Description
Return the logit offset from a supplied binary prior shift.
Class prevalence, probability mass and training weights describe different distributions. Removing a class, changing class weights or correcting prior odds changes a particular numerical basis; none of those operations by itself estimates population shift or establishes calibrated predictions.
Return the logit offset from a supplied binary prior shift.
When to use this tool
Use Binary Prior Shift Logit Offset when checking the stated probability-mass, prior-odds or weighting convention.
How to use the tool and how it works
- Enter trainingPrior, targetPrior. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read offset. Use the output convention below.
Return the logit offset from a supplied binary prior shift. Require both priors strictly in (0,1); offset = ln(target/(1-target))-ln(training/(1-training)).1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| trainingPrior | Training Prior | Required. Finite number. |
| targetPrior | Target Prior | Required. Finite number. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| offset | Natural-log target prior odds minus natural-log training prior odds. | Required. Finite number. |
{
"input": {
"trainingPrior": 0.5,
"targetPrior": 0.75
},
"output": {
"offset": 1.0986122886681096
}
}Limitations and assumptions
- This corresponds to a prior-odds correction under compatible label-shift assumptions; the shift and applicability are not estimated.
- 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
Check the complete class distribution and its sampling basis; use a justified shift model or fitted calibration method when adapting predictions to a new population.
References
Similar or alternative tools
- Classification: Label Prior Correction Odds Factor
Return an odds multiplier for a supplied binary prior change.
- Classifier Logit Tie Policy Tool
Compute classifier logit tie policy from explicit bounded inputs.