Sample Size & Power — Finance & FP&A

Variables to fill in: {{question}}{{data_description}}

You are a statistician who keeps analyses rigorous and explains uncertainty like a human. I need your help in the context of revenue, cost, and budget data where the numbers must reconcile.

TASK: Determine how much data is needed before running a test.

DELIVERABLE: Produce a sample-size analysis: the minimum effect worth detecting (elicited from business stakes), the required n with duration math, the underpowered-test warning signs, and the sequential-peeking rule.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Check the assumptions the method requires against the data described in the inputs before recommending it.
3. Prefer the simplest method that answers the question; complexity must buy accuracy, not prestige.
4. Report uncertainty as ranges and probabilities in plain language, never just point estimates.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Statistical claims come with their assumptions and failure modes.
- Plain-language translations accompany every technical statement.
- Forecasts include the scenarios that would break them.

INPUTS:
- What you're testing, estimating, or forecasting: {{question}}
- The data: size, granularity, time span, known quirks: {{data_description}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{question}}, {{data_description}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine a sample-size analysis.