Skip to content
ProductHow it worksFind a topicProject topics

Research ethics and analysis Student writing guide

How to Report a Worked Data Example Without Inventing Research

A teaching example can demonstrate a calculation, chart or analysis workflow, but it cannot stand in for data you have not collected or accessed. The distinction should remain visible in the file, chart titles, analysis text and any presentation that uses the example.

A practical guide from FINAL YEAR NG Check your department's current instructions before you submit.

Keep provenance visible

  1. Mark the source as synthetic in the filename, title and data dictionary.
  2. Describe how the records were generated or where the synthetic values came from.
  3. Do not attach invented institution names, participant identities or realistic identifiers.
  4. Retain the exact script or calculation steps used to create and analyse the example.
  5. Replace the example only with data you are authorized to use and have properly documented.

Describe output proportionately

For a synthetic example, explain only what the generated records show inside that example. Do not generalise to students, patients, customers or a location. If using real data, state the sampling, measurement, missingness and analysis limits needed to interpret the result, and follow consent, privacy and institutional approval conditions.

  • Separate observed description from interpretation.
  • Report the denominator, units and variable definitions.
  • Do not describe statistical significance as practical importance.
  • Keep unsuccessful or contradictory checks in the analysis record.
  • Label example tables and figures as synthetic wherever they are reproduced.

Write a reproducible example paragraph

Transparent wording for the companion file

In the 40-record synthetic teaching file, the mean fictional quiz score is 65.975, and the Pearson correlation between the generated study-hours and score columns is 0.758. These summaries describe only the constructed example. No students were observed, and the calculation does not estimate a real educational relationship.

Those values are printed by the companion script and are included to show how to label a result, state its denominator and name the calculation. If the file or code changes, recalculate the output before reusing the numbers. Do not add a p-value, population statement or causal explanation unless the data and design support that analysis.

  1. Keep the raw input, analysis script and a short data dictionary together.
  2. Record any changed rows, recoding, exclusions or missing-value rules.
  3. State the software and version needed to reproduce the calculation.
  4. Check that tables and figures use the same data version and units.
  5. Label every copied output 'synthetic teaching example' and separate it from real study findings.

Sources and further reading

These university writing resources inform the general advice here. They do not replace your department's handbook or supervisor's guidance.

  1. American Statistical Association: Statement on Statistical Significance and P-Values
  2. U.S. Office of Research Integrity: Definition of Research Misconduct
← All writing guidesChoosing a project topic →