Description
Return a continuity-adjusted discordant-pair statistic.
Biostatistical terms depend on a declared observation unit, exposure denominator, event order and sampling design. A risk-set flag, paired discordance contribution or support-weight ratio can be computed locally without fitting a survival model, establishing a treatment effect or validating an inferential analysis.
Return a continuity-adjusted discordant-pair statistic.
When to use this tool
Use Paired Binary Discordance Term when checking the stated exposure, event, matched-pair or cluster-support convention.
How to use the tool and how it works
- Enter firstOnly, secondOnly, continuityCorrection. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read difference, correctedAbsoluteDifference, statistic, defined. Inspect defined before interpreting the associated values.
Return a continuity-adjusted discordant-pair statistic. Require nonnegative whole firstOnly/secondOnly and correction >= 0; difference = first-second, correctedAbsoluteDifference = max(0,abs(difference)-correction), statistic = corrected²/(first+second) or zero with defined false.1
Paired binary discordant counts drive the McNemar statistic. This helper applies the stated nonnegative continuity-correction convention without calculating a p-value or selecting an inferential test.2
| Input field | Meaning and units | Accepted input |
|---|---|---|
| firstOnly | First Only | Required. Safe integer; minimum 0. |
| secondOnly | Second Only | Required. Safe integer; minimum 0. |
| continuityCorrection | Nonnegative caller-supplied correction on the count scale, not restricted to zero or one. | Required. Finite number; minimum 0. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| difference | Difference | Required. Finite number. |
| correctedAbsoluteDifference | max(0,abs(firstOnly-secondOnly)-correction), using the supplied nonnegative continuityCorrection, which may be fractional. | Required. Finite number. |
| statistic | Statistic | Required. Finite number. |
| defined | Reporting flag under the explicit denominator or information policy above; inspect any zero placeholder or policy-defined value. | Required. Boolean. |
{
"input": {
"firstOnly": 8,
"secondOnly": 2,
"continuityCorrection": 1
},
"output": {
"difference": 6,
"correctedAbsoluteDifference": 5,
"statistic": 2.5,
"defined": true
}
}Limitations and assumptions
- The correction is supplied; no p-value, exact test, sample adequacy or clinical meaning is determined.
- 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
Analyze complete verified data with a method appropriate to the design and censoring assumptions; assess uncertainty and consult qualified statistical and clinical professionals for health conclusions.
References
Similar or alternative tools
- Pair Matched Discordance Budget
Return matched binary-pair total and discordance balance.
- Binary Outcome Discordant Pair Flag
Return discordance and signed direction for two binary outcomes.