Survey and Scale Builder
Design a sociology survey instrument with constructs, item wording, response scales, and validation logic.
Clean once, document always
Reproducible Data Cleaning Workflow
Plan a reproducible workflow for cleaning, documenting, and preparing sociology data for analysis.
When to use this
- Use this when the data are messy and you need order before analysis.
- Use this when multiple files or merges make the project fragile.
- Use this when you need an audit trail for a thesis, team project, or publication.
What you should prepare first
- Data source and format: [CSV, Excel, SPSS, Stata, SQL export, scraped files, mixed sources, etc.]
- Data problems I expect: [missing values, coding inconsistency, duplicates, date issues, merge problems, text normalization, etc.]
- Software environment: [R, Python, Stata, SPSS, hybrid workflow]
- Team context: [solo project, collaborative project, teaching lab, research assistant team]
- Deliverables needed: [clean dataset, codebook, analysis-ready file, reproducibility memo, scripts folder]
Paste this prompt
You are an elite sociology research and writing partner with strong expertise in sociological theory, research design, data analysis, academic communication, and publication standards. Primary task: Design a reproducible data-cleaning and documentation workflow for my sociology dataset, including checks, transformations, versioning, and output files. Project details I will provide or you should ask me to clarify: - Data source and format: [CSV, Excel, SPSS, Stata, SQL export, scraped files, mixed sources, etc.] - Data problems I expect: [missing values, coding inconsistency, duplicates, date issues, merge problems, text normalization, etc.] - Software environment: [R, Python, Stata, SPSS, hybrid workflow] - Team context: [solo project, collaborative project, teaching lab, research assistant team] - Deliverables needed: [clean dataset, codebook, analysis-ready file, reproducibility memo, scripts folder] How you should work: 1. Lay out a staged workflow from raw data preservation to analysis-ready outputs. 2. Specify checks for missingness, invalid values, duplicates, type conversion, joins, and derived variables. 3. Recommmend folder structure, file naming, and script sequencing. 4. Explain what should be documented in a cleaning log and codebook. 5. Highlight where cleaning decisions can affect inference and how to preserve transparency. Output requirements: - A step-by-step workflow. - A documentation checklist. - A reproducibility and version-control plan. Quality guardrails: - Never overwrite the raw data source. - Flag transformations that materially change interpretation. - Keep the workflow teachable and maintainable, not just technically clever. If crucial information is missing, make the minimum reasonable assumptions, label them clearly, and show me what extra details would improve the result. Use headings, compact tables, bullet points, and examples where they improve clarity.
What this should give you
- A step-by-step workflow.
- A documentation checklist.
- A reproducibility and version-control plan.
Good inputs improve this prompt
- State whether the workflow must work for beginners or only for you.
- List the most painful data issues you already know about.
- If the data include sensitive information, mention that so security practices can be included.
AI handoff
Paste the full prompt into ChatGPT, Claude, or Gemini after replacing the placeholders with your topic, setting, constraints, and target output. If the first answer drifts, tighten the missing inputs before running it again.
Prompt requests
Need a prompt for a narrower sociology task?
Send the missing workflow, bottleneck, or deliverable. Requests land in the editorial queue with enough detail to be turned into something genuinely usable.