much-needed dose of whimsy into the often staid world of economic research.

Our findings invite further contemplation on the ludicrously lucrative link between real estate brokerage and LPG demand. Who would have thought that the bustling activities of real estate brokers in Missouri could inadvertently fuel the LPG consumption in faraway Benin? It appears that the puns and paradoxes in our research are not only a product of statistical wizardry but a delightful testament to the capricious quirks of the economic landscape.

It is our scholarly duty to assert that, based on the unassailable robustness of our findings, no further research is required in this area. We can now confidently retire our investigative hats, secure in the knowledge that the gas-tly interplay between Missouri real estate brokers and LPG consumption in Benin has been thoroughly, and humorously, unraveled.

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 Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Comparative Liquefied Petroleum Gas Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Lighthearted Linguistic Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin with an abstract of This study sets out to explore the somewhat perplexing, yet intriguing, relationship between the density of real estate brokers in Missouri and the consumption of liquefied petroleum gas in Benin. With an eclectic mix of data from the Bureau of Labor Statistics and the Energy Information Administration, our research team delved into this thoroughly entertaining and slightly absurd intersection of real estate and energy markets. The correlation coefficient of 0.8598860 (p < 0.01) for the period from 2003 to 2021 suggests a surprisingly strong connection between these two seemingly unrelated variables. Our findings not only shed light on this unusual correlation but also bring a lighthearted perspective to the often serious world of economic and energy research. After all, who knew that the number of real estate brokers in Missouri could have a gas-tly impact on LPG consumption in Benin?

ChatGPT:

propane consumption, real estate brokers, Missouri, liquefied petroleum gas, Benin, correlation, Bureau of Labor Statistics, Energy Information Administration, energy markets, economic 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 real estate brokers in Missouri
Detailed data title: BLS estimate of real estate brokers in Missouri
Source: Bureau of Larbor Statistics
See what else correlates with The number of real estate brokers in Missouri

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

Correlation r = 0.8598860 (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 = 0.7394040 (Coefficient of determination)
This means 73.9% of the change in the one variable (i.e., Liquefied petroleum gas used in Benin) is predictable based on the change in the other (i.e., The number of real estate brokers in Missouri) over the 19 years from 2003 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.4E-6.^Show 0.0000023652128213701657000000
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 0.86 in 0.00024% of random cases. Said differently, if you correlated 422,795 random variables^Note You don't actually need 422 thousand 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.

[ 0.67, 0.95 ] 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	2021
The number of real estate brokers in Missouri (Real Estate Brokers)	500	540	820	710	550	450	350	290	320	340	350	430	550	780	1050	1760	1930	1870	510
Liquefied petroleum gas used in Benin (Million Barrels/Day)	0.349589	0.348634	0.286027	0.254247	0.286027	0.31694	0.286027	0.286027	0.286027	0.380328	0.317808	0.349589	0.444931	0.540274	0.540274	0.667397	0.858082	0.921644	0.635616

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([500,540,820,710,550,450,350,290,320,340,350,430,550,780,1050,1760,1930,1870,510,])
array_2 = np.array([0.349589,0.348634,0.286027,0.254247,0.286027,0.31694,0.286027,0.286027,0.286027,0.380328,0.317808,0.349589,0.444931,0.540274,0.540274,0.667397,0.858082,0.921644,0.635616,])
array_1_name = "The number of real estate brokers in Missouri"
array_2_name = "Liquefied petroleum gas used in Benin"

# 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 real estate brokers in Missouri
Line chart for only Liquefied petroleum gas used in Benin
AI-generated correlation image
The spurious research paper: Propane and Proprietary Properties: A Probing Probe into the Punning Paradox of Missouri Real Estate Brokers and Liquefied Petroleum Gas Consumption in Benin

View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!

Correlation ID: 1414 · Black Variable ID: 10537 · Red Variable ID: 24203


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