Unequal-probability Trial Count Workbench

How to use Unequal-probability Trial Count Workbench

Create one labeled yes/no trial per probability. Multiply its two possible outcomes into the running exact count distribution, then inspect all counts, cumulative probabilities and the selected at-least threshold.

1. Use the example as the schema; replace its labels and entered model assumptions.
2. Create one labeled yes/no trial per probability. Multiply its two possible outcomes into the running exact count distribution, then inspect all counts, cumulative probabilities and the selected at-least threshold.
3. Calculate, inspect the complete witnesses and limitations, then copy or download the JSON report.

Good to know

• Use 1–50 distinct labeled trials with exact decimal-string probabilities from 0 through 1 and up to six places. The atLeast integer can be 0 through trialCount+1; the latter deliberately returns zero.
• Rows represent independently occurring events with fixed supplied probabilities. Correlated events, common uncertain rates, weighted payoffs and probability estimation are outside this model. The name Poisson-binomial does not mean a Poisson approximation.
• Local calculation with no upload, input persistence or outside lookup. Model JSON is limited to 30,000 characters and 10,000 values. Decimal quantities are strings with up to six places; count fields use plain JSON integers. Exact fractions are capped at 8,192 bits. The complete JSON output is limited to 1,000,000 characters; approximate numbers preserve their stored values. Unsupported states fail explicitly.