EvalCompassEvalCompass
Data collectionQuantitative researchAdministrative statisticsOpen dataData limitationsCost efficiency

Secondary Data Analysis

Secondary Data Analysis
Also known as: Existing data analysis、Administrative data use、Open data analysis、Secondary analysis

Uses statistics or operational records collected for another purpose in evaluation. Check fit of collection purpose, targets, definitions and timing to evaluation questions. [1]

Secondary data assessment and use plan — openReferences and checked sections
Difficulty
Intermediate
Cost
Low
Duration
Illustrative planning durations, not common standards: finding/acquiring data 1–2 weeks, quality/preprocessing 1–2 weeks, analysis 2–4 weeks
Content updated: 2026-09-13Source checked: 2026-09-13 (includes AI cross-checking)No documented human reviewIncludes fictional examples

How it works at a glance

Organize variables and periods before searching. Check metadata, missingness, revisions and use conditions and retain processing records. [1]

Available indicators may not measure intended outcomes. State population or definition mismatches and consider additional collection for unanswered questions. [1]

  1. Find secondary data
  2. Assess quality through metadata
  3. Access and acquire data
  4. Clean and preprocess
  5. Conduct analysis
  6. Describe limitations and interpretation cautions
Sequence of implementation steps. See “Implementation steps” for details of each stage.

When to use it and when it is unsuitable

When to use it

  • Understand target-area/group backgrounds and trends without new collection
  • Supplement outcomes using municipal records or statistics
  • Build long-term trends or comparison-group baselines
  • Obtain quantitative evidence with limited budgets

When it is unsuitable

  • Necessary variables absent: primary collection is needed
  • Substantially different collection times or targets invalidate comparison
  • Access or use terms restrict evaluation use

Participants, roles, and deliverables

Participants and roles

1–2 data analysts; acquisition may require coordination with administration

Main deliverables

  • Source list with metadata assessments
  • Clean analytical dataset with code and procedures
  • Quantitative report with limitations

Implementation steps

  1. Find secondary data
    Systematically search e-Stat, government statistics, international agencies, municipal open-data portals and archives such as SSJDA. List variable, sample and timing fit.
  2. Assess quality through metadata
    Check purpose, population, sampling, timing, missing-data treatment and definition history. Explicitly record coverage, timing and variable-definition mismatches.
  3. Access and acquire data
    Check terms, privacy and secondary-use permissions. Use appropriate microdata applications through SSJDA or statistical offices, APIs or downloads.
  4. Clean and preprocess
    Check missing values, outliers and coding. For joins, align area codes/times and validate keys. Record every step in R, Python or Excel scripts for reproducibility.
  5. Conduct analysis
    Use methods suited to questions and data: descriptive statistics, trends, area or group comparisons. Incorporate target/non-target or before/after comparisons.
  6. Describe limitations and interpretation cautions
    State collection purpose, times and target mismatches when reporting. Explain over/underinterpretation risks from constraints and points needing primary-data supplementation.

Strengths and limitations

Strengths

  • Uses large longitudinal datasets without new collection costs or time
  • Administrative records and censuses offer scale and coverage difficult in primary studies
  • Strong for long time-series trends and comparison groups
  • Reuse is expected in EBPM and evidence synthesis

Limitations

  • Not designed for evaluation, so necessary variables may be absent
  • Time, target and definition differences complicate comparisons
  • Terms and privacy constraints may limit access
  • Inadequate limitation assessment/reporting risks erroneous conclusions

Common pitfalls

  • Do not derive questions from available data. Set questions first, then seek necessary data.
  • Provider definition changes can distort trends. Always check metadata and annual reports' methodological-change sections.
  • Do not hide limitations only at the end. State collection-purpose, definition, target differences and missingness relevant to conclusions alongside results.

Conditions of use and evidence

  • Judge fit to purpose considering record gaps and post-creation changes. [1]
Fictional example; not actual results

Distinguish consultation counts and people

A fictional illustration examining reach using a fictional consultation register.

ItemFictional register valueInterpretation
Consultation count120 casesIncludes repeat consultations
Identifiable users80 peopleScope where duplicates could be checked
Records without identifiers10 casesFurther checks needed for person counts

Common errors in judgment

Common mistake

Compare years without checking definitions

How to revise

Check aggregation and recording changes

ReasonApparent trends may arise from institutional or recording changes.

Common mistake

Freely join individual records because data are public

How to revise

Check terms and re-identification risks

ReasonAnonymous datasets may identify people when joined.

Organize your thinking by writing

Secondary data assessment and use plan

A practical template is available to fill in and print on A4 paper.

Open worksheet

Related methods

Survey / QuestionnaireDocument ReviewDescriptive Statistics and Cross-tabulationRegression AnalysisBenchmarking

References and checked sections

  1. Existing documents
    BetterEvaluation
    Section consulted
    Types of existing documents / Advice for using this method
    How it relates to the text
    Judge fit to purpose considering record gaps and post-creation changes.
    Source checked: (includes AI cross-checking)

Editorial and checking information

Content updated: Source checked: (includes AI cross-checking)No documented human reviewIncludes fictional examplesEditorial policy and scope of checkingCite this pageReport a correction

How to cite this page

EvalCompass Editorial Team. “Secondary Data Analysis”. EvalCompass, updated 2026-09-13. https://evalcompass.jun-nakatani.com/en/methods/secondary-data/
Add the date you accessed the page. Text created by this site is available under CC BY 4.0. Quotations, external materials, and bundled fonts have their own terms of use. When reusing content, credit the source, link to the license, and indicate any changes.

Suggest a correction or improvement to this page

Change history
  • — Checked sources for definitions and conditions and added fictional examples, judgment rationales and completed entries for every field. Revised unsupported historical or uptake claims. Reviewed procedures and cautions, adjusting fixed counts, thresholds and institutional generalizations. Preserved field positions, types and counts while revising fixed conditions and thresholds.