Download png, svg

AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a vibrant baseball diamond at twilight, illuminated by the glow of floodlights, with the Chicago Cubs in action on the field. Every swing of the bat by the Cubs' players causes bright, radiant sparks to trail behind the speeding baseball, creating an electrifying and visually stunning effect. In the background, a roaring crowd can be seen, adding to the dynamic atmosphere. On the opposite side of the field, the New York Mets are depicted mirroring the Cubs' movements, showcasing their determination. The scoreboard flashes with rapidly changing numbers, symbolizing the intense and exhilarating race for runs in the NL Central and East divisions. 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: Total Runs Scored by Chicago Cubs Team in National League (Central and East Division) and Runs scored by the New York Mets. 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 macro Realistic Cute cartoon A Discovery magazine cover image a funny image macro
ChatGPT: Realistic

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 Total Runs Scored by Chicago Cubs Team in National League (Central and East Division) and Runs scored by the New York Mets, in the following situation: Because the Chicago Cubs' Total Runs Scored in the NL Central and East divisions directly correlated with Runs scored by the New York Mets, as the Cubs' offense became more prolific, it created a domino effect that motivated the Mets to step up their own game. The Cubs' bats were like a symphony of hits, inspiring the Mets to compose their own runs-filled masterpiece. It was as if the Cubs were saying, "Hey Mets, watch us score," and the Mets responded with, "Challenge accepted, we'll run with it." This friendly competition resulted in a run-scoring bonanza that kept both teams on their toes, and the scoreboard operators quite busy.. Keep the description simple.
ChatGPT: Imagine a vibrant baseball diamond where the Chicago Cubs are unleashing a flurry of hits, with every swing of the bat seeming to ignite sparks. The cheers of the crowd fuel the Cubs' unstoppable momentum as they rack up runs in the NL Central and East divisions. Meanwhile, across the field, the New York Mets are mirroring their every move, determined to match the Cubs stride for stride. Each run scored by the Cubs sets off a chain reaction, fueling the Mets' determination. Both teams engage in a thrilling competition, with the scoreboard flashing numbers at a dizzying speed, symbolizing the electrifying race to score.

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: [ Realistic ] and depicting this scene: Imagine a vibrant baseball diamond where the Chicago Cubs are unleashing a flurry of hits, with every swing of the bat seeming to ignite sparks. The cheers of the crowd fuel the Cubs' unstoppable momentum as they rack up runs in the NL Central and East divisions. Meanwhile, across the field, the New York Mets are mirroring their every move, determined to match the Cubs stride for stride. Each run scored by the Cubs sets off a chain reaction, fueling the Mets' determination. Both teams engage in a thrilling competition, with the scoreboard flashing numbers at a dizzying speed, symbolizing the electrifying race to score. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a vibrant baseball diamond at twilight, illuminated by the glow of floodlights, with the Chicago Cubs in action on the field. Every swing of the bat by the Cubs' players causes bright, radiant sparks to trail behind the speeding baseball, creating an electrifying and visually stunning effect. In the background, a roaring crowd can be seen, adding to the dynamic atmosphere. On the opposite side of the field, the New York Mets are depicted mirroring the Cubs' movements, showcasing their determination. The scoreboard flashes with rapidly changing numbers, symbolizing the intense and exhilarating race for runs in the NL Central and East divisions.

---

*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

Batting Around the Numbers: A Statistical Analysis of the Relationship Between Chicago Cubs' Total Runs Scored and New York Mets' Runs Scored The Journal of Sports Analytics and Performance Metrics Jan 2024 Reminder: This paper is AI-generated. Not real!

Problem variable:	Which variable has a problem? Total Runs Scored by Chicago Cubs Team in National League (Central and East Division) Runs scored by the New York Mets 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.
4. 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

# 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([712,611,692,664,706,614,370,676,701,762,686,680,720,660,702,690,695,593,738,500,693,772,687,831,747,764,777,706,724,789,703,716,752,855,707,685,654,613,602,614,689,808,822,761,814,265,705,657,])
array_2 = np.array([646,615,587,607,593,611,348,609,575,652,695,783,823,703,683,775,640,599,672,506,657,746,777,706,853,807,642,690,642,684,722,834,804,799,671,656,718,650,619,629,683,671,735,676,791,286,636,772,])
array_1_name = "Total Runs Scored by Chicago Cubs Team in National League (Central and East Division)"
array_2_name = "Runs scored by the New York Mets"

# 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 Total Runs Scored by Chicago Cubs Team in National League (Central and East Division)
• Line chart for only Runs scored by the New York Mets
• AI-generated correlation image
• The spurious research paper: Batting Around the Numbers: A Statistical Analysis of the Relationship Between Chicago Cubs' Total Runs Scored and New York Mets' Runs Scored