Description
Calculate supplied confidence minus observed success fraction.
Assessment records distinguish presented items, responses, deliberate skips, missingness, accommodations, versions and reference populations. A score contribution depends on its chosen denominator and weight, while one confidence gap is not a full calibration study. Recorded observations and timing differences do not establish learner ability or an appropriate intervention.
Calculate supplied confidence minus observed success fraction.
When to use this tool
Use Learner Confidence Calibration Gap when you already have reportedConfidence, observedSuccessFraction and need to calculate supplied confidence minus observed success fraction.
How to use the tool and how it works
- Enter reportedConfidence, observedSuccessFraction. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read signedCalibrationGap. Use the output convention below.
Require both fractions in [0,1]; return reportedConfidence-observedSuccessFraction.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| reportedConfidence | Reported Confidence | Required. Finite number; minimum 0; maximum 1. |
| observedSuccessFraction | Observed Success Fraction | Required. Finite number; minimum 0; maximum 1. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| signedCalibrationGap | Confidence-success as a decimal fraction difference, not a percentage or aggregate calibration metric. | Required. Finite number. |
{
"input": {
"reportedConfidence": 0.8,
"observedSuccessFraction": 0.6
},
"output": {
"signedCalibrationGap": 0.20000000000000007
}
}Limitations and assumptions
- This is one signed aggregate gap, not a reliability curve, calibration test, causal learning effect or clinical assessment.
- 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 the full assessment manual, item records, population reference and research design for score interpretation. Review missingness, exposure, accommodations and comparability; local labels or contributions do not replace psychometric analysis or an appropriate educational assessment.
References
Similar or alternative tools
- Assessment Response Speed Reference Ratio
Calculate a supplied response-duration-to-reference ratio.
- Achievement Percentile Source Label
Label a supplied percentile with its reference population and assessment version.