Cull
SAMPLING (Advanced)
Loading audio…
Press play to listen along. The line being read lights up as you go.
Show full transcript
Loading transcript…
The afternoon the club announced what the whole town thinks, Cull was the only one who asked which doors they'd actually knocked on.
She was a starling, small and glossy, feathers flecked with a hundred points of light, a cloth scoop folded over one wing. The club had knocked on the six houses nearest the schoolhouse and come back certain: the town wants a new football pitch — six houses, all in favor. "Before the answer," Cull said, laying the scoop on the table, "the frame: the list of who could have been asked. Yours was six houses in a row beside the school." She turned the scoop over. "Every one of them a family with school-age children close enough to walk. That's not the town — that's the town's football corner. The frame decided the finding before a single door opened."
She named the fault plainly, the way the academy had taught her. "This is a convenience sample — you asked whoever was easiest, and easy is never neutral. The bakers, the elders up the hill, the market families across the river were never on the list, so they couldn't have swung it however they felt. When a whole group is shut out of the frame, that's selection bias: the number leans not because the town leans but because the asking leaned." She smoothed the cloth. "A bigger convenience sample doesn't fix it. Knock on sixty football-corner doors instead of six and you'll only be more confidently wrong."
Cull had learned it in the reedbeds long before she had the words. Her flock roosted tens of thousands strong, and her grandmother ran the granary where foragers pooled their seed. "Taste the store and tell me if it's good," her grandmother had said, pushing over the little scoop. Cull dipped the near edge and reported it sweet. Her grandmother laughed, not unkindly. "You tasted where the barley settles. Now the middle. Now the far corner, where the foragers dump what they gathered last." The far corner was thick with bitter darnel. "One scoop from one place tells you about that place," her grandmother said. "If you want the store, you take a little from everywhere and mix it in your hand — and you make sure no corner is too far to reach." Years later Cull would put it in the academy's language: a sample earns the right to stand for the whole only when every part of the whole had a genuine chance of ending up in it. That chance was the whole game.
At her own workshop bench Cull kept two bowls to teach the difference. Into the first she'd let students scoop from wherever they liked; it always came up whatever-was-on-top. Into the second she'd have them draw from near, middle, and far, turning the bowl between pinches so no region was favored. "The fair one isn't more work for its own sake," she'd say. "It's the difference between a handful that mirrors the bowl and one that merely came from it." A badger cub named Ferrow once brought her a poll: the river's too cold for swimming — everyone agrees. "Who'd you ask?" Cull said. "The kids on the bank at noon." Cull tilted her head. "The kids on the bank — not in the water. The ones who feel the cold most were the only ones standing around to be asked; the ones happily swimming never stopped to answer. Your frame excluded exactly the group that would have disagreed." Ferrow's ears drooped. "So it's ruined?" "Not ruined — narrow, and now you know its edge. Draw your next handful from everywhere the question lives: some in the water, some on the bank, some at different hours. Then the answer is about the river, not about the one cold spot you were standing in."
Ferrow went and asked the otters mid-stream, and the swimmers at dawn, and the shivering ones at dusk, and came back with a mixed poll — some cold, some fine, some who never left the water — truer for the walking it cost him. "It was more effort," he admitted. "It feels solid, though." "That's the feeling of a fair frame," Cull said. "You stopped letting the loudest, nearest corner speak for the whole." She tapped his fairer handful. "Now no one who reads this will think the town said something the town was never asked."
She tucked the scoop back under her wing, and something in her chest settled, glossy and calm — the quiet of a handful that could stand for the whole and not flinch. Over the reedbeds the great flock would turn at dusk, tens of thousands of small lights folding through the sky, and Cull felt loose and unhurried, glad she'd learned young that the honest question is never only what did they answer but who was ever given the chance to.
Hear it as an audio drama
A short play starring Cull, from DataForge. Different voices, same idea. Listen any time after you read.
Loading audio…
Read the drama script
- Narrator: From Spark and Anvil and DataForge — this is Cull, in chapter 1 of the DataForge cast.
- Narrator: This drama uses an AI-generated voice. Voiced via Gemini 2.5.
- Narrator: This story covers data, fairness, and bias. Parents may want to listen first.
- Narrator: Cull is a starling-tween, small and glossy, her feathers flecked with a hundred points of light, a cloth grain-scoop folded over one wing.
- Narrator: The club has knocked on the six houses nearest the schoolhouse and come back certain: the town wants a new football pitch.
- Cull: Six houses — but before the answer, the frame. The frame is the list of who could have been asked. Yours was six houses in a row beside the school.
- Cull: All of them families with school-age children close enough to walk. That's not the town. That's the town's football corner.
- Cull: When a whole group is shut out of the frame, that's selection bias. The number leans not because the town leans, but because the asking leaned.
- Narrator: Cull learned it in the reedbeds, where her grandmother ran the granary.
- Cull: She told me to taste the store. I scooped the near edge and said it was sweet. She laughed — I'd tasted only where the barley settles.
- Cull: Scoop the middle, she said, and the far corner too. The far corner was full of bitter darnel. One scoop from one place only tells you about that place.
- Cull: A sample earns the right to stand for the whole only when every part had a real chance of ending up in it.
- Narrator: A badger cub once brought her a poll — the river's too cold for swimming, everyone agrees.
- Cull: You asked the children on the bank, not the ones in the water. The ones who feel the cold most were the only ones standing about to be asked.
- Cull: A bigger convenience sample doesn't fix it — knock on sixty football-corner doors and you're only more confidently wrong. Draw from everywhere the question lives.
- Cull: The honest question is never only what did they answer, but who was ever given the chance to.
- Narrator: You've been listening to a Spark and Anvil chapter, written by the Spark and Anvil writing team for ages 9 to 14.
- Narrator: Apps stay free forever.
- Narrator: Curriculum aligned to Computer Science Teachers Association and statistics standards.
- Narrator: If anything in this story brought up big feelings, talking to a trusted adult helps. You can also reach support lines anytime.
- Narrator: Released under Creative Commons BY-NC-SA 4.0 for educational reuse. Visit Spark and Anvil for the full transcript.
The DataForge ensemble
Cull is one of the friends in DataForge. Each friend shows you one idea by how they act; meet them all and you have the whole subject.
-
Catch
Data collection — who-what-why-when posture (every dataset has a collector + purpose + omissions)
-
Tidy
Data cleaning — preparation-with-integrity posture (every cleaning choice changes meaning; document the choices)
-
Graph
Data visualization — shape-of-the-story posture (which chart tells the truth, not the loudest one)
-
Tell
Interpretation — correlation-not-causation posture (data shows patterns; humans interpret; confidence not certainty)
-
Guard
Data ethics — bias-privacy-harm-consent posture (who benefits, who's harmed, who decided; structurally present in every kit from kit 6)
-
Crux
Summary — honest-middle posture (which middle tells the truth: mean, median, or mode; one giant value drags the average away from where most of the crowd actually sits)
-
Ladle
Rates & fair comparison — like-for-like posture (compare rates and fair portions, not raw totals; a bigger pot isn't a bigger share)
-
Stray
Reading the outlier — the-one-that-doesn't-fit posture (an outlier is a question to ask, not noise to delete; find out why before you drop it)
-
Waver
Uncertainty & margin — confidence-not-certainty posture (every estimate carries a margin of error; show the wobble honestly instead of hiding it)