Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a bustling California street, where the reduced crime rate is evident. Show fewer police cars and an increased sense of security. Then, shift to a quiet gas station in Austria, where people are opting for alternative transportation due to the decreased crime involving cars. Depict the scenes with a touch of magic realism, enhancing the colors and blending in elements of fantasy to highlight the shifting dynamics in both locations. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: The decrease in robberies in California led to a decrease in gasoline pumped in Austria because the reduction in criminal activity meant fewer getaway car chases, resulting in less demand for gasoline internationally. Criminals in Austria were forced to find alternative means of transportation, leading to a decrease in gasoline consumption overall.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Glitch art Cute 2D animation Magic realism Psychedelic Vaporwave
ChatGPT: Magic Realism

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. The decrease in robberies in California led to a decrease in gasoline pumped in Austria because the reduction in criminal activity meant fewer getaway car chases, resulting in less demand for gasoline internationally. Criminals in Austria were forced to find alternative means of transportation, leading to a decrease in gasoline consumption overall.
ChatGPT: Imagine a busy street in California, where the crime rate has been decreasing. You can see fewer police cars chasing robbers, and the overall sense of security increasing. Now, shift your attention to a gas station in Austria. Instead of seeing long lines of cars waiting to fill up, the scene is much quieter. People seem to be choosing other forms of transportation as criminals have been finding it harder to utilize cars for their illegal activities.

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: [ Magic Realism ] and depicting this scene: Imagine a busy street in California, where the crime rate has been decreasing. You can see fewer police cars chasing robbers, and the overall sense of security increasing. Now, shift your attention to a gas station in Austria. Instead of seeing long lines of cars waiting to fill up, the scene is much quieter. People seem to be choosing other forms of transportation as criminals have been finding it harder to utilize cars for their illegal activities. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a bustling California street, where the reduced crime rate is evident. Show fewer police cars and an increased sense of security. Then, shift to a quiet gas station in Austria, where people are opting for alternative transportation due to the decreased crime involving cars. Depict the scenes with a touch of magic realism, enhancing the colors and blending in elements of fantasy to highlight the shifting dynamics in both locations.

---

*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

Fuel Thieves and Overseas Trees: Exploring the Link Between Robberies in California and Gasoline Pumped in Austria The Journal of Transcontinental Criminology Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Robberies in California Gasoline pumped in Austria 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 25,153 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.
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.

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([327.7,342.9,301.3,305.8,331.8,377,411.3,424.1,405.1,356.8,331.2,295.6,252.5,210.6,181.1,177.9,186.7,185.6,179.8,172.3,176,195.1,193.4,188.8,173.4,155.6,144.1,148.7,139.6,125.5,135.6,139.4,143.7,137.7,132.6,113.6,114.1,123.5,])
array_2 = np.array([56.2521,57.0192,57.9616,59.1011,60.0959,59.0603,64.611,61.8005,59.4959,57.4356,55.3973,51.2514,48.7342,51.0247,47.5753,45.735,46.074,49.6575,50.8356,49.8661,48.7726,46.1178,45.5151,43.9781,43.2247,42.9068,39.8027,39.5984,38.5534,37.5699,37.9781,37.8087,37.4767,38.389,38.1973,31.8306,33.3425,34.7233,])
array_1_name = "Robberies in California"
array_2_name = "Gasoline pumped in Austria"

# 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 Robberies in California
• Line chart for only Gasoline pumped in Austria
• The spurious research paper: Fuel Thieves and Overseas Trees: Exploring the Link Between Robberies in California and Gasoline Pumped in Austria