Audit Trail and Provenance

Use this overview to decide whether you need the preprocessing record, figure-specific outlier log, or sample-size attrition trail, and to choose the right leaf page without overstating what this category can judge for you.

Use this section when your question is about what happened to the data before or during analysis, what record Licklider keeps of those actions, and where to inspect that record.

This section is for auditability, provenance, and disclosure of data handling decisions such as preprocessing, outlier exclusion, and sample-size reduction. It is not the place to decide whether a method is statistically appropriate overall or whether a result is scientifically valid; if your main question is about assumptions, design problems, or model diagnostics, start with another Quality Checks category instead.

This category helps you identify which audit record to inspect and what kind of evidence it contains. It should be read as a record-and-disclosure layer, not as a guarantee that Licklider can determine whether every preprocessing or exclusion choice was scientifically correct.

Is this the right section?

Use the table below to choose the leaf page that best matches your question.

If your question is...Start here
"What preprocessing steps were applied to this dataset, and where is that history recorded?"Preprocessing Audit Log
"What outlier exclusions or winsorization decisions were attached to this specific figure when it was generated?"Outlier Exclusion Log
"How did input N become analysis N, and where is attrition disclosed for this figure?"N Disclosure and Attrition Trail

If your main question is not about traceability of preprocessing, exclusions, or sample-size loss, this is usually not your first stop. For assumption checks, design threats, or model-fit issues, return to the broader Quality Checks section and choose the more specific category there.

What this category covers

This category covers three kinds of audit evidence:

Support boundary

This category is about making data handling traceable and disclosable. It is not a general validity engine, and it does not by itself decide whether a preprocessing rule, outlier exclusion, or attrition pattern was scientifically justified for your study.

Child pages

Start here

  1. Start with Preprocessing Audit Log if you need the dataset-level history of preprocessing actions.
  2. Start with Outlier Exclusion Log if you need the figure-specific record of exclusions or winsorization.
  3. Start with N Disclosure and Attrition Trail if you need to review how sample size changed from input to analysis.
  • Related links are registered in frontmatter and rendered below this stub.