Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: A visual prompt for this scene could be: Create an image of a vibrant and busy New York City street with a large voting station in the forefront. People of all ages and backgrounds are seen entering the station to cast their ballots, with a sprinkling of Libertarian party posters and banners in the crowd. As the votes for the Libertarian senators rise, a comically exaggerated gasoline pump similar to those found at gas stations starts to overflow with fuel, causing a whimsical cascade of gasoline spilling onto the street. Simultaneously, a secondary scene in the background portrays the hustle and bustle of a Netherlands Antilles gas station, where attendants are seen frantically managing the sudden influx of gasoline being pumped. The juxtaposition should capture the ironic and unexpected connection between the voting outcomes in New York and the subsequent impact on gasoline activity in the Netherlands Antilles. 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 Libertarian Senators in New York and Gasoline pumped in Netherlands Antilles. 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: Parallax art a funny image you would see on reddit a funny image macro Photorealism a funny image macro
ChatGPT: a funny image macro

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 Libertarian Senators in New York and Gasoline pumped in Netherlands Antilles, in the following situation: The more Libertarian votes for Senators in New York, the more their platform of limited government resonates. This leads to a decrease in regulations on gasoline production in the US. As a result, there is an excess of gasoline, and in an unexpected turn of events, it's decided to send the surplus to the Netherlands Antilles, thus increasing the supply of gasoline pumped in the region. It's a case of political ideologies fueling transnational petrol pandemonium!. Keep the description simple.
ChatGPT: In downtown New York, a bustling voting station is filled with people casting their ballots for Libertarian senators. As the number of votes for the Libertarian senators increases, the government officials announce a reduction in regulations on gasoline production. This leads to an overflow of gasoline in the city. Meanwhile, in the Netherlands Antilles, gas stations are brimming with activity as more gasoline is being pumped due to the sudden surplus shipped from the US. The unexpected connection between Libertarian votes in New York and the increase in gasoline pumped in the Netherlands Antilles creates a unique and unexpected political and economic entanglement.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ a funny image macro ] and depicting this scene: In downtown New York, a bustling voting station is filled with people casting their ballots for Libertarian senators. As the number of votes for the Libertarian senators increases, the government officials announce a reduction in regulations on gasoline production. This leads to an overflow of gasoline in the city. Meanwhile, in the Netherlands Antilles, gas stations are brimming with activity as more gasoline is being pumped due to the sudden surplus shipped from the US. The unexpected connection between Libertarian votes in New York and the increase in gasoline pumped in the Netherlands Antilles creates a unique and unexpected political and economic entanglement. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: A visual prompt for this scene could be: Create an image of a vibrant and busy New York City street with a large voting station in the forefront. People of all ages and backgrounds are seen entering the station to cast their ballots, with a sprinkling of Libertarian party posters and banners in the crowd. As the votes for the Libertarian senators rise, a comically exaggerated gasoline pump similar to those found at gas stations starts to overflow with fuel, causing a whimsical cascade of gasoline spilling onto the street. Simultaneously, a secondary scene in the background portrays the hustle and bustle of a Netherlands Antilles gas station, where attendants are seen frantically managing the sudden influx of gasoline being pumped. The juxtaposition should capture the ironic and unexpected connection between the voting outcomes in New York and the subsequent impact on gasoline activity in the Netherlands Antilles.

---

*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.

AI academic paper

Libertarian Largesse and Gasoline Gags: A Lively Link The Journal of Political Puns and Economic Euphemisms Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Votes for Libertarian Senators in New York Gasoline pumped in Netherlands Antilles Neither / both
Issue:	What is the issue? The data is incorrect The chart isn't displaying properly There is a typo The source link is incorrect A calculation is wrong Something else
Additional details: Optional
Confirm you are a human:

Data details

Why this works

1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
2. Lack of causal connection: There is probably^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.
3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^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.
4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^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

# 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([0.199703,1.53317,0.337638,0.164794,0.0680205,0.256088,0.446663,0.909113,0.448162,0.616879,])
array_2 = np.array([2,3.5,2,2,1.91109,2.00432,2.12666,2.22014,2.02149,2.066,])
array_1_name = "Votes for Libertarian Senators in New York"
array_2_name = "Gasoline pumped in Netherlands Antilles"

# 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

• 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 Libertarian Senators in New York
• Line chart for only Gasoline pumped in Netherlands Antilles
• AI-generated correlation image
• The spurious research paper: Libertarian Largesse and Gasoline Gags: A Lively Link