Description
Apply a supplied positive smearing factor to an exponentiated log prediction.
Data workflows require explicit training scope, feature/label availability, missingness codes, group assignments and evaluation direction. Supplied training statistics are not proof that preprocessing avoided leakage. A local target-encoding term or retransformed prediction depends on assumptions that must be checked in the complete model and validation design.
Apply a supplied positive smearing factor to an exponentiated log prediction.
When to use this tool
Use Regression Prediction Retransformation Factor when you already have logPrediction, suppliedSmearingFactor and need to apply a supplied positive smearing factor to an exponentiated log prediction.
How to use the tool and how it works
- Enter logPrediction, suppliedSmearingFactor. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read retransformedPrediction. Use the output convention below.
Require suppliedSmearingFactor positive/finite; return exp(logPrediction)*factor using natural logs.1
For a log-transformed model, a smearing factor can be estimated from exponentiated fitted residuals. This tool accepts a factor rather than estimating it, so model assumptions and the factor's applicability remain separate checks.2
| Input field | Meaning and units | Accepted input |
|---|---|---|
| logPrediction | Natural-log-scale supplied prediction, exponentiated before applying the positive supplied smearing factor. | Required. Finite number. |
| suppliedSmearingFactor | Supplied Smearing Factor | Required. Finite number; strictly above 0. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| retransformedPrediction | Retransformed Prediction | Required. Finite number. |
{
"input": {
"logPrediction": 0,
"suppliedSmearingFactor": 1.5
},
"output": {
"retransformedPrediction": 1.5
}
}Limitations and assumptions
- No factor is estimated, residual distribution checked or bias removal guaranteed. Extreme negative log predictions can underflow to zero; this is not a prediction interval or causal estimate.
- 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
Review the full data lineage, preprocessing fit, split design and evaluation procedure for model conclusions. Estimate required statistics only within the intended training folds and verify actual availability; local supplied-value transformations cannot establish those properties by themselves.
References
Similar or alternative tools
- Log Linear Coefficient Percent Crosswalk
Convert a supplied log-linear coefficient change to a model-implied multiplicative and percentage change.
- Train Only Scaler Single Value Apply
Apply a supplied training-center and scale to one value.