Description
Compare a batch mean with a supplied reference mean and standard deviation.
Feature transformations depend on training-derived parameters, category vocabularies and explicit missing-value conventions. A local formula or token rule does not ensure that fitting, application and validation avoid data leakage.
Compare a batch mean with a supplied reference mean and standard deviation.
When to use this tool
Use Batch Drift One Feature Mean Gap when checking one supplied feature-transform or encoding component.
How to use the tool and how it works
- Enter referenceMean, batchMean, referenceSd. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read difference, standardizedGap. Use the output convention below.
Compare a batch mean with a supplied reference mean and standard deviation. Require referenceSd > 0; difference = batch-reference and standardizedGap = difference/referenceSd.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| referenceMean | Reference Mean | Required. Finite number. |
| batchMean | Batch Mean | Required. Finite number. |
| referenceSd | Reference Sd | Required. Finite number; strictly above 0. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| difference | Difference | Required. Finite number. |
| standardizedGap | Standardized Gap | Required. Finite number. |
{
"input": {
"referenceMean": 10,
"batchMean": 12,
"referenceSd": 4
},
"output": {
"difference": 2,
"standardizedGap": 0.5
}
}Limitations and assumptions
- This is a standardized descriptive gap, not a hypothesis test or complete distribution-drift detector.
- 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 a correctly fitted preprocessing pipeline and suitable validation design for complete data transformation and model assessment.
References
Similar or alternative tools
- Minmax Feature Train Test Range Gap
Scale a value against training bounds and report range excess.
- Sparse Feature One Entry Density
Return sparse-feature density before and after added nonzeros.