Description
Compare a point estimate and asymmetric uncertainty bounds with a supplied decision threshold.
Customer-discovery and experiment summaries depend on who was contacted, what evidence counts and how unresolved outcomes enter the denominator. An observed fraction or uncertainty margin is descriptive evidence rather than proof of market demand or a decision rule.
Compare a point estimate and asymmetric uncertainty bounds with a supplied decision threshold.
When to use this tool
Use Experiment Decision Margin Gap when checking supplied response counts, evidence shares or decision margins.
How to use the tool and how it works
- Enter estimate, decisionThreshold, lowerUncertainty, upperUncertainty. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read pointMargin, lowerMargin, upperMargin, straddles. Inspect straddles before interpreting the associated values.
Require nonnegative lowerUncertainty and upperUncertainty. pointMargin = estimate-decisionThreshold; lowerMargin subtracts lowerUncertainty, and upperMargin adds upperUncertainty. straddles is true only if the lower endpoint is strictly below and the upper endpoint strictly above the threshold.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| estimate | Estimate | Required. Finite number. |
| decisionThreshold | Decision Threshold | Required. Finite number. |
| lowerUncertainty | Lower Uncertainty | Required. Finite number; minimum 0. |
| upperUncertainty | Upper Uncertainty | Required. Finite number; minimum 0. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| pointMargin | Point Margin | Required. Finite number. |
| lowerMargin | Lower Margin | Required. Finite number. |
| upperMargin | Upper Margin | Required. Finite number. |
| straddles | Straddles | Required. Boolean. |
{
"input": {
"estimate": 5,
"decisionThreshold": 4,
"lowerUncertainty": 2,
"upperUncertainty": 1
},
"output": {
"pointMargin": 1,
"lowerMargin": -1,
"upperMargin": 2,
"straddles": true
}
}Limitations and assumptions
- Touching an endpoint does not count as straddling. Uncertainty widths are supplied rather than estimated; no confidence level or decision recommendation is inferred.
- Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
- Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.
Alternative or Complementary methods
Use an appropriate study design and statistical analysis when sampling bias, uncertainty or causal interpretation matters.
References
Similar or alternative tools
- Customer Discovery Response Rate Gap
Compare an observed customer-discovery response fraction with a supplied reference rate.
- Hypothesis Evidence Count Share
Summarize coded hypothesis-support counts under an explicit unresolved-evidence denominator policy.