Spurious correlation #4,793 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Republican Presidential candidate in New Mexico and the second variable is Biomass power generated in Taiwan. The chart goes from 1989 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 Votes for the Republican Presidential candidate in New Mexico and the second variable is Biomass power generated in Taiwan. The chart goes from 1989 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the Republican candidate's support in New Mexico grew, so did the demand for campaign materials. This led to a surge in the production of paper and cardboard, prompting Taiwan to ramp up its biomass power generation to meet the rising paper product exports. It's a classic case of political polarization igniting a fiery passion for... renewable energy? Well, at least it's keeping the political landscape green in more ways than one!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a Polaroid photo capturing a bustling factory in New Mexico. The factory is depicted as a hive of activity, with workers moving campaign posters and signs for the Republican Presidential candidate. Show stacks of freshly printed materials ready for distribution. In the background, include a subtle indication of increasing votes, perhaps through a graph or visualization. Additionally, depict a scene from Taiwan within the same Polaroid, showing billowing smoke rising from power plants working overtime to generate biomass energy, supporting the surge in paper and cardboard production. This could be depicted as a skyline with visible smoke and industrial structures. 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: Votes for the Republican Presidential candidate in New Mexico and Biomass power generated in Taiwan. 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: Brutalism Hyper-realistic Charcoal a Polaroid photo Low poly
ChatGPT: a Polaroid photo

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 Votes for the Republican Presidential candidate in New Mexico and Biomass power generated in Taiwan, in the following situation: As the Republican candidate's support in New Mexico grew, so did the demand for campaign materials. This led to a surge in the production of paper and cardboard, prompting Taiwan to ramp up its biomass power generation to meet the rising paper product exports. It's a classic case of political polarization igniting a fiery passion for... renewable energy? Well, at least it's keeping the political landscape green in more ways than one!. Keep the description simple.
ChatGPT: A bustling factory in New Mexico churns out stacks of campaign posters and signs for the Republican Presidential candidate, showing an increase in votes. In Taiwan, smoke rises from power plants as they work overtime to generate biomass energy to support the surge in paper and cardboard production.

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 Polaroid photo ] and depicting this scene: A bustling factory in New Mexico churns out stacks of campaign posters and signs for the Republican Presidential candidate, showing an increase in votes. In Taiwan, smoke rises from power plants as they work overtime to generate biomass energy to support the surge in paper and cardboard production. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a Polaroid photo capturing a bustling factory in New Mexico. The factory is depicted as a hive of activity, with workers moving campaign posters and signs for the Republican Presidential candidate. Show stacks of freshly printed materials ready for distribution. In the background, include a subtle indication of increasing votes, perhaps through a graph or visualization. Additionally, depict a scene from Taiwan within the same Polaroid, showing billowing smoke rising from power plants working overtime to generate biomass energy, supporting the surge in paper and cardboard production. This could be depicted as a skyline with visible smoke and industrial structures.

*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 Votes for the Republican Presidential candidate in New Mexico caused Biomass power generated in Taiwan to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan

The Journal of Political Ecology and Unconventional Correlations

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 Votes for the Republican Presidential candidate in New Mexico and Biomass power generated in Taiwan. 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 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]]
"The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan"

[[ABSTRACT]]
This study delves into the unexpected connection between political preferences in the American state of New Mexico and the generation of renewable energy in the Asian country of Taiwan. Leveraging data from reputable sources such as MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team has deduced a correlation coefficient of 0.9338689 and a p-value of less than 0.01 for the period spanning from 1989 to 2020. Our findings challenge conventional wisdom and shed light on the peculiar interplay between seemingly unrelated phenomena. The results not only pique curiosity but also provoke contemplation on the intricate web of global interactions. This study flags an unusual pattern that merits further investigation and prompts us to ponder the subtle ways in which distant and distinct entities may be intertwined.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In a world brimming with unexpected connections, our research embarks on a peculiar journey to unravel the perplexing relationship between votes for the Republican presidential candidate in New Mexico and the generation of biomass power in Taiwan. The intersection of political leanings and renewable energy production may seem as unlikely as finding a pineapple on a pizza, but our analysis reveals a correlation that raises eyebrows and sparks curiosity.
As researchers, we are perpetually astounded by the curious pathways through which seemingly separate entities can be linked. Much like the unanticipated friendship between a cat and a canary, the entwining of political voting patterns in the Land of Enchantment and the growth of biomass power in the heart of Asia captivates our academic intrigue.
Our journey into this curious linkage is underscored by the fundamental principle that uncovering such unexpected correlations can unveil broader insights into the global fabric of interconnections. The faint but persistent thread that we pursue challenges dogmatic assumptions and beckons us to delve deeper into the labyrinth of cross-continental relationships.
Thus, armed with statistical rigor and a penchant for uncovering the peculiar, we present our findings that transcend geographical boundaries and traditional disciplinary silos. This investigation not only showcases the interconnectedness of the world but also underscores the delightful serendipity lurking within the data.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The literature surrounding the nexus between political voting behavior in the American state of New Mexico and the production of biomass power in Taiwan is sparse, reflecting the unconventional nature of this research inquiry. Nonetheless, several notable studies provide a starting point for exploring this unexpected relationship. Smith and colleagues (2015) delve into the dynamics of renewable energy production in the Asian continent, while Doe et al. (2017) offer insights into the socio-political landscape of New Mexico. Additionally, Jones (2019) examines global interdependencies in energy generation and consumption, offering a broad perspective that may inform our investigation.

Turning to non-fiction works that are tangentially related to our topic, "The Economics of Renewable Energy" by Anderson (2018) offers a comprehensive overview of renewable energy technologies and their implications for global energy markets. Similarly, "Political Tides: The Ebb and Flow of American Elections" by Johnson (2016) lends a political lens to our analysis, exploring the intricacies of voting patterns and their broader ramifications. On a more speculative note, the science fiction novel "Biomass Wars: Galactic Energy Disputes" by Smithson (2020) captures the imagination with its portrayal of interstellar conflicts over renewable energy sources, providing a creative backdrop for contemplating the interplay between political preferences and energy generation.

In a departure from traditional academic sources, our research team ventured into unconventional territory to glean insights from an array of unexpected texts. From perusing the backs of shampoo bottles in motel bathrooms to scouring fortune cookies for hidden revelations, our quest for unconventional wisdom led us down peculiar paths. While the scholarly purists may raise eyebrows at such unconventional sources, we stand by our commitment to casting a wide net in pursuit of knowledge, even if it means swimming in the sea of quirkiness.

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 Votes for the Republican Presidential candidate in New Mexico and Biomass power generated in Taiwan. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration . You used data from 1989 to 2020

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]]
"The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan"

[[ABSTRACT]]
This study delves into the unexpected connection between political preferences in the American state of New Mexico and the generation of renewable energy in the Asian country of Taiwan. Leveraging data from reputable sources such as MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team has deduced a correlation coefficient of 0.9338689 and a p-value of less than 0.01 for the period spanning from 1989 to 2020. Our findings challenge conventional wisdom and shed light on the peculiar interplay between seemingly unrelated phenomena. The results not only pique curiosity but also provoke contemplation on the intricate web of global interactions. This study flags an unusual pattern that merits further investigation and prompts us to ponder the subtle ways in which distant and distinct entities may be intertwined.

[[INTRODUCTION]]
In a world brimming with unexpected connections, our research embarks on a peculiar journey to unravel the perplexing relationship between votes for the Republican presidential candidate in New Mexico and the generation of biomass power in Taiwan. The intersection of political leanings and renewable energy production may seem as unlikely as finding a pineapple on a pizza, but our analysis reveals a correlation that raises eyebrows and sparks curiosity.
As researchers, we are perpetually astounded by the curious pathways through which seemingly separate entities can be linked. Much like the unanticipated friendship between a cat and a canary, the entwining of political voting patterns in the Land of Enchantment and the growth of biomass power in the heart of Asia captivates our academic intrigue.
Our journey into this curious linkage is underscored by the fundamental principle that uncovering such unexpected correlations can unveil broader insights into the global fabric of interconnections. The faint but persistent thread that we pursue challenges dogmatic assumptions and beckons us to delve deeper into the labyrinth of cross-continental relationships.
Thus, armed with statistical rigor and a penchant for uncovering the peculiar, we present our findings that transcend geographical boundaries and traditional disciplinary silos. This investigation not only showcases the interconnectedness of the world but also underscores the delightful serendipity lurking within the data.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology employed in this study reflects a systematic and rigorous approach to disentangle the enigmatic relationship between Republican votes in New Mexico and biomass power generation in Taiwan. Leveraging data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team navigated the vast expanse of information to extract the relevant variables for analysis.

To establish the connection between the seemingly disparate phenomena, an unconventional approach, akin to finding a needle in a haystack, was adopted. The first step involved employing a novel algorithm that trawled through the electoral data to identify the fluctuations in Republican votes in the Land of Enchantment from 1989 to 2020. This arduous process was reminiscent of peeling an onion, layer by layer, to reveal the underlying trends.

Simultaneously, the biomass power generation data from Taiwan was gathered from reputable sources and scrutinized with the precision of a watchmaker. This involved meticulous extraction of data points and careful curation to ensure the reliability and validity of the information. The complexities of this process mirrored the intricate dance of a Rubik's cube, as each piece of the puzzle was maneuvered into place.

Having procured the datasets, a quantitative analysis, resembling the careful balancing act of a juggler, was conducted to identify patterns and trends. The correlation coefficient and p-value were calculated with the precision of a Swiss timepiece, unveiling a robust statistical relationship between Republican votes in New Mexico and biomass power generation in Taiwan. The statistical analysis was akin to deciphering a cryptic crossword, as the hidden patterns slowly emerged from the numerical labyrinth.

It is important to note that the methodology embraced a multidisciplinary approach, much like a fusion dish that marries unexpected flavors, combining insights from political science and renewable energy research. The synthesis of these divergent disciplines provided a comprehensive understanding of the interplay between political preferences and energy generation, underscoring the depth and breadth of the investigation.

The methodology employed in this study is anchored in methodological rigor, albeit with a touch of whimsy, to untangle the skein of connections between Republican votes in New Mexico and biomass power generation in Taiwan.

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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in New Mexico and Biomass power generated in Taiwan. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration .

For the time period 1989 to 2020, you found a correlation 0.9338689, r-squared of 0.8721111, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
"The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan"

[[ABSTRACT]]
This study delves into the unexpected connection between political preferences in the American state of New Mexico and the generation of renewable energy in the Asian country of Taiwan. Leveraging data from reputable sources such as MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team has deduced a correlation coefficient of 0.9338689 and a p-value of less than 0.01 for the period spanning from 1989 to 2020. Our findings challenge conventional wisdom and shed light on the peculiar interplay between seemingly unrelated phenomena. The results not only pique curiosity but also provoke contemplation on the intricate web of global interactions. This study flags an unusual pattern that merits further investigation and prompts us to ponder the subtle ways in which distant and distinct entities may be intertwined.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In a world brimming with unexpected connections, our research embarks on a peculiar journey to unravel the perplexing relationship between votes for the Republican presidential candidate in New Mexico and the generation of biomass power in Taiwan. The intersection of political leanings and renewable energy production may seem as unlikely as finding a pineapple on a pizza, but our analysis reveals a correlation that raises eyebrows and sparks curiosity.
As researchers, we are perpetually astounded by the curious pathways through which seemingly separate entities can be linked. Much like the unanticipated friendship between a cat and a canary, the entwining of political voting patterns in the Land of Enchantment and the growth of biomass power in the heart of Asia captivates our academic intrigue.
Our journey into this curious linkage is underscored by the fundamental principle that uncovering such unexpected correlations can unveil broader insights into the global fabric of interconnections. The faint but persistent thread that we pursue challenges dogmatic assumptions and beckons us to delve deeper into the labyrinth of cross-continental relationships.
Thus, armed with statistical rigor and a penchant for uncovering the peculiar, we present our findings that transcend geographical boundaries and traditional disciplinary silos. This investigation not only showcases the interconnectedness of the world but also underscores the delightful serendipity lurking within the data.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the data collected from disparate sources has illuminated a remarkable relationship between votes for the Republican presidential candidate in New Mexico and the generation of biomass power in Taiwan. Our study uncovered a strikingly high correlation coefficient of 0.9338689, indicating a robust association between these ostensibly incongruent variables. The r-squared value of 0.8721111 further underscores the strength of this relationship, suggesting that approximately 87.21% of the variability in biomass power generation in Taiwan can be explained by the votes for the Republican presidential candidate in New Mexico.

The p-value of less than 0.01 indicates that the observed correlation is statistically significant, refuting the hypothesis that this intriguing connection is merely a serendipitous alignment of data points. This finding lends credence to the notion that there exists a substantive and nonrandom association between the political preferences in New Mexico and the renewable energy landscape in Taiwan.

The evidence of this unexpected correlation extends beyond statistical analysis. Figure 1 presents a visually compelling scatterplot that displays the unmistakable linear trend between the two variables. The figure serves as a graphic testament to the surprising bond between seemingly unrelated phenomena and compels the viewer to ponder the whimsical nature of correlations that transcend geographical and cultural boundaries.

The parallels drawn between votes for the Republican presidential candidate in New Mexico and biomass power generated in Taiwan engender a sense of wonder and intrigue. This unlikely connection prompts contemplation of the idiosyncrasies that underpin global relationships and challenges the conventional boundaries of proximal causality. These findings not only broaden our understanding of the intricate web of interconnectedness but also elicit a sense of whimsy in the realm of academic inquiry.

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 Votes for the Republican Presidential candidate in New Mexico and Biomass power generated in Taiwan. 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]]
"The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan"

[[ABSTRACT]]
This study delves into the unexpected connection between political preferences in the American state of New Mexico and the generation of renewable energy in the Asian country of Taiwan. Leveraging data from reputable sources such as MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team has deduced a correlation coefficient of 0.9338689 and a p-value of less than 0.01 for the period spanning from 1989 to 2020. Our findings challenge conventional wisdom and shed light on the peculiar interplay between seemingly unrelated phenomena. The results not only pique curiosity but also provoke contemplation on the intricate web of global interactions. This study flags an unusual pattern that merits further investigation and prompts us to ponder the subtle ways in which distant and distinct entities may be intertwined.

[[LITERATURE REVIEW]]
The literature surrounding the nexus between political voting behavior in the American state of New Mexico and the production of biomass power in Taiwan is sparse, reflecting the unconventional nature of this research inquiry. Nonetheless, several notable studies provide a starting point for exploring this unexpected relationship. Smith and colleagues (2015) delve into the dynamics of renewable energy production in the Asian continent, while Doe et al. (2017) offer insights into the socio-political landscape of New Mexico. Additionally, Jones (2019) examines global interdependencies in energy generation and consumption, offering a broad perspective that may inform our investigation.
Turning to non-fiction works that are tangentially related to our topic, "The Economics of Renewable Energy" by Anderson (2018) offers a comprehensive overview of renewable energy technologies and their implications for global energy markets. Similarly, "Political Tides: The Ebb and Flow of American Elections" by Johnson (2016) lends a political lens to our analysis, exploring the intricacies of voting patterns and their broader ramifications. On a more speculative note, the science fiction novel "Biomass Wars: Galactic Energy Disputes" by Smithson (2020) captures the imagination with its portrayal of interstellar conflicts over renewable energy sources, providing a creative backdrop for contemplating the interplay between political preferences and energy generation.
In a departure from traditional academic sources, our research team ventured into unconventional territory to glean insights from an array of unexpected texts. From perusing the backs of shampoo bottles in motel bathrooms to scouring fortune cookies for hidden revelations, our quest for unconventional wisdom led us down peculiar paths. While the scholarly purists may raise eyebrows at such unconventional sources, we stand by our commitment to casting a wide net in pursuit of knowledge, even if it means swimming in the sea of quirkiness.

[[RESULTS]]
The analysis of the data collected from disparate sources has illuminated a remarkable relationship between votes for the Republican presidential candidate in New Mexico and the generation of biomass power in Taiwan. Our study uncovered a strikingly high correlation coefficient of 0.9338689, indicating a robust association between these ostensibly incongruent variables. The r-squared value of 0.8721111 further underscores the strength of this relationship, suggesting that approximately 87.21% of the variability in biomass power generation in Taiwan can be explained by the votes for the Republican presidential candidate in New Mexico.
The p-value of less than 0.01 indicates that the observed correlation is statistically significant, refuting the hypothesis that this intriguing connection is merely a serendipitous alignment of data points. This finding lends credence to the notion that there exists a substantive and nonrandom association between the political preferences in New Mexico and the renewable energy landscape in Taiwan.
The evidence of this unexpected correlation extends beyond statistical analysis. Figure 1 presents a visually compelling scatterplot that displays the unmistakable linear trend between the two variables. The figure serves as a graphic testament to the surprising bond between seemingly unrelated phenomena and compels the viewer to ponder the whimsical nature of correlations that transcend geographical and cultural boundaries.
The parallels drawn between votes for the Republican presidential candidate in New Mexico and biomass power generated in Taiwan engender a sense of wonder and intrigue. This unlikely connection prompts contemplation of the idiosyncrasies that underpin global relationships and challenges the conventional boundaries of proximal causality. These findings not only broaden our understanding of the intricate web of interconnectedness but also elicit a sense of whimsy in the realm of academic inquiry.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study support and extend the prior research that has delved into the unexpected relationship between political preferences in New Mexico and the generation of biomass power in Taiwan. Building on the sparse literature relating to this unusual connection, our results substantiate the surprising correlation coefficient of 0.9338689, aligning with the pioneering work of Smith and colleagues (2015) on renewable energy production in the Asian continent. Additionally, our findings resonate with the socio-political insights offered by Doe et al. (2017) on the landscape of New Mexico's voting behavior, reaffirming the interconnectedness between seemingly unrelated phenomena.

Moreover, our analysis corroborates the broader perspectives presented by Jones (2019) on global energy interdependencies, providing empirical evidence for the intricate web of global interactions. The statistically significant p-value of less than 0.01 challenges the conventional wisdom that this correlation is merely a serendipitous alignment of data, lending support to the comprehensive overview of renewable energy technologies offered by Anderson (2018). Furthermore, our results provoke contemplation on the subtle ways in which distant and distinct entities may be intertwined, resonating with Johnson's (2016) exploration of voting patterns and their broader ramifications.

The high correlation coefficient and r-squared value indicate a robust association, aligning with the unconventional insights gleaned from an array of unexpected texts and sources. While some may raise eyebrows at our unconventional sources, our commitment to casting a wide net in pursuit of knowledge remains steadfast, echoing the sentiment of Anderson (2018) in exploring the implications of renewable energy technologies.

In conclusion, this study has shed light on the peculiar interplay between political preferences in New Mexico and the generation of renewable energy in Taiwan. By challenging conventional wisdom and reaffirming prior research, our findings have broadened our understanding of the intricate web of interconnectedness and elicited a sense of whimsy in the realm of academic inquiry, ultimately prompting further investigation into this unexpected nexus.

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 Votes for the Republican Presidential candidate in New Mexico and Biomass power generated in Taiwan. 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]]
"The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan"

[[ABSTRACT]]
This study delves into the unexpected connection between political preferences in the American state of New Mexico and the generation of renewable energy in the Asian country of Taiwan. Leveraging data from reputable sources such as MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team has deduced a correlation coefficient of 0.9338689 and a p-value of less than 0.01 for the period spanning from 1989 to 2020. Our findings challenge conventional wisdom and shed light on the peculiar interplay between seemingly unrelated phenomena. The results not only pique curiosity but also provoke contemplation on the intricate web of global interactions. This study flags an unusual pattern that merits further investigation and prompts us to ponder the subtle ways in which distant and distinct entities may be intertwined.

[[INTRDUCTION]]
In a world brimming with unexpected connections, our research embarks on a peculiar journey to unravel the perplexing relationship between votes for the Republican presidential candidate in New Mexico and the generation of biomass power in Taiwan. The intersection of political leanings and renewable energy production may seem as unlikely as finding a pineapple on a pizza, but our analysis reveals a correlation that raises eyebrows and sparks curiosity.
As researchers, we are perpetually astounded by the curious pathways through which seemingly separate entities can be linked. Much like the unanticipated friendship between a cat and a canary, the entwining of political voting patterns in the Land of Enchantment and the growth of biomass power in the heart of Asia captivates our academic intrigue.
Our journey into this curious linkage is underscored by the fundamental principle that uncovering such unexpected correlations can unveil broader insights into the global fabric of interconnections. The faint but persistent thread that we pursue challenges dogmatic assumptions and beckons us to delve deeper into the labyrinth of cross-continental relationships.
Thus, armed with statistical rigor and a penchant for uncovering the peculiar, we present our findings that transcend geographical boundaries and traditional disciplinary silos. This investigation not only showcases the interconnectedness of the world but also underscores the delightful serendipity lurking within the data.

[[RESULTS]]
The analysis of the data collected from disparate sources has illuminated a remarkable relationship between votes for the Republican presidential candidate in New Mexico and the generation of biomass power in Taiwan. Our study uncovered a strikingly high correlation coefficient of 0.9338689, indicating a robust association between these ostensibly incongruent variables. The r-squared value of 0.8721111 further underscores the strength of this relationship, suggesting that approximately 87.21% of the variability in biomass power generation in Taiwan can be explained by the votes for the Republican presidential candidate in New Mexico.
The p-value of less than 0.01 indicates that the observed correlation is statistically significant, refuting the hypothesis that this intriguing connection is merely a serendipitous alignment of data points. This finding lends credence to the notion that there exists a substantive and nonrandom association between the political preferences in New Mexico and the renewable energy landscape in Taiwan.
The evidence of this unexpected correlation extends beyond statistical analysis. Figure 1 presents a visually compelling scatterplot that displays the unmistakable linear trend between the two variables. The figure serves as a graphic testament to the surprising bond between seemingly unrelated phenomena and compels the viewer to ponder the whimsical nature of correlations that transcend geographical and cultural boundaries.
The parallels drawn between votes for the Republican presidential candidate in New Mexico and biomass power generated in Taiwan engender a sense of wonder and intrigue. This unlikely connection prompts contemplation of the idiosyncrasies that underpin global relationships and challenges the conventional boundaries of proximal causality. These findings not only broaden our understanding of the intricate web of interconnectedness but also elicit a sense of whimsy in the realm of academic inquiry.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has shone a light on the unexpected and delightful relationship between political proclivities in the Land of Enchantment and the generation of biomass power in the heart of Asia. The robust correlation coefficient of 0.9338689 has not only raised more eyebrows than a marathon for caterpillars but has also left us grappling with the delightful absurdity of the human experience. Much like stumbling upon a unicorn in a data set, this correlation reminds us that the world is filled with whimsy and wonder, where the unlikeliest of bedfellows can find common ground.

The statistically significant p-value of less than 0.01 has reassured us that this investigation is no mere wild goose chase. The sublime dance between Republican votes in New Mexico and biomass power in Taiwan is as real as a three-dollar bill, and it beckons us to acknowledge the captivating nuances of global interconnectedness. The r-squared value of 0.8721111 further underscores the visceral nature of this relationship, defying expectations more dramatically than a penguin in a winter wonderland.

As we reflect on the intriguing bond uncovered in this study, we cannot help but marvel at the mischievous hand of fate that has orchestrated this curious pas de deux. The very idea that the political preferences in a Southwestern American state might hold sway over the renewable energy landscape in a far-flung East Asian nation would have been dismissed as preposterous as a jackalope in a boardroom meeting. Yet here we are, faced with a correlation that defies conventional wisdom and demands our rapt attention.

Ultimately, this investigation is a testament to the serendipity that lurks within the boundless realms of data analysis. However, in light of the resounding clarity of our results, we dare say that no further research is warranted in this area. The Grand Old Biomass has revealed its secrets, leaving us both enlightened and amused by the delightful caprices of statistical analysis.

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 The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Ecology and Unconventional Correlations

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 The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Geo-Political Ecology and Alternative Energy Research

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 The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan with an abstract of This study delves into the unexpected connection between political preferences in the American state of New Mexico and the generation of renewable energy in the Asian country of Taiwan. Leveraging data from reputable sources such as MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team has deduced a correlation coefficient of 0.9338689 and a p-value of less than 0.01 for the period spanning from 1989 to 2020. Our findings challenge conventional wisdom and shed light on the peculiar interplay between seemingly unrelated phenomena. The results not only pique curiosity but also provoke contemplation on the intricate web of global interactions. This study flags an unusual pattern that merits further investigation and prompts us to ponder the subtle ways in which distant and distinct entities may be intertwined.

ChatGPT:

Republican votes New Mexico, biomass power Taiwan, political preferences, renewable energy, correlation coefficient, p-value, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, global interactions, distant entities, investigation

*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

Votes for the Republican Presidential candidate in New Mexico
Detailed data title: Total votes cast for the Republican Presidential candidate in New Mexico
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Republican Presidential candidate in New Mexico

Biomass power generated in Taiwan
Detailed data title: Total biomass power generated in Taiwan in billion kWh
Source: Energy Information Administration
See what else correlates with Biomass power generated in Taiwan

Correlation r = 0.9338689 (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 = 0.8721111 (Coefficient of determination)
This means 87.2% of the change in the one variable (i.e., Biomass power generated in Taiwan) is predictable based on the change in the other (i.e., Votes for the Republican Presidential candidate in New Mexico) over the 8 years from 1989 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00069.^Show 0.0006876458621332788000000000
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 0.069% of random cases. Said differently, if you correlated 1,454 random variables^Note Which I absolutely did.
with the same 7 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 7 because we have two variables measured over a period of 8 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, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	1992	1996	2000	2004	2008	2012	2016	2020
Votes for the Republican Presidential candidate in New Mexico (Total votes)	212824	232751	286417	376930	346832	335788	319667	401894
Biomass power generated in Taiwan (Billion kWh)	0.275204	0.690862	1.79272	3.3493	3.36123	3.4192	3.60197	3.75309

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.
Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([212824,232751,286417,376930,346832,335788,319667,401894,])
array_2 = np.array([0.275204,0.690862,1.79272,3.3493,3.36123,3.4192,3.60197,3.75309,])
array_1_name = "Votes for the Republican Presidential candidate in New Mexico"
array_2_name = "Biomass power generated in Taiwan"

# 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 Votes for the Republican Presidential candidate in New Mexico
Line chart for only Biomass power generated in Taiwan
AI-generated correlation image
The spurious research paper: The Grand Old Biomass: Uncovering the Surprising Relationship Between Republican Votes in New Mexico and Biomass Power in Taiwan

View another random correlation

How fun was this correlation?

Your rating is stellar!

Correlation ID: 4793 · Black Variable ID: 26011 · Red Variable ID: 24024


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