Data Sampling Calculator

Step-by-Step Guide

1. 1Enter Population Size: Type your population size, or check Infinite Population if it's unknown or very large.
2. 2Choose a Confidence Level: Select 90%, 95%, or 99% confidence, mapped to the corresponding Z-score.
3. 3Set Margin of Error: Enter your acceptable margin of error as a percentage, from 0.1% to 20%.
4. 4Set Expected Proportion: Use the slider or number field — 50% is the safest default without prior data.
5. 5Review and Export: Check the required sample size and formula breakdown, then copy, download, or share your result.

Key Features

• ✓Live calculation with a 150ms debounced update
• ✓Infinite population mode for unknown or very large populations
• ✓Step-by-step calculation breakdown with the full formula
• ✓Confidence level comparison table (90% / 95% / 99%)
• ✓Margin of error sensitivity chart
• ✓Synchronized slider and number field for expected proportion
• ✓Sample presets for common research scenarios
• ✓Copy result, full report, and shareable link independently
• ✓Download CSV, JSON, and print-friendly report
• ✓Shareable calculation URL using query parameters
• ✓Calculation history — save and reload past results
• ✓Auto-saves your last session and restores it on return
• ✓All processing runs locally — no data leaves your browser

Pro Tips

• 💡Use 50% expected proportion when you have no prior data — it's the most conservative estimate and won't undersize your sample.
• 💡Add a buffer to your calculated sample size (commonly 10–20%) to account for incomplete responses or data quality issues.
• 💡Use finite population correction whenever your sample would represent more than about 5% of the total population — it can meaningfully reduce the required sample.
• 💡Check the confidence level comparison table before deciding — going from 95% to 99% confidence increases the sample size substantially.
• 💡Use the margin of error sensitivity chart to find the point of diminishing returns before committing to a very tight margin.

Common Mistakes to Avoid

• ✕Don't use a very optimistic expected proportion without evidence — an incorrect assumption here can undersize your sample.
• ✕Don't forget that a smaller margin of error requires a dramatically larger sample — the relationship isn't linear.
• ✕Don't apply finite population correction to a genuinely unknown or very large population — use Infinite Population mode instead.
• ✕Don't confuse sample size for surveys with sample size for comparing two groups (like A/B tests) — comparing proportions requires a different calculation.
• ✕Don't skip validating your final response count against the calculated target — a low response rate can leave your actual margin of error wider than planned.