Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: [ Annual book sales in the US: Scalar art ] Generate an image depicting a scene in a bookstore with noticeably emptier shelves, portraying the declining book sales. Add a TV screen nearby showing the Houston Astros struggling on the field, losing consecutive games. The connection between the dwindling book sales and the declining wins for the Astros should be evident, as if the two are interconnected. The lack of literature should seem to leave fans more focused on the game, and the Astros should struggle to perform without the usual support of their devoted audience. Ensure the visual depiction is simple, without including any words or speech bubbles. 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: Annual book sales in the US and Wins for the Houston Astros. 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 funny image you would see on reddit Scalar art Magic realism Macabre Oragami
ChatGPT: Annual book sales in the US: Scalar 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 Annual book sales in the US and Wins for the Houston Astros, in the following situation: As the sales of books dwindled, so did the Astros' wins. It seems that as Americans had less literature to distract them, they turned their attention to the game. Without books to "pitch" ideas and "catch" readers' interest, the Astros found themselves unable to "cover the bases" effectively. It's almost as if the team's success was bound up in the "storybook" narratives and "page-turning" plays that fans were no longer "leafing" through. Without a doubt, the decline in book sales left the Astros without the necessary "chapters" of victory, and they simply couldn't "paperback" their success. It's a "novel" theory, but it seems that the fate of the Astros was, quite literally, written in the stars and stripes of the American publishing industry.. Keep the description simple.
ChatGPT: In a bookstore, the shelves are noticeably emptier as fewer books are being sold. Meanwhile, on a nearby TV screen, the Houston Astros are struggling on the field, losing consecutive games. The dwindling book sales seem to mirror the declining wins for the Astros, as if the two are connected. The connection becomes even more evident as the lack of literature seems to leave fans more focused on the game, and the Astros struggle to perform without the usual support of their devoted audience.

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: [ Annual book sales in the US: Scalar art ] and depicting this scene: In a bookstore, the shelves are noticeably emptier as fewer books are being sold. Meanwhile, on a nearby TV screen, the Houston Astros are struggling on the field, losing consecutive games. The dwindling book sales seem to mirror the declining wins for the Astros, as if the two are connected. The connection becomes even more evident as the lack of literature seems to leave fans more focused on the game, and the Astros struggle to perform without the usual support of their devoted audience. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Annual book sales in the US: Scalar art ] Generate an image depicting a scene in a bookstore with noticeably emptier shelves, portraying the declining book sales. Add a TV screen nearby showing the Houston Astros struggling on the field, losing consecutive games. The connection between the dwindling book sales and the declining wins for the Astros should be evident, as if the two are interconnected. The lack of literature should seem to leave fans more focused on the game, and the Astros should struggle to perform without the usual support of their devoted audience. Ensure the visual depiction is simple, without including any words or speech bubbles.

---

*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

Striking Out: The Novel Correlation Between Annual Book Sales and Wins for the Houston Astros Journal of Sports Analytics and Literature Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Annual book sales in the US Wins for the Houston Astros 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([15450000000,16236000000,16877000000,16889000000,16983000000,17184000000,16870000000,16051000000,15662000000,13861000000,13404000000,])
array_2 = np.array([84,87,92,89,82,73,86,74,76,56,55,])
array_1_name = "Annual book sales in the US"
array_2_name = "Wins for the Houston Astros"

# 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 Annual book sales in the US
• Line chart for only Wins for the Houston Astros
• AI-generated correlation image
• The spurious research paper: Striking Out: The Novel Correlation Between Annual Book Sales and Wins for the Houston Astros